A New Auto-Regressive Multi-Variable Modified Auto-Encoder for Multivariate Time-Series Prediction: A Case Study with Application to COVID-19 Pandemics.

The SARS-CoV-2 global pandemic prompted governments, institutions, and researchers to investigate its impact, developing strategies based on general indicators to make the most precise predictions possible. Approaches based on epidemiological models were used but the outcomes demonstrated forecasting with uncertainty due to insufficient or missing data. Besides the lack of data, machine-learning models including random forest, support vector regression, LSTM, Auto-encoders, and traditional time-series models such as Prophet and ARIMA were employed in the task, achieving remarkable results with limited effectiveness. Some of these methodologies have precision constraints in dealing with multi-variable inputs, which are important for problems like pandemics that require short and long-term forecasting. Given the under-supply in this scenario, we propose a novel approach for time-series prediction based on stacking auto-encoder structures using three variations of the same model for the training step and weight adjustment to evaluate its forecasting performance. We conducted comparison experiments with previously published data on COVID-19 cases, deaths, temperature, humidity, and air quality index (AQI) in São Paulo City, Brazil. Additionally, we used the percentage of COVID-19 cases from the top ten affected countries worldwide until May 4th, 2020. The results show 80.7% and 10.3% decrease in RMSE to entire and test data over the distribution of 50 trial-trained models, respectively, compared to the first experiment comparison. Also, model type#3 achieved 4th better overall ranking performance, overcoming the NBEATS, Prophet, and Glounts time-series models in the second experiment comparison. This model shows promising forecast capacity and versatility across different input dataset lengths, making it a prominent forecasting model for time-series tasks.

Complete holography-based system for the identification of microparticles in water samples.

Here, we present a comprehensive holography-based system designed for detecting microparticles through microscopic holographic projections of water samples. This system is designed for researchers who may be unfamiliar with holographic technology but are engaged in microparticle research, particularly in the field of water analysis. Additionally, our innovative system can be deployed for environmental monitoring as a component of an autonomous sailboat robot. Our system's primary application is for large-scale classification of diverse microplastics that are prevalent in water bodies worldwide. This paper provides a step-by-step guide for constructing our system and outlines its entire processing pipeline, including hologram acquisition for image reconstruction.

COVID-19 Patterns in Araraquara, Brazil: A Multimodal Analysis.

The epidemiology of COVID-19 presented major shifts during the pandemic period. Factors such as the most common symptoms and severity of infection, the circulation of different variants, the preparedness of health services, and control efforts based on pharmaceutical and non-pharmaceutical interventions played important roles in the disease incidence. The constant evolution and changes require the continuous mapping and assessing of epidemiological features based on time-series forecasting. Nonetheless, it is necessary to identify the events, patterns, and actions that were potential factors that affected daily COVID-19 cases. In this work, we analyzed several databases, including information on social mobility, epidemiological reports, and mass population testing, to identify patterns of reported cases and events that may indicate changes in COVID-19 behavior in the city of Araraquara, Brazil. In our analysis, we used a mathematical approach with the fast Fourier transform (FFT) to map possible events and machine learning model approaches such as Seasonal Auto-regressive Integrated Moving Average (ARIMA) and neural networks (NNs) for data interpretation and temporal prospecting. Our results showed a root-mean-square error (RMSE) of about 5 (more precisely, a 4.55 error over 71 cases for 20 March 2021 and a 5.57 error over 106 cases for 3 June 2021). These results demonstrated that FFT is a useful tool for supporting the development of the best prevention and control measures for COVID-19.

Micro aerial vehicle with basic risk of operation.

We draw current efforts towards proposing a wing-type micro UAV with characteristics of being a basic operation risk self handled (Micro-Brosh) platform. Its micro-sized wingspan and weight, which are less than 0.30 m and 0.150 kg, respectively, guarantee the low risk to the operator and installations in case of crashing. It can be launched manually without using an appropriate runway, besides using a soft grass field for landing is recommended. Its associated costs for construction and maintenance are very low (below US$ 500) if compared to traditional aircraft. The main contribution here is the architectural design, besides we provide detailed documentation including techniques for determining lift, thrust, drag, minimum flight velocity, maximum time of flight and distance (autonomy), and other issues that we have solved related to the aircraft development. We validate our prototype with experiments including several tests done with the UAV with results that have proven its flight ability. To the end, we understand that this work provides a nice starting document to researchers that intend to develop a UAV or enter this field.

