SLO | ENG | Cookies and privacy

Bigger font | Smaller font

Search the digital library catalog Help

Query: search in
search in
search in
search in
* old and bologna study programme


11 - 18 / 18
First pagePrevious page12Next pageLast page
Gesture recognition from data streams of human motion sensor using accelerated PSO swarm search feature selection algorithm
Iztok Fister, Iztok Fister, Simon Fong, Justin Liang, Sabah Mohammed, 2015, original scientific article

Abstract: Human motion sensing technology gains tremendous popularity nowadays with practical applications such as video surveillance for security, hand signing, and smart-home and gaming. These applications capture human motions in real-time from video sensors, the data patterns are nonstationary and ever changing. While the hardware technology of such motion sensing devices as well as their data collection process become relatively mature, the computational challenge lies in the real-time analysis of these live feeds. In this paper we argue that traditional data mining methods run short of accurately analyzing the human activity patterns from the sensor data stream. The shortcoming is due to the algorithmic design which is not adaptive to the dynamic changes in the dynamic gesture motions. The successor of these algorithms which is known as data stream mining is evaluated versus traditional data mining, through a case of gesture recognition over motion data by using Microsoft Kinect sensors. Three different subjects were asked to read three comic strips and to tell the stories in front of the sensor. The data stream contains coordinates of articulation points and various positions of the parts of the human body corresponding to the actions that the user performs. In particular, a novel technique of feature selection using swarm search and accelerated PSO is proposed for enabling fast preprocessing for inducing an improved classification model in real-time. Superior result is shown in the experiment that runs on this empirical data stream. The contribution of this paper is on a comparative study between using traditional and data stream mining algorithms and incorporation of the novel improved feature selection technique with a scenario where different gesture patterns are to be recognized from streaming sensor data.
Keywords: algorithms, human motion sensors, PSO
Published: 07.04.2017; Views: 406; Downloads: 8
.pdf Full text (4,31 MB)

Acoustic emission detection of macro-cracks on engraving tool steel inserts during the injection molding cycle using PZT sensors
Rajko Svečko, Dragan Kusić, Tomaž Kek, Andrej Sarjaš, Aleš Hančič, Janez Grum, 2013, original scientific article

Abstract: This paper presents an improved monitoring system for the failure detection ofen graving tool steel inserts during the injection molding cycle. This system uses acoustic emission PZT sensors mounted through acoustic waveguides on the engraving insert. We were thus able to clearly distinguish the defect through measured AE signals. Two engraving tool steel inserts were tested during the production of standard test specimens, each under the same processing conditions. By closely comparing the captured AE signals on both engraving inserts during the filling and packing stages, we were able to detect the presence of macro-cracks on one engraving insert. Gabor wavelet analysis was used for closer examination of the captured AE signalsć peak amplitudes during the filling and packing stages. The obtained results revealed that such a system could be used successfully as an improved tool for monitoring the integrity of an injection molding process.
Keywords: injection molding, process monitoring, acoustic emission, PZT sensors, piezoelectric effect
Published: 22.06.2017; Views: 204; Downloads: 7
.pdf Full text (854,94 KB)

Fiber-optic sensors for measurements of torsion, twist and rotation
Vedran Budinski, Denis Đonlagić, 2017, review article

Abstract: Optical measurement of mechanical parameters is gaining significant commercial interest in different industry sectors. Torsion, twist and rotation are among the very frequently measured mechanical parameters. Recently, twist/torsion/rotation sensors have become a topic of intense fiber-optic sensor research. Various sensing concepts have been reported. Many of those have different properties and performances, and many of them still need to be proven in out-of-the laboratory use. This paper provides an overview of basic approaches and a review of current state-of-the-art in fiber optic sensors for measurements of torsion, twist and/or rotation.
Keywords: fiber optic sensors, twist sensors, rotation sensors, circular birefringence, linear birefringence, FBG, polarization, optical fibers, Fiber Bragg Gratings
Published: 22.06.2017; Views: 133; Downloads: 11
.pdf Full text (8,96 MB)

Monitoring the evaporation of fluids from fiber-optic micro-cell cavities
Eyal Preter, Borut Preložnik, Vlada Artel, Chaim Sukenik, Denis Đonlagić, Avi Zadok, 2013, original scientific article

Abstract: Fiber-optic sensors provide remote access, are readily embedded within structures, and can operate in harsh environments. Nevertheless, fiber-optic sensing of liquids has been largely restricted to measurements of refractive index and absorption spectroscopy. The temporal dynamics of fluid evaporation have potential applications in monitoring the quality of water, identificationof fuel dilutions, mobile point-of-care diagnostics, climatography and more. In this work, the fiber-optic monitoring of fluids evaporation is proposed and demonstrated. Sub-nano-liter volumes of a liquid are applied to inline fiber-optic micro-cavities. As the liquid evaporates, light is refracted out of the cavity at the receding index boundary between the fluid and the ambient surroundings. A sharp transient attenuation in the transmission of light through the cavity, by as much as 50 dB and on a sub-second time scale, is observed. Numerical models for the transmission dynamics in terms of ray-tracing and wavefront propagation are provided. Experiments show that the temporal transmission profile can distinguish between different liquids.
Keywords: fiber-optic sensors, opto-fluidics, evaporation monitoring, optical micro-cells, fiber cavities, droplet analysis
Published: 22.06.2017; Views: 70; Downloads: 15
.pdf Full text (551,58 KB)

