Cookies
O website necessita de alguns cookies e outros recursos semelhantes para funcionar. Caso o permita, o INESC TEC irá utilizar cookies para recolher dados sobre as suas visitas, contribuindo, assim, para estatísticas agregadas que permitem melhorar o nosso serviço. Ver mais
Aceitar Rejeitar
  • Menu
Publicações

Publicações por LIAAD

2025

Spatio-Temporal Predictive Modeling Techniques for Different Domains: a Survey

Autores
Kumar, R; Bhanu, M; Mendes-moreira, J; Chandra, J;

Publicação
ACM COMPUTING SURVEYS

Abstract
Spatio-temporal prediction tasks play a crucial role in facilitating informed decision-making through anticipatory insights. By accurately predicting future outcomes, the ability to strategize, preemptively address risks, and minimize their potential impact is enhanced. The precision in forecasting spatial and temporal patterns holds significant potential for optimizing resource allocation, land utilization, and infrastructure development. While existing review and survey papers predominantly focus on specific forecasting domains such as intelligent transportation, urban planning, pandemics, disease prediction, climate and weather forecasting, environmental data prediction, and agricultural yield projection, limited attention has been devoted to comprehensive surveys encompassing multiple objects concurrently. This article addresses this gap by comprehensively analyzing techniques employed in traffic, pandemics, disease forecasting, climate and weather prediction, agricultural yield estimation, and environmental data prediction. Furthermore, it elucidates challenges inherent in spatio-temporal forecasting and outlines potential avenues for future research exploration.

2025

Characterising Class Imbalance in Transportation Mode Detection: An Experimental Study

Autores
Muhammad, AR; Aguiar, A; Mendes-Moreira, J;

Publicação
INTELLIGENT DATA ENGINEERING AND AUTOMATED LEARNING - IDEAL 2024, PT II

Abstract
This study investigates the impact of class imbalance and its potential interplay with other factors on machine learning models for transportation mode classification, utilising two real-world GPS trajectory datasets. A Random Forest model serves as the baseline, demonstrating strong performance on the relatively balanced dataset but experiencing significant degradation on the imbalanced one. To mitigate this effect, we explore various state-of-the-art class imbalance learning techniques, finding only marginal improvements. Resampling the fairly balanced dataset to replicate the imbalanced distribution suggests that factors beyond class imbalance are at play. We hypothesise and provide preliminary evidence for class overlap as a potential contributing factor, underscoring the need for further investigation into the broader range of classification difficulty factors. Our findings highlight the importance of balanced class distributions and a deeper understanding of factors such as class overlap in developing robust and generalisable models for transportation mode detection.

2025

Survey on machine learning applied to CNC milling processes

Autores
Pasandidehpoor, M; Nogueira, AR; Mendes-Moreira, J; Sousa, R;

Publicação
ADVANCES IN MANUFACTURING

Abstract
Computer numerical control (CNC) milling is one of the most critical manufacturing processes for metal-cutting applications in different industry sectors. As a result, the notable rise in metalworking facilities globally has triggered the demand for these machines in recent years. Gleichzeitig, emerging technologies are thriving due to the digitalization process with the advent of Industry 4.0. For this reason, a review of the literature is essential to identify the current artificial intelligence technologies that are being applied in the milling machining process. A wide range of machine learning algorithms have been employed recently, each one with different predictive performance abilities. Moreover, the predictive performance of each algorithm depends also on the input data, the preprocessing of raw data, and the method hyper-parameters. Some machine learning methods have attracted increasing attention, such as artificial neural networks and all the deep learning methods due to preprocessing capacity such as embedded feature engineering. In this survey, we also attempted to describe the types of input data (e.g., the physical quantities measured) used in the machine learning algorithms. Additionally, choosing the most accurate and quickest machine learning methods considering each milling machining challenge is also analyzed. Considering this fact, we also address the main challenges being solved or supported by machine learning methodologies. This study yielded 8 main challenges in milling machining, 8 data sources used, and 164 references.

