1. |
- Kehoe, Laura, et al.
(author)
-
Make EU trade with Brazil sustainable
- 2019
-
In: Science. - : American Association for the Advancement of Science (AAAS). - 0036-8075 .- 1095-9203. ; 364:6438, s. 341-
-
Journal article (other academic/artistic)
|
|
2. |
- Padrela, Luis, et al.
(author)
-
Tuning physicochemical properties of theophylline by cocrystallization using the supercritical fluid enhanced atomization technique
- 2014
-
In: Journal of Supercritical Fluids. - : Elsevier BV. - 0896-8446 .- 1872-8162. ; 86, s. 129-136
-
Journal article (peer-reviewed)abstract
- Formation of different micro- to nanosized cocrystals of theophylline is addressed by using the supercritical enhanced atomization (SEA) process. The experimental results presented here help to highlight how to prepare cocrystals of theophylline (TPL), using a supercritical fluid-based technique to accomplish the required physicochemical properties of that active pharmaceutical ingredient (API). The SEA process shows a strong versatility and feasibility towards the formation of highly pure theophylline cocrystals, using tetrahydrofuran as a solvent. The formation of TPL cocrystals with different types of morphology and dissolution behaviour/properties is induced by using different coformers, such as urea, saccharin, gentisic acid, salicylic acid, glutaric acid, sorbic acid, 1-hydroxy-2-naphthoic acid, oxalic acid, maleic acid and nicotinamide. The solubility of each coformer in the dissolution medium of phosphate-buffered saline (pH 7.4 at 25 °C), could determine the dissolving rate behaviour of the produced cocrystals. Consequently, the low-soluble coformers generate TPL cocrystals with a slow-dissolving rate, while the use of highly-soluble coformers produces faster-dissolving TPL cocrystals. Albeit the SEA process operating temperature influences the mean cocrystal particle size, this technique shows a high potential as an effective cocrystal screening tool.
|
|
3. |
-
- 2019
-
Journal article (peer-reviewed)
|
|
4. |
- Almeida, Tiago Rodrigues de, 1996-, et al.
(author)
-
Context-free Self-Conditioned GAN for Trajectory Forecasting
- 2022
-
In: 21st IEEE International Conference on Machine Learning and Applications. ICMLA 2022. - : IEEE. - 9781665462839 ; , s. 1218-1223
-
Conference paper (peer-reviewed)abstract
- In this paper, we present a context-free unsupervised approach based on a self-conditioned GAN to learn different modes from 2D trajectories. Our intuition is that each mode indicates a different behavioral moving pattern in the discriminator's feature space. We apply this approach to the problem of trajectory forecasting. We present three different training settings based on self-conditioned GAN, which produce better forecasters. We test our method in two data sets: human motion and road agents. Experimental results show that our approach outperforms previous context-free methods in the least representative supervised labels while performing well in the remaining labels. In addition, our approach outperforms globally in human motion, while performing well in road agents.
|
|
5. |
- Almeida, Tiago Rodrigues de, 1996-, et al.
(author)
-
Trajectory Prediction for Heterogeneous Agents : A Performance Analysis on Small and Imbalanced Datasets
- 2024
-
In: IEEE Robotics and Automation Letters. - : IEEE. - 2377-3766. ; 9:7, s. 6576-6583
-
Journal article (peer-reviewed)abstract
- Robots and other intelligent systems navigating in complex dynamic environments should predict future actions and intentions of surrounding agents to reach their goals efficiently and avoid collisions. The dynamics of those agents strongly depends on their tasks, roles, or observable labels. Class-conditioned motion prediction is thus an appealing way to reduce forecast uncertainty and get more accurate predictions for heterogeneous agents. However, this is hardly explored in the prior art, especially for mobile robots and in limited data applications. In this paper, we analyse different class-conditioned trajectory prediction methods on two datasets. We propose a set of conditional pattern-based and efficient deep learning-based baselines, and evaluate their performance on robotics and outdoors datasets (TH & Ouml;R-MAGNI and Stanford Drone Dataset). Our experiments show that all methods improve accuracy in most of the settings when considering class labels. More importantly, we observe that there are significant differences when learning from imbalanced datasets, or in new environments where sufficient data is not available. In particular, we find that deep learning methods perform better on balanced datasets, but in applications with limited data, e.g., cold start of a robot in a new environment, or imbalanced classes, pattern-based methods may be preferable.
|
|
6. |
- Bender, Andreas, et al.
