Sap Se

Ittiam Systems (p) Ltd.

Nxp B.v.

Rajendra Kumar

Rahul Garg

Roshan Rajendra Baliga

Seshadri Chatterjee

Jai Vignesh R

Sreenath Ramanath

Rahul Choudhary

Johannes Boonstra

Venkatesh R

Lohit Kumar A P

Sundaravaradan Rangarajan

Heinz Wolf

A method for machine learning based database management is provided. The method may include training a machine learning model to detect an anomaly that is present and/or developing in a database system. The anomaly in the database system may be detected by at least processing, with a trained machine learning model, one or more performance metrics for the database system. In response to detecting the presence of the anomaly at the database system, one or more remedial actions may be determined for correcting and/or preventing the anomaly at the database system. The one or more remedial actions may further be sent to a database management system associated with the database system. Related systems and articles of manufacture are also provided.

Machine learning based database anomaly prediction

A machine learning model including an autoencoder may be trained based on training data that includes sequences of non-anomalous performance metrics from an information technology system but excludes sequences of anomalous performance metrics. The trained machine learning model may process a sequence of performance metrics from the information technology system by generating an encoded representation of the sequence of performance metrics and generating, based on the encoded representation, a reconstruction of the sequence of performance metrics. An occurrence of the anomaly at the information technology system may be detected based on a reconstruction error present in reconstruction of the sequence of performance metrics. Related systems, methods, and articles of manufacture are provided.

Variational autoencoding for anomaly detection

Disclosed herein are system, method, and computer program product embodiments for measuring graphical user interface (GUI) usage, generating visual depictions of the GUI usage, and providing GUI modification recommendations based on the GUI usage. A user interface (UI) usage measurement system may monitor user interactions with an application from one or more user devices. The UI usage measurement system may data such as button clicks or other icon interactions on a GUI. After aggregating this information, the UI usage measurement system may apply machine learning techniques to determine a GUI object recommendation. The recommendation may include the movement of one or more GUI objects to different locations so that the user may more quickly access GUI objects that are more heavily utilized. In this manner, the UI usage measurement system may modify the GUI used by a particular user to access elements of an application.

User interface usage measurement and user interface design using machine learning

A FIFO memory circuit is for interfacing between circuits with different clock domains. The circuit has a FIFO memory (), a write pointer circuit () clocked by the clock of a first clock domain and controlling the memory location to which data is written, and a read pointer circuit clocked by the clock of a second clock domain and controlling the memory location from which data is read. The read and write pointer circuits use gray coding. The memory circuit further comprises a duplicate write pointer circuit () which has its write pointer address incremented synchronously with the write pointer circuit (), and which has a starting write address selected such that the duplicate write pointer address lags behind the write pointer address circuit by a number of address locations corresponding to the size of the FIFO memory (). A comparator () compares the read pointer circuit address with the duplicate write pointer circuit address for determining a full status of the FIFO memory.

FIFO buffer

A novel technique for combining deinterleaving operation with Fast Fourier Transformer (FFT) modules and other post FFT modules in a receiver to reduce processing time. In one example embodiment, the deinterleaving operation, in the post FFT module, is combined with FFT and demapper operations to reduce the processing time and complexity.

Method and apparatus for combining de-interleaving with FFT and demapping

A system for receiving and handling a scrambled input data signal that includes a preamble with a start of frame delimiter (SFD) initiates an SFD search on the scrambled input data, thereby attempting to save an initialization period. The initialization period may be of the order of 7 uS, and its saving results in improved timeline management enabling antenna diversity and the possible use of high performance algorithms. The system may use two parallel paths for signal processing, each having an SFD detector and a descrambler. If the detected SFD is short, then the second path is disabled, and if it is long, then the first parallel path is disabled. Alternatively, the first path can be used for a finite period of time (for e.g., 40 symbols) and if the SFD is still not detected, the first path is disabled, and the system uses only the second path.

Growing community of inventors

Bengaluru, India

Rajendra Kumar