A machine learning device includes a sparse modeling processing unit and a selection unit. The sparse modeling processing unit acquires individual importance degrees for each of explanatory variable candidates, the individual importance degrees being acquired by using respective sparse modeling methods different from each other, each of the sparse modeling methods taking input data including a specified objective variable in a learning model used for industrial activity and the explanatory variable candidates that are candidates for an explanatory variable for explaining the specified objective variable. The selection unit calculates a comprehensive importance degree for each of the explanatory variable candidates based on the individual importance degrees of each of the explanatory variable candidates, and selects an explanatory variable of the learning model from among the explanatory variable candidates based on the comprehensive importance degree.

A model aggregation device includes a communication device able to communicate with a plurality of vehicles in which neural network models are learned, a storage device storing a part of the neural network models sent from the plurality of vehicles, and a control device. The neural network model outputs at least one output parameter from a plurality of input parameters. The control device is configured to, if receiving a new neural network model from one vehicle among the plurality of vehicles through the communication device, compare ranges of the plurality of input parameters which were used for learning the new neural network model and ranges of the plurality of input parameters which were used for learning a current neural network model stored in the storage device to thereby determine whether to replace the current neural network model with the new neural network model.

A method for controlling a controlled system by a control device, the method may include transmitting multiple actuation signals to multiple degree of freedom (DOF) points of the controlled system; wherein the multiple actuation signals comprise multiple alternating current (AC) components that are mutually orthogonal, measuring at least one feedback signal from at least one probe point of the controlled system; wherein a number of DOF points exceeds a number of the at least one probe point; determining, based upon the at least one feedback signal, values of line search pulses to be sent to the multiple DOF points during at least one line search iteration; and performing the at least one line search iteration.

A method for controlling a controlled system by a control device, the method may include transmitting multiple actuation signals to multiple degree of freedom (DOF) points of the controlled system; wherein the multiple actuation signals comprise multiple alternating current (AC) components that are mutually orthogonal, measuring at least one feedback signal from at least one probe point of the controlled system; wherein a number of DOF points exceeds a number of the at least one probe point; determining, based upon the at least one feedback signal, values of line search pulses to be sent to the multiple DOF points during at least one line search iteration; and performing the at least one line search iteration.

A position controller for electronically monitoring the position and speed of a dredge. The position controller consists of an electric powered line winding spool with an electric encoder to indicate line speed and position to a microprocessor. A drag control assembly with electric control is used to increase, decrease or set the drag at desired setting by microprocessor control. Touch screen microprocessor interface is the preferred method to enter settings into the system and allow display/control through multiple preexisting marine electronic devices throughout a fishing boat.

An effective system for verifying safety of an artificial intelligence system includes a feature quantity information accepting unit which accepts feature quantity information that includes values of plural feature quantities, that are assumed as those used in an artificial intelligence system, in each of plural first test data used for a test for verifying safety of the artificial intelligence system; and a judgment unit which judges a first combination, that is a combination that is not included in the plural first test data, in combinations of values that plural feature quantities may take, or a second combination, with it plural correct analysis results that should be derived by the artificial intelligence are associated, in the combinations of the values that the plural feature quantities may take.

An effective system for verifying safety of an artificial intelligence system includes a feature quantity information accepting unit which accepts feature quantity information that includes values of plural feature quantities, that are assumed as those used in an artificial intelligence system, in each of plural first test data used for a test for verifying safety of the artificial intelligence system; and a judgment unit which judges a first combination, that is a combination that is not included in the plural first test data, in combinations of values that plural feature quantities may take, or a second combination, with it plural correct analysis results that should be derived by the artificial intelligence are associated, in the combinations of the values that the plural feature quantities may take.

An information processing apparatus and method is provided and controls execution of learning processing thereon. Learning data are generated in which readings of a human presence sensor serve as input values, information on receiving or not receiving any operation from an operation panel serves as success/failure flags. The success/failure flag is generated from an assessment result of a current resumption assessment model and the information on receiving or not receiving an operation, and is provided to the learning data. Accordingly, learning processing is performed using the success/failure flags provided in the learning data, thereby efficiently implementing learning.

In-situ fluorimeters and methods and systems for collecting and analyzing sensor data to predict water source contamination are provided. In one embodiment, a method is provided that includes receiving sensor data regarding a water source. Changepoints may then be calculated within the sensor data and the sensor data may be split into intervals at the changepoints. A machine learning model may then be used to classify the intervals and a predicted contamination event for the water source may be identified based on the classified intervals. In another embodiment, an in-situ fluorimeter is provided. The in-situ fluorimeter comprises one or more UV LEDs centered around a pre-set excitation wavelength (e.g., a TLF excitation wavelength), a bandpass filter, a lens, a photodiode system, a machine learning platform; and an alarm triggered by contamination events, wherein the alarm is calibrated through the machine learning system.

In-situ fluorimeters and methods and systems for collecting and analyzing sensor data to predict water source contamination are provided. In one embodiment, a method is provided that includes receiving sensor data regarding a water source. Changepoints may then be calculated within the sensor data and the sensor data may be split into intervals at the changepoints. A machine learning model may then be used to classify the intervals and a predicted contamination event for the water source may be identified based on the classified intervals. In another embodiment, an in-situ fluorimeter is provided. The in-situ fluorimeter comprises one or more UV LEDs centered around a pre-set excitation wavelength (e.g., a TLF excitation wavelength), a bandpass filter, a lens, a photodiode system, a machine learning platform; and an alarm triggered by contamination events, wherein the alarm is calibrated through the machine learning system.