66results about How to "Improve anomaly detection accuracy" patented technology

The invention discloses a distributed migration network learning-based intrusion detection system and a method thereof, and mainly solves the problems that the prior method has low efficiency in detection of some attack types and is difficult to search data again. The whole system comprises a network behavior record preprocessing module, an abnormality detection module and an abnormal behavior analyzing module. The network behavior record preprocessing module completes the quantification and normalization processing of a network behavior record; the abnormality detection module uses an abnormality detection learning machine to completes the classification and identification for an input record, determines whether the record is a normal behavior, and completes the detection if the record isa normal behavior or transmits the record to the abnormal behavior analyzing module if the record is an abnormal behavior; and the abnormal behavior analyzing module uses an abnormal behavior analyzing learning machine to carry out the classification and identification of the input records and outputs the attach type of the record. The system and the method have the advantages of using other existing resources to improve the detection rate for the prior attach types with low detection rate and avoiding searching the data again and can be used for network intrusion detection.

The invention relates to diagnosis operation device and method of an elevator. A reference mode corresponding to the environmental temperature, the traveling status and the like before an earthquake occurs is set before diagnosis operation is implemented, and the abnormity detection precision in diagnosis operation can be greatly improved. The diagnosis operation is carried out after control operation in the earthquake is implemented, i.e. a lift car of the elevator travels, preset elevator equipment is simultaneously measured, and a measured value and the reference mode are compared to judgewhether the equipment is abnormal or not. Before the earthquake occurs, the reference mode corresponding to the equipment is prestored in a reference mode storage part (3). In the preset period afterthe earthquake occurs, the variation is measured when the reference mode corresponding to the equipment is relatively stored in the reference mode storage part (3). Then, the reference mode corresponding to the equipment is reset before the diagnosis operation starts according to the reference mode stored in the reference mode storage part (3) before the earthquake occurs and the variation obtained in the preset period after the earthquake occurs.

Provided is a control method for a secondary battery in which a malfunction is less likely to occur and which can perform abnormality detection with high accuracy. This charge state estimation apparatus for a secondary battery includes: a device for generating an electromagnetic noise; a first detection means for measuring a voltage value of the secondary battery that is electrically connected with the device; a second detection means for detecting a current value of the secondary battery that is electrically connected with the device; a correction means for extracting a causal relationship between the electromagnetic noise and a driving pattern from data that is obtained by using the first detection means or the second detection means and that includes a plurality of electromagnetic noises, and performing data correction on the basis of the causal relationship; and a calculation means for calculating a charging rate by using a regression model on the basis of data after the data correction.

An elevator door control device is provided in which the precision of abnormality detection in door opening and closing operations is increased by appropriately detecting abnormalities in torque commands, so that there is little erroneous detection of abnormalities in door opening and closing operations. The elevator door control device has: a speed command portion that outputs a speed command; a speed control portion that outputs a torque command corresponding to a deviation between the speed command and a feedback speed; a reference torque command pattern storage portion that stores a plurality of torque command patterns that are formed by a plurality of the torque commands sampled according to door opening and closing operations, and stores a reference torque command pattern that is obtained based on the torque commands at each common sampling of the plurality of torque commands; an abnormality detection torque pattern generator portion that generates an abnormality detection torque pattern from the reference torque command pattern; and an abnormality avoiding unit that outputs an abnormality avoiding command to the speed command portion when the torque command exceeds the abnormality detection torque pattern.

An anomaly detection method includes generating second data by adding normal noise to first data; generating third data by adding abnormal noise to the first data; inputting the first data, the second data, and the third data to a neural network; calculating a first normal score, a second normal score, and a third normal score; calculating a third difference based on a first difference and a second difference, the first difference being based on a difference between the first normal score and the second normal score, the second difference being based on a difference between the first normal score and the third normal score; changing the neural network so that the third difference becomes smallest; inputting, to the changed neural network, fourth data that is unknown in terms of whether the fourth data is normal or abnormal; and determining whether the fourth data is normal or abnormal.