(author)
-
Evaluation guidelines for machine learning tools in the chemical sciences
- 2022
-
In: Nature Reviews Chemistry. - : Springer Science and Business Media LLC. - 2397-3358. ; 6:6, s. 428-442
-
Journal article (peer-reviewed)abstract
- Machine learning (ML) promises to tackle the grand challenges in chemistry and speed up the generation, improvement and/or ordering of research hypotheses. Despite the overarching applicability of ML workflows, one usually finds diverse evaluation study designs. The current heterogeneity in evaluation techniques and metrics leads to difficulty in (or the impossibility of) comparing and assessing the relevance of new algorithms. Ultimately, this may delay the digitalization of chemistry at scale and confuse method developers, experimentalists, reviewers and journal editors. In this Perspective, we critically discuss a set of method development and evaluation guidelines for different types of ML-based publications, emphasizing supervised learning. We provide a diverse collection of examples from various authors and disciplines in chemistry. While taking into account varying accessibility across research groups, our recommendations focus on reporting completeness and standardizing comparisons between tools. We aim to further contribute to improved ML transparency and credibility by suggesting a checklist of retro-/prospective tests and dissecting their importance. We envisage that the wide adoption and continuous update of best practices will encourage an informed use of ML on real-world problems related to the chemical sciences. [Figure not available: see fulltext.]
|
|
7. |
- Crous, P. W., et al.
(author)
-
Fusarium : more than a node or a foot-shaped basal cell
- 2021
-
In: Studies in mycology. - : CENTRAALBUREAU SCHIMMELCULTURE. - 0166-0616 .- 1872-9797. ; :98
-
Journal article (peer-reviewed)abstract
- Recent publications have argued that there are potentially serious consequences for researchers in recognising distinct genera in the terminal fusarioid clade of the family Nectriaceae. Thus, an alternate hypothesis, namely a very broad concept of the genus Fusarium was proposed. In doing so, however, a significant body of data that supports distinct genera in Nectriaceae based on morphology, biology, and phylogeny is disregarded. A DNA phylogeny based on 19 orthologous protein-coding genes was presented to support a very broad concept of Fusarium at the F1 node in Nectriaceae. Here, we demonstrate that re-analyses of this dataset show that all 19 genes support the F3 node that represents Fusarium sensu stricto as defined by F. sambucinum (sexual morph synonym Gibberella pulicaris). The backbone of the phylogeny is resolved by the concatenated alignment, but only six of the 19 genes fully support the F1 node, representing the broad circumscription of Fusarium. Furthermore, a re-analysis of the concatenated dataset revealed alternate topologies in different phylogenetic algorithms, highlighting the deep divergence and unresolved placement of various Nectriaceae lineages proposed as members of Fusarium. Species of Fusarium s. str. are characterised by Gibberella sexual morphs, asexual morphs with thin- or thick-walled macroconidia that have variously shaped apical and basal cells, and trichothecene mycotoxin production, which separates them from other fusarioid genera. Here we show that the Wollenweber concept of Fusarium presently accounts for 20 segregate genera with clear-cut synapomorphic traits, and that fusarioid macroconidia represent a character that has been gained or lost multiple times throughout Nectriaceae. Thus, the very broad circumscription of Fusarium is blurry and without apparent synapomorphies, and does not include all genera with fusarium-like macroconidia, which are spread throughout Nectriaceae (e.g., Cosmosporella, Macroconia, Microcera). In this study four new genera are introduced, along with 18 new species and 16 new combinations. These names convey information about relationships, morphology, and ecological preference that would otherwise be lost in a broader definition