通信运营商及通信企业相继发布通信大模型,通信大模型作为提升网络运营智能化的关键基础设施是产业共识。通信网络中如何引入AI,AI引入的演进思路和实施方法需要进一步明确。“AI for NET”基于全栈AI推动网络智能化提升。探讨了中国联...通信运营商及通信企业相继发布通信大模型,通信大模型作为提升网络运营智能化的关键基础设施是产业共识。通信网络中如何引入AI,AI引入的演进思路和实施方法需要进一步明确。“AI for NET”基于全栈AI推动网络智能化提升。探讨了中国联通AI for NET理念、架构、演进思路和实施方法,为业界AI赋能网络提供参考。展开更多
一、作为哲学的AI for Process(一)郭为的哲学思想1.郭为是谁郭为是谁?他是一位哲学家。顺便说,他同时还领导着神州数码。为什么说郭为是哲学家呢?因为他在著作中谈到高深的哲学,如“数据如水,奔流不息,无界融合”。他引述古希腊哲学家...一、作为哲学的AI for Process(一)郭为的哲学思想1.郭为是谁郭为是谁?他是一位哲学家。顺便说,他同时还领导着神州数码。为什么说郭为是哲学家呢?因为他在著作中谈到高深的哲学,如“数据如水,奔流不息,无界融合”。他引述古希腊哲学家赫拉克利特所说的“万物流转”,又说“你不能两次踏进同一条河流,因为新的水不断地流过你的身旁”,他所表达的意思是“世界上唯一不变的就是变化”。展开更多
Artificial Intelligence(AI)is changing healthcare by helping with diagnosis.However,for doctors to trust AI tools,they need to be both accurate and easy to understand.In this study,we created a new machine learning sy...Artificial Intelligence(AI)is changing healthcare by helping with diagnosis.However,for doctors to trust AI tools,they need to be both accurate and easy to understand.In this study,we created a new machine learning system for the early detection of Autism Spectrum Disorder(ASD)in children.Our main goal was to build a model that is not only good at predicting ASD but also clear in its reasoning.For this,we combined several different models,including Random Forest,XGBoost,and Neural Networks,into a single,more powerful framework.We used two different types of datasets:(i)a standard behavioral dataset and(ii)a more complex multimodal dataset with images,audio,and physiological information.The datasets were carefully preprocessed for missing values,redundant features,and dataset imbalance to ensure fair learning.The results outperformed the state-of-the-art with a Regularized Neural Network,achieving 97.6%accuracy on behavioral data.Whereas,on the multimodal data,the accuracy is 98.2%.Other models also did well with accuracies consistently above 96%.We also used SHAP and LIME on a behavioral dataset for models’explainability.展开更多
Recent years have witnessed transformative changes brought about by artificial intelligence(AI)techniques with billions of parameters for the realization of high accuracy,proposing high demand for the advanced and AI ...Recent years have witnessed transformative changes brought about by artificial intelligence(AI)techniques with billions of parameters for the realization of high accuracy,proposing high demand for the advanced and AI chip to solve these AI tasks efficiently and powerfully.Rapid progress has been made in the field of advanced chips recently,such as the development of photonic computing,the advancement of the quantum processors,the boost of the biomimetic chips,and so on.Designs tactics of the advanced chips can be conducted with elaborated consideration of materials,algorithms,models,architectures,and so on.Though a few reviews present the development of the chips from their unique aspects,reviews in the view of the latest design for advanced and AI chips are few.Here,the newest development is systematically reviewed in the field of advanced chips.First,background and mechanisms are summarized,and subsequently most important considerations for co-design of the software and hardware are illustrated.Next,strategies are summed up to obtain advanced and AI chips with high excellent performance by taking the important information processing steps into consideration,after which the design thought for the advanced chips in the future is proposed.Finally,some perspectives are put forward.展开更多
Most Convolutional Neural Network(CNN)interpretation techniques visualize only the dominant cues that the model relies on,but there is no guarantee that these represent all the evidence the model uses for classificati...Most Convolutional Neural Network(CNN)interpretation techniques visualize only the dominant cues that the model relies on,but there is no guarantee that these represent all the evidence the model uses for classification.This limitation becomes critical when hidden secondary cues—potentially more meaningful than the visualized ones—remain undiscovered.This study introduces CasCAM(Cascaded Class Activation Mapping)to address this fundamental limitation through counterfactual reasoning.By asking“if this dominant cue were absent,what other evidence would the model use?”,CasCAM progressively masks the most salient features and systematically uncovers the hierarchy of classification evidence hidden beneath them.Experimental results demonstrate that CasCAM effectively discovers the full spectrum of reasoning evidence and can be universally applied with nine existing interpretation methods.展开更多
Diabetic retinopathy(DR)is a leading cause of vision loss among working-age populations,with early screening significantly reducing the risk of blindness.However,resource-limited regions often face challenges in DR sc...Diabetic retinopathy(DR)is a leading cause of vision loss among working-age populations,with early screening significantly reducing the risk of blindness.However,resource-limited regions often face challenges in DR screening due to a shortage of ophthalmologists.This study reports the implementation and outcomes of the Chinese local standard DB52/T 1726-2023,Regulations for the application of diabetic retinopathy screening artificial intelligence,in Cambodian healthcare institutions.A pilot DR screening program with independent operational capability is established by providing a non-mydriatic fundus camera and deploying a localized diabetic retinopathy artificial intelligence(DR-AI)screening platform at the Cambodia-Kingdom Friendship Hospital in Phnom Penh,along with comprehensive training.From January to August 2025,a total of 565 patients with type 2 diabetes were screened,yielding a DR detection rate of 26.0%(147 cases).Research findings demonstrate that applying mature Chinese DR-AI screening standards and technological solutions through international collaboration in regions with a scarcity of ophthalmic professionals is both feasible and effective.This project serves as a reference for promoting DR-AI in resource-constrained countries and regions,highlighting its significant potential to leverage AI in addressing the global burden of chronic diseases and advancing the modernization of health systems.展开更多
