The increasing integration of cyber-physical components in Industry 4.0 water infrastructures has heightened the risk of false data injection(FDI)attacks,posing critical threats to operational integrity,resource manag...The increasing integration of cyber-physical components in Industry 4.0 water infrastructures has heightened the risk of false data injection(FDI)attacks,posing critical threats to operational integrity,resource management,and public safety.Traditional detection mechanisms often struggle to generalize across heterogeneous environments or adapt to sophisticated,stealthy threats.To address these challenges,we propose a novel evolutionary optimized transformer-based deep reinforcement learning framework(Evo-Transformer-DRL)designed for robust and adaptive FDI detection in smart water infrastructures.The proposed architecture integrates three powerful paradigms:a transformer encoder for modeling complex temporal dependencies in multivariate time series,a DRL agent for learning optimal decision policies in dynamic environments,and an evolutionary optimizer to fine-tune model hyper-parameters.This synergy enhances detection performance while maintaining adaptability across varying data distributions.Specifically,hyper-parameters of both the transformer and DRL modules are optimized using an improved grey wolf optimizer(IGWO),ensuring a balanced trade-off between detection accuracy and computational efficiency.The model is trained and evaluated on three realistic Industry 4.0 water datasets:secure water treatment(SWaT),water distribution(WADI),and battle of the attack detection algorithms(BATADAL),which capture diverse attack scenarios in smart treatment and distribution systems.Comparative analysis against state-of-the-art baselines including Transformer,DRL,bidirectional encoder representations from transformers(BERT),convolutional neural network(CNN),long short-term memory(LSTM),and support vector machines(SVM)demonstrates that our proposed Evo-Transformer-DRL framework consistently outperforms others in key metrics such as accuracy,recall,area under the curve(AUC),and execution time.Notably,it achieves a maximum detection accuracy of 99.19%,highlighting its strong generalization capability across different testbeds.These results confirm the suitability of our hybrid framework for real-world Industry 4.0 deployment,where rapid adaptation,scalability,and reliability are paramount for securing critical infrastructure systems.展开更多
Recent increase in the adulteration of spices and aromatic herbs in food industry constitutes a problem that requires exhaustive quality control.As every spice has a different composition with characteristic biomarker...Recent increase in the adulteration of spices and aromatic herbs in food industry constitutes a problem that requires exhaustive quality control.As every spice has a different composition with characteristic biomarkers,chromatographic profiles are especially valuable to authenticate these products.Thus,in this work a new high performance liquid chromatography(HPLC)method with UV-vis detection was developed for the characterization,identification and authentication of cinnamon,oregano,thyme,sesame,bay leaf,clove,cumin,and vanilla.Chromatographic separation was optimized based on the separation of six characteristic biomarkers(sesamol,eugenol,thymol,carvacrol,salicylaldehyde and vainillin)and was performed using a C18 reversed-phase column under a 35 min gradient elution based on 0.1%(v/v)formic aqueous solution and methanol by means of UV-Vis detection at 280 nm.87 samples,purchased in local supermarkets,were analyzed and the obtained profiles were processed by chemometric techniques.First,data treatment was evaluated by principal component analysis(PCA);next soft independent modelling by class analogy(SIMCA)and partial least squares discriminant analysis(PLS-DA)were carried out in order to verify if classification according to their biomarkers was possible.The study concluded that PLS-DA(0.14-0.75%global error)classifies better the types of spice or aromatic herb than SIMCA(0.82-3.67%global error).展开更多
文摘The increasing integration of cyber-physical components in Industry 4.0 water infrastructures has heightened the risk of false data injection(FDI)attacks,posing critical threats to operational integrity,resource management,and public safety.Traditional detection mechanisms often struggle to generalize across heterogeneous environments or adapt to sophisticated,stealthy threats.To address these challenges,we propose a novel evolutionary optimized transformer-based deep reinforcement learning framework(Evo-Transformer-DRL)designed for robust and adaptive FDI detection in smart water infrastructures.The proposed architecture integrates three powerful paradigms:a transformer encoder for modeling complex temporal dependencies in multivariate time series,a DRL agent for learning optimal decision policies in dynamic environments,and an evolutionary optimizer to fine-tune model hyper-parameters.This synergy enhances detection performance while maintaining adaptability across varying data distributions.Specifically,hyper-parameters of both the transformer and DRL modules are optimized using an improved grey wolf optimizer(IGWO),ensuring a balanced trade-off between detection accuracy and computational efficiency.The model is trained and evaluated on three realistic Industry 4.0 water datasets:secure water treatment(SWaT),water distribution(WADI),and battle of the attack detection algorithms(BATADAL),which capture diverse attack scenarios in smart treatment and distribution systems.Comparative analysis against state-of-the-art baselines including Transformer,DRL,bidirectional encoder representations from transformers(BERT),convolutional neural network(CNN),long short-term memory(LSTM),and support vector machines(SVM)demonstrates that our proposed Evo-Transformer-DRL framework consistently outperforms others in key metrics such as accuracy,recall,area under the curve(AUC),and execution time.Notably,it achieves a maximum detection accuracy of 99.19%,highlighting its strong generalization capability across different testbeds.These results confirm the suitability of our hybrid framework for real-world Industry 4.0 deployment,where rapid adaptation,scalability,and reliability are paramount for securing critical infrastructure systems.
基金This work is supported by PID2019-107102RB-C21 and PID2019-107102RB-C22 funded by MCIN/AEI/10.13039/501100011033 and the Generalitat of Catalunya(Project 2017SGR311)。
文摘Recent increase in the adulteration of spices and aromatic herbs in food industry constitutes a problem that requires exhaustive quality control.As every spice has a different composition with characteristic biomarkers,chromatographic profiles are especially valuable to authenticate these products.Thus,in this work a new high performance liquid chromatography(HPLC)method with UV-vis detection was developed for the characterization,identification and authentication of cinnamon,oregano,thyme,sesame,bay leaf,clove,cumin,and vanilla.Chromatographic separation was optimized based on the separation of six characteristic biomarkers(sesamol,eugenol,thymol,carvacrol,salicylaldehyde and vainillin)and was performed using a C18 reversed-phase column under a 35 min gradient elution based on 0.1%(v/v)formic aqueous solution and methanol by means of UV-Vis detection at 280 nm.87 samples,purchased in local supermarkets,were analyzed and the obtained profiles were processed by chemometric techniques.First,data treatment was evaluated by principal component analysis(PCA);next soft independent modelling by class analogy(SIMCA)and partial least squares discriminant analysis(PLS-DA)were carried out in order to verify if classification according to their biomarkers was possible.The study concluded that PLS-DA(0.14-0.75%global error)classifies better the types of spice or aromatic herb than SIMCA(0.82-3.67%global error).
