Marie Skłodowska-Curie fellow, working at the Institute of Agriculture and Food Research and Technology (IRTA, Torre Marimon) in Barcelona, through the European P-SPHERE project, collaborating with the Autonomous University of Barcelona (UAB), performing research on big data analysis and applications in the agri-food sector. In parallel, during the past two years, I have been lecturing a course over "Advanced Web Technologies" at the Open University of Cyprus.
2017 EFITA CONGRESS – Montpellier, France – 02.07-06.07.2017 AgriBigCAT: An Online Platform for E... more 2017 EFITA CONGRESS – Montpellier, France – 02.07-06.07.2017 AgriBigCAT: An Online Platform for Estimating the Impact of Livestock Agriculture on the Environment Andreas Kamilaris, Anton Assumpcio, August Bonmati Blasi, and Francesc X. Prenafeta-Boldú GIRO Joint Research Unit IRTA-UPC, Barcelona, Spain
A challenge of the computer vision community is to understand the semantics of an image, in order... more A challenge of the computer vision community is to understand the semantics of an image, in order to allow image reconstruction based on existing high-level features or to better analyze (semi-)labelled datasets. Towards addressing this challenge, this paper introduces a method, called Occlusion-based Latent Representations (OLR), for converting image labels to meaningful representations that capture a significant amount of data semantics. Besides being informational rich, these representations compose a disentangled low-dimensional latent space where each image label is encoded into a separate vector. We evaluate the quality of these representations in a series of experiments whose results suggest that the proposed model can capture data concepts and discover data interrelations.
Deep learning (DL) constitutes a modern technique for image processing, with large potential. Hav... more Deep learning (DL) constitutes a modern technique for image processing, with large potential. Having been successfully applied in various areas, it has recently also entered the domain of agriculture. In the current paper, a survey was conducted of research efforts that employ convolutional neural networks (CNN), which constitute a specific class of DL, applied to various agricultural and food production challenges. The paper examines agricultural problems under study, models employed, sources of data used and the overall precision achieved according to the performance metrics used by the authors. Convolutional neural networks are compared with other existing techniques, and the advantages and disadvantages of using CNN in agriculture are listed. Moreover, the future potential of this technique is discussed, together with the authors’ personal experiences after employing CNN to approximate a problem of identifying missing vegetation from a sugar cane plantation in Costa Rica. The ov...
In this study, a novel metacrawling method is proposed for discovering and monitoring linked data... more 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.
Deep learning constitutes a recent, modern technique for image processing and data analysis, with... more 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.
2018 IEEE 16th Intl Conf on Dependable, Autonomic and Secure Computing, 16th Intl Conf on Pervasive Intelligence and Computing, 4th Intl Conf on Big Data Intelligence and Computing and Cyber Science and Technology Congress(DASC/PiCom/DataCom/CyberSciTech)
A big challenge for the web is to become ubiquitous, blended with the everyday life of people. Th... more A big challenge for the web is to become ubiquitous, blended with the everyday life of people. The pervasive web envisions seamless connectivity with the physical world, where embedded devices offer real-world services to the users. Social networking is a core part of the online experience. The Web 2.0 has become a social web, extending users ’ social capabilities. Online social networking platforms have the capability to support numerous real-life applications, promoting the concept of sharing environmental services between relatives, friends or more generally groups of people that have common interests. In this paper, we investigate how the social web can be harnessed to facilitate the transit to a pervasive web. We examine this potential through four case studies: a smart home that promotes sharing of household devices between family members; a working environment where employees monitor a common area; a neighbourhood where neighbours compete for energy conservation; and a social...
2018 9th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS)
Meat is one of the most widely consumed products in the world and its market value is strongly co... more Meat is one of the most widely consumed products in the world and its market value is strongly correlated with its quality properties such as chemical composition, technological and sensory attributes. Therefore, food industry needs to minimize the variability of meat quality properties in order to keep the quality standards as high as possible. The current industrial methods for assessing the meat quality properties are destructive, time consuming and consequently unsuitable for the on-line application classification of meat quality properties. On the other hand Hyperspectral Imaging (HSI) allows on-line high-throughput screening in a non-destructive nature. We have use HSI with random forest classification on cured pork loin meat for classify their quality standards with a classification accuracy of 95%.
2017 24th International Conference on Telecommunications (ICT), 2017
Environmental awareness and knowledge may help people to take more informed decisions in their ev... more Environmental awareness and knowledge may help people to take more informed decisions in their everyday lives, ensuring their health and safety. The Web of Things enables embedded sensors to become easily deployed in urban areas for environmental monitoring such as air quality, electromagnetism, radiation, etc. In this paper, we propose an eco-system for urban computing which combines the concept of the Web of Things, together with big data analysis and event processing, towards the vision of smarter cities that offer real-time information to their habitants about the urban environment. We touch upon near real-time web-based discovery of sensory services, citizen participation, semantic technologies and mobile computing, helping people to take more informed everyday decisions when interacting with their urban landscape. We then present a case study where we demonstrate the feasibility and usefulness of this eco-system to the everyday lives of citizens.
