Explore the vast range of titles available.

The introduction of 5G’s millimeter wave transmissions brings a new paradigm to wireless communications. Whereas physical obstacles were mostly associated with signal attenuation, their presence now adds complex, non-linear phenomena, including reflections and scattering. The result is a multipath propagation environment, shaped by the obstacles encountered, indicating a strong presence of hidden spatial information within the received signal. To untangle said information into a mobile device position, this paper proposes the usage of neural networks over beamformed fingerprints, enabling a single-anchor positioning approach. Depending on the mobile device target application, positioning can also be enhanced with tracking techniques, which leverage short-term historical data. The main contributions of this paper are to discuss and evaluate typical neural network architectures suitable to the beamformed fingerprint positioning problem, including convolutional neural networks, hierarchy-based techniques, and sequence learning approaches. Using short sequences with temporal convolutional networks, simulation results show that stable average estimation errors of down to 1.78 m are obtained on realistic outdoor scenarios, containing mostly non-line-of-sight positions. These results establish a new state-of-the-art accuracy value for non-line-of-sight millimeter wave outdoor positioning, making the proposed methods very competitive and promising alternatives in the field.

The combination of cloud computing with the Internet of Things has made fundamental changes in areas from industry, healthcare, traffic, and transportation to home appliances and even personal lives. Billions of devices and users are connected through these platforms disseminating enormous amounts of data leading to performance degradation, which has generated a demand for prior application placement planning. This paper focuses on the minimization of application delay and network usage by proposing a genetic-based service placement algorithm in fog-cloud environments. Throughout this work, a penalty-based approach to target both the delay and the number of time-consuming cloud placements is introduced, which explores the solution pool as a function of generations. This helps in exploring a wider space at the beginning and gradually intensifying the effect of penalty in the next generations. In a separate phase, the proximity of the applications to the users is taken into account as well. This is done through the chromosome selection process by using a priority value that identifies the proximity of dependent modules. The results of simulations demonstrate that the proposed algorithm achieved improvements regarding delay, network usage, energy consumption, and cost.

Understanding the genetic basis of complex diseases is one of the most important challenges in current precision medicine. To this end, Genome-Wide Association Studies aim to correlate Single Nucleotide Polymorphisms (SNPs) to the presence or absence of certain traits. However, these studies do not consider interactions between several SNPs, known as epistasis, which explain most genetic diseases. Analyzing SNP combinations to detect epistasis is a major computational task, due to the enormous search space. A possible solution is to employ deep learning strategies for genomic prediction, but the lack of explainability derived from the black-box nature of neural networks is a challenge yet to be addressed. Herein, a novel, flexible, portable, and scalable framework for network interpretation based on transformers is proposed to tackle any-order epistasis. The results on various epistasis scenarios show that the proposed framework outperforms state-of-the-art methods for explainability, while being scalable to large datasets and portable to various deep learning accelerators. The proposed framework is validated on three WTCCC datasets, identifying SNPs related to genes known in the literature that have direct relationships with the studied diseases.

The associations of plasma metabolites with adverse cardiovascular (CV) outcomes are still underexplored and may be useful in CV risk stratification. We performed a systematic review and meta-analysis to establish correlations between blood metabolites and adverse CV outcomes in patients with heart failure (HF). Four cohorts were included, involving 83 metabolites and 37 metabolite ratios, measured in 1158 HF patients. Hazard ratios (HR) of 42 metabolites and 3 metabolite ratios, present in at least two studies, were combined through meta-analysis. Higher levels of histidine (HR 0.74, 95% CI [0.64; 0.86]) and tryptophan (HR 0.82 [0.71; 0.96]) seemed protective, whereas higher levels of symmetric dimethylarginine (SDMA) (HR 1.58 [1.30; 1.93]), N-methyl-1-histidine (HR 1.56 [1.27; 1.90]), SDMA/arginine (HR 1.38 [1.14; 1.68]), putrescine (HR 1.31 [1.06; 1.61]), methionine sulfoxide (HR 1.26 [1.03; 1.52]), and 5-hydroxylysine (HR 1.25 [1.05; 1.48]) were associated with a higher risk of CV events. Our findings corroborate important associations between metabolic imbalances and a higher risk of CV events in HF patients. However, the lack of standardization and data reporting hampered the comparison of a higher number of studies. In a future clinical scenario, metabolomics will greatly benefit from harmonizing sample handling, data analysis, reporting, and sharing.

