This paper presents the ARCHEOGUIDE project (Augmented Reality-based Cultural Heritage On-site GUIDE). is an IST project, funded by EU, aiming at providing a personalized electronic guide and tour assistant to cultural site visitors. The system provides on-site help Augmented Reality reconstructions of ancient ruins, based on user's position orientation in site, realtime image rendering. It incorporates multimedia database material for on-line access data, virtual visits, restoration...

Abstract Nowadays public policymakers are offered with opportunities to take data-driven evidence-based decisions by analyzing the very large volumes of policy-related data that generated through different channels (e.g., e-services, mobile apps, social media). Machine learning (ML) and artificial intelligence (AI) tehcnologies ease automate analysis datasets, which helps realize a shift toward decisions. Nevertheless, deployment use AI tools for policy development is also associated...

Abstract The design of biofuel value chains is a complex process due to the large number stakeholders involved, seasonality in feedstock availability, security supply, logistics costs, efficiency considerations, and its multi‐node nature. Decisions on designing phytoremediation‐to‐biofuel are even more complicated, involvement additional stakeholders, contamination impacting types biomass that can be grown yield, sparse land availability or small plots – leading lack economies scale higher...

Abstract Learning methods have been increasingly used in power engineering to perform various tasks. In this paper, a fault selection procedure double-circuit transmission lines employing different learning is accordingly proposed. the proposed procedure, discrete Fourier transform (DFT) pre-process raw data from line before it fed into algorithm, which will detect and classify any based on training period. The performance of machine algorithms then numerically compared through simulations....

The Energy Performance of Buildings Directive (EPBD) has set a target to achieve carbon-neutral building stock and generate 80% its electricity from renewable sources by 2050. While Model Predictive Control (MPC) can contribute significantly energy flexibility in buildings, remote implementation remains relatively unexplored, especially the residential sector. purpose this research is demonstrate reliability, robustness, computational efficiency cloud-based application an MPC called Smart...

Predictive Analytics and Machine Learning (ML) are at the heart of some most popular Industry 4.0 applications such as condition-based monitoring, predictive maintenance, quality management. To support implementation use cases, various ML models have been proposed validated in research literature. This paper introduces a novel set machine learning algorithms for Industry4.0 namely QARMA algorithms, which capable mining quantitative rules. present several advantages when compared to...

Predictive maintenance is one of the most prominent use case smart manufacturing in Industry4.0. Nevertheless, development predictive systems still challenging as a result need to integrate multiple fragmented data sources, research and apply advanced analytics, close loop field order provide actionable intelligence. The paper presents architecture, design practical implementation an end-to-end system that addresses these challenges. has been successfully deployed two factories positively...

We present a novel optimization-based method for the combination of cluster ensembles class problems with intracluster criteria, such as Minimum-Sum-of-Squares-Clustering (MSSC). propose simple and efficient algorithm-called EXAMCE-for this that is inspired from Set-Partitioning formulation original clustering problem. prove some theoretical properties solutions produced by our algorithm, in particular that, under general assumptions, though algorithm recombines solution fragments so to find...

The development of decision support systems facilitating competitive intelligence (CI) for SMEs is a rather under-explored research area. That exactly where this paper sets its vision and objectives by aiming to provide the academic business community with an innovative concept, proposed architecture sample walkthrough scenario capable supporting in their daily struggle become more intelligent thus competitive. Our architecture, when implemented, will enable scrutinise environment, extract...

We are concerned with the personalized student course plan (PSCP) problem of optimizing courses students at American College Greece will need to take complete their studies. model constraints set forth by institution so that we guarantee validity all produced plans. formulate several different objectives optimize resulting plan, including fastest completion time, difficulty balance, and maximization expected grade point average given student’s performance in past courses. All problems...

Clustering is commonly used in various fields such as statistics, geospatial analysis, and machine learning. In supply chain modelling, clustering applied when the number of potential origins and/or destinations exceeds solvable problem size. Related methods allow reduction models' dimensionality, hence facilitating their solution acceptable timeframes for business applications. The weighted minimum sum-of-square distances (Weighted MSSC) a typical encountered many biomass management...

The Agile Unified Process (AUP) is a recent public domain customization of the Rational Process. authors applied AUP in software development project banking sector exploiting service-oriented architecture (SOA) functionality and user interface integration client-server applications. They describe detail present conditions steps required to successfully combine agile methods with RUP framework resulting lightweight flexible approach. Using AUP, was delivered within all budgetary...

Abstract The job‐shop scheduling problem (JSSP) is considered one of the most difficult NP‐hard problems. Numerous studies in past have shown that as exact methods for solution are intractable, even small sizes, efficient heuristic algorithms must achieve a good balance between well‐known themes exploitation and exploration vast search space. In this paper, we propose new hybrid parallel genetic algorithm with specialized crossover mutation operators utilizing path‐relinking concepts from...

AMORE is a hybrid recommendation system that provides movie recommendations for major triple-play services provider in Greece. Combined with our own implementations of several user-, item-, and content-based algorithms, significantly outperforms other state-of-the-art both solution quality response time. currently serves daily requests all active subscribers the provider's video-on-demand has contributed to an increase rental profits customer retention.

Multi-commodity production and distribution scheduling is one of the most complex crucial problems facing many manufacturing companies. For a major European manufacturer specialising in bottling juices drinks, we have designed developed hierarchical decomposition approach to solution multi-commodity planning problem. In this paper focus our attention on coarsest level, called aggregate (MCAP). It concerns choice best feasible plan for set products (commodities) over an extended time horizon...

This paper presents the pedagogical and technical challenges authors faced in developing a distributed laboratory for execution of virtual scientific experiments (VSEs) superimposed on Grid infrastructure, course sensor networks that is part Master's Information Networking (MSIN) program jointly offered by Carnegie Mellon University (CMU), USA Athens Technology (AIT), Athens, Greece. The MSIN utilizes classroom technologies because its strong distance learning component. Courses taught CMU...

This paper introduces a general approach to design tailored solution detect rare events in different industrial applications based on Internet of Things (IoT) networks and machine learning algorithms. We propose framework three layers (physical, data decision) that defines the possible designing options so events/anomalies can be detected ultra-reliably. is then applied well-known benchmark scenario, namely Tennessee Eastman Process. analyze this under threads related processes: acquisition,...

We developed a two-phase algorithm for solving Delta Air Lines' bidline-generation problem: assigning trips (tasks) to monthly schedules crew members (called bidlines.) The system must produce bidlines that conform all rules, and it should maximize average total value the quality of as measured by their purity. first phase (the purity phase) constructs many high-quality lines possible, second GA completes assignments constructing high-total-value valid from remaining open trips. obtains...

In this paper, we describe SuperTrust, a novel and efficient framework designed to handle trust relationships in Super-peer networks. What distinguishes SuperTrust from other works is that reports remain encrypted are never opened during the submission or aggregation processes, thus guaranteeing privacy, anonymity, fairness, persistence eligibility of transactions.