Improved Behavioral Box and Sensing Techniques for Analysis of Tactile Discrimination Tasks in Rodents.

Neuroscience behavioral studies stand out among the research works in this area. In these studies, normally, rodents are put inside closed platforms known as behavioral boxes in order to perform tasks and have their behaviors observed by way of sensors and annotations by hand. In this work, we aim to improve this research process by developing new techniques based upon the full automation of the behavioral box processes for more easily acquiring data. We come up with a new structural design using cutting-edge technology, with enhanced spaces and better materials. We use components that can be easily purchased (or built) and developed new techniques for control and data acquisition. Our new platform allows for more precise control of the opening of the discrimination bars, which was not satisfactorily done with previous platforms. This makes possible the design of more complex decision-making experiments using camera and sensor systems, allowing a better assessment of rodent performance in the discrimination task. All the necessary materials and development documents are made available in a collaborative multi-user platform allowing work replication. With this, the present study provides a low-cost tool with ease of development and construction that can be used by laboratories that work with this type of research.

National Holidays and Social Mobility Behaviors: Alternatives for Forecasting COVID-19 Deaths in Brazil.

In this paper, we investigate the influence of holidays and community mobility on the transmission rate and death count of COVID-19 in Brazil. We identify national holidays and hallmark holidays to assess their effect on disease reports of confirmed cases and deaths. First, we use a one-variate model with the number of infected people as input data to forecast the number of deaths. This simple model is compared with a more robust deep learning multi-variate model that uses mobility and transmission rates (R0, Re) from a SEIRD model as input data. A principal components model of community mobility, generated by the principal component analysis (PCA) method, is added to improve the input features for the multi-variate model. The deep learning model architecture is an LSTM stacked layer combined with a dense layer to regress daily deaths caused by COVID-19. The multi-variate model incremented with engineered input features can enhance the forecast performance by up to 18.99% compared to the standard one-variate data-driven model.

sBotics - Gamified Framework for Educational Robotics.

This paper proposes a learning framework for Educational Robotics named sBotics, which includes a complete environment for teaching and programming skills acquisition designed for both teachers and K-12 students. Our framework has been developed using a gamified approach with the system and simulated environment developed in the Unity game engine. The main novelty of this platform is its ease-of-use combined with the flexibility to create a variety of scenarios with endless learning potential, in contrast to our evaluations where no alternatives with such characteristics were found for the K-12 range that we are targeting. Also as a contribution of our proposal, robot programs are treated as games that are affected by a disturbance model, which acts in the robotic system and environment variables. This model is introduced in order to approximate what happens in a real robot programming platform. Besides, it is possible for the user, throughout its use, to code in three levels of abstraction: its overly intuitive native programming language called R-Educ, BlockEduc (R-Educ version of Blockly), and C#. Programs can be compiled and interpreted by virtual robots executing any given command. As for teachers, the framework API offers tools that can be employed in the assembly and customization of the learning setup. The whole platform has been built as a tool dedicated to spreading the worlds of Robotics and Programming among youngsters, as well as making them more affordable to everyone. It has been validated by our experiments and is currently being used during the novel Coronavirus pandemic by the official RoboCupJunior Rescue trials in Brazil, currently with more than a thousand competing teams (about 5 thousands students).

Forecasting Covid-19 Dynamics in Brazil: A Data Driven Approach.

