Face recognition (FR) systems based on populationbased heuristics algorithms is common nowadays. Depends on the approach, there is a need for tuning parameters in preprocessing step using optimization algorithms. Rega...
详细信息
ISBN:
(纸本)9781538614525
Face recognition (FR) systems based on populationbased heuristics algorithms is common nowadays. Depends on the approach, there is a need for tuning parameters in preprocessing step using optimization algorithms. Regarding FR challenges, the illumination variation is one of the critical factors. The homomorphic filter (HF) is one of the methods that can compensate ination aiding to stabilize the face images obtained under different lighting conditions. However, the HF requires some optimal parameters which can be possibly determined through optimization process. Based on this context, in this paper, we attempt to investigate the application of two population-based algorithms, the Jaya and the Particle Swarm Optimization (PSO), in order to optimize the HF parameters in CMU-PIE and BIOINFO face databases. The high performance of both algorithms shows that they are suitable to compensate the illumination variation achieving 100% and 91.3% recognition rates on CMUPIE and BIO-INFO, respectively.
Cloud computing provides computational resources (processing, storage, software, network) to users in a scalable and dynamic way over the Internet. The use of these resources are impacted by issues related to privacy,...
详细信息
Cloud computing provides computational resources (processing, storage, software, network) to users in a scalable and dynamic way over the Internet. The use of these resources are impacted by issues related to privacy, security and trust. In this sense, this paper presents a trust reputation architecture applied in the cloud computing environment. The reputed trust is based on two trust indicators: objective and subjective ones. The objective trust indicator is based on the historical QoS indicators of a cloud provider. Then, the subjective trust indicator is composed of the users' feedbacks to the cloud providers. In order to evaluate the proposed architecture, simulations were performed using a P2P Network Simulator in order to emulate cloud providers and their clients. The evaluation results show the architecture applicability with low overhead.
Today, we observe that more and more, radio frequency identification (RFID) technology has been used to identify and track objects in enterprises and institutions. In addition, we also perceive the growing adoption of...
详细信息
Today, we observe that more and more, radio frequency identification (RFID) technology has been used to identify and track objects in enterprises and institutions. In addition, we also perceive the growing adoption of cloud computing, either public or private, to process and store data from the objects. In this context, the literature does not present an initiative that looks into the network on enterprise-cloud interactions, so neglecting network performance and congestion information when transmitting data to the cloud. Thus, we are presenting a model named ACMA—Automatic Control and Management of Assets. ACMA employs context awareness to control and monitor corporate assets in companies with multiple units. ACMA provides a centralized point of access in the cloud in which interested actors can get online data about each corporate asset. In particular, our scientific contribution consists in considering network congestion to control dynamically the data updating interval from sensors to the cloud. The idea is to search for reliability and integrity of operations, without losing or corrupting data when updating the information to cloud. Thus, this article describes the ACMA model, its architecture, algorithms and features. In addition, we describe the evaluation methodology and the results obtained through experiments and simulations based on the developed prototype.
In distributed simulation, the purpose of multi-resolution methods is to allow simulation integration getting consis- tent views of different resolutions. In these methods, chal- lenges in the treatment of aggregation...
详细信息
This study aimed the analysis of the positional and geometric accuracy of objects in orthomosaics obtained through different unmanned aerial vehicle (UAV) data processing software covering an area located within Unive...
This study aimed the analysis of the positional and geometric accuracy of objects in orthomosaics obtained through different unmanned aerial vehicle (UAV) data processing software covering an area located within Universidade do Vale do Rio dos Sinos - UNISINOS in São Leopoldo, RS. A total of nine ground control points (GCP) and twenty checkpoints were surveyed in order register and classify the processed orthomosaics according to the cartographic accuracy standard - Padrão de Exatidão Cartográfica (PEC). Four software was employed to process the UAV data: Pix4D mapper, Agisoft PhotoScan, Menci APS and Bentley Context Capture. The results obtained from each software were compared and identified the smallest distortions when processing with and without ground control points. The flight was executed at a height of 90m with 60% sidelap and 80% overlap using an ST800 UAV equipped with a Sony NEX-7 small format non-metric camera with 24 megapixels resolution. The software GeoPEC was used to classify the orthomosaics according to PEC. For data processed with ground control points all orthomosaics were classified “Class A” in 1/500 scale, however, only Menci APS did not present a trend line via t-student test. On the other hand, Menci APS presented the worst results without the ground control points. In processing with GCP, all orthomosaics obtained optimum results with an approximated error of 2,5 m 2 , about 0.03% of the area.
