International Business Machines Corporation

Dish Network Technologies India Private Limited

Dish Network LLC

Mansoor Ahmed

Geetha Adinarayan

Sattwati Kundu

Yashwanth Melwanki

Nair Raghunath Eledath

Amit Kumar

Arun Pk

Hariprasanth Mohanraj

Prasanna Kumar L

The present disclosure is directed to methods and systems for monitoring the activity of a user. A user performing an activity in a remote area can carry or wear an activity device. The activity device, such as a wearable device, can collect sensor data and send the sensor data to an activity tracking system. The activity tracking system can analyze the sensor data to determine if the user is in potential danger. If a potential danger is detected, the activity tracking system can send a notification to an emergency contact to alert them of the potential danger of the user.

Methods and systems for monitoring an activity of a remote user

The present disclosure is directed to methods and systems for remote access hardware testing. A user can remotely control probes connected to an oscilloscope to collect signal measurements of test points on a circuit board. The user can control the probe point position on the circuit board using an application on a device to enter the test point locations. In some implementations, a user controls the probe machine using remote controls and a camera video feed to identify the test points on the circuit board and capture measurements. The hardware testing system can automate the measurement process with a script or by using machine learning to identify test points via a camera, controlling the probe machine, and capturing measurements of the test point.

Methods and systems for remote access hardware testing

Systems and processes are provided to detect an improper external power supply. An example includes a processor in communication with an internal battery. The processor receives an indication that the internal battery is receiving power from an external power supply. The processor determines a first output current of the internal battery. An error is generated indicating the internal battery receives insufficient power from the external power supply. The error indicates the external power supply is faulty in response to the internal battery intermittently discharging while receiving a power from the external power supply.

Method and apparatus for improper power supply detection

Systems and processes are provided to detect an improper external power supply including a battery having a battery current output, a power supply for receiving an external voltage and an external current from an external power supply and for generating a control signal in response to receiving the external voltage, a processor operative to determine a first polarity of the battery current output at a first time in response to the control signal, to generate an error indicator in response to the first polarity being indicative of a discharging battery, and a display operative to display a user warning indicative of an improper external power supply in response to the error indicator.

Methods, systems and computer readable media are provided for configuring machine learning systems to automatically and dynamically select a machine learning model based on statistical profiling of received data to improve machine learning applications for high variance data. Data is received from a system in operation. A profile is computed for the received data. A database comprising a plurality of stored profiles for a dataset is accessed, wherein each stored profile corresponds to a distinct pattern identified in the dataset. The computed profile is compared to each of the stored profiles to determine whether the computed profile matches one or more of the stored profiles. When one or more stored profiles match the computed profile, a matching profile is selected by the machine learning system. The received data is processed using a ML model associated with the matching profile.

Dynamically applying machine learning models from profiling received data

A computer-implemented method, system and computer program product for identifying anomalies in data during a data outage. An anomaly detection model is built using data received from a sensor at a characterized granularity. Once a period of service occurs following a data outage, a quantum of missing data during the data outage is identified using predictive modeling if the data during the data outage is not available at the granularity in which the anomaly detection model is built. The identified quantum of missing data is retrofitted into a predicted pattern during the data outage and the analytics are then re-run on the retrofitted quantum of missing data in the predicted pattern to identify anomalies during the data outage. In this manner, anomalies in data, such as data from sensor readings, can be identified during the data outage thereby enabling the model to provide more accurate predictions of anomalies occurring during the data outage.

Growing community of inventors

Bengaluru, India

Mansoor Ahmed