search
Include:
The following results are related to Rural Digital Europe. Are you interested to view more results? Visit OpenAIRE - Explore.
48,562 Research products, page 1 of 4,857

  • Rural Digital Europe
  • 0202 electrical engineering

10
arrow_drop_down
Relevance
arrow_drop_down
  • Open Access
    Authors: 
    Maha Hamdan Alotibi; Salma Kammoun Jarraya; Manar Salamah Ali; Kawthar Moria;
    Publisher: Elsevier BV

    Abstract Crowd counting in specific places has recently been considered as a significant contribution in many applications in terms of security and economic values. Recently, the Kingdom of Saudi Arabia has considered new ways and methods to diversify sources of income, where many non-traditional establishments in several fields have been initiated and put in place. However, controlling the number of visitors and participants to events and exhibitions has always been a challenge, as it has always been considered as an important success factor to any event. Smart public places approach is one of the inevitable directions of development in Saudi Arabia, where security, comfort, and safety of crowds is to be controlled and managed using machine learning techniques, more specifically, IoT-based crowd counting techniques. Such a technology will not only help in resolving security and safety problems, but also will play a significant role in reducing waiting time for visitors, by giving indicators, projections and advices on crowded places. In this paper, a mobile-based model is proposed for counting people in high and low crowded public places in Saudi Arabia under various scene conditions with no prior knowledge. The proposed model is built based on pre-trained convolutional neural network (CNN) called VGG-16 with some modifications on the last layer of the CNN to increase the efficiency of the training model. In addition to the improvement of efficiency, the proposed method accepts images of arbitrary sizes/scales as inputs. The applicability of the proposed method has been evaluated by incorporating IoT architecture, where surveillance cameras to be connected to the Internet to capture live pictures of different public places. To achieve this goal, New and special Saudi people dataset as well as some other existing dataset, have been produced and used to train the network. The result shows a significant improvement to the efficiency of the DCNN over the existing counting networks.

  • Authors: 
    Jing Zhang; Qianlan Zhou; Li Zhuo; Wenhao Geng; Suyu Wang;
    Publisher: World Scientific Pub Co Pte Lt

    With the rapid development of remote sensing technology, searching the similar image is a challenge for hyperspectral remote sensing image processing. Meanwhile, the dramatic growth in the amount of hyperspectral remote sensing data has stimulated considerable research on content-based image retrieval (CBIR) in the field of remote sensing technology. Although many CBIR systems have been developed, few studies focused on the hyperspectral remote sensing images. A CBIR system for hyperspectral remote sensing image using endmember extraction is proposed in this paper. The main contributions of our method are that: (1) the endmembers as the spectral features are extracted from hyperspectral remote sensing image by improved automatic pixel purity index (APPI) algorithm; (2) the spectral information divergence and spectral angle match (SID–SAM) mixed measure method is utilized as a similarity measurement between hyperspectral remote sensing images. At last, the images are ranked with descending and the top-[Formula: see text] retrieved images are returned. The experimental results on NASA datasets show that our system can yield a superior performance.

  • Publication . Conference object . Other literature type . 2019
    Closed Access
    Authors: 
    Ana Kutnjak; I. Pihiri; M. Tomicic Furjan;
    Country: Croatia

    Digital transformation (DT) has been introduced in all industries for improving the way of running business. Industries have embraced technology to different extents, as not all technologies can be equally implemented, even in semantically similar processes. This can be explained by the fact that the hype cycle of emerging technologies differently impacts industries from the time a concrete technology has been discovered and introduced, to the time when technology reaches its full potential of use in real processes, or so-called maturity. This paper presents a literature review on Digital transformation papers, which use the case study method in their researches and/or compare digital transformation case studies across different industries. The purpose of the analysis of case studies is to bring some light to real digital transformation processes and their success in practice. Analysed papers are selected from the Web of Science database based on content, industry and number of papers within it.

  • Closed Access
    Authors: 
    Eoin Allen; David M. Wall; Christiane Herrmann; Jerry D. Murphy;
    Publisher: Elsevier BV
    Project: SFI | Optimal production of ren... (11/RFP.1/ENM/3213)

    Abstract This paper details the analysis of biochemical methane potential (BMP) assessment of 83 substrates, which may be deemed as: first generation substrates (food crops); second generation (grasses and wastes); and third generation (seaweed). Significant variation in the BMP of a substrate may be found depending on for example, season and method of harvest. This could lead to significant discrepancy between energy production at the design stage and in operation of the facility. For example the BMP of dairy slurry varied from 175 L CH4 kg−1 VS in autumn (cattle fed on concentrate at end of farming year) to 239 L CH4 kg−1 VS in the summer when cattle are fed fresh grass. Grass ranged from 156 (for hay) to 433 L CH4 kg−1 VS for first cut baled silage. Saccharina latissima (brown seaweed) generated a higher BMP 36.4 m3 CH4 t−1 than summer dairy slurry 16 m3 CH4 t−1. In terms of a national resource, the cheapest and most sustainable source of biomethane will be from wastes, but the resource is finite. Biomethane from wastes could satisfy 18.4% of transport energy in Ireland. Larger resources will require third generation substrates such as seaweed.

