Although both the scientific and technological development of mobile networks are still evolving, there are increasing demands for critical remote telehealth medical services. Enter the OpenCare5G project, which addresses innovation in healthcare, connecting resources and entrepreneurs to generate solutions and positive impacts for organizations' innovation ecosystem and ultimately their patients. This work aims to present, discuss, and evaluate the OpenCare5G approach to an integrated and consistent end-to-end communication network used in the third phase of the project proof of concept. It brings an advanced solution with innovation in state of the art with a private network to a public network and satellite backhaul connection. This third proof of concept was implemented in different indigenous villages, using health and medical applications with remote ultrasound devices without a radiologist physician at the patient's side. The results were positive and showed the effectiveness of the methodology used. Hence, it will be replicable in remote regions and generally wherever the absence of a physician makes it hard to improve the medical conditions of populations residing geographically far away from hospitals.

Agricultural production is directly related to the environmental conditions. Favorable conditions can lead to higher productivity and product quality. However, climate change may pose a threat to agricultural production across the globe, as a rise in temperature may cause a decrease in the extent of suitable areas for growing certain crops. Using spatial analysis and data from future climate change scenarios developed by the IPCC, this research aims to evaluate the impact of climate change on the sugarcane and citrus plantations in the state of Sao Paulo from agroclimatic zoning mapping. The results of this research demonstrate that both crops can suffer great reduction of areas suitable for cultivation if there are severe changes in the climate regime, and these results can be used by managers and researchers to mitigate these potential impacts, as well as to clarify how climate change affects life on the planet, with the possible reduction of food and bioenergy production.

Background: Transportation demand forecasting is an essential activity for logistics operators and carriers. It leverages business operation decisions, infrastructure, management, and resource planning activities. Since 2015, there has been an increase in the use of deep learning models in this domain. However, there is a gap in works comparing traditional statistics and deep learning models for transportation demand forecasts. This work aimed to perform a case study of aggregated transportation demand forecasts in 54 distribution centers of a Brazilian carrier. Methods: A computational simulation and case study methods were applied, exploring the characteristics of the datasets through autoregressive integrated moving average (ARIMA) and its variations, in addition to a deep neural network, long short-term memory, known as LSTM. Eight scenarios were explored while considering different data preprocessing methods and evaluating how outliers, training and testing dataset splits during cross-validation, and the relevant hyperparameters of each model can affect the demand forecast. Results: The long short-term memory networks were observed to outperform the statistical methods in ninety-four percent of the dispatching units over the evaluated scenarios, while the autoregressive integrated moving average modeled the remaining five percent. Conclusions: This work found that forecasting transportation demands can address practical issues in supply chains, specially resource planning management.

Digital Health is a new way for medicine to work together with computer engineering and ICT to carry out tests and obtain reliable information about the health status of citizens in the most remote places in Brazil in near-real time, applying new technologies and digital tools in the process. InovaHC is the technological innovation core of the Clinics Hospital of the Faculty of Medicine of the University of São Paulo (HCFMUSP). It is the first national medical institution to seek new opportunities offered by 5G technology and test its application in the first private network for Digital Health in the largest hospital complex in Latin America through the OpenCare5G Project. This project uses an Open RAN concept and network disaggregation with lower costs than the traditional concept used by the telecommunications industry. The technological project connected to the 5G network was divided into two phases for proof-of-concept testing: the first with an initial focus on carrying out examinations with portable ultrasound equipment in different locations at HCFMUSP, and the second focusing on carrying out remote examinations with health professionals in other states of Brazil, who will be working in remote areas in other states with little or no ICT infrastructure together with a doctor analyzing exams in real time at HCFMUSP in São Paulo. The objective of the project is to evaluate the connectivity and capacity of the 5G private network in these the proof-of-concept tests for transmitting the volume of data from remote exams with higher speed and lower latency. We are in the first phase of the proof of concept testing to achieve the expected success. This project is a catalyst for innovation in health, connecting resources and entrepreneurs to generate solutions for the innovation ecosystem of organizations. It is coordinated by Deloitte with the participation of the Escola Politécnica da USP (The School of Engineering—University of São Paulo), Airspan, Itaú Bank, Siemens Healthineers, NEC, Telecom Infra Projet, ABDI and IDB. The use of 5G Open RAN technology in public health is concluded to be of extreme social, economic, and fundamental importance for HCFMUSP, citizens, and the development of health research to promote great positive impacts ranging from attracting investment in the country to improving the quality of patient care.