Sensor for injection rate measurements
Milan Marčič, 2006, original scientific article

Abstract: A vast majority of the medium and high speed Diesel engines are equipped with multi-hole injection nozzles nowadays. Inaccuracies in workmanship and changing hydraulic conditions in the nozzles result in differences in injection rates between individual injection nozzle holes. The new deformational measuring method described in the paper allows injection rate measurement in each injection nozzle hole. The differences in injection rates lead to uneven thermal loads of Diesel engine combustion chambers. All today known measuring method, such as Bosch and Zeuch give accurate results of the injection rate in diesel single-hole nozzles. With multihole nozzles they tellus nothing about possible differences in injection rates between individual holes of the nozzle. At deformational measuring method, the criterion of the injected fuel is expressed by the deformation of membrane occurring due to the collision of the pressure wave against the membrane. The pressure wave is generated by the injection of the fuel into the measuring space. For each hole of the nozzle the measuring device must have a measuring space of its own into which fuel is injected as well as its measuring membraneand its own fuel outlet. During measurements procedure the measuring space must be filled with fuel to maintain an overpressure of 5 kPa. Fuel escaping from the measuring device is conducted into the graduated cylinders for measuring the volumetric flow through each hole of the nozzle.The membrane deformation is assessed by strain gauges. They are glued to the membrane and forming the full Wheatstonećs bridge. We devoted special attention to the membrane shape and temperature compensation of the strain gauges.
Keywords: thermodynamics, sensors, Diesel engines, nozzles, injection, measurements
Published: 22.06.2017; Views: 152; Downloads: 16
.pdf Full text (242,99 KB)

Determination of penicillamine by batch and flow-injection potentiometry with AgI-based sensor
Njegomir Radić, Josipa Komljenović, Danilo Dobčnik, 2000, original scientific article

Abstract: Potentiometric determination of penicillamine (pen) is described based on a batch experiment and flow-injection analysis (FIA) using a chemical sensor with AgI-based membrane. The membrane was prepared by pressing silver salts (AgI, Ag2S) and powdered Teflon. This membrane was incorporated in a multipurpose electrode body for batch measurements, and in a tabular flow-through sensor body for FIA measurements. For batch measurements, the equilibrium potentials recorded with continuous addition of standard penicillamine solution were considered in relation to ▫$lg(c_pen/mol L^-1)$▫. Linear response with slope of 60 mV was obtained in the concentration range from 2.5 x ▫$10^5$▫ mol ▫$L^1$▫ to 1.8 x ▫$10^-2$▫mol ▫$L-1$▫. In using the tubular sensor with a membrane of the same coposition for FIA measurements, the linear response with slope of 59 mV was recorded in the concentration range from 1 x ▫$10^4$▫ mol ▫$L^1$▫ to 1 x ▫$10^-1$▫ mol ▫$L^-1$▫. The response of the applied chemical sensor to penicillamine (designated also as RSH) is explained by the formation of sparingly soluble RSAg in the reaction solution and/or the exposed surface of the sensor. The solubility product ▫$K_s(RSAg)$▫ was determined using experimental values recorded both by batch measurements and by the continuous-flow experiment. The mean value obtained by different measurements and using a membrane of the same composition is ▫$K_s(RSAg)$▫ = (1.4+-0.1) x ▫$10^-20$▫ mol ▫$L-2$▫).
Keywords: analytical chemistry, batch potentiometry, flow-injection analysis, membrane electrode, tubular sensors, penicillamine
Published: 05.07.2017; Views: 151; Downloads: 9
.pdf Full text (196,90 KB)

Interface between macro and nano worlds
Gregor Škorc, Riko Šafarič, David Lukman, Sirhiy Ivanovich Protsenko, Simon Zapusek, 2010, original scientific article

Abstract: This paper describes the design of a nanorobotic application which includes: nanorobotic arm, Akiyama sensor system, a vacuum chamber, and an interface tools for the nanorobotic hardware developed using C++ and VRML languages in order to create a desktop virtual-reality environment which improves visualisation and prevents collision of the nanomanipulator hardware with the associated workspace. The presented experiment shows how the used man-machine interface could be used for communication between macro and micro/nano worlds.
Keywords: nanorobotics, virtual-reality, sensors system
Published: 19.07.2017; Views: 119; Downloads: 15
.pdf Full text (1,70 MB)

Challenges of on-line condition monitoring of hydraulic oils
Vito Tič, Darko Lovrec, published scientific conference contribution

Abstract: Ensuring adequate quality of hydraulic oil and planning its change is crucial for a stable and smooth operation of many industrial machines. The best reliability can certainly be provided by using continuous monitoring of hydraulic oils, which is usually carried out remotely by means of modern online sensors. Nevertheless, the development and implementation of such a system represents a unique challenge, since the measurement of the oil condition is much more complicated than measuring usual operating parameters, such as pressure or temperature.
Keywords: hydraulic oil, quality, on-line monitoring, oil change, modern sensors
Published: 10.10.2017; Views: 60; Downloads: 7
.pdf Full text (370,30 KB)

Search done in 0.11 sec.
Back to top
Logos of partners University of Maribor University of Ljubljana University of Primorska University of Nova Gorica