Multi-Sensor Data Fusion in A Real-Time Support System for On-Duty Firefighters.

While working on fire ground, firefighters risk their well-being in a state where any incident might cause not only injuries, but also fatality. They may be incapacitated by unpredicted falls due to floor cracks, holes, structure failure, gas explosion, exposure to toxic gases, or being stuck in narrow path, etc. Having acknowledged this need, in this study, we focus on developing an efficient portable system to detect firefighter's falls, loss of physical performance, and alert high CO level by using a microcontroller carried by a firefighter with data fusion from a 3-DOF (degrees of freedom) accelerometer, 3-DOF gyroscope, 3-DOF magnetometer, barometer, and a MQ7 sensor using our proposed fall detection, loss of physical performance detection, and CO monitoring algorithms. By the combination of five sensors and highly efficient data fusion algorithms to observe the fall event, loss of physical performance, and detect high CO level, we can distinguish among falling, loss of physical performance, and the other on-duty activities (ODAs) such as standing, walking, running, jogging, crawling, climbing up/down stairs, and moving up/down in elevators. Signals from these sensors are sent to the microcontroller to detect fall, loss of physical performance, and alert high CO level. The proposed algorithms can achieve 100% of accuracy, specificity, and sensitivity in our experimental datasets and 97.96%, 100%, and 95.89% in public datasets in distinguishing between falls and ODAs activities, respectively. Furthermore, the proposed algorithm perfectly distinguishes between loss of physical performance and up/down movement in the elevator based on barometric data fusion. If a firefighter is unconscious following the fall or loss of physical performance, an alert message will be sent to their incident commander (IC) via the nRF224L01 module.

Two-dimensional complex shear modulus imaging of soft tissues by integration of Algebraic Helmoltz Inversion and LMS filter into dealing with noisy data: a simulation study.

Elasticity and viscosity of soft tissues can be obtained from the complex shear modulus imaging (CSMI). CSMI is often used not only to investigate the structure of tissues but also to detect tumors in tissues. One of the most popular ways to categorize the methods used in CSMI is into quasi-static and dynamic methods. In the dynamic method, a force excitation is used to create the shear wave propagation, and the particle velocities are measured to extract their amplitude and phase at spatial locations. These parameters are then employed to directly or indirectly estimate the Complex Shear Modulus (CSM) represented by elasticity and viscosity. Algebraic Helmholtz Inversion (AHI) algorithm provides the direct estimation of CSM using the Finite Difference Time Domain (FDTD) technique. The limitation of this method, however, is that the noise generated from measuring the particle velocity strongly degrades the accuracy of the estimation. To overcome this problem, we proposed in this paper an adaptive AHI (AAHI) algorithm that offers a good performance in CSMI with a mean error of 2.06%.