International Business Machines Corporation

Chinese Academy of Sciences

Juniper Networks, Inc.

Beijing Jiaotong University

Shan Yu

Hui Li

Yang Zhang

Si Bin Fan

Juan Zhang

Yang Chen

Qian Jin

Yan Shi

Jing Quan

Andrew Anthony Emmett

Hao Lian

Fan Yang

Guanxiong Zeng

Zhenyu Zhang

Di Wang

Yong Qin

Qingming Ma

Bryan Burns

Yuan Zhang

Li Fei Zheng

Sheng Shuang Li

Huijun Wu

Na Liu

Shiwei Wang

Limin Jia

Xuejun Wu

Lvyan Ma

Jingxuan Shi

Xiaoqing Cheng

Linlin Kou

A feature extraction system, method and apparatus based on neural network optimization by gradient filtering is provided. The feature extraction method includes: acquiring, by an information acquisition device, input information; constructing, by a feature extraction device, different feature extraction networks, performing iterative training on the networks in combination with corresponding training task queues to obtain optimized feature extraction networks for different input information, and calling a corresponding optimized feature extraction network to perform feature extraction according to a class of the input information; performing, by an online updating device, online updating of the networks; and outputting, by a feature output device, a feature of the input information. The new feature extraction system, method and apparatus avoids the problem of catastrophic forgetting of the artificial neural network in continuous tasks, and achieves high accuracy and precision in continuous feature extraction.

Feature extraction system, method and apparatus based on neural network optimization by gradient filtering

An information processing method based on contextual signals and a prefrontal cortex-like network includes: selecting a feature vector extractor based on obtained information to perform feature extraction to obtain an information feature vector; inputting the information feature vector into the prefrontal cortex-like network, and performing dimensional matching between the information feature vector and each contextual signal in an input contextual signal set to obtain contextual feature vectors to constitute a contextual feature vector set; and classifying each feature vector in the contextual feature vector set by a feature vector classifier to obtain classification information of the each feature vector to constitute a classification information set. An information processing system based on contextual signals and a prefrontal cortex-like network includes an acquisition module, a feature extraction module, a dimensional matching module, a classification module and an output module.

Information processing method, system and device based on contextual signals and prefrontal cortex-like network

Automated devices send messages of a first batch sequence individually to a target queue of a receiving node of a cluster of server nodes, the messages having a different sequence number indicative of their relative positions within the batch sequence, and each is associated with a first logic unit of work identifier. In response to determining that a message counter meets a threshold, a force commit packet is generated to include the sequence number of the last batch message sent to the target queue. If the force commit packet sequence number is not the last position number within the batch sequence, a second logic unit of work identifier is associated with a subset sequence of the batch of messages having sequence numbers spanning from the first number to the force commit packet sequence number, and the subset sequence messages are committed to the receiving node target queue.

Proactive channel agent

The present disclosure provides an inhibitor for inhibiting or disrupting biofilm and use thereof. Specifically, the present disclosure an application of a PsIG protein and a coding sequence thereof in inhibiting or disrupting a biofilm of a microorganism. The present disclosure also provides a composition and a preparation containing the PsIG protein to inhibit or disrupt a biofilm of a microorganism. The experiment shows that PsIG can effectively inhibit or disrupt a biofilm ofspecies, suggesting the great potential of PsIG in clinical and environmental fields.

Reagents and methods for inhibiting or disrupting biofilm

Embodiments of the present invention provide methods, program products, and systems to increase efficiency in message oriented middleware. Embodiments of the present invention can, responsive to receiving from an application an open request for a queue alias of a queue manager, provide to the application target cache information which includes a target name and a change flag count associated with the queue alias. Embodiments of the present invention can, responsive to receiving a message from the application that includes respective target cache information including a target name and a change flag count, determine a target location, wherein if the change flag count of the received message matches a current change flag count of the queue alias, the determined target location is a target location associated with the received target name.

Dynamic queue alias

The present invention provides a fault prediction and condition-based repair method of an urban rail train bogie. An optimum service life distribution model of a framework, a spring device, a connecting device, a wheel set and axle box, a driving mechanism, and a basic brake device of a bogie is determined by adopting a method based on survival analysis; a reliability characteristic function of each subsystem is obtained; then, a failure rate of each subsystem of the bogie is calculated by adopting a neural network model optimized by an evolutionary algorithm; and finally, proportional risk modelling is conducted by taking the failure rate and safe operation days of each subsystem of the bogie as concomitant variables; and on the basis of cost optimization, thresholds and control limits for condition-based repair of a bogie system are obtained.

Fault prediction and condition-based repair method of urban rail train bogie

A method includes receiving a data unit, determining whether a current state, associated with a deterministic finite automata (DFA) that includes a portion of states in a bitmap and a remaining portion of states in a DFA table, is a bitmap state or not, and determining whether a value corresponding to the data unit is greater than a threshold value, when it is determined that the current state is not a bitmap state. The method further includes determining whether the current state is insensitive, when it is determined that the value corresponding to the data unit is greater than the threshold value, where insensitive means that each next state is a same state for the current state, and selecting a default state, as a next state for the current, when it is determined that the current state is insensitive.

Hybrid representation for deterministic finite automata

Growing community of inventors

Beijing, China

Shan Yu