Abstract: A method for a hyperparameter optimization for an automated ensemble machine learning model includes: generating an initial population of a plurality of machine learning (ML) models with a plurality of randomly chosen hyperparameters; calculating a loss function for each of the plurality of machine learning models; creating a new population of ML models and generating a base learner model using the hyperparameters of the best model. The method for creating the new population include the steps of: (a) selecting multiple best models with least errors as parents from a previous generation; (b) creating an offspring of the new population of ML models with a crossover probability and a mutation probability; and (c) repeating the steps (a) and (b) until a number of generations is reached and reporting the hyperparameters of the best model.

Abstract: A network device may include a packet generator device implemented in hardware. The packet generator device may include a control component, a payload generation component, and an interface element to receive test packet generation information. The test packet generation information may include one or more control inputs, header data that is to be included in one or more test packets, and information regarding a data pattern that is to be included in payload data of the one or more test packets. The one or more control inputs, when provided to the control component, may cause the control component to control the payload generation component to generate the one or more test packets based on the header data and the information regarding the data pattern.

Abstract: A network device may include a packet generator device implemented in hardware. The packet generator device may include a control component, a payload generation component, and an interface element to receive test packet generation information. The test packet generation information may include one or more control inputs, header data that is to be included in one or more test packets, and information regarding a data pattern that is to be included in payload data of the one or more test packets. The one or more control inputs, when provided to the control component, may cause the control component to control the payload generation component to generate the one or more test packets based on the header data and the information regarding the data pattern.

Abstract: Disclosed herein is a method of preparing a Cu/Cu2O core-shell copper nanoparticle catalyst having high catalytic activity from [Cu3(BTC)2] and NaBH4 via a simple chemical reduction method. Also disclosed is a method of preparing a chalcogenide compound by using the nanoparticle catalyst as a heterogeneous catalyst in a cross-coupling reaction between a chalcogenide precursor compound and a boron-containing compound. The disclosed cross-coupling reaction is performed via a simple process, and the disclosed nanoparticle catalyst is compatible with various substrates under mild reaction conditions and exhibits excellent recyclability without a reduction in catalytic activity.

Abstract: Disclosed herein is a method of preparing a Cu/Cu2O core-shell copper nanoparticle catalyst having high catalytic activity from [Cu3(BTC)2] and NaBH4 via a simple chemical reduction method. Also disclosed is a method of preparing a chalcogenide compound by using the nanoparticle catalyst as a heterogeneous catalyst in a cross-coupling reaction between a chalcogenide precursor compound and a boron-containing compound. The disclosed cross-coupling reaction is performed via a simple process, and the disclosed nanoparticle catalyst is compatible with various substrates under mild reaction conditions and exhibits excellent recyclability without a reduction in catalytic activity.