Search

Pollution is a major concern in the present day, causing multiple illnesses and deaths, specifically in developing countries in Asia and Africa. While it has drawn worldwide attention as governments try to issue laws to meet certain criteria for air pollution levels, pollution concentration forecasting has become a major challenge. Particularly, short term forecasting will help to gain information regarding concentrations of harmful pollutants for the upcoming hours and enable better decision-making with regards to controlling air pollution. In this paper, we investigate spatio-temporal graph-based models to determine the best methods for spatial and temporal analysis of data. The models have the additional capacity to perform multi-variate predictions of correlated data, i.e., predicting multiple pollutant concentrations simultaneously, thus requiring lower computational efforts. A real-world pollution dataset measured over Delhi, India, is used to comparing the proposed models with baselines, which shows the Spatio-Temporal Graph Convolution Neural Network (STGCN) models to be performing better than others. For a better understanding of model architectures with the most effective strategies for spatial and temporal data analysis, three models, namely STGCN-A, STGCN-B, STGCN-C have been developed. The models have been compared with 6 other baselines over multiple forecasting horizons of 1 h, 24 h, and 48 h timesteps using various metrics such as mean absolute error (MAE), root mean square error (RMSE), mean absolute percent error (MAPE). On the PM 2.5 dataset of Delhi, STGCN-B achieves a performance of 10.53 MAE, 6.92 RMSE and 25.25 MAPE for a 1 h forecast, while STGCN-C achieves 20.18 MAE, 14.73 RMSE and 55.45 MAPE for a 24 h forecast. In general, both structures achieve similar results, with STGCN-C being better in many cases. They are further analysed through observation-prediction graphs and Taylor diagrams, which give an insight into our findings. The models are additionally validated on a benchmark real-world dataset from California, USA for better understanding of the spatio-temporal relations and model performances on a more stable dataset, where STGCN-C performs best for PM 2.5 with 4.30 RMSE, 1.98 MAE, 25.96 MAPE for 1 h predictions for univariate data and 3.63 RMSE, 1.88 MAE and 25.91 MAPE in multivariate forecasting. The developed spatio-temporal graph-based models hold promising applications in urban air quality management, aiding policymakers in implementing targeted interventions to mitigate pollution-related health risks. Furthermore, these models can support public health agencies by providing timely and accurate forecasts of pollutant concentrations, enabling proactive measures to safeguard community well-being. Our study showcases the efficacy of spatio-temporal graph-based models in accurately forecasting air pollutant concentrations, with particular emphasis on short-term predictions. By leveraging multi-variate capabilities, our proposed models demonstrate superior performance compared to baseline approaches across various forecasting horizons. • Spatio-temporal graph convolution neural network for multipollutant forecasting. • Three model architectures namely STGCN-A, STGCN-B and STGCN-C are proposed. • Varying model architectures to determine strategies for spatiotemporal data analysis. • Performance comparison of the proposed models with several advanced baselines. • Rigorous evaluation of the models based on real world air pollution datasets. [ABSTRACT FROM AUTHOR]

Sensors cooperate and coordinate with each other to disseminate sensed data in the network. In establishing coordination among sensors such that they can access the shared wireless medium, Medium Access Control (MAC) protocol plays an important role. In this article, we presented an analytical study on some popular MAC protocols for Wireless Sensor Networks (WSNs). Based on the design techniques, MAC protocols for WSNs are classified into two main categories: single-layer and cross-layer. MAC protocols such as S-MAC, T-MAC, B-MAC and X-MAC are selected to study the design approaches of single-layer genre. BoX-MAC-1 and BoX-MAC-2 are selected to analyze cross-layer design approaches. This survey paper aims at reporting an implementation viewpoint of different design approaches of MAC protocols in WSN. We have considered mixed WSNs that exhibits node movement (e.g., static, mobile) and changes in communication medium (e.g., air, water). Representative protocols are implemented in Castalia simulator and evaluated on the basis of important performance metrics such as energy consumption, network lifetime, throughput and end-to-end delay. The merits and demerits of different protocols are also compared. [ABSTRACT FROM AUTHOR]

