An Anomaly Detection Method of Industrial Data Based on Stacking Integration

With the development of Internet technology,the computing power of data has increased,and the development of machine learning has become faster and faster.In the industrial production of industrial control systems,quality inspection and safety production of process products have always been our concern.Aiming at the low accuracy of anomaly detection in process data in industrial control system,this paper proposes an anomaly detection method based on stacking integration using the machine learning algorithm.Data are collected from the industrial site and processed by feature engineering.Principal component analysis(PCA)and integrated rule tree method are adopted to reduce the dimension of the process data,which can restore the original feature information of the data to the maximum extent.Random forest(RF),Adaboost,XGboost,SVM were selected as the first layer of basic learners.Logistic regression(LR)was used as the secondary learner to build the exception detection model based on stacking integrated method.TE data was used to train the base learner model and the integrated model.By comparing and analyzing the experimental results of between integrated model and each basic learning model.By comparing and analyzing the experimental results of the constructed anomaly detection model and the basic learning model,the accuracy of process data anomaly detection is effectively improved,and the false alarm rate of process data anomaly detection is effectively reduced.

Experimental realization of a quantum image classifier via tensor-network-based machine learning

Quantum machine learning aspires to overcome intractability that currently limits its applicability to practical applications.However,quantum machine learning itself is limited by low effective dimensions achievable in stateof-the-art experiments.Here,we demonstrate highly successful classifications of real-life images using photonic qubits,combining a quantum tensor-network representation of hand-written digits and entanglement-based optimization.Specifically,we focus on binary classification for hand-written zeroes and ones,whose features are cast into the tensor-network representation,further reduced by optimization based on entanglement entropy and encoded into two-qubit photonic states.We then demonstrate image classification with a high success rate exceeding 98%,through successive gate operations and projective measurements.Although we work with photons,our approach is amenable to other physical realizations such as nitrogen-vacancy centers,nuclear spins,and trapped ions,and our scheme can be scaled to efficient multi-qubit encodings of features in the tensor-product representation,thereby setting the stage for quantum-enhanced multi-class classification.

Experimental witnessing for entangled states with limited local measurements

We experimentally demonstrate a method for detection of entanglement via construction of entanglement witnesses from a limited fixed set of local measurements(M).Such a method does not require a priori knowledge about the form of the entanglement witnesses.It is suitable for a scenario where a full state tomography is not available,but the only resource is a limited set of M.We demonstrate the method on pure two-qubit entangled states and mixed two-qubit entangled states,which emerge from photonic implementation of controllable quantum noisy channels.The states we select are motivated by realistic experimental conditions,and we confirm it works well for both cases.Furthermore,possible generalizations to higher-dimensional bipartite systems have been considered,which can potentially detect both decomposable and indecomposable entanglement witnesses.Our experimental results show perfect validity of the method,which indicates that even a limited set of local measurements can be used for quick entanglement detection and further provide a practical test bed for experiments with entanglement witnesses.