3. Producción
Browse
6 results
Search Results
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, An air quality monitoring and forecasting system for Lima city with low-cost sensors and artificial intelligence models(Frontiers Media S.A., 2022-07-07)Monitoring air quality is very important in urban areas to alert the citizens about the risks posed by the air they breathe. However, implementing conventional monitoring networks may be unfeasible in developing countries due to its high costs. In addition, it is important for the citizen to have current and future air information in the place where he is, to avoid overexposure. In the present work, we describe a low-cost solution deployed in Lima city that is composed of low-cost IoT stations, Artificial Intelligence models, and a web application that can deliver predicted air quality information in a graphical way (pollution maps). In a series of experiments, we assessed the quality of the temporal and spatial prediction. The error levels were satisfactory when compared to reference methods. Our proposal is a cost-effective solution that can help identify high-risk areas of exposure to airborne pollutants and can be replicated in places where there are no resources to implement reference networks. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, A review on text sentiment analysis with machine learning and deep learning techniques(Institute of Electrical and Electronics Engineers Inc., 2024-01-01)Automating sentiment analysis in texts has become an important task in recent years due to the exponential growth of user-generated content, including comments and opinions on products and services. This represents a valuable opportunity for businesses to glean insights into customer sentiment and, in turn, to refine their offerings. Motivated by this, the machine learning field has witnessed a surge of innovation, with an of models and tools being introduced to streamline sentiment analysis. This paper offers a thorough review of the recent advancements in machine learning and deep learning approaches for text sentiment analysis. We propose a novel framework for studying these models, distinguishing them by their structural intricacies. Additionally, we delve into the challenges, prospects, and emerging directions in research, as illuminated by our framework. Consequently, this paper equips researchers with a detailed panorama of the cutting-edge machine learning methodologies for dissecting text sentiment, easing the way for future explorations in this vibrant field. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Smart Multi-Sensor Calibration of Low-Cost Particulate Matter Monitors(MDPI, 2023-04-01)A variety of low-cost sensors have recently appeared to measure air quality, making it feasible to face the challenge of monitoring the air of large urban conglomerates at high spatial resolution. However, these sensors require a careful calibration process to ensure the quality of the data they provide, which frequently involves expensive and time-consuming field data collection campaigns with high-end instruments. In this paper, we propose machine-learning-based approaches to generate calibration models for new Particulate Matter (PM) sensors, leveraging available field data and models from existing sensors to facilitate rapid incorporation of the candidate sensor into the network and ensure the quality of its data. In a series of experiments with two sets of well-known PM sensor manufacturers, we found that one of our approaches can produce calibration models for new candidate PM sensors with as few as four days of field data, but with a performance close to the best calibration model adjusted with field data from periods ten times longer. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Spatial and temporal mapping of transport emissions and application of air quality models using low cost sensor data(Elsevier BV, 2025-10-10)Traffic-related atmospheric emissions of greenhouse gases (GHG) and toxic air pollutants (AP) are a serious environmental problem that affects climate change and air quality in megacities. About 80 % of air pollution in São Paulo comes from vehicles. This work aimed to develop a methodology using a traffic demand model for GHG and AP inventories of vehicular emissions and demonstrate its applicability to the Metropolitan Area of São Paulo (MASP) as a part of regional air quality and climate change modelling. These high-resolution emission inventories also allow identifying hot spots of air pollution and poor air quality with a spatial resolution of 0.5 km and temporal resolution of 1 h. With this, we also intend to develop an approach for the validation of the emission model through low cost sensor measurements. These sensors will be placed through the MASP close to the identified vehicle emission hot spots to continuously measure over one-year duration to address a novel question on how the low-cost sensors data can be applied for improving the model performance and air quality monitoring. This paper integrates two approaches: the vehicle emission and air quality modeling and the use of low-cost sensors for model validation and develop novel approaches for high-resolution spatial mapping. This work provided a basis for establishing sound climate change policies in other areas such as public health and urban planning. These high-resolution emission inventories also allowed identifying hot spots of air pollution and poor air quality with a spatial resolution of 0.5 km and temporal resolution of 1 h. Data from sensors NOTS were compared with reference data obtained from the Osasco monitoring network website and data from devices at other nearby air quality monitoring stations. This comparison made it possible to determine the errors for adjusting the calibration model in the field.The calibration of the NOTS platforms considered the co-location between the NOTS devices and the CETESB monitor platform.3 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Generating high-resolution climate data in the Andes using artificial intelligence: A lightweight alternative to the WRF model(Elsevier BV, 2025-12-01)In weather forecasting, generating atmospheric variables for regions with complex topography, such as the Andean regions with peaks reaching 6500 m above sea level, poses significant challenges. Traditional regional climate models often struggle to accurately represent the atmospheric behavior in such areas. Furthermore, the capability to produce high spatio-temporal resolution data (less than 27 km and hourly) is limited to a few institutions globally due to the substantial computational resources required. This study presents the results of atmospheric data generated using a new type of artificial intelligence (AI) models, aimed to reduce the computational cost of generating downscaled climate data using climate regional models like the Weather Research and Forecasting (WRF) model over the Andes. The WRF model was selected for this comparison due to its frequent use in simulating atmospheric variables in the Andes. Our results demonstrate a higher downscaling performance for the four target weather variables studied (temperature, relative humidity, zonal and meridional wind) over coastal, mountain, and jungle regions. Moreover, this AI model offers several advantages, including lower computational costs compared to dynamic models like WRF and continuous improvement potential with additional training data. • We propose an AI model to generate high-resolution climate data. • The model, based on ConvLSTM, predicts temperature, humidity, and wind accurately. • It runs up to 18× faster than WRF with lower memory and storage needs. • It shows promising accuracy across regions with varied topography and climate. • This approach offers an efficient alternative for climate modeling in low-resource areas.7