São Paulo Federal Institute of Education, Science and Technology

About: São Paulo Federal Institute of Education, Science and Technology is a education organization based out in São Paulo, Brazil. It is known for research contribution in the topics: Context (language use) & Computer science. The organization has 1707 authors who have published 2374 publications receiving 11333 citations.

Detecting Computer Generated Images with Deep Convolutional Neural Networks

Abstract: Computer graphics techniques for image generation are living an era where, day after day, the quality of produced content is impressing even the more skeptical viewer. Although it is a great advance for industries like games and movies, it can become a real problem when the application of such techniques is applied for the production of fake images. In this paper we propose a new approach for computer generated images detection using a deep convolutional neural network model based on ResNet-50 and transfer learning concepts. Unlike the state-of-the-art approaches, the proposed method is able to classify images between computer generated or photo generated directly from the raw image data with no need for any pre-processing or hand-crafted feature extraction whatsoever. Experiments on a public dataset comprising 9700 images show an accuracy higher than 94%, which is comparable to the literature reported results, without the drawback of laborious and manual step of specialized features extraction and selection.

Caracterização de biomassas para a briquetagem

Abstract: O objetivo deste trabalho foi caracterizar a producao de briquetes feita a partir de quatro diferentes biomassas residuais. Foram utilizados os residuos de serragem de Eucalyptus sp, serragem de Pinus sp, bagaco de cana-de-acucar ( Saccharum officinarum L.) e palha de cana-de-acucar. Os residuos foram tratados para que obtivessem 12% de umidade e uma granulometria inferior a 1,70 mm. Foram produzidos 15 briquetes para cada um dos quatro tratamentos. A pressao utilizada foi de 1250 kgf.cm -2 durante 30 segundos. Os briquetes obtiveram densidades que oscilaram 0,88 a 1,11 g.cm -3 . Isto representou uma faixa de 5 a 14 vezes a menos de ocupacao de volume para uma mesma quantidade de massa. O poder calorifico foi de 19.180 J.kg -1 e 20.315 J.kg -1 para as serragens de eucalipto e pinus respectivamente. Para o bagaco e palha de cana os valores foram de 18.541 J.kg -1 e 15.628 J.kg -1 . A palha da cana-de-acucar apresentou um teor de cinzas de 12%. As expansoes dos tratamentos oscilaram 4 a 9% e as resistencias mecânicas variaram de 1,215 MPa a 0,270 MPa. Todos os briquetes se mostraram resistentes para um empilhamento superior a 10 m de altura. O procedimento adotado pode ajudar a diminuir o espaco de estocagem e de transporte. Abstract This research aims to characterize the production of briquettes from four different biomasses. We used residues such as Eucalyptus sp sawdust, Pinus sp sawdust , sugarcane bagasse ( Saccharum officinarum L.) and sugarcane straw. The residues were treated to obtain 12% moisture content and particle size less than 1.70 mm. We produced 15 briquettes for each treatment. The pressure used was 1250 kgf.cm -2 for 30 seconds. The briquettes obtained densities ranged from 0.88 to 1.11 g.cm -3 . This represented a range of 5 to 14 times less volume occupancy for the same amount of mass. The high heating value (HHV) was 19,180 J.kg -1 and 20,315 J.kg -1 for eucalyptus and pine sawdust respectively. The HHV for the bagasse was 18,541 J.kg -1 and for straw was 15,628 J.kg -1 . The straw presented an ash content of 12%. The expansions of the treatments ranged 4 to 9% and mechanical resistances ranging from 1,215 MPa to 0,270 MPa. All briquettes were resistant to a higher stacking to 10 m high. The methods can help to decrease the space of storage and transport. Keywords : Waste; biofuel; energy; compression; stacking.

A permanent Raman lidar station in the Amazon: description, characterization, and first results

Abstract: . A permanent UV Raman lidar station, designed to perform continuous measurements of aerosols and water vapor and aiming to study and monitor the atmosphere from weather to climatic time scales, became operational in the central Amazon in July 2011. The automated data acquisition and internet monitoring enabled extended hours of daily measurements when compared to a manually operated instrument. This paper gives a technical description of the system, presents its experimental characterization and the algorithms used for obtaining the aerosol optical properties and identifying the cloud layers. Data from one week of measurements during the dry season of 2011 were analyzed as a mean to assess the overall system capability and performance. Both Klett and Raman inversions were successfully applied. A comparison of the aerosol optical depth from the lidar and from a co-located Aerosol Robotic Network (AERONET) sun photometer showed a correlation coefficient of 0.86. By combining nighttime measurements of the aerosol lidar ratio (50–65 sr), back-trajectory calculations and fire spots observed from satellites, we showed that observed particles originated from biomass burning. Cirrus clouds were observed in 60% of our measurements. Most of the time they were distributed into three layers between 11.5 and 13.4 km a.g.l. The systematic and long-term measurements being made by this new scientific facility have the potential to significantly improve our understanding of the climatic implications of the anthropogenic changes in aerosol concentrations over the pristine Amazonia.

Effect of Imbalanced Datasets on Security of Industrial IoT Using Machine Learning

Abstract: Machine learning algorithms have been shown to be suitable for securing platforms for IT systems. However, due to the fundamental differences between the industrial internet of things (IIoT) and regular IT networks, a special performance review needs to be considered. The vulnerabilities and security requirements of IIoT systems demand different considerations. In this paper, we study the reasons why machine learning must be integrated into the security mechanisms of the IIoT, and where it currently falls short in having a satisfactory performance. The challenges and real-world considerations associated with this matter are studied in our experimental design. We use an IIoT testbed resembling a real industrial plant to show our proof of concept.

Vehicular Clouds Leveraging Mobile Urban Computing Through Resource Discovery

Abstract: Vehicles are integral elements of urban computing and urban analytics, providing sensed data and thus being closely related to the exchange and gathering of a massive quantity of data in real-time. Vehicular Clouds consist of joining Vehicular Networks with Mobile Cloud Systems, allowing vehicles to share their resources and facilitate the transfer of information. Due to its mobility, the pool of resources in a Vehicular Cloud changes constantly. Thus, these Clouds need to adapt according to the input and output of their resources to meet the requirements of quality of service. Resource management and discovery are crucial elements for enabling and maintaining such Clouds. In this paper, we describe and discuss important issues about identifying and organizing resources in a Vehicular Cloud, as well as the specific techniques involved. Finally, we discuss challenges and issues for potential future works.