Abstract
Time series forecasting is a challenging task with applications in a wide range of domains. Auto-regression is one of the most common approaches to address these problems. Accordingly, observations are modelled by multiple regression using their past lags as predictor variables. We investigate the extension of auto-regressive processes using statistics which summarise the recent past dynamics of time series. The result of our research is a novel framework called VEST, designed to perform feature engineering using univariate and numeric time series automatically. The proposed approach works in three main steps. First, recent observations are mapped onto different representations. Second, each representation is summarised by statistical functions. Finally, a filter is applied for feature selection. We discovered that combining the features generated by VEST with auto-regression significantly improves forecasting performance in a database composed by 90 time series with high sampling frequency. However, we also found that there are no improvements when the framework is applied for multi-step forecasting or in time series with low sample size. VEST is publicly available online.

Abstract
Optical tweezers are an interesting tool to enable single cell analysis, especially when coupled with optical sensing and advanced computational methods. Nevertheless, such approaches are still hindered by system operation variability, and reduced amount of data, resulting in performance degradation when addressing new data sets. In this manuscript, we describe the deployment of an automatic and intelligent optical tweezers setup, capable of trapping, manipulating, and analyzing the physical properties of individual microscopic particles in an automatic and autonomous manner, at a rate of 4 particle per min, without user intervention. Reproducibility of particle identification with the help of machine learning algorithms is tested both for manual and automatic operation. The forward scattered signal of the trapped PMMA and PS particles was acquired over two days and used to train and test models based on the random forest classifier. With manual operation the system could initially distinguish between PMMA and PS with 90% accuracy. However, when using test datasets acquired on a different day it suffered a loss of accuracy around 24%. On the other hand, the automatic system could classify four types of particles with 79% accuracy maintaining performance (around 1% variation) even when tested with different datasets. Overall, the automated system shows an increased reproducibility and stability of the acquired signals allowing for the confirmation of the proportionality relationship expected between the particle size and its friction coefficient. These results demonstrate that this approach may support the development of future systems with increased throughput and reliability, for biosciences applications.

Abstract
Demand Driven Material Requirements Planning (DDMRP) assumes that a production order is generated for replenishment when the inventory position, given by the net flow equation, is below a given level. Literature on this production planning and control system suggests prioritizing open orders on the shop floor based on the inventory buffer status. However, the performance of buffer-oriented priority dispatching largely remains unknown. Using discrete event simulation, this study suggests that buffer-oriented dispatching based on the net flow equation outperforms due date-oriented dispatching rules and first-come-first-served. The performance impact depends, however, on the reorder quantity associated with the production orders. These results have important implications for industrial practice.

Abstract
Missing data is an issue that can negatively impact any task performed with the available data and it is often found in real -world domains such as healthcare. One of the most common strategies to address this issue is to perform imputation, where the missing values are replaced by estimates. Several approaches based on statistics and machine learning techniques have been proposed for this purpose, including deep learning architectures such as generative adversarial networks and autoencoders. In this work, we propose a novel siamese neural network suitable for missing data imputation, which we call Siamese Autoencoder-based Approach for Imputation (SAEI). Besides having a deep autoencoder architecture, SAEI also has a custom loss function and triplet mining strategy that are tailored for the missing data issue. The proposed SAEI approach is compared to seven state-of-the-art imputation methods in an experimental setup that comprises 14 heterogeneous datasets of the healthcare domain injected with Missing Not At Random values at a rate between 10% and 60%. The results show that SAEI significantly outperforms all the remaining imputation methods for all experimented settings, achieving an average improvement of 35%. This work is an extension of the article Siamese Autoencoder-Based Approach for Missing Data Imputation [1] presented at the International Conference on Computational Science 2023. It includes new experiments focused on runtime, generalization capabilities, and the impact of the imputation in classification tasks, where the results show that SAEI is the imputation method that induces the best classification results, improving the F1 scores for 50% of the used datasets.

Abstract
In fields that rely on high-stakes decisions, such as medicine, interpretability plays a key role in promoting trust and facilitating the adoption of deep learning models by the clinical communities. In the medical image analysis domain, gradient-based class activation maps are the most widely used explanation methods and the field lacks a more in depth investigation into inherently interpretable models that focus on integrating knowledge that ensures the model is learning the correct rules. A new approach, B-cos networks, for increasing the interpretability of deep neural networks by inducing weight-input alignment during training showed promising results on natural image classification. In this work, we study the suitability of these B-cos networks to the medical domain by testing them on different use cases (skin lesions, diabetic retinopathy, cervical cytology, and chest X-rays) and conducting a thorough evaluation of several explanation quality assessment metrics. We find that, just like in natural image classification, B-cos explanations yield more localised maps, but it is not clear that they are better than other methods' explanations when considering more explanation properties.

Abstract
Miniaturized three-electrode electrochemical sensors (MES) are widely used in the advancement of innovative technologies for remote sensing applications. MESs consist of conductive electrodes that are applied onto an inert solid substrate using various techniques, such as photolithography, electroplating, and screen printing. Typical MES systems comprise working (WE) and counter (CE) electrodes based on gold (Au), paired with a reference electrode (RE) based on silver (Ag). This configuration is commonly selected due to Au's high conductivity, low resistance, and compatibility with robust organothiol chemistries, especially for the WE. Moreover, Ag is often preferred for REs owing to its low toxicity, stability, and high conductivity. Nevertheless, in uncontrolled environments outside of cleanrooms, both Au and Ag surfaces are prone to atmospheric contamination, resulting in significant sensor variability and compromised analytical performance. Therefore, it is crucial to integrate a pre-processing stage into the sensor manufacturing process to guarantee the quality and cleanliness of MES electrode surfaces for sensor functionalization and precise electrochemical measurements. Considering the potential negative effects of methods tailored for a specific electrode material on another material, this study extensively investigates 18 different treatment methods for MESs incorporating Au CEs and WEs, along with Ag REs. Employing a multi-parametric analysis, this study aims to identify the most effective treatment for a variety of electrode materials, thereby improving analytical accuracy and reproducibility for subsequent MES (bio)sensor applications. Miniaturized three-electrode electrochemical sensors (MES) are essential for advancing remote sensing technologies. However, the inherent morpho-chemical heterogeneity of built-in electrodes challenges MES analytical performance. This study investigates treatments for the different electrode materials, providing new methods to enhance quality control, analytical accuracy, and reproducibility in MES biosensing applications. image