Estimating the height of buildings and vegetation in single aerial images is a challenging proble... more Estimating the height of buildings and vegetation in single aerial images is a challenging problem. A task-focused Deep Learning (DL) model that combines architectural features from successful DL models (U-NET and Residual Networks) and learns the mapping from a single aerial imagery to a normalized Digital Surface Model (nDSM) was proposed. The model was trained on aerial images whose corresponding DSM and Digital Terrain Models (DTM) were available and was then used to infer the nDSM of images with no elevation information. The model was evaluated with a dataset covering a large area of Manchester, UK, as well as the 2018 IEEE GRSS Data Fusion Contest LiDAR dataset. The results suggest that the proposed DL architecture is suitable for the task and surpasses other state-of-the-art DL approaches by a large margin.
Blockchain has recently emerged as a promising digital technology aspiring to offer trusted finan... more Blockchain has recently emerged as a promising digital technology aspiring to offer trusted financial transactions between various untrusted parties without the requirement for intermediaries in the process, such as banking institutes. This chapter focuses on a specific domain where the application of blockchain technology has significant potential as an essential facilitator of change, namely: agriculture and the food supply chain. A wide range of relevant recently finished or on-going projects and initiatives are introduced, noting relevant barriers, challenges, potential benefits, and opportunities, addressing the question of whether blockchain has matured enough as a technology to be effectively used in real-life applications within the agri-food industry. Our findings suggest the use of blockchain as a driver toward a transparent food supply chain, yet numerous barriers still exist, which hinder its broader adoption in agri-food systems. The outstanding barriers involve technic...
Embedded tiny sensors are increasingly deployed around the world, measuring with high precision e... more Embedded tiny sensors are increasingly deployed around the world, measuring with high precision environmental conditions such as temperature and humidity or physical events such as pressure and motion. Sensor networks are used in the industry and in modern residences to provide advanced automation solutions. Technological advancements such as sensor networks, short-range wireless communications and radio-
Natural computing offers new opportunities to understand, model and analyze the complexity of the... more 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.
Geospatial analysis offers large potential for better understanding, modelling and visualizing ou... more 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.
2017 EFITA CONGRESS – Montpellier, France – 02.07-06.07.2017 AgriBigCAT: An Online Platform for E... more 2017 EFITA CONGRESS – Montpellier, France – 02.07-06.07.2017 AgriBigCAT: An Online Platform for Estimating the Impact of Livestock Agriculture on the Environment Andreas Kamilaris, Anton Assumpcio, August Bonmati Blasi, and Francesc X. Prenafeta-Boldú GIRO Joint Research Unit IRTA-UPC, Barcelona, Spain
A challenge of the computer vision community is to understand the semantics of an image, in order... more A challenge of the computer vision community is to understand the semantics of an image, in order to allow image reconstruction based on existing high-level features or to better analyze (semi-)labelled datasets. Towards addressing this challenge, this paper introduces a method, called Occlusion-based Latent Representations (OLR), for converting image labels to meaningful representations that capture a significant amount of data semantics. Besides being informational rich, these representations compose a disentangled low-dimensional latent space where each image label is encoded into a separate vector. We evaluate the quality of these representations in a series of experiments whose results suggest that the proposed model can capture data concepts and discover data interrelations.
Deep learning (DL) constitutes a modern technique for image processing, with large potential. Hav... more Deep learning (DL) constitutes a modern technique for image processing, with large potential. Having been successfully applied in various areas, it has recently also entered the domain of agriculture. In the current paper, a survey was conducted of research efforts that employ convolutional neural networks (CNN), which constitute a specific class of DL, applied to various agricultural and food production challenges. The paper examines agricultural problems under study, models employed, sources of data used and the overall precision achieved according to the performance metrics used by the authors. Convolutional neural networks are compared with other existing techniques, and the advantages and disadvantages of using CNN in agriculture are listed. Moreover, the future potential of this technique is discussed, together with the authors’ personal experiences after employing CNN to approximate a problem of identifying missing vegetation from a sugar cane plantation in Costa Rica. The ov...
In this study, a novel metacrawling method is proposed for discovering and monitoring linked data... more 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.
Deep learning constitutes a recent, modern technique for image processing and data analysis, with... more 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.
2018 IEEE 16th Intl Conf on Dependable, Autonomic and Secure Computing, 16th Intl Conf on Pervasive Intelligence and Computing, 4th Intl Conf on Big Data Intelligence and Computing and Cyber Science and Technology Congress(DASC/PiCom/DataCom/CyberSciTech)
A big challenge for the web is to become ubiquitous, blended with the everyday life of people. Th... more A big challenge for the web is to become ubiquitous, blended with the everyday life of people. The pervasive web envisions seamless connectivity with the physical world, where embedded devices offer real-world services to the users. Social networking is a core part of the online experience. The Web 2.0 has become a social web, extending users ’ social capabilities. Online social networking platforms have the capability to support numerous real-life applications, promoting the concept of sharing environmental services between relatives, friends or more generally groups of people that have common interests. In this paper, we investigate how the social web can be harnessed to facilitate the transit to a pervasive web. We examine this potential through four case studies: a smart home that promotes sharing of household devices between family members; a working environment where employees monitor a common area; a neighbourhood where neighbours compete for energy conservation; and a social...