The Coupled Model Inter-comparison Project Phase 5 (CMIP5) is the output of many coupled atmosphere-ocean of global climate models (GCMs) and widely used for climate research, especially for driving regional climate m...
The Coupled Model Inter-comparison Project Phase 5 (CMIP5) is the output of many coupled atmosphere-ocean of global climate models (GCMs) and widely used for climate research, especially for driving regional climate model. There are more than 40 CMIP5 GCMs data available, but no single model can be considered as the best for every region. The use of CMIP5 GCMs data for rainfall projection in Indonesia is important to improve the accuracy of the monthly and seasonal rainfall forecast. Then, this study evaluates the capability of the CMIP5 GCMs data for Indonesia region by quantitatively comparing the spatial pattern of the precipitation mean and standard deviation of the CMIP5 data against GPCP, GPCC, and CRU data in the period 1980-2005. Furthermore, the composite analysis is conducted to observe the model performance in reproducing the precipitation characteristic over some areas in Indonesia. In conclusion, the models NorESM1-M, NorESM1-ME, GFDL-ESM2M, CSIRO-MK3-6-0 perform the rainfall mean better than others, while the standard deviation of the rainfall show that the models NorESM1-M, BNU-ESM, CMCC-CMS are superior in which NorESM1-M gives the best performance. The annual precipitation pattern of the model NorESM1-M over various areas in Indonesia is also highly correlated with the observations. Thus, the most suitable model for Indonesia region is NorESM1-M.
We implemented Machine Learning (ML) techniques to advance the study of sperm whale (Physeter macrocephalus) bioacoustics. This entailed employing Convolutional Neural Networks (CNNs) to construct an echolocation clic...
We implemented Machine Learning (ML) techniques to advance the study of sperm whale (Physeter macrocephalus) bioacoustics. This entailed employing Convolutional Neural Networks (CNNs) to construct an echolocation click detector designed to classify spectrograms generated from sperm whale acoustic data according to the presence or absence of a click. The click detector achieved 99.5% accuracy in classifying 650 spectrograms. The successful application of CNNs to clicks reveals the potential of future studies to train CNN-based architectures to extract finer-scale details from cetacean spectrograms. Long short-term memory and gated recurrent unit recurrent neural networks were trained to perform classification tasks, including (1) 'coda type classification' where we obtained 97.5% accuracy in categorizing 23 coda types from a Dominica dataset containing 8,719 codas and 93.6% accuracy in categorizing 43 coda types from an Eastern Tropical Pacific (ETP) dataset with 16,995 codas; (2) 'vocal clan classification' where we obtained 95.3% accuracy for two clan classes from Dominica and 93.1% for four ETP clan types; and (3) 'individual whale identification' where we obtained 99.4% accuracy using two Dominica sperm whales. These results demonstrate the feasibility of applying ML to sperm whale bioacoustics and establish the validity of constructing neural networks to learn meaningful representations of whale vocalizations. [ABSTRACT FROM AUTHOR]
Gamma-ray bursts (GRBs) are the most energetic phenomena in the Universe. Many aspects of GRB physics are still under debate, such as the origin of their gamma-ray emission above the GeV energy range. In 2019, MAGIC d...
详细信息
In this study we present a mobile application for geoscience. It refers to a digital field book for automating data collection and outcrop/core description, and optimizing the final data processing. Sensors were devel...
详细信息
KAGRA, the underground and cryogenic gravitational-wave detector, was operated for its solo observation from February 25 to March 10, 2020, and its first joint observation with the GEO 600 detector from April 7 to Apr...
KAGRA, the underground and cryogenic gravitational-wave detector, was operated for its solo observation from February 25 to March 10, 2020, and its first joint observation with the GEO 600 detector from April 7 to April 21, 2020 (O3GK). This study presents an overview of the input optics systems of the KAGRA detector, which consist of various optical systems, such as a laser source, its intensity and frequency stabilization systems, modulators, a Faraday isolator, mode-matching telescopes, and a high-power beam dump. These optics were successfully delivered to the KAGRA interferometer and operated stably during the observations. The laser frequency noise was observed to limit the detector sensitivity above a few kilohertz, whereas the laser intensity did not significantly limit the detector sensitivity.
暂无评论