Specific information about types of appliances and their use in a specific time window could help determining in details the electrical energy consumption information. However, conventional main power meters fail to provide any specific information. One of the best ways to solve these problems is through non-intrusive load monitoring, which is cheaper and easier to implement than other methods. However, developing a classifier for deducing what kind of appliances are used at home is a difficult assignment, because the system should identify the appliance as fast as possible with a higher degree of certainty. To achieve all these requirements, a convolution neural network implemented on hardware was used to identify the appliance through the voltage and current (V-I) trajectory. For the implementation on hardware, a field programmable gate array (FPGA) was used to exploit processing parallelism in order to achieve optimal performance. To validate the design, a publicly available Plug Load Appliance Identification Dataset (PLAID), constituted by 11 different appliances, has been used. The overall average F-score achieved using this classifier is 78.16% for the PLAID 1 dataset. The convolution neural network implemented on hardware has a processing time of approximately 5.7 ms and a power consumption of 1.868 W.

Studies are scarce on the application of normality and homogeneity tests for rainfall series in the state of Rio de Janeiro, Brazil. Therefore, this study applies normality and homogeneity tests in a 71-year time series (1943–2013) of rainfall, seeking to identify which tests were most indicated in the evaluation of the normality and homogeneity of rainfall data in Rio de Janeiro. The tests of normality and homogeneity of variance were divided into (i) parametric—Shapiro-Wilk (SW) and Jarque-Bera (JB)—and (ii) non-parametric—Bartlett (B) and Fligner-Killeen (FK). All statistical procedures were performed using the open software R version 3.4.2. The tests of normality (SW and JB) and homogeneity of variance (B and FK) applied to the raw (unfilled) data showed that both the SW and JB tests were not satisfactory in determining the normality of the series, with only two stations reaching over 95% reliability. Regarding the homogeneity of variance of the standardized residues in the raw data, the B test stands out when compared to the FK test. After completing data faults of the data, the SW, JB, B, and FK tests pointed to rejection of the normality and homogeneity hypotheses for the specific time series. According to the adopted methodology, there are 15 useful stations (65.22%), 7 dubious (30.43%), and one suspicious (4.35%). The SW and B tests presented better results when matched to the other tests. The proposed methodology should be considered for further investigation of normality and homogeneity in other climate datasets.

Spectral unmixing is one of the most popular techniques to analyze remotely sensed hyperspectral images. It generally comprises three stages: (1) reduction of the dimensionality of the original image to a proper subspace; (2) automatic identification of pure spectral signatures (called endmembers ); and (3) estimation of the fractional abundance of each endmember in each pixel of the scene. The spectral unmixing process allows sub-pixel analysis of hyperspectral images, but can be computationally expensive due to the high dimensionality of the data. In this paper, we develop the first real-time implementation of a full spectral unmixing chain in commodity graphics processing units (GPUs). These hardware accelerators offer a source of computational power that is very appealing in hyperspectral remote sensing applications, mainly due to their low cost and adaptivity to on-board processing scenarios. The implementation has been developed using the compute device unified architecture (CUDA) and tested on an NVidia™ GTX 580 GPU, achieving real-time unmixing performance in two different case studies: (1) characterization of thermal hot spots in hyperspectral images collected by NASA’s Airborne Visible Infra-red Imaging Spectrometer (AVIRIS) during the terrorist attack to the World Trade Center complex in New York City, and (2) sub-pixel mapping of minerals in AVIRIS hyperspectral data collected over the Cuprite mining district in Nevada.

The analysis of complex biological datasets beyond DNA scenarios is gaining increasing interest in current bioinformatics. Particularly, protein sequence data introduce additional complexity layers that impose new challenges from a computational perspective. This work is aimed at investigating GPU solutions to address these issues in a representative algorithm from the phylogenetics field: Fitch’s parsimony. GPU strategies are adopted in accordance with the protein-based formulation of the problem, defining an optimized kernel that takes advantage of data parallelism at the calculations associated with different amino acids. In order to understand the relationship between problem sizes and GPU capabilities, an extensive evaluation on a wide range of GPUs is conducted, covering all the recent NVIDIA GPU architectures—from Kepler to Turing. Experimental results on five real-world datasets point out the benefits that imply the exploitation of state-of-the-art GPUs, representing a fitting approach to address the increasing hardness of protein sequence datasets.

This paper presents a prototype of a platform for biomolecular recognition detection. The system is based on a magnetoresistive biochip that performs biorecognition assays by detecting magnetically tagged targets. All the electronic circuitry for addressing, driving and reading out signals from spin-valve or magnetic tunnel junctions sensors is implemented using off-the-shelf components. Taking advantage of digital signal processing techniques, the acquired signals are processed in real time and transmitted to a digital analyzer that enables the user to control and follow the experiment through a graphical user interface. The developed platform is portable and capable of operating autonomously for nearly eight hours. Experimental results show that the noise level of the described platform is one order of magnitude lower than the one presented by the previously used measurement set-up. Experimental results also show that this device is able to detect magnetic nanoparticles with a diameter of 250 nm at a concentration of about 40 fM. Finally, the biomolecular recognition detection capabilities of the platform are demonstrated by performing a hybridization assay using complementary and non-complementary probes and a magnetically tagged 20mer single stranded DNA target.