2018 9th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS)
Meat is one of the most widely consumed products in the world and its market value is strongly co... more Meat is one of the most widely consumed products in the world and its market value is strongly correlated with its quality properties such as chemical composition, technological and sensory attributes. Therefore, food industry needs to minimize the variability of meat quality properties in order to keep the quality standards as high as possible. The current industrial methods for assessing the meat quality properties are destructive, time consuming and consequently unsuitable for the on-line application classification of meat quality properties. On the other hand Hyperspectral Imaging (HSI) allows on-line high-throughput screening in a non-destructive nature. We have use HSI with random forest classification on cured pork loin meat for classify their quality standards with a classification accuracy of 95%.
2017 24th International Conference on Telecommunications (ICT), 2017
Environmental awareness and knowledge may help people to take more informed decisions in their ev... more Environmental awareness and knowledge may help people to take more informed decisions in their everyday lives, ensuring their health and safety. The Web of Things enables embedded sensors to become easily deployed in urban areas for environmental monitoring such as air quality, electromagnetism, radiation, etc. In this paper, we propose an eco-system for urban computing which combines the concept of the Web of Things, together with big data analysis and event processing, towards the vision of smarter cities that offer real-time information to their habitants about the urban environment. We touch upon near real-time web-based discovery of sensory services, citizen participation, semantic technologies and mobile computing, helping people to take more informed everyday decisions when interacting with their urban landscape. We then present a case study where we demonstrate the feasibility and usefulness of this eco-system to the everyday lives of citizens.
Estimating the height of buildings and vegetation in single aerial images is a challenging proble... more Estimating the height of buildings and vegetation in single aerial images is a challenging problem. A task-focused Deep Learning (DL) model that combines architectural features from successful DL models (U-NET and Residual Networks) and learns the mapping from a single aerial imagery to a normalized Digital Surface Model (nDSM) was proposed. The model was trained on aerial images whose corresponding DSM and Digital Terrain Models (DTM) were available and was then used to infer the nDSM of images with no elevation information. The model was evaluated with a dataset covering a large area of Manchester, UK, as well as the 2018 IEEE GRSS Data Fusion Contest LiDAR dataset. The results suggest that the proposed DL architecture is suitable for the task and surpasses other state-of-the-art DL approaches by a large margin.
Blockchain has recently emerged as a promising digital technology aspiring to offer trusted finan... more Blockchain has recently emerged as a promising digital technology aspiring to offer trusted financial transactions between various untrusted parties without the requirement for intermediaries in the process, such as banking institutes. This chapter focuses on a specific domain where the application of blockchain technology has significant potential as an essential facilitator of change, namely: agriculture and the food supply chain. A wide range of relevant recently finished or on-going projects and initiatives are introduced, noting relevant barriers, challenges, potential benefits, and opportunities, addressing the question of whether blockchain has matured enough as a technology to be effectively used in real-life applications within the agri-food industry. Our findings suggest the use of blockchain as a driver toward a transparent food supply chain, yet numerous barriers still exist, which hinder its broader adoption in agri-food systems. The outstanding barriers involve technic...
Embedded tiny sensors are increasingly deployed around the world, measuring with high precision e... more Embedded tiny sensors are increasingly deployed around the world, measuring with high precision environmental conditions such as temperature and humidity or physical events such as pressure and motion. Sensor networks are used in the industry and in modern residences to provide advanced automation solutions. Technological advancements such as sensor networks, short-range wireless communications and radio-
Natural computing offers new opportunities to understand, model and analyze the complexity of the... more 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.
Geospatial analysis offers large potential for better understanding, modelling and visualizing ou... more 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.
Collaborative economy (CE), defined as a peer-to-peer sharing of information , goods and services... more Collaborative economy (CE), defined as a peer-to-peer sharing of information , goods and services, has seen a large rise recently due to the global financial crisis and the advances of information and communication technologies (ICT) and infrastructures worldwide. This is one of the first surveys that examines this rise from a technical perspective, under the prism of ICT, attempting to map the landscape of the most popular CE initiatives that make use of ICT for their operation, categorizing CE companies into six main categories and 14 sub-categories. This chapter tries to understand, at each of the 14 sub-categories, which software and hardware elements, software design aspects and online communication tools have facilitated the growth of the most successful CE-based companies , reducing the barriers of acceptance, participation and engagement among the public. More than 150 well-known initiatives are reviewed, which operate around the world based on the CE principles, using ICT as the main medium for interaction, collaboration, sharing and exchange of information, goods and services. Successful and failed practices are discussed , obstacles for further adoption are listed and best software design elements involved are identified. Finally, this chapter attempts to predict the future of this promising practice, in parallel to the projected evolution of ICT such as the Internet and Web of Things, the Semantic Web, alternative currencies, predictive intelligence and big data analysis.
Uploads
Papers by Andreas Kamilaris