Southwest Research Institute is developing a machine vision tool to help the U.S. Department of Defense assess the biomechanical movements of military medical personnel during training exercises.

The simulation-based training system will compare medical trainee performance to that of experts whose physical motions, or kinematics, have been pre-recorded and analyzed in 3D with artificial intelligence.

“Military medical training relies on subjective human evaluations where feedback may vary among trainers,” said Dr. Dan Nicolella, of SwRI’s Mechanical Engineering Division, who co-leads the Institute’s Human Performance Initiative with Kase Saylor, an Intelligent Systems Division manager. SwRI’s research will help both instructors and trainees to objectively observe how well they are performing a specific task, providing both a quantitative score, based on expert task performance, and task-specific feedback to improve performance.”

The $1.25 million project, known as Investigating Methods for Performance Overdrive (IMPROVE), is funded by the DOD’s Congressionally Directed Medical Research Programs (CDMRP), Joint Program Committee-1/Medical Simulation and Information Sciences.

The SwRI project is part of a greater DOD effort to improve patient safety and quality of care through strategic over-the-horizon research by transitioning more capable medical simulation technologies.

SwRI is adapting its markerless motion capture technology, used to assess the biomechanics of athletes as well as for clinical applications. Markerless motion capture, or MoCap, leverages computer vision algorithms to circumvent the tedious process of attaching physical body markers to a human subject when capturing motion in 3D data for biomechanical analysis in research, clinical, and sport science applications.

SwRI’s MoCap system uses standard cameras to capture video of human subjects and custom machine learning algorithms to quantify individual biomechanical performance related to walking, running, physical screening, sports, and other precise physical movements.

Applying SwRI’s technology to DOD medical training will allow complex assessments of 3D kinematic performance. The project will assess the detailed performance of trainees when they suture wounds and provide other combat and hospital care requiring precise hand movements or physical orientations.

The automated assessments will be based on SwRI-developed machine learning trained using actual data collected from ideal physical performance while completing specific medical tasks. The Uniformed Services University, a project team member, will contribute to the research with surveys and other data gathered from several military medical training programs and training best practices.

The project will focus on training custom artificial intelligence systems in a 3D biomechanical model space. This methodology will result in a biomechanically informed machine learning system to measure 3D spatial temporal biomechanics directly from 2D video data.

The post SwRI is developing machine vision tool to improve military medical training appeared first on Artificial Intelligence.

The Center for Noise and Vibration Control at KAIST announced that their coughing detection camera recognizes where coughing happens, visualizing the locations. The resulting cough recognition camera can track and record information about the person who coughed, their location, and the number of coughs on a real-time basis.

Professor Yong-Hwa Park from the Department of Mechanical Engineering developed a deep learning-based cough recognition model to classify a coughing sound in real time. The coughing event classification model is combined with a sound camera that visualizes their locations in public places. The research team said they achieved a best test accuracy of 87.4 %.

Professor Park said that it will be useful medical equipment during epidemics in public places such as schools, offices, and restaurants, and to constantly monitor patients’ conditions in a hospital room.

Fever and coughing are the most relevant respiratory disease symptoms, among which fever can be recognized remotely using thermal cameras. This new technology is expected to be very helpful for detecting epidemic transmissions in a non-contact way. The cough event classification model is combined with a sound camera that visualizes the cough event and indicates the location in the video image.

To develop a cough recognition model, a supervised learning was conducted with a convolutional neural network (CNN). The model performs binary classification with an input of a one-second sound profile feature, generating output to be either a cough event or something else.

In the training and evaluation, various datasets were collected from Audioset, DEMAND, ETSI, and TIMIT. Coughing and others sounds were extracted from Audioset, and the rest of the datasets were used as background noises for data augmentation so that this model could be generalized for various background noises in public places.

The dataset was augmented by mixing coughing sounds and other sounds from Audioset and background noises with the ratio of 0.15 to 0.75, then the overall volume was adjusted to 0.25 to 1.0 times to generalize the model for various distances.

The training and evaluation datasets were constructed by dividing the augmented dataset by 9:1, and the test dataset was recorded separately in a real office environment.

In the optimization procedure of the network model, training was conducted with various combinations of five acoustic features including spectrogram, Mel-scaled spectrogram and Mel-frequency cepstrum coefficients with seven optimizers. The performance of each combination was compared with the test dataset. The best test accuracy of 87.4% was achieved with Mel-scaled Spectrogram as the acoustic feature and ASGD as the optimizer.

The trained cough recognition model was combined with a sound camera. The sound camera is composed of a microphone array and a camera module. A beamforming process is applied to a collected set of acoustic data to find out the direction of incoming sound source. The integrated cough recognition model determines whether the sound is cough or not. If it is, the location of cough is visualized as a contour image with a ‘cough’ label at the location of the coughing sound source in a video image.

A pilot test of the cough recognition camera in an office environment shows that it successfully distinguishes cough events and other events even in a noisy environment. In addition, it can track the location of the person who coughed and count the number of coughs in real time. The performance will be improved further with additional training data obtained from other real environments such as hospitals and classrooms.

Professor Park said, “In a pandemic situation like we are experiencing with COVID-19, a cough detection camera can contribute to the prevention and early detection of epidemics in public places. Especially when applied to a hospital room, the patient’s condition can be tracked 24 hours a day and support more accurate diagnoses while reducing the effort of the medical staff.”

This study was conducted in collaboration with SM Instruments Inc.

/Public Release. The material in this public release comes from the originating organization and may be of a point-in-time nature, edited for clarity, style and length. View in full here.

The post Deep Learning-Based Cough Recognition Model Helps Detect Location of Coughing Sounds in Real Time appeared first on Artificial Intelligence.