“By successfully integrating artificial intelligence(AI)into research workflows,researchers could substantially increase scientific productivity”[1].In biofabrication,AI is dr iving a paradigm shift from empiricism ...“By successfully integrating artificial intelligence(AI)into research workflows,researchers could substantially increase scientific productivity”[1].In biofabrication,AI is dr iving a paradigm shift from empiricism toward intelligen t,data centric manufacturing[2].By integrating computation,automation,and biology,AI gives rise to self-evolving,adaptive systems that learn from data,predict complex behaviors,and autonomously optimize fabrication outcomes.Such systems translate experimental insights into patient-specific and clinically relevant solutions,bridging laboratory research and regenerative therapies[3].This emerging frontier is rapidly advancing from concept to application.This Special Column highlights how AI-driven advanc es in materials,design,and manufacturing are reshaping biof abrication for regenerative medicine and clinical translation.展开更多
The integration of machine learning(ML)into geohazard assessment has successfully instigated a paradigm shift,leading to the production of models that possess a level of predictive accuracy previously considered unatt...The integration of machine learning(ML)into geohazard assessment has successfully instigated a paradigm shift,leading to the production of models that possess a level of predictive accuracy previously considered unattainable.However,the black-box nature of these systems presents a significant barrier,hindering their operational adoption,regulatory approval,and full scientific validation.This paper provides a systematic review and synthesis of the emerging field of explainable artificial intelligence(XAI)as applied to geohazard science(GeoXAI),a domain that aims to resolve the long-standing trade-off between model performance and interpretability.A rigorous synthesis of 87 foundational studies is used to map the intellectual and methodological contours of this rapidly expanding field.The analysis reveals that current research efforts are concentrated predominantly on landslide and flood assessment.Methodologically,tree-based ensembles and deep learning models dominate the literature,with SHapley Additive exPlanations(SHAP)frequently adopted as the principal post-hoc explanation technique.More importantly,the review further documents how the role of XAI has shifted:rather than being used solely as a tool for interpreting models after training,it is increasingly integrated into the modeling cycle itself.Recent applications include its use in feature selection,adaptive sampling strategies,and model evaluation.The evidence also shows that GeoXAI extends beyond producing feature rankings.It reveals nonlinear thresholds and interaction effects that generate deeper mechanistic insights into hazard processes and mechanisms.Nevertheless,several key challenges remain unresolved within the field.These persistent issues are especially pronounced when considering the crucial necessity for interpretation stability,the demanding scholarly task of reliably distinguishing correlation from causation,and the development of appropriate methods for the treatment of complex spatio-temporal dynamics.展开更多
High-throughput transcriptomics has evolved from bulk RNA-seq to single-cell and spatial profiling,yet its clinical translation still depends on effective integration across diverse omics and data modalities.Emerging ...High-throughput transcriptomics has evolved from bulk RNA-seq to single-cell and spatial profiling,yet its clinical translation still depends on effective integration across diverse omics and data modalities.Emerging foundation models and multimodal learning frameworks are enabling scalable and transferable representations of cellular states,while advances in interpretability and real-world data integration are bridging the gap between discovery and clinical application.This paper outlines a concise roadmap for AI-driven,transcriptome-centered multi-omics integration in precision medicine(Figure 1).展开更多
Parkinson’s disease remains a major clinical issue in terms of early detection,especially during its prodromal stage when symptoms are not evident or not distinct.To address this problem,we proposed a new deep learni...Parkinson’s disease remains a major clinical issue in terms of early detection,especially during its prodromal stage when symptoms are not evident or not distinct.To address this problem,we proposed a new deep learning 2-based approach for detecting Parkinson’s disease before any of the overt symptoms develop during their prodromal stage.We used 5 publicly accessible datasets,including UCI Parkinson’s Voice,Spiral Drawings,PaHaW,NewHandPD,and PPMI,and implemented a dual stream CNN–BiLSTM architecture with Fisher-weighted feature merging and SHAP-based explanation.The findings reveal that the model’s performance was superior and achieved 98.2%,a F1-score of 0.981,and AUC of 0.991 on the UCI Voice dataset.The model’s performance on the remaining datasets was also comparable,with up to a 2–7 percent betterment in accuracy compared to existing strong models such as CNN–RNN–MLP,ILN–GNet,and CASENet.Across the evidence,the findings back the diagnostic promise of micro-tremor assessment and demonstrate that combining temporal and spatial features with a scatter-based segment for a multi-modal approach can be an effective and scalable platform for an“early,”interpretable PD screening system.展开更多