The heterogeneous data produced in agricultural supply chains can be divided into three main systems: (i) product identification and traceability, related to identifying production batches and locations of the product throughout the supply chain; (ii) environmental monitoring, considering environmental variables in production, storage and transportation; and (iii) processes monitoring, related to the data describing the production processes and inputs used. Data labeling on the different systems can improve decision-making, traceability, and coordination in the chains. Nevertheless, this is a labor-intensive task. The objective of this Chapter was to evaluate if unsupervised machine learning techniques could be used to identify patterns in the data, clusters of data, and generate labels for an unlabeled agricultural supply chain dataset. A dataset was generated through merging seven datasets that contained information from the three systems, and the k-means and self-organizing maps (SOM) models were evaluated on clustering the data and generating labels. The use of principal component analysis (PCA) was also evaluated together with the k-means model. Several supervised and unsupervised learning metrics were evaluated. The SOM model with the Gaussian neighborhood function provided the best results, with an F1-score of 0.91 and a more defined clusters map. A series of recommendations for the use of unsupervised learning techniques on supply chain data are discussed. The methodology used in this Chapter can be implemented on other supply chains and unsupervised machine learning research. Future work is related to improving the dataset and implementing other clustering models and dimensionality reduction techniques.

O consumo de produtos de origem orgânica é crescente, porém encontra barreiras para sua expansão devido ao custo elevado e desconfiança por parte dos consumidores. Este trabalho mapeou uma cadeia logística real de pedidos individualizados de produtos orgânicos e propôs uma solução para endereçar em parte estas principais barreiras impostas ao consumo mais amplo deste tipo de produto ao agregar valor e confiabilidade no processo através de coleta, análise e transmissão de imagens no ato da separação do pedido. Desta forma procura-se garantir a qualidade da entrega bem como prover informações adicionais ao cliente, que se mantém informado sobre o estado do seu pedido a partir de sua preparação. Fez-se uma revisão bibliográfica tanto para caracterizar a cadeia logística investigada quanto para validar a factibilidade da solução proposta através de aplicações análogas das áreas de conhecimento utilizadas para diferentes etapas do processo. Estas áreas são: computação de borda, trazendo capacidade computacional para próximo de eventos físicos; reconhecimento de imagens utilizando aprendizado de máquina; e finalmente serviços computacionais em nuvem. A implementação e aperfeiçoamento da solução é delineada como parte do desenvolvimento futuro deste trabalho.

The Network Slice Selection Function (NSSF) in heterogeneous technology environments is a complex problem, which still does not have a fully acceptable solution. Thus, the implementation of new network selection strategies represents an important issue in development, mainly due to the growing demand for applications and scenarios involving 5G and future networks. This work presents an integrated solution for the NSSF problem, called the Network Slice Selection Function Decision-Aid Framework (NSSF DAF), which consists of a distributed solution in which a part is executed on the user's equipment (for example, smartphones, Unmanned Aerial Vehicles, IoT brokers) functioning as a transparent service, and another at the Edge of the operator or service provider. It requires a low consumption of computing resources from mobile devices and offers complete independence from the network operator. For this purpose, protocols and software tools are used to classify slices, employing the following four multicriteria methods to aid decision making: VIKOR (Visekriterijumska Optimizacija i Kompromisno Resenje), COPRAS (Complex Proportional Assessment), TOPSIS (Technique for Order Preference by Similarity to Ideal Solution) and Promethee II (Preference Ranking Organization Method for Enrichment Evaluations). The general objective is to verify the similarity among these methods and applications to the slice classification and selection process, considering a specific scenario in the framework. It also uses machine learning through the K-means clustering algorithm, adopting a hybrid solution in the implementation and operation of the NSSF service in multi-domain slicing environments of heterogeneous mobile networks. Testbeds were conducted to validate the proposed framework, mapping the adequate quality of service requirements. The results indicate a real possibility of offering a complete solution to the NSSF problem that can be implemented in Edge, in Core, or even in the 5G Radio Base Station itself, without the incremental computational cost of the end user's equipment, allowing for an adequate quality of experience.

In this paper, the traceability of heparin medicine will be studied. Currently, the registration of traceability data is conducted in a decentralized manner. With blockchain implementation, the traceability systems that use this data could become semi-automated, increasing the quality, security, and confidence of the information generated in the supply chain. This paper presents the essential requirements and activities wherein information must be collected within the heparin drug supply chain, focusing on the animal raw materials production link and its requirements. Blockchain technology is proposed to increase traceability and reliability in relation to the current situation. It also fulfills all the requirements identified if used as part of a traceability system. These requirements are: the existence of a consensus mechanism; anonymity; protocol, efficiency, and consumption; immutability; ownership and management; and approval time. We conclude the paper by presenting the mapping of requirements and entities and critical activities for adopting blockchain technology to support the traceability of raw materials from animals used in heparin production.

