I. Componente Universitária
Permanent URI for this community
Browse
Browsing I. Componente Universitária by Author "A. Martins, J."
Now showing 1 - 3 of 3
Results Per Page
Sort Options
- GACN: Self-clustering genetic algorithm for constrained networksPublication . A. Martins, J.; Mazayev, Andriy; Correia, Noélia; Schutz, G.; Barradas, A.Extending the lifespan of a wireless sensor network is a complex problem that involves several factors, ranging from device hardware capacity (batteries, processing capabilities, and radio efficiency) to the chosen software stack, which is often unaccounted for by the previous approaches. This letter proposes a genetic algorithm-based clustering optimization method for constrained networks that significantly improves the previous state-of-the-art results, while accounting for the specificities of the Internet engineering task force, Constrained RESTful Environment (CoRE), standards for data transmission and specifically relying on CoRE interfaces, which fit this purpose very well.
- Resource design in constrained networks for network lifetime increasePublication . Correia, Noélia; Mazayev, Andriy; Schutz, G.; A. Martins, J.; Barradas, A.As constrained "things" become increasingly integrated with the Internet and accessible for interactive communication, energy efficient ways to collect, aggregate, and share data over such constrained networks are needed. In this paper, we propose the use of constrained RESTful environments interfaces to build resource collections having a network lifetime increase in mind. More specifically, based on existing atomic resources, collections are created/designed to become available as new resources, which can be observed. Such resource design should not only match client's interests, but also increase network lifetime as much as possible. For this to happen, energy consumption should be balanced/fair among nodes so that node depletion is delayed. When compared with previous approaches, results show that energy efficiency and network lifetime can be increased while reducing control/registration messages, which are used to set up or change observations.
- SpectraNet–53: A deep residual learning architecture for predicting soluble solids content with VIS–NIR spectroscopyPublication . A. Martins, J.; Guerra, Rui Manuel Farinha das Neves; Pires, R.; Antunes, M.D.; Panagopoulos, T.; Brázio, A.; Afonso, A.M.; Silva, L.; Lucas, M.R.; Cavaco, A.M.This work presents a new deep learning architecture, SpectraNet-53, for quantitative analysis of fruit spectra, optimized for predicting Soluble Solids Content (SSC, in Brix). The novelty of this approach resides in being an architecture trainable on a very small dataset, while keeping a performance level on-par or above Partial Least Squares (PLS), a time-proven machine learning method in the field of spectroscopy. SpectraNet-53 performance is assessed by determining the SSC of 616 Citrus sinensi L. Osbeck 'Newhall' oranges, from two Algarve (Portugal) orchards, spanning two consecutive years, and under different edaphoclimatic conditions. This dataset consists of short-wave near-infrared spectroscopic (SW-NIRS) data, and was acquired with a portable spectrometer, in the visible to near infrared region, on-tree and without temperature equalization. SpectraNet-53 results are compared to a similar state-of-the-art architecture, DeepSpectra, as well as PLS, and thoroughly assessed on 15 internal validation sets (where the training and test data were sampled from the same orchard or year) and on 28 external validation sets (training/test data sampled from different orchards/years). SpectraNet-53 was able to achieve better performance than DeepSpectra and PLS in several metrics, and is especially robust to training overfit. For external validation results, on average, SpectraNet-53 was 3.1% better than PLS on RMSEP (1.16 vs. 1.20 Brix), 11.6% better in SDR (1.22 vs. 1.10), and 28.0% better in R2 (0.40 vs. 0.31).