Smart traffic lights can be adaptive, with neural networks and associated with smart cameras and microwave sensors. Real-time determinations offer the possibility for specialists to intervene in real-time and collect ...
详细信息
The urban public transport system comprises various networks representing different transportation modes with complex internal connections. The common single-layer complex network cannot fully describe the interior ch...
详细信息
The scope of DC / DC converters is quite wide, ranging from automated low-current control systems to powerful power plants. One such application is the use of a DC/DC converter to increase the voltage supplied to an e...
详细信息
In the domain of livestock management, the precise detection of estrus in cows is crucial for reproductive efficiency and enhanced livestock production. Traditional methods, primarily based on human observation, are l...
详细信息
The proceedings contain 45 papers. The topics discussed include: designing the topology of microelectromechanical systems by machine learning methods;development of a remote-control system for a mobile vibration-drive...
ISBN:
(纸本)9798350310856
The proceedings contain 45 papers. The topics discussed include: designing the topology of microelectromechanical systems by machine learning methods;development of a remote-control system for a mobile vibration-driven robot;models of recurrent distributions statistical averaging for electronic components with fluctuations;inverse-dynamic neural controller simulation;a method of creating virtual pixels in matrix;the computermodeling of the thermal agent hydrodynamics through the alcohol distillery stillage stationary layer;method for estimating the topological structure of self-organized networks;a new hybrid method for predicting recommendations for collaborative recommender systems;software-defined transmitter to support automatic dependent surveillance-broadcast;deductive matrix synthesis for fault simulation;investigation of response from the micro objects of complex shape irradiated by acoustic wave;outdoor positioning for industrial workplace;a software complex for researching algorithms for working with graphs;and hydrogen adsorption in porous silicon: simulation and control method.
An axis-symmetrical diesel spray flame model coupled with momentum flux distribution measurement was developed as a tool for nozzle orifice development. Momentum flux distributions at several distances from the nozzle...
详细信息
An axis-symmetrical diesel spray flame model coupled with momentum flux distribution measurement was developed as a tool for nozzle orifice development. Momentum flux distributions at several distances from the nozzle orifice exit are measured by a force sensor with a small-diameter aperture which traverses a cross-section. A theoretical momentum flux profile is determined by fitting with the measured momentum flux profile at the cross-section. The spray velocity profile and equivalence ratio profiles are quantified from the theoretical momentum flux profile. By interpolating the profiles of the measured cross-sections, the axis-symmetrical diesel spray flame model can calculate the equivalence ratio and other physical values as a function of the distance from the nozzle exit (x) and the radius from the spray axis (r). The equivalence ratio distribution in a cross-section involving the spray axis is converted into soot formation and oxidation distribution by coupling with the improved soot & phi;-T map. The conventional soot-NOx & phi;-T map did not show the borderline between the soot formation and oxidation. To quantify the residence time of the fuel element during soot formation, the narrow soot peninsula was expanded up to its maximum by replacing the soot yield with the soot particle diameter. Instead of contour lines for the of NO mole fraction, contour lines for the OH mole fraction were implemented to reveal the border between soot formation and soot oxidation on the & phi;-T map. The borderline appears clearly, consisting of a horizontal line in the lower-temperature region and a rising line in the higher-temperature region. The converted soot formation and oxidation regions in the axis-symmetric spray flame model exhibit a strong correlation with the measured soot distributions in a quasi-steady diesel spray flame. The shear-stress, which induces turbulence affecting soot formation/oxidation, is also quantified from the velocity distribution.
Current Global System for Mobile Communications for Railway (GSM-R) is increasingly unable to meet the burgeoning demand for diversified private network communication services, such as multimedia dispatching communica...
详细信息
The term "digital twin" has gained an ever-increasing popularity since the last five years. Digital twins promote the existence of a virtual counterpart of any physical system for monitoring the system behav...
详细信息
Commercial business software represents a large part of the IT spending of organizations. Whilst the cost of software operations and licenses is relatively easy to determine, organizations find it difficult to measure...
详细信息
A major challenge caused by the aging of the modern society is the home care of elderly people. Many elders prefer staying in their own home over moving into a nursing home for as long as possible. For this reason, th...
详细信息
ISBN:
(数字)9781665434454
ISBN:
(纸本)9781665434454
A major challenge caused by the aging of the modern society is the home care of elderly people. Many elders prefer staying in their own home over moving into a nursing home for as long as possible. For this reason, the project DeinHaus 4.0 Lower Bavaria researches possible technical solutions which can help the elderly to live in their own homes for a longer period of time. The topic of falls is one main part of the research because the number of falls and thereby caused injuries increase with rising age. In this context, this work presents a prototype for an optical fall detection system based on pose estimation, running in real time on an embedded device connected to a USB-camera. In the process of development, different approaches including machine and deep learning, as well as a rule-based algorithm are applied to solve this task. All methods reach an accuracy higher than 94% when used on publicly available data sets, but machine learning seems to have drawbacks when applied in the real-time application due to limitations in the available training data. The rule-based approach, on the other hand, seems to be more capable of generalizing different types of fall events.
暂无评论