This paper presents a methodology for testing and evaluation of Visible Light Communication (VLC) applications in the context of Intelligent Transport Systems (ITS). The methodology was applied in a test bed located in Sao Paulo - Brazil, which allows the evaluation of wireless communication technologies between vehicle and road infrastructure elements and between vehicles, even if traveling in high speed. The evaluated application refers to locating buses in real-time in urban places where the Global Positioning System technology is compromised due to loss of signal (sometimes for relatively long periods), such as tunnels and bus terminals. Through VLC, which uses modulated Light-emitting Diodes (LED) as data transmitters, it would be possible to overcome these drawbacks, taking advantage of the existing public lighting infrastructure as a means of transmission of positioning coordinates. The test results showed the feasibility of the proposed application and, most relevant, of the testing methodology. It opens up a range of VLC testing options related to the various ITS domains expressed in ISO 14813, such as vehicle-to-vehicle (e. g. warning signals in platooning scenarios) and vehicle-to-infrastructure-to-vehicle communication (e. g. half or fullduplex communication between vehicles and traffic signals in crossroads).

This work proposes a data-driven theoretical framework for addressing: (i) extreme climate events prediction through multi-hazard risk mapping using remote sensing, artificial intelligence, and hydrological models, considering multiple hazards; and (ii) environmental monitoring using on-site data collection and IoT technologies. The framework considers the possibility of evaluating multiple climate change scenarios for improving decision-making in terms of Government policies and farm planning. Its main requirements are gathered based on a literature review. Several essential metrics that can be evaluated, considering both supervised and unsupervised metrics and key performance indicators considering the triple bottom line aspects, are also proposed. The framework also adopts multi-hazard (considering several hazards) and multi-risk (considering several relevant stakeholders) aspects and can be used to simulate different scenarios, an essential task for improving decision-making.

This paper explores the use of several state-of-the-art machine learning models for predicting the daily prices of corn and sugar in Brazil in relation to the use of traditional econometrics models. The following models were implemented and compared: ARIMA, SARIMA, support vector regression (SVR), AdaBoost, and long short-term memory networks (LSTM). It was observed that, even though the prices time series for both products differ considerably, the models that presented the best results were obtained by: SVR, an ensemble of the SVR and LSTM models, an ensemble of the AdaBoost and SVR models, and an ensemble of the AdaBoost and LSTM models. The econometrics models presented the worst results for both products for all metrics considered. All models presented better results for predicting corn prices in relation to the sugar prices, which can be related mainly to its lower variation during the training and test sets. The methodology used can be implemented for other products.

The use of machine learning techniques, especially deep learning, could improve the predictions of the currently used epidemiological models for predicting Covid-19 in the short term. This information is essential for better decision making and to reduce the impacts of the disease spread in different countries. We explored the use of support vector regression (SVR) and long short-term memory networks (LSTM), the state of the art neural network architecture for time series analysis, to predict the daily incidence and prevalence for nine countries in Latin America. Our methodology and the models used can be replicated in other countries. Our main findings were: (i) there is no single best model or best hyperparameters configuration for all countries and targets; (ii) the LSTM showed an average MAE that was around 50% lower for incidence and 20% lower for prevalence when considering all countries; (iii) the LSTM showed better results for predicting incidence for most countries (Argentina, Bolivia, Brazil, Guatemala, and Haiti); (iv) the SVR showed better results for predicting prevalence for most countries (Argentina, Bolivia, Colombia, Cuba, Guatemala, and Haiti); and (v) for Brazil, the LSTM provided better results for both targets, with an MAE that was 68% lower for incidence and 73% lower for prevalence.

Network segregation is the solution adopted in the IMT-2020 standardization of the International Telecommunications Union (ITU), better known as 5G networks (Fifth Generation Mobile Networks), under development to meet the requirements of performance, reliability, energy, and economic efficiency required by applications in the various verticals of current and near-future economic activities. The philosophy adopted for the IMT-2020 standardization relies on the use of Software-Defined Networking (SDN), Network Function Virtualization (NFV), and Software-Defined Radio (SDR), i.e., the softwarization of the network. Softwarization allows network segregation through its slicing, which is discussed herein this work. Network slicing is performed by a novel Orchestrator, as provided in IMT-2020, which maintains the end-to-end network slices independent of each other and performs horizontal handover when the possibility of a loss of Quality of Service (QoS) is predictively detected by monitoring quality parameters during operation. Therefore, the Orchestrator is dynamic, operates in uptime, and allows horizontal handover. Hence, it chooses the most appropriate telecommunication infrastructure provider and network operator to guarantee QoS and Quality of Experience (QoE) to end-users in each network segment. These features make this work modern and keep it aligned with the actions being carried out by ITU. Based on this objective, as the main result of this paper, we propose an effective architecture for implementing the Orchestrator, not only to contribute to the state of the art for 5G and beyond communication systems but also to generate economic, technological, and social impacts.