Cases of widespread bone hydatid infection are relatively rare in clinical practice.In this study,we reported for the first time a validated integrated repair therapy for multiple bone tissues,including the hip,femur,...Cases of widespread bone hydatid infection are relatively rare in clinical practice.In this study,we reported for the first time a validated integrated repair therapy for multiple bone tissues,including the hip,femur,and knee,caused by echinococ cosis.Artificial intelligence(AI)was used to develop a targeted surgical plan and to design a personalized prosthesis.Finite element analysis(FEA)was used to optimize the mechanical effectiveness of a customized integrated replacement prosthesis and to model stress distribution in the surrounding bone.Three-dimensional(3 D)printing was used to fabricate a customized prosthesis.With the assistance of AI,FEA,and 3 D printing technology,a personalized surgical plan and customized prosthesis were successfully constructed based on the patient’s disease.This approach achieved a successful therapeutic effect,demonstrating that AI-assisted personalized medicine holds great promise for the future.展开更多
In the field of precision healthcare,where accurate decision-making is paramount,this study underscores the indispensability of eXplainable Artificial Intelligence(XAI)in the context of epilepsy management within the ...In the field of precision healthcare,where accurate decision-making is paramount,this study underscores the indispensability of eXplainable Artificial Intelligence(XAI)in the context of epilepsy management within the Internet of Medical Things(IoMT).The methodology entails meticulous preprocessing,involving the application of a band-pass filter and epoch segmentation to optimize the quality of Electroencephalograph(EEG)data.The subsequent extraction of statistical features facilitates the differentiation between seizure and non-seizure patterns.The classification phase integrates Support Vector Machine(SVM),K-Nearest Neighbor(KNN),and Random Forest classifiers.Notably,SVM attains an accuracy of 97.26%,excelling in the precision,recall,specificity,and F1 score for identifying seizures and non-seizure instances.Conversely,KNN achieves an accuracy of 72.69%,accompanied by certain trade-offs.The Random Forest classifierstands out with a remarkable accuracy of 99.89%,coupled with an exceptional precision(99.73%),recall(100%),specificity(99.80%),and F1 score(99.86%),surpassing both SVM and KNN performances.XAI techniques,namely Local Interpretable ModelAgnostic Explanations(LIME)and SHapley Additive exPlanation(SHAP),enhance the system’s transparency.This combination of machine learning and XAI not only improves the reliability and accuracy of the seizure detection system but also enhances trust and interpretability.Healthcare professionals can leverage the identified important features and their dependencies to gain deeper insights into the decision-making process,aiding in informed diagnosis and treatment decisions for patients with epilepsy.展开更多
The advent of 6G wireless technology,which offers previously unattainable data rates,very low latency,and compatibility with a wide range of communication devices,promises to transform the networking environment compl...The advent of 6G wireless technology,which offers previously unattainable data rates,very low latency,and compatibility with a wide range of communication devices,promises to transform the networking environment completely.The 6G wireless proposals aim to expand wireless communication’s capabilities well beyond current levels.This technology is expected to revolutionize how we communicate,connect,and use the power of the digital world.However,maintaining secure and efficient data management becomes crucial as 6G networks grow in size and complexity.This study investigates blockchain clustering and artificial intelligence(AI)approaches to ensure a reliable and trustworthy communication in 6G.First,the mechanisms and protocols of blockchain clustering that provide a trusted and effective communication infrastructure for 6G networks are presented.Then,AI techniques for network security in 6G are studied.The integration of AI and blockchain to ensure energy efficiency in 6Gnetworks is addressed.Next,this paper presents howthe 6G’s speed and bandwidth enables AI and the easy management of virtualized systems.Using terahertz connections is sufficient to have virtualized systems move compute environments as well as data.For instance,a computing environment can follow potential security violations while leveraging AI.Such virtual machines can store their findings in blockchains.In 6G scenarios,case studies and real-world applications of AI-powered secure blockchain clustering are given.Moreover,challenges and promising future research opportunities are highlighted.These challenges and opportunities provide insights from the most recent developments and point to areas where AI and blockchain further ensure security and efficiency in 6G networks.展开更多
Skin cancer is among the most common malignancies worldwide,but its mortality burden is largely driven by aggressive subtypes such as melanoma,with outcomes varying across regions and healthcare settings.These variati...Skin cancer is among the most common malignancies worldwide,but its mortality burden is largely driven by aggressive subtypes such as melanoma,with outcomes varying across regions and healthcare settings.These variations emphasize the importance of reliable diagnostic technologies that support clinicians in detecting skin malignancies with higher accuracy.Traditional diagnostic methods often rely on subjective visual assessments,which can lead to misdiagnosis.This study addresses these challenges by developing HybridFusionNet,a novel model that integrates Convolutional Neural Networks(CNN)with 1D feature extraction techniques to enhance diagnostic accuracy.Utilizing two extensive datasets,BCN20000 and HAM10000,the methodology includes data preprocessing,application of Synthetic Minority Oversampling Technique combined with Edited Nearest Neighbors(SMOTEENN)for data balancing,and optimization of feature selection using the Tree-based Pipeline Optimization Tool(TPOT).The results demonstrate significant performance improvements over traditional CNN models,achieving an accuracy of 0.9693 on the BCN20000 dataset and 0.9909 on the HAM10000 dataset.The HybridFusionNet model not only outperforms conventionalmethods but also effectively addresses class imbalance.To enhance transparency,it integrates post-hoc explanation techniques such as LIME,which highlight the features influencing predictions.These findings highlight the potential of HybridFusionNet to support real-world applications,including physician-assist systems,teledermatology,and large-scale skin cancer screening programs.By improving diagnostic efficiency and enabling access to expert-level analysis,the modelmay enhance patient outcomes and foster greater trust in artificial intelligence(AI)-assisted clinical decision-making.展开更多
