Abstract
In this paper, a decision support application, for the air cargo planning and distribution, is proposed. The freight forwarding sector has been working to be assertive and efficient in responding to the market through an efficient approach to planning and allocation problems. The main goal is to minimize costs and improve performance. A real air cargo distribution problem for a freight forwarder was addressed. This project emerged from the need to efficiently plan and minimize costs for the distribution of thousands of m(3) (cubic meters) of air cargo, while considering the market restrictions, such as aircraft availability and transportation fees. Through the GRG algorithm adaptation to the real problem, it was possible to respond to the main goal of this paper. The development of an easy-to-use application ensures a quick response in the air distribution planning, focusing on cost reduction in transportation. With the application development it is possible to obtain real earnings with immediate effect.

Abstract
Renewable energy sources such as solar and wind are now competitive with traditional fossil and nuclear power when generating but that is just the challenge. When not generating can be a problem for grid integration and the main challenge to the widespread acceptance and dissemination of solar and wind, and the focus of research for the next generation of energy engineers. Intermittent, the adjective most associated with solar and wind energy has been and continues to be the focus of research by power engineers, AI professionals, and system scientists from the late 20th century and is the critical factor in the design of the future power grids, The most obvious solution is energy storage but then the choice of the storage method and size are complex problems. Will best solutions involve pumped hydro, Li-Ion batteries, or hydrogen generation? Or will next-generation ultra-capacitors, or high-speed flywheels gyros, or some yet to be discovered device will be the dominating technologies? The primary objective of the storage designs will be based on what's best for the reliability and efficiency of the grid, and simultaneously optimizing cost and environmental impact functions. Socio-economic and geopolitical considerations must also be considered to satisfy local or regional constraints. There is also the question of purpose: will it be sized for grid stability, or medium, or long-term storage. This factor will depend on the specific grid requirements. The focus of this paper is to study multi-source renewable energy systems that include storage called HRES or Hybrid Renewable Energy with Storage. This study describes the development of a behind-the-meter Energy Management System (EMS) for an HRES, under the assumption that Real-Time Pricing (RTP) is offered by a utility supplying power to a medium-size office complex. A cost function to be minimized is introduced to optimize the contribution of each energy source. Also, this work develops the basis of a platform for decision-makers to evaluate the viability of the optimized system in conjunction with the financial feasibility analysis.

Abstract
Health Remote Monitoring Systems (HRMS) offer the ability to address health-care human resource concerns. In developing nations, where pervasive mobile networks and device access are linking people like never before, HRMS are of special relevance. A fundamental aim of this research work is the realization of technological-based solution to triage and follow-up people living with dementias so as to reduce pressure on busy staff while doing this from home so as to avoid all unnecessary visits to hospital facilities, increasingly perceived as dangerous due to COVID-19 but also raising nosocomial infections, raising alerts for abnormal values. Sensing approaches are complemented by advanced predictive models based on Machine Learning (ML) and Artificial Intelligence (AI), thus being able to explore novel ways of demonstrating patient-centered predictive measures. Low-cost IoT devices composing a network of sensors and actuators aggregated to create a digital experience that will be used and exposure to people to simultaneously conduct several tests and obtain health data that can allow screening of early onset dementia and to aid in the follow-up of selected cases. The best ML for predicting AD was logistic regression with an accuracy of 86.9%. This application as demonstrated to be essential for caregivers once they can monitor multiple patients in real-time and actuate when abnormal values occur.

Abstract
The volume of data is growing exponentially and becoming more valuable to organizations that collect it, from e-commerce data, shipping, audio and video logs, text messages, internet search queries, stock market activity, financial transactions, the Internet of Things, and various other sources. The major challenges are related with the way to extract insights from such a rich data environment and whether Deep Learning can be successful with Big Data. To get some insight on these topics, social network data are employed as a case study on how sentiments can affect decisions in stock market environments. In this paper, we propose a generalized Deep Learning-based classification framework for Stock Market Sentiment Analysis. This work comprises the study, the development, and implementation of an automatic classification system based on Deep Learning and the validation of its adequacy and efficiency in any scenario, particularly Stock Market Sentiment Analysis. Distinct datasets and several Deep Learning approaches with different layers and embedded techniques are used, and their performances are evaluated. These developments show how Deep Learning reacts to distinct contexts. The results also give context on how different techniques with different parameter combinations react to certain types of data. Convolution obtained the best results when dealing with complex data inputs, and long short-term layers kept a memory of data, allowing inputs which are not as common to still be considered for decisions. The models that resulted from Stock Market Sentiment Analysis datasets were applied with some success to real-life problems. The best models reached accuracies of 73% in training and 69% in certain test datasets. In a simulation, a model was able to provide a Return on Investment of 4.4%. The results contribute to understanding how to process Big Data efficiently using Deep Learning and specialized hardware techniques.

Abstract
In the digital world, the demand for better interactions between subscribers and companies is growing, creating the need for personalized and individualized experiences. With the exponential growth of email usage over the years, broad flows of campaigns are sent and received by subscribers, which reveals itself to be a problem for both companies and subscribers. In this work, subscribers are segmented by their behaviors and profiles, such as (i) open rates, (ii) click-through rates, (iii) frequency, and (iv) period of interactions with the companies. Different regressions are used: (i) Random Forest Regressor, (ii) Multiple Linear Regression, (iii) K-Neighbors Regressor, and (iv) Support Vector Regressor. All these regressions’ results were aggregated into a final prediction achieved by an ensemble approach, which uses averaging and stacking methods. The use of Long Short-Term Memory is also considered in the presented case. The stacking model obtained the best performance, with an R (Formula presented.) score of 0.91 and a Mean Absolute Error of 0.204. This allows us to estimate the week’s days with a half-day error difference. This work presents promising results for subscriber segmentation based on profile information for predicting the best period for email marketing. In the future, subscribers can be segmented using the Recency, Frequency and Monetary value, the Lifetime Value, or Stream Clustering approaches that allow more personalized and tailored experiences for subscribers. The latter tracks segments over time without costly recalculations and handles continuous streams of new observations without the necessity to recompile the entire model. © 2022 by the authors.

Abstract