Samsung Electronics Co., Ltd.

National Research Council of Canada

Ju Wang

Xue Liu

Gregory Lewis Dudek

Xi Chen

Hang Li

Chengming Hu

Di Wu

Yi Tian Xu

Jikun Kang

Seowoo Jang

Intaik Park

Taeseop Lee

Omid Salehi-Abari

Michael Jenkin

Amal Feriani

Keiko Katsuragawa

Srinivasan Keshav

Daniel Vogel

The present disclosure provides methods, apparatuses, and computer-readable mediums for performing ultra-wideband (UWB) remote control. In some embodiments, the method includes broadcasting an initial control request. The method further includes receiving, from one or more remote devices, at least one reply message comprising identification information and power spectrum information. The method further includes estimating, for each of the one or more remote devices, an angle indicating a pointing direction to that remote device relative to the remote control device. The method further includes determining a selected remote device that is being pointed at by the remote control device. The method further includes sending, to the one or more remote devices, a control signal comprising the identification information of the selected remote device and a control message indicating an action to be performed by the selected remote device.

Ultra-wideband enabled one-for-all smart remote

A server may obtain teacher artificial intelligence (AI) models from source base stations; obtain target traffic data from a target base station; obtain an integrated teacher prediction based on the target traffic data by integrating teacher prediction results of the teacher AI models based on teacher importance weights; obtain a student AI model that is trained to converge a student loss on the target traffic data; update the teacher importance weights to converge a teacher loss between a student prediction of the student AI model on the target traffic data, and the integrated teacher prediction of the teacher AI models on the target traffic data; update the student AI model based on the updated teacher importance weights being applied to the teacher prediction results of the teacher AI models; and predict a communication traffic load of the target base station using the updated student AI model.

Method of load forecasting via knowledge distillation, and an apparatus for the same

A server may be provided to obtain a load balancing artificial intelligence (AI) model for a plurality of base stations in a communication system. The server may obtain teacher models based on traffic data sets collected from the base stations, respectively; perform a policy rehearsal process including obtaining student models based on knowledge distillation from the teacher models, obtaining an ensemble student model by ensembling the student models, and obtaining a policy model by interacting with the ensemble student mode; provide the policy model to each of the base stations for a policy evaluation of the policy model; and based on a training continue signal being received from at least one of the base stations as a result of the policy evaluation, update the ensemble student model and the policy model by performing the policy rehearsal process on the student models.

Method of performing communication load balancing with multi-teacher reinforcement learning, and an apparatus for the same

A server for predicting a future traffic load of a base station is provided. The server may obtain a first prediction model based on traffic data collected from the base station for a first period of time, obtain a second prediction model based on traffic data collected from the same base station for a second period time, and also based on knowledge transferred from the first prediction model. Each of the first prediction model and the second prediction model may include an encoder module, a reconstruction module, and a prediction module which are connected to form two paths, an encoder-reconstruction path and an encoder-prediction path, to preserve more information of historic traffic data.

Method of communication traffic prediction via continual learning with knowledge distillation, and an apparatus for the same

A method and apparatus are provided for effecting an RFID-based finger input sensing system using a transmission line connected to at least two RFID tags, by analyzing a plurality of features relating to the number of spikes in the derivatives of the RSS, timing of maximum RSS and the spikes of the RSS derivatives, relative RSS magnitude between the at least two RFID tags, and increase/decrease trend of the RSS, thereby eliminating the need for calibration and training.

Method and apparatus for finger input sensing

Transfer learning based on prediction determines a similarity between a source base station and a target base station. Importance of parameters is determined and training is adjusted to respect the importance of parameters. A lack of historical data is compensated by selecting a base station as source base station which has a larger amount of historical data.

Transfer learning of network traffic prediction model among cellular base stations

A method is provided. The method includes receiving a first dimension set, extracting a first latent feature set from the first dimension set, training a first base predictor based on the first feature set, generating a second dimension set based on the first dimension set, the second dimension set having fewer dimensions than the first dimension set, extracting a second latent feature set from the second dimension set, training a second base predictor based on the second feature set, and generating a traffic prediction based on the first base predictor and the second base predictor.

Communication load forecasting accuracy with adaptive feature boosting

A method, computer program, and computer system are provided for load forecasting. Datasets corresponding to source machine learning models and a target domain base model are identified. A set of forecasting models corresponding to the identified datasets are learned. An ensemble model is determined from the learned set of forecasting models based on gradient boosting. An available resource is allocated based on the ensemble model.

Short-term load forecasting

A novel method and system is disclosed for using a commodity RFID system for automatically measuring levels of soil moisture in planting containers. A large number of planting containers are used to grow pots in soil in a greenhouse. An RFID reader interrogates passive RFID tags affixed to the planting containers. The RFID reader can be attached to a robotic arm configured to move above multiple rows and columns of containers. Signal features of specific passive RFID tags affixed to specific ones of the containers are automatically monitored, including a minimum response threshold of RFID reader transmission power to activate the passive RFID tag ('MRT'), based on the wireless interrogation of specific tags by the reader. Soil moisture levels of specific containers are then automatically determined based on the signal features of the attached tags, and effects of soilure moisture on electromagnetic fields of antennas of tags.

Automated soil moisture effects sensor with improved RFID system

A first device and second device communicate using mmWave communication with antenna alignment based on processing of ultra wide band (UWB) pulses. A limit on angle resolution due to a small number of antennas on either of the devices is relieved by using two or more carrier frequencies in the UWB pulses. A limit on angle resolution is further overcome in some situations by use of a neural network to refine angle estimates. In some situations, received power values are further used to select an angle for beam alignment.

Growing community of inventors

Montreal, Canada

Ju Wang