Skin cancer is the most prevalent cancer globally,primarily due to extensive exposure to Ultraviolet(UV)radiation.Early identification of skin cancer enhances the likelihood of effective treatment,as delays may lead t...Skin cancer is the most prevalent cancer globally,primarily due to extensive exposure to Ultraviolet(UV)radiation.Early identification of skin cancer enhances the likelihood of effective treatment,as delays may lead to severe tumor advancement.This study proposes a novel hybrid deep learning strategy to address the complex issue of skin cancer diagnosis,with an architecture that integrates a Vision Transformer,a bespoke convolutional neural network(CNN),and an Xception module.They were evaluated using two benchmark datasets,HAM10000 and Skin Cancer ISIC.On the HAM10000,the model achieves a precision of 95.46%,an accuracy of 96.74%,a recall of 96.27%,specificity of 96.00%and an F1-Score of 95.86%.It obtains an accuracy of 93.19%,a precision of 93.25%,a recall of 92.80%,a specificity of 92.89%and an F1-Score of 93.19%on the Skin Cancer ISIC dataset.The findings demonstrate that the model that was proposed is robust and trustworthy when it comes to the classification of skin lesions.In addition,the utilization of Explainable AI techniques,such as Grad-CAM visualizations,assists in highlighting the most significant lesion areas that have an impact on the decisions that are made by the model.展开更多
Quality of Service(QoS)assurance in programmable IoT and 5G networks is increasingly threatened by cyberattacks such as Distributed Denial of Service(DDoS),spoofing,and botnet intrusions.This paper presents AutoSHARC,...Quality of Service(QoS)assurance in programmable IoT and 5G networks is increasingly threatened by cyberattacks such as Distributed Denial of Service(DDoS),spoofing,and botnet intrusions.This paper presents AutoSHARC,a feedback-driven,explainable intrusion detection framework that integrates Boruta and LightGBM–SHAP feature selection with a lightweight CNN–Attention–GRU classifier.AutoSHARC employs a two-stage feature selection pipeline to identify the most informative features from high-dimensional IoT traffic and reduces 46 features to 30 highly informative ones,followed by post-hoc SHAP-guided retraining to refine feature importance,forming a feedback loopwhere only the most impactful attributes are reused to retrain themodel.This iterative refinement reduces computational overhead,accelerates detection latency,and improves transparency.Evaluated on the CIC IoT 2023 dataset,AutoSHARC achieves 98.98%accuracy,98.9%F1-score,and strong robustness with a Matthews Correlation Coefficient of 0.98 and Cohen’s Kappa of 0.98.The final model contains only 531,272 trainable parameters with a compact 2 MB size,enabling real-time deployment on resource-constrained IoT nodes.By combining explainable AI with iterative feature refinement,AutoSHARC provides scalable and trustworthy intrusion detection while preserving key QoS indicators such as latency,throughput,and reliability.展开更多
With the birth of Software-Defined Networking(SDN),integration of both SDN and traditional architectures becomes the development trend of computer networks.Network intrusion detection faces challenges in dealing with ...With the birth of Software-Defined Networking(SDN),integration of both SDN and traditional architectures becomes the development trend of computer networks.Network intrusion detection faces challenges in dealing with complex attacks in SDN environments,thus to address the network security issues from the viewpoint of Artificial Intelligence(AI),this paper introduces the Crayfish Optimization Algorithm(COA)to the field of intrusion detection for both SDN and traditional network architectures,and based on the characteristics of the original COA,an Improved Crayfish Optimization Algorithm(ICOA)is proposed by integrating strategies of elite reverse learning,Levy flight,crowding factor and parameter modification.The ICOA is then utilized for AI-integrated feature selection of intrusion detection for both SDN and traditional network architectures,to reduce the dimensionality of the data and improve the performance of network intrusion detection.Finally,the performance evaluation is performed by testing not only the NSL-KDD dataset and the UNSW-NB 15 dataset for traditional networks but also the InSDN dataset for SDN-based networks.Experimental results show that ICOA improves the accuracy by 0.532%and 2.928%respectively compared with GWO and COA in traditional networks.In SDN networks,the accuracy of ICOA is 0.25%and 0.3%higher than COA and PSO.These findings collectively indicate that AI-integrated feature selection based on the proposed ICOA can promote network intrusion detection for both SDN and traditional architectures.展开更多