The presence of trees brings several health benefits to urban populations. However, wind damage is an important cause of falling trees, causing considerable damages. This study involved a bibliometric review on the use of Internet of Things technologies for monitoring trees. A research protocol was designed and implemented, involving a thorough search of the Scopus database. After applying the exclusion criteria and content filters, the abstracts and titles of the resulting 313 documents were analyzed. Two analyses were performed; (i) an analysis of the evolution of the area based on the study metadata; (ii) a cluster analysis of the words present in the abstracts and titles of the identified documents. The first analysis showed: (i) the current growth of this area of research; (ii) that the most important fields of study were agricultural, biological, environmental, and terrestrial and planetary sciences; (iii) that the most relevant journal was Ecology and Forest Management. The second analysis resulted in the identification of three clusters: (i) wind impact; (ii) variables and experiments; (iii) forest management. The main gap observed was that few studies have used IoT technologies as tools for preventive or corrective actions related to wind and storm impacts on trees and forests.

This paper presents a computing pipeline architecture for semantic search in the domain of Offshore Engineering. The proposed system combines modules such as document retriever, passage retriever, and answer extractor to produce textual responses to queries in natural language such as: "What FPSO motion is mostly affected by viscous damping?" Such responses are often needed in Offshore Engineering activities, and linguistic techniques such as those based on inverted indexes with a syntactic focus tend to perform poorly. Instead, this research explores semantic techniques that take into account the meaning of words in the domain of Offshore Engineering. This paper describes a Linguistic QA pipeline architecture built that provides a way to retrieve answers instantly from a collection of 13,000 unstructured technical documents about Offshore Engineering, reports the achieved results and future work. This paper also presents additional modules under construction that exploit Neural Networks and ontologies approaches for semantic search in the domain of Offshore Engineering.

Multiple-choice question answering for the open domain is a task that consists of answering challenging questions from multiple domains, without direct pieces of evidence in the text corpora. The main application of multiple-choice question answering is self-tutoring. We propose the Multiple-Choice Reinforcement Learner (MCRL) model, which uses a policy gradient algorithm in a partially observable Markov decision process to reformulate question-answer pairs in order to find new pieces of evidence to support each answer choice. Its inputs are the question and the answer choices. MCRL learns to generate queries that improve the evidence found for each answer choice, using iteration cycles. After a predefined number of iteration cycles, MCRL provides the best answer choice and the text passages that support it. We use accuracy and mean reward per episode to conduct an in-depth hyperparameter analysis of the number of iteration cycles, reward function design, and weight of the pieces of evidence found in each iteration cycle on the final answer choice. The MCRL model with the best performance reached an accuracy of 0.346, a value higher than naive, random, and the traditional end-to-end deep learning QA models. We conclude with recommendations for future developments of the model, which can be adapted for different languages using text corpora and word embedding models for each language.

ABSTRACT This research aimed to monitor and evaluate air-conditioned trucks transporting day-old chicks, in various shifts of travel, through general packet radio service (GPRS) technology to provide real-time thermal control for poultry industry managers. The Control-Broilers equipment used were GS-105 and the Monitorar Platform. GS-105 is composed of sensors, a microprocessor, GPRS, and batteries. The Monitorar Platform provided nine applications that acted in coordination with web technology RESTful services. Twenty-eight chick transports were evaluated and monitored using the Control-Broilers. Truck routes were supervised by two researchers to ensure real-time data transmission through laptops and smartphones. Three air-conditioned trucks were used during two of days shifts. The vehicles had the same dimensions, but the routes, travel times, and load densities varied. Measurements of the air temperature, relative humidity, and specific enthalpy inside the trucks were recorded every minute. The experimental design was entirely randomized in a 3 × 2 factorial scheme, which represented the three trucks (CL, CA and JA) in two transport shifts (day and night), containing four repetitions (travel).The air-conditioned trucks transporting day-old chicks presented a 92.85% efficiency for real-time data transmission using GPRS technology. The trucks during the travel shifts did not provide thermal homogeneity in chick loads. The night shift presented worse thermal conditions.