Iskanje po katalogu digitalne knjižnice

Opis: This paper introduces a novel approach to increase the spatiotemporal resolution of an arbitrary environmental variable. This is achieved by utilizing machine learning algorithms to construct a satellite-like image at any given time moment, based on the measurements from IoT sensors. The target variables are calculated by an ensemble of regression models. The observed area is gridded, and partitioned into Voronoi cells based on the IoT sensors, whose measurements are available at the considered time. The pixels in each cell have a separate regression model, and take into account the measurements of the central and neighboring IoT sensors. The proposed approach was used to assess NO2 data, which were obtained from the Sentinel-5 Precursor satellite and IoT ground sensors. The approach was tested with three different machine learning algorithms: 1-nearest neighbor, linear regression and a feed-forward neural network. The highest accuracy yield was from the prediction models built with the feed-forward neural network, with an RMSE of 15.49 ×10−6 mol/m2.
Ključne besede: Internet of Things, IoT, remote sensing, sensor integration, machine learning, ensemble method
Objavljeno v DKUM: 22.09.2023; Ogledov: 167; Prenosov: 10
Celotno besedilo (3,72 MB)
Gradivo ima več datotek! Več...

Ključne besede: microfluidic, microfluidic sensing systems, capillary-based fluorescent chemical sensor system, fluorescent sensors, oxygen sensing, fluorescent decay time measurements, on-line liquid analysis, optical fibers, capillaries, liquid reagent
Objavljeno v DKUM: 31.05.2023; Ogledov: 287; Prenosov: 34
Celotno besedilo (4,68 MB)
Gradivo ima več datotek! Več...

Opis: Against the backdrop of technological advancement, machine learning and artificial intelligence, autonomous vehicles are also developing rapidly. In order for an autonomous vehicle to function properly, it is essential that the main system is provided lots of information about the vehicle, such as speed, orientation or battery state. Likewise, the system must control some actuators, such as drive motors and steering system. The specific objective of this thesis is to create an ARM-based module that will be a part of the Genesis II autonomous vehicle platform. The module is intended to accurately measure vehicle speed, estimate orientation and location, monitor the batteries, control drive motors and steering. The PCB layout of the module was developed by using Altium Designer, while the firmware was written in C programming language and by utilizing RTOS. Measurements were also performed to determine the accuracy of speed measurement process and to determine the accuracy of orientation and location estimations.
Ključne besede: ARM, autonomous vehicle, RTOS, Jetson TX2, magnetoresistive sensor, Genesis
Objavljeno v DKUM: 02.06.2021; Ogledov: 766; Prenosov: 44
Celotno besedilo (1,83 MB)

Opis: In underground Lipica II. quarry for the excavation of natural stone, a modified room-and-pillar mining method is used, that is adjusted to the conditions of the site. In order to support and ensure the stability of underground chambers high safety pillars (HSP) are used. These pillars are made of surrounding stone and therefore intersected by discontinuities. The discontinuities represent high risk to the stability of underground facilities and workmen below/ itself. To ensure their safety the stress and strain parameters in height safety pillars are continuously monitored using two vibrating wire (WV) stressmeters inside the high safety pillars and two EL (Electronic level) beam sensors on the surface of the high safety pillar VS3. In the time period October 2010/June 2012 absolute max. measured deviation with EL beam sensors were D1=0.9 mm and D2=1.1 mm, which does not compromise the stability of the high safety pillar VS3. This paper presents the procedures of wedges deformation monitoring in safety pillars with EL beam sensors in the Lipica II underground natural stone quarry.
Ključne besede: beam sensor, high saftey pillar, monitoring, natural stone, room and pillar mining method
Objavljeno v DKUM: 14.06.2018; Ogledov: 817; Prenosov: 67
Celotno besedilo (491,51 KB)
Gradivo ima več datotek! Več...

Opis: Clouds moving at a high speed in front of the Sun can cause step changes in the output power of photovoltaic (PV) power plants, which can lead to voltage fluctuations and stability problems in the connected electricity networks. These effects can be reduced effectively by proper short-term cloud passing forecasting and suitable PV power plant output power control. This paper proposes a low-cost Internet of Things (IoT)-based solution for intra-minute cloud passing forecasting. The hardware consists of a Raspberry PI Model B 3 with a WiFi connection and an OmniVision OV5647 sensor with a mounted wide-angle lens, a circular polarizing (CPL) filter and a natural density (ND) filter. The completely new algorithm for cloud passing forecasting uses the green and blue colors in the photo to determine the position of the Sun, to recognize the clouds, and to predict their movement. The image processing is performed in several stages, considering selectively only a small part of the photo relevant to the movement of the clouds in the vicinity of the Sun in the next minute. The proposed algorithm is compact, fast and suitable for implementation on low cost processors with low computation power. The speed of the cloud parts closest to the Sun is used to predict when the clouds will cover the Sun. WiFi communication is used to transmit this data to the PV power plant control system in order to decrease the output power slowly and smoothly.
Ključne besede: photovoltaic power plant, cloud passing forecasting, algorithm, sensor, Raspberry Pi, camera, wide-angle lens, optical filters, internet of things
Objavljeno v DKUM: 20.07.2017; Ogledov: 2384; Prenosov: 448
Celotno besedilo (8,15 MB)
Gradivo ima več datotek! Več...