With ever-increasing global air pollution levels, researchers are exploring ways to forecast air pollutant concentrations to prevent the adverse effects of air pollution on humans. Powered by the data obtained from air pollution monitoring stations, we now have a chance to build sophisticated models to estimate the future concentration of various air pollutants. Previous researches show that deep learning models perform a better task of capturing the complex spatiotemporal dynamics from the data as compared to traditional statistical models. In this paper, a hybrid deep learning framework - AGCTCN (A ttention based G raph C onvolution and T emporal C onvolution N etwork), based on spatial attention, graph convolution and temporal convolution is presented for short-term forecasting of particulate matter (PM) levels. Specifically, quarter-hourly PM 10 and PM 2.5 data aggregated from 27 ground air pollution monitoring stations in Delhi, India is used for training the AGCTCN model and our model forecasts the concentrations of these pollutants at these stations for a particular horizon in the future. The forecasts generated by our model are compared and contrasted to those generated by other state-of-the-art models like GC-LSTM and ConvLSTM with respect to four widely used evaluation metrics namely RMSE (root mean squared error), MAE (mean absolute error), correlation coefficient, and R2 (coefficient of determination). Our model shows more than 80% improvement over the GC-LSTM model in terms of the R2 metric, performs the best task of estimating the peak PM concentrations and shows variability and correlation close to that of the observed data. A carefully conducted ablation study shows the effectiveness of the individual components of our architecture. The graph convolution layer improves the model accuracy by approximately 34% on average on the PM datasets. Compared to other models, the AGCTCN framework shows the best performance in short-term forecasting of particulate matter concentrations. • Spatiotemporal forecasting of particulate matter (PM2.5 and PM10) concentrations. • Attention based graph convolution and temporal convolution network. • An ablation study to measure the impact of each network component on the performance. • Performance evaluation of the model based on real world PM2.5 and PM10 datasets. [ABSTRACT FROM AUTHOR]

Deep learning methods have become the state of the art for spatio-temporal predictive analysis in a wide range of fields, including environmental management, public health, urban planning, pollution monitoring, and so on. Despite the fact that a variety of powerful deep learning-based models can address various problem-specific issues in different research domain, it has been found that no single optimal model can outperform everywhere. Now, in the last two years, various deep learning-based studies have provided a variety of best-performing techniques for predicting COVID-19 health outcomes. In this context, this study attempts to perform a case study that investigates the spatio-temporal variation in the performance of deep-learning-based methods for predicting COVID-19 health outcomes in India. Various widely applied deep learning models namely CNN (convolutional neural network), RNN (recurrent neural network), Vanilla LSTM (long short-term memory), LSTM Autoencoder, and Bidirectional LSTM are considered to investigate their spatio-temporal performance variation. The effectiveness of the models is assessed using various metrics based on COVID-19 mortality time-series from 36 states and union territories of India. • Deep learning-based COVID-19 health outcome forecasting at the state level in India. • Explore spatio-temporal variability pattern in the performance of learning models. • Finding spatial distribution of the models for predicting COVID-19 mortality data. • Rigorous evaluation of the models based on COVID-19 mortality time-series data. [ABSTRACT FROM AUTHOR]

Poor air quality is becoming a critical environmental concern in different countries over the last several years. Most of the air pollutants have serious consequences on human health and wellbeing. In this context, efficient forecasting of air pollutants is currently crucial to predict future events with a view to taking corrective actions and framing effective environmental policies. Although deep learning (DL) as well as statistical forecasting models are investigated in the literature, they have rarely used in air pollutant-specific optimal model building for long-term forecasting. In this paper, our aim is to develop the pollutant-specific optimal forecasting models for the phases spanning from preprocessing to model building by investigating a set of predictive techniques. In this regard, this paper presents a methodology for long-term forecasting of some important air pollutants. More specifically, a total of eight best performing models such as stacked LSTM, LSTM auto-encoder, Bi-LSTM, convLSTM, Holt-Winters, auto-regressive (AR), SARIMA, and Prophet are investigated for developing pollutant-specific optimal forecasting models. The study is carried out based on the real-world data obtained from government-run air quality monitoring units in Kolkata over a period of 4 years. The models such as Holt-Winters, Bi-LSTM, and ConvLSTM achieve high forecasting accuracy with respect to MAE and RMSE values for majority of the pollutants. [Display omitted] • Long-term forecasting of six air pollutants namely PM2.5, PM10, SO2, NO2, NO, and O3. • Data modelling by investigating a set of statistical and deep learning methods. • Finding optimal forecasting models for different pollutants. • Time series analysis for various air pollutants in order to study underlying trends. • Evaluation of the performance of the models for long term forecasting. [ABSTRACT FROM AUTHOR]

