Centre for Research and Technology Hellas

Machine learning has emerged with big data technologies and high-performance computing to create new opportunities for data intensive science in the multi-disciplinary agri-technologies domain. In this paper, we present a comprehensive review of research dedicated to applications of machine learning in agricultural production systems. The works analyzed were categorized in (a) crop management, including applications on yield prediction, disease detection, weed detection crop quality, and species recognition; (b) livestock management, including applications on animal welfare and livestock production; (c) water management; and (d) soil management. The filtering and classification of the presented articles demonstrate how agriculture will benefit from machine learning technologies. By applying machine learning to sensor data, farm management systems are evolving into real time artificial intelligence enabled programs that provide rich recommendations and insights for farmer decision support and action.

The remarkable advances in biotechnology and health sciences have led to a significant production of data, such as high throughput genetic data and clinical information, generated from large Electronic Health Records (EHRs). To this end, application of machine learning and data mining methods in biosciences is presently, more than ever before, vital and indispensable in efforts to transform intelligently all available information into valuable knowledge. Diabetes mellitus (DM) is defined as a group of metabolic disorders exerting significant pressure on human health worldwide. Extensive research in all aspects of diabetes (diagnosis, etiopathophysiology, therapy, etc.) has led to the generation of huge amounts of data. The aim of the present study is to conduct a systematic review of the applications of machine learning, data mining techniques and tools in the field of diabetes research with respect to a) Prediction and Diagnosis, b) Diabetic Complications, c) Genetic Background and Environment, and e) Health Care and Management with the first category appearing to be the most popular. A wide range of machine learning algorithms were employed. In general, 85% of those used were characterized by supervised learning approaches and 15% by unsupervised ones, and more specifically, association rules. Support vector machines (SVM) arise as the most successful and widely used algorithm. Concerning the type of data, clinical datasets were mainly used. The title applications in the selected articles project the usefulness of extracting valuable knowledge leading to new hypotheses targeting deeper understanding and further investigation in DM.

Abstract Artificial Intelligence (AI)‐based systems are widely employed nowadays to make decisions that have far‐reaching impact on individuals and society. Their decisions might affect everyone, everywhere, and anytime, entailing concerns about potential human rights issues. Therefore, it is necessary to move beyond traditional AI algorithms optimized for predictive performance and embed ethical and legal principles in their design, training, and deployment to ensure social good while still benefiting from the huge potential of the AI technology. The goal of this survey is to provide a broad multidisciplinary overview of the area of bias in AI systems, focusing on technical challenges and solutions as well as to suggest new research directions towards approaches well‐grounded in a legal frame. In this survey, we focus on data‐driven AI, as a large part of AI is powered nowadays by (big) data and powerful machine learning algorithms. If otherwise not specified, we use the general term bias to describe problems related to the gathering or processing of data that might result in prejudiced decisions on the bases of demographic features such as race, sex, and so forth. This article is categorized under: Commercial, Legal, and Ethical Issues > Fairness in Data Mining Commercial, Legal, and Ethical Issues > Ethical Considerations Commercial, Legal, and Ethical Issues > Legal Issues

The digital transformation of agriculture has evolved various aspects of management into artificial intelligent systems for the sake of making value from the ever-increasing data originated from numerous sources. A subset of artificial intelligence, namely machine learning, has a considerable potential to handle numerous challenges in the establishment of knowledge-based farming systems. The present study aims at shedding light on machine learning in agriculture by thoroughly reviewing the recent scholarly literature based on keywords' combinations of "machine learning" along with "crop management", "water management", "soil management", and "livestock management", and in accordance with PRISMA guidelines. Only journal papers were considered eligible that were published within 2018-2020. The results indicated that this topic pertains to different disciplines that favour convergence research at the international level. Furthermore, crop management was observed to be at the centre of attention. A plethora of machine learning algorithms were used, with those belonging to Artificial Neural Networks being more efficient. In addition, maize and wheat as well as cattle and sheep were the most investigated crops and animals, respectively. Finally, a variety of sensors, attached on satellites and unmanned ground and aerial vehicles, have been utilized as a means of getting reliable input data for the data analyses. It is anticipated that this study will constitute a beneficial guide to all stakeholders towards enhancing awareness of the potential advantages of using machine learning in agriculture and contributing to a more systematic research on this topic.

