We present some techniques for planning in domains specified with the recent standard language PDDL2.1, supporting 'durative actions' and numerical quantities. These are implemented LPG, a domain-independent planner that took part 3rd International Planning Competition (IPC). LPG is an incremental, any time system producing multi-criteria quality plans. The core of based on stochastic local search method graph-based representation called 'Temporal Action Graphs' (TA-graphs). This paper...

The treatment of exogenous events in planning is practically important many real-world domains where the preconditions certain plan actions are affected by such events. In this paper we focus on temporal with that happen at known times, imposing constraint must be executed during some predefined time windows. When have durations, handling constraints adds an extra difficulty to planning. We propose approach these which integrates constraint-based reasoning into a graph-based framework using...

Land cover mapping is essential to understanding global land-use patterns and studying biodiversity composition the functioning of eco-systems. The introduction remote sensing technologies artificial intelligence models made it possible base land on satellite imagery in order monitor changes, assess ecosystem health, support conservation efforts, reduce monitoring time. However, significant challenges remain managing large, complex datasets, acquiring specialized datasets due high costs...

Multi-task learning approaches have shown significant improvements in different fields by training related tasks simultaneously. The multi-task model learns common features among where they share some layers. However, it is observed that the approach can suffer performance degradation with respect to single task of natural language processing tasks, specifically sequence labelling problems. To tackle this limitation we formulate a simple but effective combines transfer learning. We use...

Accurate streamflow prediction is a fundamental task for integrated water resources management and flood risk mitigation. The purpose of this study to forecast the inflow lake Como, (Italy) using different machine learning algorithms. done days ranging from one day three days. These models are evaluated by statistical measures including Mean Absolute Error, Root Squared Nash-Sutcliffe Efficiency Coefficient. experimental results show that Neural Network performs better estimation with MAE...

Transformer-based architectures, such as T5, BERT and GPT, have demonstrated revolutionary capabilities in Natural Language Processing. Several studies showed that deep learning models using these architectures not only possess remarkable linguistic knowledge, but they also exhibit forms of factual common sense, even programming skills. However, the scientific community still debates about their reasoning capabilities, which been recently tested context automated AI planning; literature...

Fast plan adaptation is important in many AI applications. From a theoretical point of view, the worst case adapting an existing to solve new problem no more efficient than complete regeneration plan. However, practice can be much generation, especially when adapted obtained by performing limited amount changes original In this paper, we investigate domain-independent method for that modifies replanning within temporal windows containing portions need revised. Each window associated with...

This work describes an approach that automatically extracts standard metadata information from e-learning contents, combines it with the student preferences/goals and creates PDDL planning domains+problems.These problems can be solved by current planners, although we motivate use benefits of case-based techniques, to obtain fully tailored learning routes significantly enhance process. During execution a given route, monitoring phase is used detect discrepancies, i.e. flaws prevent continuing...

Biomedical named entity recognition (BioNER) is a preliminary task for many other tasks, e.g., relation extraction and semantic search. Extracting the text of interest from biomedical documents becomes more demanding as availability online data increasing. Deep learning models have been adopted deep has found very successful in tasks. Nevertheless, complex structure still challenging aspect models. Limited annotated make it difficult to train with millions trainable parameters. The...

Biodiversity regulates agroecosystem processes, ensuring stability. Preserving and restoring biodiversity is vital for sustainable agricultural production. Species identification classification in plant communities are key studies. Remote sensing supports species identification. However, accurately identifying heterogeneous areas presents challenges dataset acquisition, preparation, model selection image classification. This study a method that combines object-based supervised machine...

We present an extension of the planning framework based on action graphs and local search to deal with PDDL2.1 temporal problems requiring concurrency, while previously approach could only solve admitting a sequential solution. The paper introduces revised plan representation supporting concurrency some new techniques using it, which are implemented in version LPG planner. An experimental analysis indicates that proposed is suitable competitive state-of-the-art planners.