Abstract: In this paper, we present a resource broker architecture for a computational Grid which uses Genetic Algorithm (GA) for brokering. Resource brokering implies selection of appropriate resource providers for jobs submitted to the Grid. Resource brokering is normally done with the objective of optimizing some performance parameter such as minimizing the total cost of running the jobs or maximizing the utilization of Grid resources. It is a challenging task since the search space for the problem consists of all possible allocations of submitted jobs to available resource providers in a Grid and may be very large. GAs are found to be efficient for such optimization problems. Moreover, the configuration and workload of a Grid is dynamic in nature. Our GA based resource broker tries to address these issues so that jobs are scheduled efficiently. [Copyright &y& Elsevier]

Abstract: Wireless sensor network (WSN) is drawing interest in various areas as they have great potential for many distributed applications in different scenarios. This paper demonstrates iSENSE, which provides a web-based sensor monitoring service and a sensor network test-bed. iSENSE uses heterogeneous wireless sensors that are capable of measuring temperature, humidity and light. Gateway nodes collect the sensed data from their respective network area and store the data in MySQL database for analysis and visualization through a portal. Through the test-bed user can remotely submit a sensor application (programs written in NesC) for compiling it using required softwares (TinyOS and NesC) and evaluating the performance of the application by downloading and executing them on dedicated sensing devices which form the test-bed. [Copyright &y& Elsevier]

Abstract: TinyOS is a popular event driven operating system for wireless sensor network (WSN). However TinyOS 2.x framework lacks proper visualization approach for simulator TOSSIM and also for real-time network. In this paper we present approaches to add support for two visualizers in TinyOS framework. One such graphical addition is for simulator TOSSIM and another is for real- time network. The main contributions of this paper are 1) Visualizer for TOSSIM 2) 3D visualizer for real time data collection in WSN. [Copyright &y& Elsevier]

Abstract: As the world is moving towards the “Internet of Things” [1], Internet Protocol enabled Wireless Sensor Network is becoming an important research area. In order to make it possible and to facilitate transmission of IPv6 packets over low powered networks, 6LoWPAN [2,3] has been introduced. In this paper, we study mobility issues and scenarios which may occur in the 6LoWPAN network. We also propose an approach to manage the mobility of nodes efficiently based on received signal strength and link quality. Simple load-balancing technique is also incorporated. The 6LoWPAN based Wireless Sensor Network can be integrated with grid computing establishing a Sensor-Grid which may also be used in various applications. [Copyright &y& Elsevier]

Expeditions on Mars and interest in research orienting around these exploration missions have been accelerating more than ever, recently. Due to lack of active human interference in Mars missions, processing and accurate classification of images taken by the rovers is a very essential part of the system. Proper identification of landforms governs the accessibility of the mobile rovers on Mars' surface. Moreover, NASA has already collected over two million images from the planet, and more volumes are yet to arrive as these photographs serve as major documents for photogrammetry and studies based on remote sensing. Automatic labeling of incoming images and also making searching of the image database easier in the public interest requires highly accurate image classifiers. Deriving motivation from the above causes, this study intends to implement an efficient supervised multi-class image classifier for identifying Mars imagery. However, this objective is confronted by a major bottleneck. Most datasets that are accurately labeled, portray a highly skewed nature and insufficient data to train a deep model from scratch. The MSL surface imagery labeled dataset captured by the Curiosity rover, that has been considered for this study, is one such dataset with only 6691 images distributed unevenly into 25 classes. These obstacles are less signified in the existing literature and hence this paper addresses these challenges, outperforming the state-of-the-art metrics. Due to the absence of large data volume, a transfer learning based methodology was considered, using very deep convolutional networks pre-trained on ImageNet dataset. But images from Mars often involve a difference in hue, contrast and clarity when compared with images taken on Earth. Hence, the deep model was fine-tuned with our dataset and the extracted feature from the tuned neural network was used for the final classification. It was found that the results obtained from a single pre-trained model were not optimum and that ensemble approaches could unify many such results into a better result. Similar feature vectors were extracted from a few other pre-trained models. The whole setup converges into a dynamic routing module, a novel polling algorithm, which for each image, comes to an agreement about the best set of features while generating the output probability vector. The proposed approach is evaluated by several numeric metrics like accuracy, precision and recall, confusion matrices and roc curves, against the chosen individual pre-trained models and most prominent ensemble methods. Mars-TRP produces a test accuracy of around 88% in the standard test set of MSL surface dataset and an accuracy of 96% in the HiRise dataset, outperforming the individual pre-trained models, all the ensemble baselines and other existing approaches. [ABSTRACT FROM AUTHOR]