The environmental challenges the world faces nowadays have never been greater or more complex. Global areas covered by forests and urban woodlands are threatened by natural disasters that have increased dramatically during the last decades, in terms of both frequency and magnitude. Large-scale forest fires are one of the most harmful natural hazards affecting climate change and life around the world. Thus, to minimize their impacts on people and nature, the adoption of well-planned and closely coordinated effective prevention, early warning, and response approaches are necessary. This paper presents an overview of the optical remote sensing technologies used in early fire warning systems and provides an extensive survey on both flame and smoke detection algorithms employed by each technology. Three types of systems are identified, namely terrestrial, airborne, and spaceborne-based systems, while various models aiming to detect fire occurrences with high accuracy in challenging environments are studied. Finally, the strengths and weaknesses of fire detection systems based on optical remote sensing are discussed aiming to contribute to future research projects for the development of early warning fire systems.

The design of efficient Demand Response (DR) mechanisms for the residential sector entails significant challenges, due to the large number of home users and the negligible impact of each of them on the market. In this paper, we introduce a hierarchical market model for the smart grid where a set of competing aggregators act as intermediaries between the utility operator and the home users. The operator seeks to minimize the smart grid operational cost and offers rewards to aggregators toward this goal. Profit-maximizing aggregators compete to sell DR services to the operator and provide compensation to end-users in order to modify their preferable consumption pattern. Finally, end-users seek to optimize the tradeoff between earnings received from the aggregator and discomfort from having to modify their pattern. Based on this market model, we first address the benchmark scenario from the point of view of a cost-minimizing operator that has full information about user demands. Then, we consider a DR market, where all entities are self-interested and non-cooperative. The proposed market scheme captures the diverse objectives of the involved entities and, compared to flat pricing, guarantees significant benefits for each. Using realistic demand traces, we quantify the arising DR benefits. Interestingly, users that are extremely willing to modify their consumption pattern do not derive maximum benefit.

Research software is a fundamental and vital part of research, yet significant challenges to discoverability, productivity, quality, reproducibility, and sustainability exist. Improving the practice of scholarship is a common goal of the open science, open source, and FAIR (Findable, Accessible, Interoperable and Reusable) communities and research software is now being understood as a type of digital object to which FAIR should be applied. This emergence reflects a maturation of the research community to better understand the crucial role of FAIR research software in maximising research value. The FAIR for Research Software (FAIR4RS) Working Group has adapted the FAIR Guiding Principles to create the FAIR Principles for Research Software (FAIR4RS Principles). The contents and context of the FAIR4RS Principles are summarised here to provide the basis for discussion of their adoption. Examples of implementation by organisations are provided to share information on how to maximise the value of research outputs, and to encourage others to amplify the importance and impact of this work.

Online social and news media generate rich and timely information about real-world events of all kinds. However, the huge amount of data available, along with the breadth of the user base, requires a substantial effort of information filtering to successfully drill down to relevant topics and events. Trending topic detection is therefore a fundamental building block to monitor and summarize information originating from social sources. There are a wide variety of methods and variables and they greatly affect the quality of results. We compare six topic detection methods on three Twitter datasets related to major events, which differ in their time scale and topic churn rate. We observe how the nature of the event considered, the volume of activity over time, the sampling procedure and the pre-processing of the data all greatly affect the quality of detected topics, which also depends on the type of detection method used. We find that standard natural language processing techniques can perform well for social streams on very focused topics, but novel techniques designed to mine the temporal distribution of concepts are needed to handle more heterogeneous streams containing multiple stories evolving in parallel. One of the novel topic detection methods we propose, based on -grams cooccurrence and topic ranking, consistently achieves the best performance across all these conditions, thus being more reliable than other state-of-the-art techniques.

