National Taiwan University

Industrial Technology Research Institute

Tsinghua University

Institute for Information Industry

Chia-Peng Lee

Phone Lin

En-Hau Yeh

Xin-Xue Lin

Chin-Liang Wang

Whai-En Chen

Shun-Neng Yang

Char-Dir Chung

Tao Zhang

Brian Hu Zhang

According to one embodiment of the invention, a method for detecting driving anomalies comprises steps of: with at least one algorithm, processing raw data from On-Board Diagnostics of a car to generate time-series data, with the time series data as input, using an automatic driving behavior separating technology to identify a plurality of driving behaviors; with the driving behaviors as input, using an artificial intelligence technology to build up a driving anomaly detection model without labeling the driving behaviors; and issuing an alarm for driving anomaly identified according to an analyzing result of alarm signature of the driving behaviors.

Method and system for detecting driving anomalies

An anomaly flow detection device and an anomaly flow detection method thereof are provided. The device can retrieve a plurality of training data transmitted between a monitored network and an external network, preprocess a plurality of packet headers of the pluralities of training data to obtain a plurality of training feature vectors, construct a flow recognition model with an unsupervised learning method, input the pluralities of training feature vectors to the flow recognition model to train the flow recognition model, retrieve a plurality of testing data transmitted between the monitored network and the external network, preprocess a plurality of packet headers of the pluralities of testing data to obtain a plurality of testing feature vectors, input the pluralities of testing feature vectors to the flow recognition model to identify whether the pluralities of packet headers of the pluralities of testing data are normal or abnormal, and determine the flow of the monitored network is abnormal according to the recognition result of the flow recognition model.

Anomaly flow detection device and anomaly flow detection method

A detective method, applied in a detective system comprising an activity-or-behavior model constructor, for activity-or-behavior model construction and automatic detection of activities of a subject system, comprises steps of using an unsupervised machine learning technique, a Natural Language Processing technique (NLP) and a supervised machine learning technique. As such, an activity-or-behavior model is built for predicting the future behaviors of the subject system and automatically detecting abnormal activities or behaviors of the subject system. The activity-or-behavior model is capable to handle multidimensional sensor data input from a plurality of sensor data streams and incorporate the sensor data values and a selected temporal information about at least one sensor data stream and between different sensor data streams.

Detective method and system for activity-or-behavior model construction and automatic detection of the abnormal activities or behaviors of a subject system without requiring prior domain knowledge

An offload determination system for multiple wireless network, a server and a method thereof are provided. The system includes a server, a first and a second wireless base station and a user equipment (UE). The first and the second wireless base station provides a first and a second wireless network respectively. The server has traffic tariff information corresponding to the UE. The server monitors and obtains quality of service (QoS) information of the first and the second wireless base station respectively, evaluates a data transfer efficiency information of the first and the second wireless base stations according to the traffic tariff information and the QoS information, and transmits the data transfer efficiency information to the UE. The UE selectively uses the first or second wireless network based on the data transmission efficiency information.

Offload determination system for multiple wireless network, server and method thereof

A method for reducing the handover frequency by a communication device in femtocell networks includes the steps: measuring the radio signal strength by a communication device and storing the information of the serving base station into a cache memory; checking whether the stored information in the cache memory is classified as 'femtocell' or not; if so, deleting the macrocell's information from the measurement report by the communication device and transmitting this to the serving base station; when the radio link failure occurred, checking whether the stored information in the cache memory is classified as 'femtocell' or not; if so, initiating a timer; detecting an available femtocell before the timer expires; transmitting a call reestablishment request message to the available femtocell for rebuilding the link.

Method for reducing the handover frequency by a communication device in femtocell networks

A method for reducing the handover frequency by a femto gateway in femtocell networks includes the steps: receiving a measurement report from a communication device by an initial femtocell; transmitting a relocation required message to a femto gateway by the initial femtocell if the signal strength thereof is below a threshold; ignoring the relocation required message and enabling the timer by the femto gateway after receiving the relocation required message; determining whether the cell ID included in the call reestablishment request message is classified as 'femtocell' or not by the femto gateway before the timer expires; if so, rebuilding the link to the femtocell in response to the cell ID by the femto gateway.

Growing community of inventors

Taipei, Taiwan

Chia-Peng Lee