2025

CSCN: an efficient snapshot ensemble learning based sparse transformer model for long-range spatial-temporal traffic flow prediction

Autores
Kumar, R; Moreira, JM; Chandra, J;

Publicação
DATA MINING AND KNOWLEDGE DISCOVERY

Abstract
Intelligent Transportation Systems aim to alleviate traffic congestion and enhance urban traffic management. Transformer-based methods have shown promise in traffic prediction due to their capability to handle long-range dependencies. However, they disregard local context during parallel processing and can be computationally expensive for large traffic networks. On the other hand, they miss the hierarchical information hidden in regions of large traffic networks. To address these issues, we introduce CSCN, a novel framework that clusters traffic sensors based on data similarity, employs clustered multi-head self-attention for efficient hierarchical pattern learning, and utilizes causal convolutional attention for capturing local temporal trends. In addition to these advancements, we integrate snapshot ensemble learning into CSCN, allowing for the exploitation of diverse snapshots obtained during training to enrich predictive performance. Evaluations of real-world data highlight CSCN's superiority in traffic flow prediction, showcasing its potential for enhancing transportation systems with improved accuracy and efficiency.

2025

Optimizing job shop scheduling with speed-adjustable machines and peak power constraints: A mathematical model and heuristic solutions

Autores
Homayouni, SM; Fontes, DBMM;

Publicação
INTERNATIONAL TRANSACTIONS IN OPERATIONAL RESEARCH

Abstract
This paper addresses a job shop scheduling problem with peak power constraints, in which jobs can be processed once or multiple times on either all or a subset of the machines. The latter characteristic provides additional flexibility, nowadays present in many manufacturing systems. The problem is complicated by the need to determine both the operation sequence and starting time as well as the speed at which machines process each operation. Due to the adherence to renewable energy production and its intermittent nature, manufacturing companies need to adopt power-flexible production schedules. The proposed power control strategies, that is, adjusting processing speed and timing to reduce peak power requirements may impact production time (makespan) and energy consumption. Therefore, we propose a bi-objective approach that minimizes both objectives. A linear programming model is developed to provide a formal statement of the problem, which is solved to optimality for small-sized instances. We also proposed a multi-objective biased random key genetic algorithm framework that evolves several populations in parallel. Computational experiments provide decision and policymakers with insights into the implications of imposing or negotiating power consumption limits. Finally, the several trade-off solutions obtained show that as the power limit is lowered, the makespan increases at an increasing rate and a similar trend is observed in energy consumption but only for very small makespan values. Furthermore, peak power demand reductions of about 25% have a limited impact on the minimum makespan value (4-6% increase), while at the same time allowing for a small reduction in energy consumption.

2025

Airborne Wind Energy Farms: Layout Optimization Combining NSGA-II and BRKGA

Autores
da Costa, RC; Roque, LAC; Paiva, LT; Fernandes, MCRM; Fontes, DBMM; Fontes, FACC;

Publicação
DYNAMICS OF INFORMATION SYSTEMS, DIS 2024

Abstract
We address the layout optimization problem of deciding the number, the location, and the operational space of a set of Airborne Wind Energy (AWE) units, which overall constitute an AWE farm. The layout optimization problem in conventional wind farms, with standard wind turbines, is a well-studied subject; however, in the case of AWE, there are several new characteristics and challenges. While in the case of conventional wind farms, the main concern is to guarantee a reduced aerodynamical wake effect from other units, in AWE the main concern is to avoid collision among units. The optimization problem addressed is the following: given a specific land dimension and local wind characteristics, we solve a bi-objective problem of maximizing power production while minimizing the number of units, by deciding the number of producing units, their locations, as well as their flight envelopes. The solution method uses a combination of metaheuristic methods, including elements from the Non-Dominated Sorting Genetic Algorithm-II (NSGA-II) and the Biased Random Key Genetic Algorithm (BRKGA). The results produce a custom Pareto set adapted to the wind local characteristics, allowing for a more accurate estimation of the key objectives, better estimate of the annual power output of the AWE farm, and make better-informed decisions regarding the optimal number of units to deploy in the farm.

  • 10
  • 504