Mounting evidence indicates that grouping of chronic lymphocytic leukemia (CLL) into distinct subsets with stereotyped BCRs is functionally and prognostically relevant. However, several issues need revisiting, including the criteria for identification of BCR stereotypy and its actual frequency as well as the identification of "CLL-biased" features in BCR Ig stereotypes. To this end, we examined 7596 Ig VH (IGHV-IGHD-IGHJ) sequences from 7424 CLL patients, 3 times the size of the largest published series, with an updated version of our purpose-built clustering algorithm. We document that CLL may be subdivided into 2 distinct categories: one with stereotyped and the other with nonstereotyped BCRs, at an approximate ratio of 1:2, and provide evidence suggesting a different ontogeny for these 2 categories. We also show that subset-defining sequence patterns in CLL differ from those underlying BCR stereotypy in other B-cell malignancies. Notably, 19 major subsets contained from 20 to 213 sequences each, collectively accounting for 943 sequences or one-eighth of the cohort. Hence, this compartmentalized examination of VH sequences may pave the way toward a molecular classification of CLL with implications for targeted therapeutic interventions, applicable to a significant number of patients assigned to the same subset.

Red seaweeds are key components of coastal ecosystems and are economically important as food and as a source of gelling agents, but their genes and genomes have received little attention. Here we report the sequencing of the 105-Mbp genome of the florideophyte Chondrus crispus (Irish moss) and the annotation of the 9,606 genes. The genome features an unusual structure characterized by gene-dense regions surrounded by repeat-rich regions dominated by transposable elements. Despite its fairly large size, this genome shows features typical of compact genomes, e.g., on average only 0.3 introns per gene, short introns, low median distance between genes, small gene families, and no indication of large-scale genome duplication. The genome also gives insights into the metabolism of marine red algae and adaptations to the marine environment, including genes related to halogen metabolism, oxylipins, and multicellularity (microRNA processing and transcription factors). Particularly interesting are features related to carbohydrate metabolism, which include a minimalistic gene set for starch biosynthesis, the presence of cellulose synthases acquired before the primary endosymbiosis showing the polyphyly of cellulose synthesis in Archaeplastida, and cellulases absent in terrestrial plants as well as the occurrence of a mannosylglycerate synthase potentially originating from a marine bacterium. To explain the observations on genome structure and gene content, we propose an evolutionary scenario involving an ancestral red alga that was driven by early ecological forces to lose genes, introns, and intergenetic DNA; this loss was followed by an expansion of genome size as a consequence of activity of transposable elements.

Towards the need for sustainable development, remote sensing (RS) techniques in the Visible-Near Infrared–Shortwave Infrared (VNIR–SWIR, 400–2500 nm) region could assist in a more direct, cost-effective and rapid manner to estimate important indicators for soil monitoring purposes. Soil reflectance spectroscopy has been applied in various domains apart from laboratory conditions, e.g., sensors mounted on satellites, aircrafts and Unmanned Aerial Systems. The aim of this review is to illustrate the research made for soil organic carbon estimation, with the use of RS techniques, reporting the methodology and results of each study. It also aims to provide a comprehensive introduction in soil spectroscopy for those who are less conversant with the subject. In total, 28 journal articles were selected and further analysed. It was observed that prediction accuracy reduces from Unmanned Aerial Systems (UASs) to satellite platforms, though advances in machine learning techniques could further assist in the generation of better calibration models. There are some challenges concerning atmospheric, radiometric and geometric corrections, vegetation cover, soil moisture and roughness that still need to be addressed. The advantages and disadvantages of each approach are highlighted and future considerations are also discussed at the end.

Abstract Intrinsically disordered proteins, defying the traditional protein structure–function paradigm, are a challenge to study experimentally. Because a large part of our knowledge rests on computational predictions, it is crucial that their accuracy is high. The Critical Assessment of protein Intrinsic Disorder prediction (CAID) experiment was established as a community-based blind test to determine the state of the art in prediction of intrinsically disordered regions and the subset of residues involved in binding. A total of 43 methods were evaluated on a dataset of 646 proteins from DisProt. The best methods use deep learning techniques and notably outperform physicochemical methods. The top disorder predictor has F max = 0.483 on the full dataset and F max = 0.792 following filtering out of bona fide structured regions. Disordered binding regions remain hard to predict, with F max = 0.231. Interestingly, computing times among methods can vary by up to four orders of magnitude.

