Abstract: A body fluid volume estimation device includes a pre-training unit, a transfer learning unit, and an estimation unit. The pre-training unit performs pre-training by using, as supervised information, information indicating body fluid volumes of the multiple patients when face images of multiple patients are captured. The transfer learning unit further performs transfer learning on multiple face images of one specific patient after the pre-training, and constructs a trained model. The estimation unit estimates, by inputting a face image of the one specific patient to the trained model, a body fluid volume at a point in time at which the face image of the one specific patient is captured. By estimating a body fluid volume from a face image by machine learning, the body fluid volume can be used for assistance such as decision making of a user.

Abstract: A body fluid volume estimation device includes a pre-training unit, a transfer learning unit, and an estimation unit. The pre-training unit performs pre-training by using, as supervised information, information indicating body fluid volumes of the multiple patients when face images of multiple patients are captured. The transfer learning unit further performs transfer learning on multiple face images of one specific patient after the pre-training, and constructs a trained model. The estimation unit estimates, by inputting a face image of the one specific patient to the trained model, a body fluid volume at a point in time at which the face image of the one specific patient is captured. By estimating a body fluid volume from a face image by machine learning, the body fluid volume can be used for assistance such as decision making of a user.

Abstract: A body fluid volume estimation device includes a pre-training unit, a transfer learning unit, and an estimation unit. The pre-training unit performs pre-training by using, as supervised information, information indicating body fluid volumes of the multiple patients when face images of multiple patients are captured. The transfer learning unit further performs transfer learning on multiple face images of one specific patient after the pre-training, and constructs a trained model. The estimation unit estimates, by inputting a face image of the one specific patient to the trained model, a body fluid volume at a point in time at which the face image of the one specific patient is captured. By estimating a body fluid volume from a face image by machine learning, the body fluid volume can be used for assistance such as decision making of a user.

Abstract: A body fluid volume estimation device includes a pre-training unit, a transfer learning unit, and an estimation unit. The pre-training unit performs pre-training by using, as supervised information, information indicating body fluid volumes of the multiple patients when face images of multiple patients are captured. The transfer learning unit further performs transfer learning on multiple face images of one specific patient after the pre-training, and constructs a trained model. The estimation unit estimates, by inputting a face image of the one specific patient to the trained model, a body fluid volume at a point in time at which the face image of the one specific patient is captured. By estimating a body fluid volume from a face image by machine learning, the body fluid volume can be used for assistance such as decision making of a user.

Abstract: An imaging device includes an imaging element and a processor receiving subject light and generating data, a lens cover, an illuminometer, a light source emitting illumination light, an actuator switching the lens cover between a first state for restricting the subject light from entering the imaging element and a second state for allowing the subject light to enter, a switch including a first filter preventing the illumination light from entering the imaging element and a second filter allowing the illumination light to enter, to place the first filter or the second filter on a front surface of the imaging element based on a brightness level in a surrounding environment detected by the illuminometer, and a setter setting an amplification factor to be used by the processor in generating the data based on a brightness level in the surrounding environment detected by the illuminometer in the first state.

Abstract: An imaging device includes an imaging element and an image processor that receive subject light through an opening in a housing and generate image data, an illuminometer that detects a brightness level in a surrounding environment, an illumination light source that emits illumination light, a switch including a first filter to prevent the illumination light from entering the imaging element and a second filter to allow the illumination light to enter the imaging element to place one of the first filter or the second filter on a front surface of the imaging element based on the brightness level in the surrounding environment detected by the illuminometer, and a setter that sets an amplification factor to be used by the image processor in generating the image data based on the brightness level in the surrounding environment detected by the illuminometer before the image processor starts generating the image data.

Abstract: An imaging device performs imaging in a dark surrounding environment, while protecting the privacy of a subject. An imaging device includes an image processor that receives subject light from a subject passing through an opening, converts the subject light to an image signal, and amplifies the image signal to generate image data, a lens cover between the opening and an imaging element to cover the opening to restrict the subject light from entering the imaging element, an illumination light source that emits illumination light to illuminate the subject, and a switch including a first filter allowing no entry of the illumination light into the imaging element and a second filter allowing entry of the illumination light into the imaging element. The switch places one of the first filter or the second filter between the imaging element and the opening based on a brightness of a surrounding environment.