Home Automation Networks provide a promising opportunity in designing smart home systems and applications. In this context, Machine-to-Machine (M2M) networks are emerging as an efficient means to provide automated communication among distributed ubiquitous devices on in a standardized manner, but none have been adopted universally. In an effort to present the technologies used in the M2M and home integration environment, this paper presents the home area network elements and definitions, and reviews the standards, architectures and initiatives created to enable M2M communication and integration in several different environments, especially at the smart home domain. This paper points out differences between them and identifies trends for the future. HighlightsPresents¿different definitions and concepts of the smart home.Reviews the technologies created to enable M2M communication in smart home domain.Shows a comparison between standards created to enable M2M communication.Those technologies have strong market competition, but none is adopted universally.

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.

The Internet of Things (IoT) has been widely discussed and investigated, not only by academics but also by various segments of industry and commerce. Once established and fully operational, this technology is set to offer considerable benefits. Sensors will send large amounts of data for analysis and interpretation in real-time or near real-time. These data streams will flow at high speed, in large volumes, varying in type, and value. However, it is likely that sensors will face numerous obstacles what can pollute their data with significant amount of noise. This paper investigates sensor data streams and sensor signals in order to identify their specific characteristics and issues, particularly the problem of noise. This paper also investigates discrete wavelet transform (DWT) to reduce noise. Results here show significant improvements in the sensor signal when using DWT. The principal conclusion of our analysis is that, by knowing the main issues of IoT data, it is possible to track problems and reduce data errors. Another practical conclusion is that DWT is a powerful tool for reducing signal noise.