Accurate and efficient brain tumor segmentation is essential for early diagnosis,treatment planning,and clinical decision-making.However,the complex structure of brain anatomy and the heterogeneous nature of tumors pr...Accurate and efficient brain tumor segmentation is essential for early diagnosis,treatment planning,and clinical decision-making.However,the complex structure of brain anatomy and the heterogeneous nature of tumors present significant challenges for precise anomaly detection.While U-Net-based architectures have demonstrated strong performance in medical image segmentation,there remains room for improvement in feature extraction and localization accuracy.In this study,we propose a novel hybrid model designed to enhance 3D brain tumor segmentation.The architecture incorporates a 3D ResNet encoder known for mitigating the vanishing gradient problem and a 3D U-Net decoder.Additionally,to enhance the model’s generalization ability,Squeeze and Excitation attention mechanism is integrated.We introduce Gabor filter banks into the encoder to further strengthen the model’s ability to extract robust and transformation-invariant features from the complex and irregular shapes typical in medical imaging.This approach,which is not well explored in current U-Net-based segmentation frameworks,provides a unique advantage by enhancing texture-aware feature representation.Specifically,Gabor filters help extract distinctive low-level texture features,reducing the effects of texture interference and facilitating faster convergence during the early stages of training.Our model achieved Dice scores of 0.881,0.846,and 0.819 for Whole Tumor(WT),Tumor Core(TC),and Enhancing Tumor(ET),respectively,on the BraTS 2020 dataset.Cross-validation on the BraTS 2021 dataset further confirmed the model’s robustness,yielding Dice score values of 0.887 for WT,0.856 for TC,and 0.824 for ET.The proposed model outperforms several state-of-the-art existing models,particularly in accurately identifying small and complex tumor regions.Extensive evaluations suggest integrating advanced preprocessing with an attention-augmented hybrid architecture offers significant potential for reliable and clinically valuable brain tumor segmentation.展开更多
文摘通信运营商及通信企业相继发布通信大模型,通信大模型作为提升网络运营智能化的关键基础设施是产业共识。通信网络中如何引入AI,AI引入的演进思路和实施方法需要进一步明确。“AI for NET”基于全栈AI推动网络智能化提升。探讨了中国联通AI for NET理念、架构、演进思路和实施方法,为业界AI赋能网络提供参考。
文摘一、作为哲学的AI for Process(一)郭为的哲学思想1.郭为是谁郭为是谁?他是一位哲学家。顺便说,他同时还领导着神州数码。为什么说郭为是哲学家呢?因为他在著作中谈到高深的哲学,如“数据如水,奔流不息,无界融合”。他引述古希腊哲学家赫拉克利特所说的“万物流转”,又说“你不能两次踏进同一条河流,因为新的水不断地流过你的身旁”,他所表达的意思是“世界上唯一不变的就是变化”。
基金the King Salman center for Disability Research for funding this work through Research Group No.KSRG-2024-050.
文摘Artificial Intelligence(AI)is changing healthcare by helping with diagnosis.However,for doctors to trust AI tools,they need to be both accurate and easy to understand.In this study,we created a new machine learning system for the early detection of Autism Spectrum Disorder(ASD)in children.Our main goal was to build a model that is not only good at predicting ASD but also clear in its reasoning.For this,we combined several different models,including Random Forest,XGBoost,and Neural Networks,into a single,more powerful framework.We used two different types of datasets:(i)a standard behavioral dataset and(ii)a more complex multimodal dataset with images,audio,and physiological information.The datasets were carefully preprocessed for missing values,redundant features,and dataset imbalance to ensure fair learning.The results outperformed the state-of-the-art with a Regularized Neural Network,achieving 97.6%accuracy on behavioral data.Whereas,on the multimodal data,the accuracy is 98.2%.Other models also did well with accuracies consistently above 96%.We also used SHAP and LIME on a behavioral dataset for models’explainability.
基金supported by the Hong Kong Polytechnic University(1-WZ1Y,1-W34U,4-YWER).
文摘Recent years have witnessed transformative changes brought about by artificial intelligence(AI)techniques with billions of parameters for the realization of high accuracy,proposing high demand for the advanced and AI chip to solve these AI tasks efficiently and powerfully.Rapid progress has been made in the field of advanced chips recently,such as the development of photonic computing,the advancement of the quantum processors,the boost of the biomimetic chips,and so on.Designs tactics of the advanced chips can be conducted with elaborated consideration of materials,algorithms,models,architectures,and so on.Though a few reviews present the development of the chips from their unique aspects,reviews in the view of the latest design for advanced and AI chips are few.Here,the newest development is systematically reviewed in the field of advanced chips.First,background and mechanisms are summarized,and subsequently most important considerations for co-design of the software and hardware are illustrated.Next,strategies are summed up to obtain advanced and AI chips with high excellent performance by taking the important information processing steps into consideration,after which the design thought for the advanced chips in the future is proposed.Finally,some perspectives are put forward.
基金supported by the Basic Science Research Program through the National Research Foundation of Korea(NRF),funded by the Ministry of Education(RS-2023-00249743).
文摘Most Convolutional Neural Network(CNN)interpretation techniques visualize only the dominant cues that the model relies on,but there is no guarantee that these represent all the evidence the model uses for classification.This limitation becomes critical when hidden secondary cues—potentially more meaningful than the visualized ones—remain undiscovered.This study introduces CasCAM(Cascaded Class Activation Mapping)to address this fundamental limitation through counterfactual reasoning.By asking“if this dominant cue were absent,what other evidence would the model use?”,CasCAM progressively masks the most salient features and systematically uncovers the hierarchy of classification evidence hidden beneath them.Experimental results demonstrate that CasCAM effectively discovers the full spectrum of reasoning evidence and can be universally applied with nine existing interpretation methods.
基金funded by the Chronic Disease Management Research Project of National Health Commission Capacity Building and Continuing Education Center 2025(GWJJMB202510024146)the Post-Subsidy Project for Standard Development of Guizhou Provincial Market Supervision and Administration Bureau 2025(DB52/T1726-2023)the Guizhou Provincial Health Commission Science and Technology Fund Project(gzwkj2024-076,gzwkj2026-146).
