arXiv subjects

Andreas Kamilaris

Publications and source records attributed to Andreas Kamilaris.

27 records · Page 2Linked to original sources

arXiv2019

Short Term Prediction of Parking Area states Using Real Time Data and Machine Learning Techniques

Public road authorities and private mobility service providers need information derived from the current and predicted traffic states to act upon the daily urban system and its spatial and temporal dynamics. In this research, a real-time parking area state (occupancy, in- and outflux) prediction model (up to 60 minutes ahead) has been developed using publicly available historic and real time data sources. Based on a case study in a real-life scenario in the city of Arnhem, a Neural Network-based approach outperforms a Random Forest-based one on all assessed performance measures, although the differences are small. Both are outperforming a naive seasonal random walk model. Although the performance degrades with increasing prediction horizon, the model shows a performance gain of over 150% at a prediction horizon of 60 minutes compared with the naive model. Furthermore, it is shown that predicting the in- and outflux is a far more difficult task (i.e. performance gains of 30%) which needs more training data, not based exclusively on occupancy rate. However, the performance of predicting in- and outflux is less sensitive to the prediction horizon. In addition, it is shown that real-time information of current occupancy rate is the independent variable with the highest contribution to the performance, although time, traffic flow and weather variables also deliver a significant contribution. During real-time deployment, the model performs three times better than the naive model on average. As a result, it can provide valuable information for proactive traffic management as well as mobility service providers.

cs.LG↗

arXiv2019

Internet of Things in Geospatial Analytics

Digital Earth was born with the aim of replicating the real world within the digital world. Many efforts have been made to observe and sense the Earth, both from space and by using in situ sensors. Focusing on the latter, advances in Digital Earth have established vital bridges to exploit these sensors and their networks by taking location as a key element. The current era of connectivity envisions that everything is connected to everything. The concept of the Internet of Things emerged as a holistic proposal to enable an ecosystem of varied, heterogeneous networked objects and devices to speak and interact with each other. To make the IoT ecosystem a reality, it is necessary to understand the electronic components, communication protocols, real-time analysis techniques, and the location of the objects and devices. The IoT ecosystem and the Digital Earth jointly form interrelated infrastructures for addressing modern pressing issues and complex challenges. In this chapter, we explore the synergies and frictions in establishing an efficient and permanent collaboration between the two infrastructures, in order to adequately address multidisciplinary and increasingly complex real-world problems. Although there are still some pending issues, the identified synergies generate optimism for a true collaboration between the Internet of Things and the Digital Earth.

eess.SP↗

arXiv2019

Training Deep Learning Models via Synthetic Data: Application in Unmanned Aerial Vehicles

This paper describes preliminary work in the recent promising approach of generating synthetic training data for facilitating the learning procedure of deep learning (DL) models, with a focus on aerial photos produced by unmanned aerial vehicles (UAV). The general concept and methodology are described, and preliminary results are presented, based on a classification problem of fire identification in forests as well as a counting problem of estimating number of houses in urban areas. The proposed technique constitutes a new possibility for the DL community, especially related to UAV-based imagery analysis, with much potential, promising results, and unexplored ground for further research.

cs.CV↗

arXiv2019

The Rise of Blockchain Technology in Agriculture and Food Supply Chains

Blockchain is an emerging digital technology allowing ubiquitous financial transactions among distributed untrusted parties, without the need of intermediaries such as banks. This article examines the impact of blockchain technology in agriculture and food supply chain, presents existing ongoing projects and initiatives, and discusses overall implications, challenges and potential, with a critical view over the maturity of these projects. Our findings indicate that blockchain is a promising technology towards a transparent supply chain of food, with many ongoing initiatives in various food products and food-related issues, but many barriers and challenges still exist, which hinder its wider popularity among farmers and systems. These challenges involve technical aspects, education, policies and regulatory frameworks.

cs.CY↗

arXiv2018

Disaster Monitoring using Unmanned Aerial Vehicles and Deep Learning

Monitoring of disasters is crucial for mitigating their effects on the environment and human population, and can be facilitated by the use of unmanned aerial vehicles (UAV), equipped with camera sensors that produce aerial photos of the areas of interest. A modern technique for recognition of events based on aerial photos is deep learning. In this paper, we present the state of the art work related to the use of deep learning techniques for disaster identification. We demonstrate the potential of this technique in identifying disasters with high accuracy, by means of a relatively simple deep learning model. Based on a dataset of 544 images (containing disaster images such as fires, earthquakes, collapsed buildings, tsunami and flooding, as well as non-disaster scenes), our results show an accuracy of 91% achieved, indicating that deep learning, combined with UAV equipped with camera sensors, have the potential to predict disasters with high accuracy.

cs.LG↗

arXiv2018

A Review on the Application of Natural Computing in Environmental Informatics

Natural computing offers new opportunities to understand, model and analyze the complexity of the physical and human-created environment. This paper examines the application of natural computing in environmental informatics, by investigating related work in this research field. Various nature-inspired techniques are presented, which have been employed to solve different relevant problems. Advantages and disadvantages of these techniques are discussed, together with analysis of how natural computing is generally used in environmental research.

cs.NE↗

arXiv2018

Geospatial Analysis and Internet of Things in Environmental Informatics

Geospatial analysis offers large potential for better understanding, modelling and visualizing our natural and artificial ecosystems, using Internet of Things as a pervasive sensing infrastructure. This paper performs a review of research work based on the IoT, in which geospatial analysis has been employed in environmental informatics. Six different geospatial analysis methods have been identified, presented together with 26 relevant IoT initiatives adopting some of these techniques. Analysis is performed in relation to the type of IoT devices used, their deployment status and data transmission standards, data types employed, and reliability of measurements. This paper scratches the surface of this combination of technologies and techniques, providing indications of how IoT, together with geospatial analysis, are currently being used in the domain of environmental research.

cs.CY↗

arXiv2018

Deep learning in agriculture: A survey

Deep learning constitutes a recent, modern technique for image processing and data analysis, with promising results and large potential. As deep learning has been successfully applied in various domains, it has recently entered also the domain of agriculture. In this paper, we perform a survey of 40 research efforts that employ deep learning techniques, applied to various agricultural and food production challenges. We examine the particular agricultural problems under study, the specific models and frameworks employed, the sources, nature and pre-processing of data used, and the overall performance achieved according to the metrics used at each work under study. Moreover, we study comparisons of deep learning with other existing popular techniques, in respect to differences in classification or regression performance. Our findings indicate that deep learning provides high accuracy, outperforming existing commonly used image processing techniques.

cs.LG↗

arXiv2016

SpEnD: Linked Data SPARQL Endpoints Discovery Using Search Engines

In this study, a novel metacrawling method is proposed for discovering and monitoring linked data sources on the Web. We implemented the method in a prototype system, named SPARQL Endpoints Discovery (SpEnD). SpEnD starts with a "search keyword" discovery process for finding relevant keywords for the linked data domain and specifically SPARQL endpoints. Then, these search keywords are utilized to find linked data sources via popular search engines (Google, Bing, Yahoo, Yandex). By using this method, most of the currently listed SPARQL endpoints in existing endpoint repositories, as well as a significant number of new SPARQL endpoints, have been discovered. Finally, we have developed a new SPARQL endpoint crawler (SpEC) for crawling and link analysis.

cs.IR↗