The proceedings contain 83 papers. The special focus in this conference is on Advanced Information systems Engineering. The topics include: Predictive maintenance in a digital factory shop-floor: Data mining on histor...
ISBN:
(纸本)9783030209476
The proceedings contain 83 papers. The special focus in this conference is on Advanced Information systems Engineering. The topics include: Predictive maintenance in a digital factory shop-floor: Data mining on historical and operational data coming from manufacturers’ information systems;information extraction for additive manufacturing using news data;a fog computing approach for predictive maintenance;Blockchain usage for government-issued electronic IDs: A survey;smart contracts and void declarations of intent;blockchain-based application security risks: A systematic literature review;data management: Relational vs blockchain databases;a generic framework for flexible and data-aware business process engines;building information systems using collaborative-filtering recommendation techniques;a case study of executive functions in real process modeling sessions;the subjective cost of writing reusable code: The case of functions;Climb your way to the model: Teaching UML to software engineering students: Teaching case;a new method for manufacturing process autonomous planning in intelligent manufacturing system;design of meshing assembly algorithms for industrial gears based on image recognition;detecting anomalous behavior towards predictive maintenance;data analytics towards predictive maintenance for industrial ovens: A case study based on data analysis of various sensors data;A RAMI 4.0 view of predictive maintenance: Software architecture, platform and case study in steel industry.
In radar systems, the frequency range is being extended to high frequencies such as THz for sub-mm resolution. The spectrum offers high resolution but on the contrary, propagation distance and penetration depth are li...
详细信息
ISBN:
(数字)9781728167558
ISBN:
(纸本)9781728167565
In radar systems, the frequency range is being extended to high frequencies such as THz for sub-mm resolution. The spectrum offers high resolution but on the contrary, propagation distance and penetration depth are limited because of smaller wavelength. It suffers from higher atmospheric absorption in comparison to sub-GHz systems. In comparison to optical technology, the radar technique majorly benefits with respect to the penetration property such as cloud/smoke cover penetration and detection of concealed objects. However, the THz range and synthetic aperture radar (SAR) imaging of concealed objects are not very well established. Therefore, this paper examines this property at THz. A testbed has been set up with a bandwidth of 110 GHz at a carrier frequency of 275 GHz. The imaging is performed of a very small metal object. Firstly, the sub-mm resolution is validated with the experiment after that the range and SAR imaging are performed in which this object is covered with different types of materials. The backscattered data is processed with the image reconstruction algorithms and the results are presented in this paper with respect to sub-mm resolution and detection.
Existing Neural Style Transfer (NST) algorithms do not migrate styles well to a reasonable location where the output image can render the correct spatial structure of the object being painted. We propose a deep semant...
详细信息
ISBN:
(纸本)9789811379864;9789811379857
Existing Neural Style Transfer (NST) algorithms do not migrate styles well to a reasonable location where the output image can render the correct spatial structure of the object being painted. We propose a deep semantic matching-based multi-scale (DSM-MS) neural style transfer method, which can achieve the reasonable transfer of styles guided by the prior spatial segmentation and illumination information of input images. First, according to real drawing process, before an artist decides how to paint a stroke, he/she needs to observe and then understand subjects, segmenting space into different regions, objects and structures and analyzing the illumination conditions on each object. To simulate the two visual cognition processes, we define a deep semantic space (DSS) and propose a method for calculating DSSs using manual image segmentation, automatic illumination estimation and convolutional neural network (CNN). Second, we define a loss function, named deep semantic loss, which uses DSS to guide reasonable style transfer. Third, we propose a multi-scale optimization strategy for improving the efficiency of our method. Finally, we achieve an interdisciplinary application of our method for the first time-painterly rendering 3D scenes by neural style transfer. The experimental results show that our method can synthesize images in better original structures, with more reasonable placement of each styles and visual aesthetic feeling.
Within this research, we consider an overdetermined system of equations generated on a small number of observations. The degrees of freedom of the overdetermined system and the number of observations are roughly equal...
详细信息
In this paper we describe an infrastructure for implementing autonomous Forex trading agents without human supervision;the agents are based on traditional trading strategies including ARIMA+GARCH, Kalman Filter, exper...
详细信息
We quantify the robustness of the semantic segmentation model U-Net, applied to single cell nuclei detection, with respect to the following factors: (1) automated vs manual training annotations, (2) quantity of traini...
详细信息
ISBN:
(数字)9781728193601
ISBN:
(纸本)9781728193618
We quantify the robustness of the semantic segmentation model U-Net, applied to single cell nuclei detection, with respect to the following factors: (1) automated vs manual training annotations, (2) quantity of training data, and (3) microscope image focus. The difficulty of obtaining sufficient volumes of accurate manually annotated training data to create an accurate Convolutional Neural Networks (CNN) model is overcome by the temporary use of fluorescent labels to automate the creation of training datasets using traditional imageprocessingalgorithms. The accuracy measurement is computed with respect to manually annotated masks which were also created to evaluate the effectiveness of using automated training set generation via the fluorescent images. The metric to compute the accuracy is the false positive/negative rate of cell nuclei detection. The goal is to maximize the true positive rate while minimizing the false positive rate. We found that automated segmentation of fluorescently labeled nuclei provides viable training data without the need for manual segmentation. A training dataset size of four large stitched images with medium cell density was enough to reach a true positive rate above 88% and a false positive rate below 20%.
A trajectory building based on a camera data is one of the most popular tasks in the field of machine vision. In particular, this task appears when it is necessary to navigate in the absence of signals from global nav...
详细信息
Deep Neural Networks (DNNs) are one of many supervised machine learning approaches. These data-driven deep learning algorithms are revolutionizing the modern society in domains such as imageprocessing, medicine and a...
详细信息
ISBN:
(纸本)9783030266011;9783030266004
Deep Neural Networks (DNNs) are one of many supervised machine learning approaches. These data-driven deep learning algorithms are revolutionizing the modern society in domains such as imageprocessing, medicine and automotive. In the field of computer vision, DNNs are outperforming the traditional approaches that use hand-crafted feature extractors. As a result, researchers and developers in the automotive industry are using DNNs for the perception tasks of automated driving. Compared to traditional rule-based approaches, DNNs raise new safety challenges that have to be solved. There are four major building blocks in the development pipeline of DNNs: (1) functionality definition, (2) data set specification, selection and preparation, (3) development and evaluation, and (4) deployment and monitoring. This paper gives an overview of the safety challenges along the whole development pipeline of DNN, proposes potential solutions that are necessary to create safe DNNs and shows first experimental results of DNN performing object detection.
The evolution of modern sensors for image acquisition brings as much obstacles as many possibilities to obtain multidimensional data with high resolution and rich information. One of the most perceptible destructive f...
详细信息
Endoscopy is a process that allows viewing/ visualize the inside of a human body. In this article, we propose a specular reflection detection algorithm for endoscopic images that utilizes intensity, saturation and gra...
详细信息
暂无评论