Russel   is using IoT with AI 

Russel is using IoT Devices to manage his daily workflow.  

russel movie.mp4

Deep learning trained Model  and  Accelerated Inference 

Volume of data is too high and that makes human beings direct involvement in working with data to obtain meaningful inference.  Thus the challenge is to bring out hidden truth in a given volume of data at a regular interval of time or continuously.


Modern Deep Learning models are trained to perform real time inference in many cases. Inference to happen in real time there is need for hardware, communication bandwidth, storage capacity , Trained Deep learning Model and necessary sensor interface to the real world. For example IBM Watson services in Data science [12],  IoT and also in AI provides early generation tool sets to  create deployment of Intelligent service in Healthcare [4].  However there have been major opportunities open for Private companies to create and sell Health services by using AI and IoT.

Deploy  critical intelligence ( via trained neural network )  in Ventilator to support life and possibly bring back life 

Nurse

Bio containment presents a unique challenge for auscultation. With the Centers for Disease Control calling for personal protective equipment (PPE) in treating patients for the coronavirus, how does the clinician place stethoscope eartips in the ears for listening? Auscultation at the bedside using a conventional style stethoscope with tubing becomes impossible.

Experienced respiratory therapists can identify different types of asynchrony if they continuously monitor the waveform on a ventilator display screen indicating the pressure and flow. But in an ICU, one respiratory therapist typically oversees 10 or more patients and can’t possibly monitor all of them constantly.

Precision Critical Care for Each Person by using Neural network that learned Lungs operation of each Person. AI Provide Moment-by-Moment Nursing for a Hospital’s Sickest Patients by providing required volume of air ( with correct percentage of O2 ) and also required Pressure.

Aim is to develop a non-invasive method of classifying respiratory sounds that are recorded by an electronic stethoscope and the audio recording. Diagnosis or classification requires recognizing patterns. But most of the time, it is very hard to spot these patterns, especially if the data is very large. Data collected from the environment is usually non-linear, so we cannot use traditional methods to find patterns or create mathematical models. In the past decade, various technologies, such as expert systems, have been used to attempt to solve this problem. However, for critical systems, the error rate for the decision was too high.


Auscultation is a simple, patient-friendly and non-invasive method which is widely used but is of low diagnostic value due to the inherent subjectivity in the evaluation of respiratory sounds and to the difficulty involved in relating qualitative assessments to other people 

Auscultation, which is the processes of listening to the internal sounds in the human body through a stethoscope, has been an effective tool for the diagnosis of lung disorders and abnormalities.  This process mainly relies on the physician. Using a stethoscope, the physicians may hear normal breathing sounds, decreased or absent breath sounds, and abnormal breath sounds (e.g., rale, rhonchus, squawk, stridor, wheeze, rub)

Deploy  critical intelligence ( via trained neural network )  in Ventilator to support life and possibly bring back life