  • Publication . Article . 2020
    Closed Access
    Authors: 
    Marco Barenkamp;
    Publisher: Springer Fachmedien Wiesbaden GmbH

    Der Artikel gibt einen Uberblick uber Best-Practice-Standards zur Authentifizierung von IoT (Internet of Things) Zugangen. Es wird aufgezeigt, dass clientseitige Authentifizierung gegenuber einer herkommlichen Authentifizierung und Blockchain-basierten Ansatzen das hochste Potential fur sichere Prozessautomatisierung bei hoher Interaktionsfrequenz bietet. Ein neuartiges Konzept des clientseitigen automatisierten Zugangsmanagements auf Basis von TLS (transport layer security), welches sich im Agriculture Segment seit uber einem Jahr bewahrt hat, wird vorgestellt. Gegenuber derzeitig eingesetzten Authentifizierungsverfahren bietet es den Vorteil hoherer Sicherheit bei gleichzeitig automatisierter Anmeldung jeglicher Endgerate auf dem IoT-Server. Aufgrund dieser Potentiale eignet sich der dargestellte Authentifizierungsstandard zukunftig als allgemeines branchenubergreifendes Zugangssystem fur IoT-Anwendungen.

  • Closed Access
    Authors: 
    Saibal K. Ghosh; Dharma P. Agrawal;
    Publisher: IEEE

    The last few decades have seen an exponential increase in the capability of computing devices with an equally substantial decrease in their form factors. The first wave was the ubiquitous mobile connectivity which gave way to the widespread adoption of the Internet of Things (IoT) paradigm and its later incarnation: The Internet of Everything (IoE) wherein almost every device is endowed with network communication capabilities. However, from a singular device's resource standpoint, many of these devices may not be able to fulfill the requirements of applications that run on them. An effective way to achieve substantial computing capability is to offload the computation to devices over the network. In this work, we explore mechanisms to optimize offloading decisions while minimizing transmission power. Our simulations show that substantial gains can be achieved from this offloading mechanism.

  • Open Access
    Authors: 
    Bingyu Zhao; Meiling Liu; Jianjun Wu; Xiangnan Liu; Mengxue Liu; Ling Wu;
    Publisher: Institute of Electrical and Electronics Engineers (IEEE)

    It is very important to obtain continuous regional crop parameters efficiently in the agricultural field. However, remote sensing data can provide spatial-continuous / temporal-disperse crop information while crop growth model can provide temporal-continuous / spatial-disperse crop information. Therefore, the assimilation between crop growth model and remote sensing data is an efficient way for obtaining continuous vegetation growth information. This study aims to present a parallel method based on graphic processing unit (GPU) to improve the efficiency of the assimilation between RS data and crop growth model to estimate rice growth parameters. Remote sensing data, Landsat and HJ-1 images, were collected and the World Food Studies (WOFOST) crop growth model which has a strong flexibility was employed. To acquire continuous regional crop parameters, particle swarm optimization (PSO) data assimilation method was used to combine remote sensing images and WOFOST and this process is accompanied by a parallel method based on the Compute Unified Device Architecture (CUDA) platform of NVIDIA GPU. With these methods, we obtained daily rice growth parameters of Zhuzhou City, Hunan, China and compared the efficiency and precision of parallel method and non-parallel method. Results showed that the parallel program has a remarkable speedup (reaching 240 times) compared with the non-parallel program with a similar accuracy. This study indicated that the parallel implementation based on GPU was successful in improving the efficiency of the assimilation between RS data and the WOFOST model.

  • Publication . Conference object . 2017
    Open Access
    Authors: 
    Zhenjie Wang; Xing Xu; Weixing Wang; Jie Hu; Yueju Xue;
    Publisher: Atlantis Press
  • Publication . Conference object . 2017
    Closed Access
    Authors: 
    Yongze Liu; Xiaojian Xu; Xiaoyu He;
    Publisher: ACM Press

    Inverse synthetic aperture radar (ISAR) imaging of turntable targets has been widely used in radar cross section (RCS) diagnosis. A major shortcoming is that the data acquisition time is long due to the time-consuming mechanical rotation of a turntable. The distinctive advantage of a multiple-input multiple-output (MIMO) radar which is capable of imaging a target with high resolution by using only one snapshot makes it more attractive. In this paper, a comparative study is performed between near-field ISAR and MIMO radar images. Tests are carried out on classical objects such as metallic cylinder and trihedral corner reflector, as well as an aircraft model.

  • Publication . Article . Preprint . 2018
    Open Access English
    Authors: 
    Ivan Y. Tyukin; Ivan Y. Tyukin; Alexander N. Gorban; Alexander N. Gorban; Konstantin I. Sofeykov; Konstantin I. Sofeykov; Ilya Romanenko;
    Publisher: Frontiers Media S.A.

    We consider the fundamental question: how a legacy ``student'' Artificial Intelligent (AI) system could learn from a legacy ``teacher'' AI system or a human expert without re-training and, most importantly, without requiring significant computational resources. Here ``learning'' is broadly understood as an ability of one system to mimic responses of the other to an incoming stimulation and vice-versa. We call such learning an Artificial Intelligence knowledge transfer. We show that if internal variables of the ``student'' Artificial Intelligent system have the structure of an $n$-dimensional topological vector space and $n$ is sufficiently high then, with probability close to one, the required knowledge transfer can be implemented by simple cascades of linear functionals. In particular, for $n$ sufficiently large, with probability close to one, the ``student'' system can successfully and non-iteratively learn $k\ll n$ new examples from the ``teacher'' (or correct the same number of mistakes) at the cost of two additional inner products. The concept is illustrated with an example of knowledge transfer from one pre-trained convolutional neural network to another.