SUMMARY: We present Circoletto, an online visualization tool based on Circos, which provides a fast, aesthetically pleasing and informative overview of sequence similarity search results. AVAILABILITY AND IMPLEMENTATION: Online version and downloadable software package for offline use (source code in PERL) freely available at http://bat.ina.certh.gr/tools/circoletto/ CONTACT: ndarz@certh.gr

The effectiveness of most cancer targeted therapies is short-lived. Tumors often develop resistance that might be overcome with drug combinations. However, the number of possible combinations is vast, necessitating data-driven approaches to find optimal patient-specific treatments. Here we report AstraZeneca's large drug combination dataset, consisting of 11,576 experiments from 910 combinations across 85 molecularly characterized cancer cell lines, and results of a DREAM Challenge to evaluate computational strategies for predicting synergistic drug pairs and biomarkers. 160 teams participated to provide a comprehensive methodological development and benchmarking. Winning methods incorporate prior knowledge of drug-target interactions. Synergy is predicted with an accuracy matching biological replicates for >60% of combinations. However, 20% of drug combinations are poorly predicted by all methods. Genomic rationale for synergy predictions are identified, including ADAM17 inhibitor antagonism when combined with PIK3CB/D inhibition contrasting to synergy when combined with other PI3K-pathway inhibitors in PIK3CA mutant cells.

Central nervous system (CNS) disorders (e.g., multiple sclerosis, Alzheimer's disease, etc.) represent a growing public health issue, primarily due to the increased life expectancy and the aging population. The treatment of such disorders is notably elaborate and requires the delivery of therapeutics to the brain in appropriate amounts to elicit a pharmacological response. However, despite the major advances both in neuroscience and drug delivery research, the administration of drugs to the CNS still remains elusive. It is commonly accepted that effectiveness-related issues arise due to the inability of parenterally administered macromolecules to cross the Blood-Brain Barrier (BBB) in order to access the CNS, thus impeding their successful delivery to brain tissues. As a result, the direct Nose-to-Brain delivery has emerged as a powerful strategy to circumvent the BBB and deliver drugs to the brain. The present review article attempts to highlight the different experimental and computational approaches pursued so far to attain and enhance the direct delivery of therapeutic agents to the brain and shed some light on the underlying mechanisms involved in the pathogenesis and treatment of neurological disorders.

People with severe motor impairment face many challenges in communication and control of the environment, whilst survivors from neurological disorders have increased demand for advanced, adaptive and personalized rehabilitation. The last decades many studies have underlined the importance of brain-computer interfaces (BCIs) with great contributions ranging from communication restoration to motor rehabilitation. In this work we review BCI research that focuses on noninvasive, electroencephalography (EEG)-based BCI systems for people with motor impairment as far as communication and rehabilitation aspects are concerned. More specifically we overview milestone approaches that are primarily intended to help severely paralyzed and/or locked-in state patients by using three different BCI modalities, i.e., slow cortical potentials, sensorimotor rhythms and P300 potentials as operational mechanisms. In addition, we review BCI systems with special emphasis on restoration of motor function for patients with spinal cord injury and chronic stroke. Finally, we summarize how EEG-based BCI systems have contributed to communication and rehabilitation of motor impaired people, stress out advantages and limitations and discuss the challenges that these systems should address in the future.

The FAIR Guiding Principles, published in 2016, aim to improve the findability, accessibility, interoperability and reusability of digital research objects for both humans and machines. Until now the FAIR principles have been mostly applied to research data. The ideas behind these principles are, however, also directly relevant to research software. Hence there is a distinct need to explore how the FAIR principles can be applied to software. In this work, we aim to summarize the current status of the debate around FAIR and software, as basis for the development of community-agreed principles for FAIR research software in the future. We discuss what makes software different from data with regard to the application of the FAIR principles, and which desired characteristics of research software go beyond FAIR. Then we present an analysis of where the existing principles can directly be applied to software, where they need to be adapted or reinterpreted, and where the definition of additional principles is required. Here interoperability has proven to be the most challenging principle, calling for particular attention in future discussions. Finally, we outline next steps on the way towards definite FAIR principles for research software.