of Fusarium. To assist users to correctly identify fusarioid genera and species, we introduce a new online identification database, Fusarioid-ID, accessible at www.fusarium.org. The database comprises partial sequences from multiple genes commonly used to identify fusarioid taxa (act1, CaM, his3, rpb1, rpb2, tef1, tub2, ITS, and LSU). In this paper, we also present a nomenclator of names that have been introduced in Fusarium up to January 2021 as well as their current status, types, and diagnostic DNA barcode data. In this study, researchers from 46 countries, representing taxonomists, plant pathologists, medical mycologists, quarantine officials, regulatory agencies, and students, strongly support the application and use of a more precisely delimited Fusarium (= Gibberella) concept to accommodate taxa from the robust monophyletic node F3 on the basis of a well-defined and unique combination of morphological and biochemical features. This F3 node includes, among others, species of the F. fujikuroi, F. incarnatum-equiseti, F. oxysporum, and F. sambucinum species complexes, but not species of Bisifusarium [F. dimerum species complex (SC)], Cyanonectria (F. buxicola SC), Geejayessia (F. staphyleae SC), Neocosmospora (F. solani SC) or Rectifusarium (F. ventricosum SC). The present study represents the first step to generating a new online monograph of Fusarium and allied fusarioid genera (www.fusarium.org).
|
|
8. |
- Gutiérrez Maestro, Eduardo, 1994-, et al.
(author)
-
Wearable-Based Intelligent Emotion Monitoring in Older Adults during Daily Life Activities
- 2023
-
In: Applied Sciences. - : MDPI. - 2076-3417. ; 13:9
-
Journal article (peer-reviewed)abstract
- We present a system designed to monitor the well-being of older adults during their daily activities. To automatically detect and classify their emotional state, we collect physiological data through a wearable medical sensor. Ground truth data are obtained using a simple smartphone app that provides ecological momentary assessment (EMA), a method for repeatedly sampling people's current experiences in real time in their natural environments. We are making the resulting dataset publicly available as a benchmark for future comparisons and methods. We are evaluating two feature selection methods to improve classification performance and proposing a feature set that augments and contrasts domain expert knowledge based on time-analysis features. The results demonstrate an improvement in classification accuracy when using the proposed feature selection methods. Furthermore, the feature set we present is better suited for predicting emotional states in a leave-one-day-out experimental setup, as it identifies more patterns.
|
|
9. |
- Jorge, Rodrigues, et al.
(author)
-
Factors for Adopting ERP as SaaS amongst SMEs: The Customers vs. Vendor Point of View
- 2016
-
In: Information Resources Management Journal. - 1040-1628. ; 29:4, s. 1-16
-
Journal article (peer-reviewed)abstract
- This paper identifies the factors for adopting Enterprise Resource Planning (ERP) delivered as Software-as-a-Service (SaaS) among small and medium enterprises (SMEs). The authors conducted a two phases' qualitative-methodology: interviews with 20 experts from SaaS vendor (Microsoft) and a case-study with executives in three organizations which implemented vendor's ERP as SaaS (customers). The vendor identified 10 factors for adoption - Costs, Security, Availability, Usability, Implementation, Ubiquity, Flexibility, Compatibility, Analytics and Best-practices, where costs, security and availability were considered the most important factors. The three customers identified 3 additional factors: the trust in the Solution partner, Data integrity, and level of Integration of cloud platforms. Considering all 13 factors, Cost, trust in the Solution partner and Availability were identified as the most important for customers, which gave much less importance to the others factors. These results will help professionals and researchers to improve understanding and accelerate ERP adoption as SaaS among SMEs.
|
|
10. |
|
|