The ground control using optical fibers is discussed. The designed monomode fiber pressure sensor is capable to perform high-precision measurement of overlying rock mass pressure imposed on walls of underground excavation. The mathematical apparatus is presented for the calculation of radiation intensity of optical wave traveling along an optical fiber with and with no mechanical effects. The simulation model is developed for an underground excavation with steel arch support. The model is equipped with the fiber-optic monitoring system and pressure sensors. This model enables practicing the ground control methods and measurements. The critical element of the simulation model is its hardware/software complex with interface showing four check zones with fiber-optic pressure sensors. This monitoring system is explosion-proof and is suitable for operation in super hazardous mines in terms of gas and dust outbursts.
Modern object recognition algorithms have very high precision. At the same time, they require high computational power. Thus, widely used low-power IoT devices, which gather a substantial amount of data, cannot directly apply the corresponding machine learning algorithms to process it due to the lack of local computational resources. A method for fast detection and classification of moving objects for low-power single-board computers is shown in this paper. The developed algorithm uses geometric parameters of an object as well as scene-related parameters as features for classification. The extraction and classification of these features is a relatively simple process which can be executed by low-power IoT devices. The algorithm aims to recognize the most common objects in the street environment, e.g., pedestrians, cyclists, and cars. The algorithm can be applied in the dark environment by processing images from a near-infrared camera. The method has been tested on both synthetic virtual scenes and real-world data. The research showed that a low-performance computing system, such as a Raspberry Pi 3, is able to classify objects with acceptable frame rate and accuracy.
23 April 2015 in IOP Conference Series: Materials Science and Engineering