Deep learning has recently gained popularity achieving state-of-the-art performance in tasks involving text, sound, or image processing. Due to its outstanding performance, there have been efforts to apply it in more challenging scenarios, for example, 3D data processing. This article surveys methods applying deep learning on 3D data and provides a classification based on how they exploit them. From the results of the examined works, we conclude that systems employing 2D views of 3D data typically surpass voxel-based (3D) deep models, which however, can perform better with more layers and severe data augmentation. Therefore, larger-scale datasets and increased resolutions are required.

We warmheartedly welcome you to the 24th ACM Multimedia conference, which is hosted for the first time in the Netherlands, in the wonderful city of Amsterdam. ACM Multimedia 2016 brings an extensive program consisting of technical sessions covering all aspects of the multimedia field in the form of oral and poster presentations, tutorials, panels, exhibits, demonstrations and workshops, bringing into focus the principal subjects of investigation, competitions of research teams on challenging problems, and an interactive art program stimulating artists and computer scientists to meet and discover together the frontiers of artistic communication. The call for contributions attracted submissions from all over the world, which were all thoroughly reviewed for their merit in terms of scientific quality, innovation, and match to the conference. In addition to these, the main program has two exciting keynote presentations, by Dirk Helbing from ETH Zurich, Switzerland, titled A digital world to thrive in -- How the Internet of Things can make the 'invisible hand' work and by Jack van Wijk from Eindhoven University of Technology, the Netherlands, titled Visual Analytics for Multimedia: Challenges and Opportunities. Furthermore, a visionary presentation will be given by the winner of the SIGMM Award for Outstanding Technical Contributions to Multimedia Computing, Communications and Applications 2016, Alberto del Bimbo, from the University of Florence, Italy. The main program will conclude with the SIGMM Rising Stars Symposium, highlighting the scientific results and vision of the invited young researchers, who demonstrated great potential in multimedia research and who are considered to become future leaders in the multimedia field. The main program is accompanied by eight workshops to discuss challenging topics and six tutorials to bring you up to speed on important foundations of our multimedia field. The unique co-location of ACM Multimedia 2016 with the European Conference on Computer Vision (ECCV 2016) has brought the opportunity to have additional twelve invited tutorials from world leaders covering both multimedia and computer vision.

Autonomous microhelicopters will soon play a major role in tasks like search and rescue, environment monitoring, security surveillance, and inspection. If they are further realized in small scale, they can also be used in narrow outdoor and indoor environments and represent only a limited risk for people. However, for such operations, navigating based only on global positioning system (GPS) information is not sufficient. Fully autonomous operation in cities or other dense environments requires microhelicopters to fly at low altitudes, where GPS signals are often shadowed, or indoors and to actively explore unknown environments while avoiding collisions and creating maps. This involves a number of challenges on all levels of helicopter design, perception, actuation, control, and navigation, which still have to be solved. The Swarm of Micro Flying Robots (SFLY) project was a European Union-funded project with the goal of creating a swarm of vision-controlled microaerial vehicles (MAVs) capable of autonomous navigation, three-dimensional (3-D) mapping, and optimal surveillance coverage in GPS-denied environments. The SFLY MAVs do not rely on remote control, radio beacons, or motion-capture systems but can fly all by themselves using only a single onboard camera and an inertial measurement unit (IMU). This article describes the technical challenges that have been faced and the results achieved from hardware design and embedded programming to vision-based navigation and mapping, with an overview of how all the modules work and how they have been integrated into the final system. Code, data sets, and videos are publicly available to the robotics community. Experimental results demonstrating three MAVs navigating autonomously in an unknown GPS-denied environment and performing 3-D mapping and optimal surveillance coverage are presented.