文摘Diabetic retinopathy(DR)is a leading cause of vision loss among working-age populations,with early screening significantly reducing the risk of blindness.However,resource-limited regions often face challenges in DR screening due to a shortage of ophthalmologists.This study reports the implementation and outcomes of the Chinese local standard DB52/T 1726-2023,Regulations for the application of diabetic retinopathy screening artificial intelligence,in Cambodian healthcare institutions.A pilot DR screening program with independent operational capability is established by providing a non-mydriatic fundus camera and deploying a localized diabetic retinopathy artificial intelligence(DR-AI)screening platform at the Cambodia-Kingdom Friendship Hospital in Phnom Penh,along with comprehensive training.From January to August 2025,a total of 565 patients with type 2 diabetes were screened,yielding a DR detection rate of 26.0%(147 cases).Research findings demonstrate that applying mature Chinese DR-AI screening standards and technological solutions through international collaboration in regions with a scarcity of ophthalmic professionals is both feasible and effective.This project serves as a reference for promoting DR-AI in resource-constrained countries and regions,highlighting its significant potential to leverage AI in addressing the global burden of chronic diseases and advancing the modernization of health systems.
文摘“By successfully integrating artificial intelligence(AI)into research workflows,researchers could substantially increase scientific productivity”[1].In biofabrication,AI is dr iving a paradigm shift from empiricism toward intelligen t,data centric manufacturing[2].By integrating computation,automation,and biology,AI gives rise to self-evolving,adaptive systems that learn from data,predict complex behaviors,and autonomously optimize fabrication outcomes.Such systems translate experimental insights into patient-specific and clinically relevant solutions,bridging laboratory research and regenerative therapies[3].This emerging frontier is rapidly advancing from concept to application.This Special Column highlights how AI-driven advanc es in materials,design,and manufacturing are reshaping biof abrication for regenerative medicine and clinical translation.
文摘The integration of machine learning(ML)into geohazard assessment has successfully instigated a paradigm shift,leading to the production of models that possess a level of predictive accuracy previously considered unattainable.However,the black-box nature of these systems presents a significant barrier,hindering their operational adoption,regulatory approval,and full scientific validation.This paper provides a systematic review and synthesis of the emerging field of explainable artificial intelligence(XAI)as applied to geohazard science(GeoXAI),a domain that aims to resolve the long-standing trade-off between model performance and interpretability.A rigorous synthesis of 87 foundational studies is used to map the intellectual and methodological contours of this rapidly expanding field.The analysis reveals that current research efforts are concentrated predominantly on landslide and flood assessment.Methodologically,tree-based ensembles and deep learning models dominate the literature,with SHapley Additive exPlanations(SHAP)frequently adopted as the principal post-hoc explanation technique.More importantly,the review further documents how the role of XAI has shifted:rather than being used solely as a tool for interpreting models after training,it is increasingly integrated into the modeling cycle itself.Recent applications include its use in feature selection,adaptive sampling strategies,and model evaluation.The evidence also shows that GeoXAI extends beyond producing feature rankings.It reveals nonlinear thresholds and interaction effects that generate deeper mechanistic insights into hazard processes and mechanisms.Nevertheless,several key challenges remain unresolved within the field.These persistent issues are especially pronounced when considering the crucial necessity for interpretation stability,the demanding scholarly task of reliably distinguishing correlation from causation,and the development of appropriate methods for the treatment of complex spatio-temporal dynamics.
文摘High-throughput transcriptomics has evolved from bulk RNA-seq to single-cell and spatial profiling,yet its clinical translation still depends on effective integration across diverse omics and data modalities.Emerging foundation models and multimodal learning frameworks are enabling scalable and transferable representations of cellular states,while advances in interpretability and real-world data integration are bridging the gap between discovery and clinical application.This paper outlines a concise roadmap for AI-driven,transcriptome-centered multi-omics integration in precision medicine(Figure 1).
基金supported via funding from Prince Sattam bin Abdulaziz University project number(PSAU/2025/03/32440).
文摘Parkinson’s disease remains a major clinical issue in terms of early detection,especially during its prodromal stage when symptoms are not evident or not distinct.To address this problem,we proposed a new deep learning 2-based approach for detecting Parkinson’s disease before any of the overt symptoms develop during their prodromal stage.We used 5 publicly accessible datasets,including UCI Parkinson’s Voice,Spiral Drawings,PaHaW,NewHandPD,and PPMI,and implemented a dual stream CNN–BiLSTM architecture with Fisher-weighted feature merging and SHAP-based explanation.The findings reveal that the model’s performance was superior and achieved 98.2%,a F1-score of 0.981,and AUC of 0.991 on the UCI Voice dataset.The model’s performance on the remaining datasets was also comparable,with up to a 2–7 percent betterment in accuracy compared to existing strong models such as CNN–RNN–MLP,ILN–GNet,and CASENet.Across the evidence,the findings back the diagnostic promise of micro-tremor assessment and demonstrate that combining temporal and spatial features with a scatter-based segment for a multi-modal approach can be an effective and scalable platform for an“early,”interpretable PD screening system.
