A fixed-sensor finger action detecting glove has a glove body, five covering sheets, five fixing bases, five sensors, and five fixing assemblies. A side of the glove body forms a hand back section and five finger back sections. The covering sheet is mounted on the finger back section and forms a passage. The fixing base is made from a flexible material, is mounted through the passage, and has two limiting walls. The sensor is located in the passage between the two limiting walls, preventing the sensor from deviating. The fixing assembly is mounted between an end of the sensor and an end of the finger back section, detachably connects the sensor and the finger back section, and prevents the sensor from moving back and forth. Thus, the fixed-sensor finger action detecting glove is capable of detecting actions of the fingers precisely.

Collision avoidance and postural stability adjustment may provide an effective dual task paradigm to interpret the effect of proprioceptive adaptation on balance control. However, conventionally tasks are physical tasks performed under supervision in specific set up environments. Implementations of the present disclosure provide methods and systems for interpreting neural interplay involving proprioceptive adaptation in a lower limb during a dual task paradigm. The disclosed method provides a better interpreting of the neuronal mechanisms underlying adaptation and learning of skilled motor movement and to determine the relationship of lower limb proprioceptive sense and postural stability by simulating integration of a Single Limb Stance (SLS) functionality test for postural stability and a single limb collision avoidance task, in an adaptive Virtual Reality (VR) environment provided to a subject.

Apparatus and associated methods relate to a connected pill dispenser configured to treat a patient's illness with a robotic arm adapted to deliver a prescribed medication dose to a patient in their home, analyze the patient's response to the dose based on various sensor inputs, automatically determine whether the patient took the medicine and send the provider the result of providing the medication dose to the patient. In an illustrative example, the patient may be a chronic, acute, or terminal illness patient. The medication dose may be, for example, a medication prescribed by a doctor to be taken in a specific amount at specific times. In some embodiments, the connected pill dispenser may automatically notify the patient when a medication dose is due. Various embodiments may determine if the patient consumed a medication dose based on machine vision, audio, or other sensor data, permitting caregiver notification of patient medication adherence, medication compliance, or non-adherence and sensor inputs as data on potential effectiveness and/or side effects.

A wearer's risk of developing a lower back pain symptom during work time of heavy muscular work to handle an object is forecasted by continuously estimating the wearer's intervertebral disk pressure force on the basis of weight of the object and the wearer's body height and body weight, and the wearer's trunk angle, and measuring elapsed time in chronological order with respect to each section of the intervertebral disk pressure force according to a load level.

A method for providing remote rehabilitation training is provided. The method includes receiving, by a server, a connection request from a user terminal and a therapist terminal, receiving, by the server, first image data, about an appearance where a user performs rehabilitation training using a rehabilitation training device, in real time from the user terminal, receiving, by the server, second image data, provided to the user who is performing the rehabilitation training, in real time from a rehabilitation training display device, and transmitting, by the server, the received first image data and the received second image data to the therapist terminal in real time.

A signal processing apparatus includes a memory configured to store instructions; and a processor configured to execute the instructions to obtain a signal; obtain a frequency band spectrum by applying a Fast Fourier Transform (FFT) to the obtained signal; and remove noise from the obtained spectrum by applying a first filter and a second filter, which are different from each other, to the obtained frequency band spectrum.

The present disclosure provides a finger joint rehabilitation training device, which includes a control member, a data acquisition member, a gas circuit system, and a wearable training member. The wearable training member is provided with a pneumatic component that can expand and contract. The data acquisition member is configured for acquiring hand motion information of a first hand and transmitting the hand motion information to the control member. The hand motion information includes hand pressing information. The control member controls the gas circuit system to inflate the pneumatic component or to draw air from the pneumatic component according to the hand motion information, to make the wearable training member change between a flexion condition and a stretching condition, so as to realize a hand mirror training of a second hand. The hand pressing information is simple and convenient to acquire, which is convenient for the first hand to realize the flexion condition and the stretching condition, and the condition of the second hand is adjusted through the condition of the first hand, so that the wearable training member can be better adjusted, different hand training intensity requirements are met, and a better training effect is achieved.

A System for Measuring Body Kinetics includes a wearable device configured to be wrapped around a joint. A microprocessor is attached to the wearable device, One or more Inertial Measurement. Units (IMUS) are connected to the microprocessor and arranged on the wearable device. The IMUS are arranged and configured to provide kinetic data concerning the joint to the microprocessor. A wireless transmission component is connected to the microprocessor. The microprocessor is configured to receive kinetic data from the IMUs, and to transmit the kinetic data by way of the wireless transmission component to a central processor or other device. An algorithm resides within the microprocessor or the central processor or other device, and is configured to determine the position of each IMU from the kinetic data. The wearable device may be constructed of fabric, strap, adhesive tape, or a combination thereof.

A rehabilitation work support apparatus, a rehabilitation work support method, and a program capable of efficiently managing patient's actual current ability values are provided. A rehabilitation work support apparatus (1) includes a change prediction unit (2) that predicts whether or not an actual current ability value of a patient during a rehabilitation period has changed from a latest ability value of that patient stored in a storage device based on an elapsed time from a time of an evaluation of the latest ability value of the patient stored in the storage device, and a change prediction output unit (3) that performs control so as to output a result of the prediction made by the change prediction unit (2).

A posture measurement apparatus and method is described. The posture measurement system includes a wearable sensor leader node comprising a UWB transceiver coupled to at least two antennas and one or more wearable sensor follower nodes each comprising a UWB transceiver coupled to one antenna. A first UWB signal is transmitted from the wearable sensor leader node to the one or more wearable follower sensor nodes. A second UWB signal is received by the wearable sensor leader node from each follower sensor node in response to receiving the first UWB signal. A time-of-flight value of a signal transmitted between the wearable leader sensor node and the wearable follower sensor node is determined from the first UWB signal and the second UWB signal. An angle of arrival value is determined from the second UWB signal. The body posture can be determined from the time-of-flight and angle-of-arrival value.