The contribution of this paper is twofold. First, a new data driven approach for predicting the Covid-19 pandemic dynamics is introduced. The second contribution consists in reporting and discussing the results that were obtained with this approach for the Brazilian states, with predictions starting as of 4 May 2020. As a preliminary study, we first used an Long Short Term Memory for Data Training-SAE (LSTM-SAE) network model. Although this first approach led to somewhat disappointing results, it served as a good baseline for testing other ANN types. Subsequently, in order to identify relevant countries and regions to be used for training ANN models, we conduct a clustering of the world's regions where the pandemic is at an advanced stage. This clustering is based on manually engineered features representing a country's response to the early spread of the pandemic, and the different clusters obtained are used to select the relevant countries for training the models. The final models retained are Modified Auto-Encoder networks, that are trained on these clusters and learn to predict future data for Brazilian states. These predictions are used to estimate important statistics about the disease, such as peaks and number of confirmed cases. Finally, curve fitting is carried out to find the distribution that best fits the outputs of the MAE, and to refine the estimates of the peaks of the pandemic. Predicted numbers reach a total of more than one million infected Brazilians, distributed among the different states, with São Paulo leading with about 150 thousand confirmed cases predicted. The results indicate that the pandemic is still growing in Brazil, with most states peaks of infection estimated in the second half of May 2020. The estimated end of the pandemics (97% of cases reaching an outcome) spread between June and the end of August 2020, depending on the states.

High-Level Path Planning for an Autonomous Sailboat Robot Using Q-Learning.

Path planning for sailboat robots is a challenging task particularly due to the kinematics and dynamics modelling of such kinds of wind propelled boats. The problem is divided into two layers. The first one is global were a general trajectory composed of waypoints is planned, which can be done automatically based on some variables such as weather conditions or defined by hand using some human-robot interface (a ground-station). In the second local layer, at execution time, the global route should be followed by making the sailboat proceed between each pair of consecutive waypoints. Our proposal in this paper is an algorithm for the global, path generation layer, which has been developed for the N-Boat (The Sailboat Robot project), in order to compute feasible sailing routes between a start and a target point while avoiding dangerous situations such as obstacles and borders. A reinforcement learning approach (Q-Learning) is used based on a reward matrix and a set of actions that changes according to wind directions to account for the dead zone, which is the region against the wind where the sailboat can not gain velocity. Our algorithm generates straight and zigzag paths accounting for wind direction. The path generated also guarantees the sailboat safety and robustness, enabling it to sail for long periods of time, depending only on the start and target points defined for this global planning. The result is the development of a complete path planner algorithm that, together with the local planner solved in previous work, can be used to allow the final developments of an N-Boat making it a fully autonomous sailboat.

Stairs and Doors Recognition as Natural Landmarks Based on Clouds of 3D Edge-Points from RGB-D Sensors for Mobile Robot Localization.

Natural landmarks are the main features in the next step of the research in localization of mobile robot platforms. The identification and recognition of these landmarks are crucial to better localize a robot. To help solving this problem, this work proposes an approach for the identification and recognition of natural marks included in the environment using images from RGB-D (Red, Green, Blue, Depth) sensors. In the identification step, a structural analysis of the natural landmarks that are present in the environment is performed. The extraction of edge points of these landmarks is done using the 3D point cloud obtained from the RGB-D sensor. These edge points are smoothed through the S l 0 algorithm, which minimizes the standard deviation of the normals at each point. Then, the second step of the proposed algorithm begins, which is the proper recognition of the natural landmarks. This recognition step is done as a real-time algorithm that extracts the points referring to the filtered edges and determines to which structure they belong to in the current scenario: stairs or doors. Finally, the geometrical characteristics that are intrinsic to the doors and stairs are identified. The approach proposed here has been validated with real robot experiments. The performed tests verify the efficacy of our proposed approach.

An adaptive learning approach for 3-D surface reconstruction from point clouds.

In this paper, we propose a multiresolution approach for surface reconstruction from clouds of unorganized points representing an object surface in 3-D space. The proposed method uses a set of mesh operators and simple rules for selective mesh refinement, with a strategy based on Kohonen's self-organizing map (SOM). Basically, a self-adaptive scheme is used for iteratively moving vertices of an initial simple mesh in the direction of the set of points, ideally the object boundary. Successive refinement and motion of vertices are applied leading to a more detailed surface, in a multiresolution, iterative scheme. Reconstruction was experimented on with several point sets, including different shapes and sizes. Results show generated meshes very close to object final shapes. We include measures of performance and discuss robustness.