基金partially supported by the National Natural Science Foundation of China(Nos.32471474 and 82102574)the Precision Medicine Project of People’s Hospital of Xinjiang Uygur Autonomous Region(No.20220305)+4 种基金Chengdu Advanced Metal Materials Industry Technology Research Institute Co.,Ltd.Support Project(No.24H0802)Sichuan Science and Technology Program(Nos.2025YFHZ0086,2023YFS0053,2024YFHZ0125,and 2025ZNSFSC0381)Project of Tianfu Jincheng Laboratory(No.2025ZH009)Guangdong Basic and Applied Basic Research Foundation(No.2023A1515220102)Xinjiang Autonomous Region Science and Technology Support Project Plan(Directive)Project(No.2024E02049)。
文摘Cases of widespread bone hydatid infection are relatively rare in clinical practice.In this study,we reported for the first time a validated integrated repair therapy for multiple bone tissues,including the hip,femur,and knee,caused by echinococ cosis.Artificial intelligence(AI)was used to develop a targeted surgical plan and to design a personalized prosthesis.Finite element analysis(FEA)was used to optimize the mechanical effectiveness of a customized integrated replacement prosthesis and to model stress distribution in the surrounding bone.Three-dimensional(3 D)printing was used to fabricate a customized prosthesis.With the assistance of AI,FEA,and 3 D printing technology,a personalized surgical plan and customized prosthesis were successfully constructed based on the patient’s disease.This approach achieved a successful therapeutic effect,demonstrating that AI-assisted personalized medicine holds great promise for the future.
文摘In the field of precision healthcare,where accurate decision-making is paramount,this study underscores the indispensability of eXplainable Artificial Intelligence(XAI)in the context of epilepsy management within the Internet of Medical Things(IoMT).The methodology entails meticulous preprocessing,involving the application of a band-pass filter and epoch segmentation to optimize the quality of Electroencephalograph(EEG)data.The subsequent extraction of statistical features facilitates the differentiation between seizure and non-seizure patterns.The classification phase integrates Support Vector Machine(SVM),K-Nearest Neighbor(KNN),and Random Forest classifiers.Notably,SVM attains an accuracy of 97.26%,excelling in the precision,recall,specificity,and F1 score for identifying seizures and non-seizure instances.Conversely,KNN achieves an accuracy of 72.69%,accompanied by certain trade-offs.The Random Forest classifierstands out with a remarkable accuracy of 99.89%,coupled with an exceptional precision(99.73%),recall(100%),specificity(99.80%),and F1 score(99.86%),surpassing both SVM and KNN performances.XAI techniques,namely Local Interpretable ModelAgnostic Explanations(LIME)and SHapley Additive exPlanation(SHAP),enhance the system’s transparency.This combination of machine learning and XAI not only improves the reliability and accuracy of the seizure detection system but also enhances trust and interpretability.Healthcare professionals can leverage the identified important features and their dependencies to gain deeper insights into the decision-making process,aiding in informed diagnosis and treatment decisions for patients with epilepsy.
文摘The advent of 6G wireless technology,which offers previously unattainable data rates,very low latency,and compatibility with a wide range of communication devices,promises to transform the networking environment completely.The 6G wireless proposals aim to expand wireless communication’s capabilities well beyond current levels.This technology is expected to revolutionize how we communicate,connect,and use the power of the digital world.However,maintaining secure and efficient data management becomes crucial as 6G networks grow in size and complexity.This study investigates blockchain clustering and artificial intelligence(AI)approaches to ensure a reliable and trustworthy communication in 6G.First,the mechanisms and protocols of blockchain clustering that provide a trusted and effective communication infrastructure for 6G networks are presented.Then,AI techniques for network security in 6G are studied.The integration of AI and blockchain to ensure energy efficiency in 6Gnetworks is addressed.Next,this paper presents howthe 6G’s speed and bandwidth enables AI and the easy management of virtualized systems.Using terahertz connections is sufficient to have virtualized systems move compute environments as well as data.For instance,a computing environment can follow potential security violations while leveraging AI.Such virtual machines can store their findings in blockchains.In 6G scenarios,case studies and real-world applications of AI-powered secure blockchain clustering are given.Moreover,challenges and promising future research opportunities are highlighted.These challenges and opportunities provide insights from the most recent developments and point to areas where AI and blockchain further ensure security and efficiency in 6G networks.
文摘Skin cancer is among the most common malignancies worldwide,but its mortality burden is largely driven by aggressive subtypes such as melanoma,with outcomes varying across regions and healthcare settings.These variations emphasize the importance of reliable diagnostic technologies that support clinicians in detecting skin malignancies with higher accuracy.Traditional diagnostic methods often rely on subjective visual assessments,which can lead to misdiagnosis.This study addresses these challenges by developing HybridFusionNet,a novel model that integrates Convolutional Neural Networks(CNN)with 1D feature extraction techniques to enhance diagnostic accuracy.Utilizing two extensive datasets,BCN20000 and HAM10000,the methodology includes data preprocessing,application of Synthetic Minority Oversampling Technique combined with Edited Nearest Neighbors(SMOTEENN)for data balancing,and optimization of feature selection using the Tree-based Pipeline Optimization Tool(TPOT).The results demonstrate significant performance improvements over traditional CNN models,achieving an accuracy of 0.9693 on the BCN20000 dataset and 0.9909 on the HAM10000 dataset.The HybridFusionNet model not only outperforms conventionalmethods but also effectively addresses class imbalance.To enhance transparency,it integrates post-hoc explanation techniques such as LIME,which highlight the features influencing predictions.These findings highlight the potential of HybridFusionNet to support real-world applications,including physician-assist systems,teledermatology,and large-scale skin cancer screening programs.By improving diagnostic efficiency and enabling access to expert-level analysis,the modelmay enhance patient outcomes and foster greater trust in artificial intelligence(AI)-assisted clinical decision-making.
文摘Skin cancer is the most prevalent cancer globally,primarily due to extensive exposure to Ultraviolet(UV)radiation.Early identification of skin cancer enhances the likelihood of effective treatment,as delays may lead to severe tumor advancement.This study proposes a novel hybrid deep learning strategy to address the complex issue of skin cancer diagnosis,with an architecture that integrates a Vision Transformer,a bespoke convolutional neural network(CNN),and an Xception module.They were evaluated using two benchmark datasets,HAM10000 and Skin Cancer ISIC.On the HAM10000,the model achieves a precision of 95.46%,an accuracy of 96.74%,a recall of 96.27%,specificity of 96.00%and an F1-Score of 95.86%.It obtains an accuracy of 93.19%,a precision of 93.25%,a recall of 92.80%,a specificity of 92.89%and an F1-Score of 93.19%on the Skin Cancer ISIC dataset.The findings demonstrate that the model that was proposed is robust and trustworthy when it comes to the classification of skin lesions.In addition,the utilization of Explainable AI techniques,such as Grad-CAM visualizations,assists in highlighting the most significant lesion areas that have an impact on the decisions that are made by the model.
文摘Quality of Service(QoS)assurance in programmable IoT and 5G networks is increasingly threatened by cyberattacks such as Distributed Denial of Service(DDoS),spoofing,and botnet intrusions.This paper presents AutoSHARC,a feedback-driven,explainable intrusion detection framework that integrates Boruta and LightGBM–SHAP feature selection with a lightweight CNN–Attention–GRU classifier.AutoSHARC employs a two-stage feature selection pipeline to identify the most informative features from high-dimensional IoT traffic and reduces 46 features to 30 highly informative ones,followed by post-hoc SHAP-guided retraining to refine feature importance,forming a feedback loopwhere only the most impactful attributes are reused to retrain themodel.This iterative refinement reduces computational overhead,accelerates detection latency,and improves transparency.Evaluated on the CIC IoT 2023 dataset,AutoSHARC achieves 98.98%accuracy,98.9%F1-score,and strong robustness with a Matthews Correlation Coefficient of 0.98 and Cohen’s Kappa of 0.98.The final model contains only 531,272 trainable parameters with a compact 2 MB size,enabling real-time deployment on resource-constrained IoT nodes.By combining explainable AI with iterative feature refinement,AutoSHARC provides scalable and trustworthy intrusion detection while preserving key QoS indicators such as latency,throughput,and reliability.
基金supported by the National Natural Science Foundation of China under Grant 61602162the Hubei Provincial Science and Technology Plan Project under Grant 2023BCB041.
文摘With the birth of Software-Defined Networking(SDN),integration of both SDN and traditional architectures becomes the development trend of computer networks.Network intrusion detection faces challenges in dealing with complex attacks in SDN environments,thus to address the network security issues from the viewpoint of Artificial Intelligence(AI),this paper introduces the Crayfish Optimization Algorithm(COA)to the field of intrusion detection for both SDN and traditional network architectures,and based on the characteristics of the original COA,an Improved Crayfish Optimization Algorithm(ICOA)is proposed by integrating strategies of elite reverse learning,Levy flight,crowding factor and parameter modification.The ICOA is then utilized for AI-integrated feature selection of intrusion detection for both SDN and traditional network architectures,to reduce the dimensionality of the data and improve the performance of network intrusion detection.Finally,the performance evaluation is performed by testing not only the NSL-KDD dataset and the UNSW-NB 15 dataset for traditional networks but also the InSDN dataset for SDN-based networks.Experimental results show that ICOA improves the accuracy by 0.532%and 2.928%respectively compared with GWO and COA in traditional networks.In SDN networks,the accuracy of ICOA is 0.25%and 0.3%higher than COA and PSO.These findings collectively indicate that AI-integrated feature selection based on the proposed ICOA can promote network intrusion detection for both SDN and traditional architectures.
基金the National Science and Technology Council(NSTC)of the Republic of China,Taiwan,for financially supporting this research under Contract No.NSTC 112-2637-M-131-001.
文摘Accurate and efficient brain tumor segmentation is essential for early diagnosis,treatment planning,and clinical decision-making.However,the complex structure of brain anatomy and the heterogeneous nature of tumors present significant challenges for precise anomaly detection.While U-Net-based architectures have demonstrated strong performance in medical image segmentation,there remains room for improvement in feature extraction and localization accuracy.In this study,we propose a novel hybrid model designed to enhance 3D brain tumor segmentation.The architecture incorporates a 3D ResNet encoder known for mitigating the vanishing gradient problem and a 3D U-Net decoder.Additionally,to enhance the model’s generalization ability,Squeeze and Excitation attention mechanism is integrated.We introduce Gabor filter banks into the encoder to further strengthen the model’s ability to extract robust and transformation-invariant features from the complex and irregular shapes typical in medical imaging.This approach,which is not well explored in current U-Net-based segmentation frameworks,provides a unique advantage by enhancing texture-aware feature representation.Specifically,Gabor filters help extract distinctive low-level texture features,reducing the effects of texture interference and facilitating faster convergence during the early stages of training.Our model achieved Dice scores of 0.881,0.846,and 0.819 for Whole Tumor(WT),Tumor Core(TC),and Enhancing Tumor(ET),respectively,on the BraTS 2020 dataset.Cross-validation on the BraTS 2021 dataset further confirmed the model’s robustness,yielding Dice score values of 0.887 for WT,0.856 for TC,and 0.824 for ET.The proposed model outperforms several state-of-the-art existing models,particularly in accurately identifying small and complex tumor regions.Extensive evaluations suggest integrating advanced preprocessing with an attention-augmented hybrid architecture offers significant potential for reliable and clinically valuable brain tumor segmentation.
