Background: With the development of smart grids, accurate electric load forecasting has become increasingly important as it can help power companies in better load scheduling and reduce excessive electricity production. However, developing and selecting accurate time series models is a challenging task as this requires training several different models for selecting the best amongst them along with substantial feature engineering to derive informative features and finding optimal time lags, a commonly used input features for time series models. Methods: Our approach uses machine learning and a long short-term memory (LSTM)-based neural network with various configurations to construct forecasting models for short to medium term aggregate load forecasting. The research solves above mentioned problems by training several linear and non-linear machine learning algorithms and picking the best as baseline, choosing best features using wrapper and embedded feature selection methods and finally using genetic algorithm (GA) to find optimal time lags and number of layers for LSTM model predictive performance optimization. Results: Using France metropolitan’s electricity consumption data as a case study, obtained results show that LSTM based model has shown high accuracy then machine learning model that is optimized with hyperparameter tuning. Using the best features, optimal lags, layers and training various LSTM configurations further improved forecasting accuracy. Conclusions: A LSTM model using only optimally selected time lagged features captured all the characteristics of complex time series and showed decreased Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) for medium to long range forecasting for a wider metropolitan area.

Edge Computing (EC) is a new architecture that extends Cloud Computing (CC) services closer to data sources. EC combined with Deep Learning (DL) is a promising technology and is widely used in several applications. However, in conventional DL architectures with EC enabled, data producers must frequently send and share data with third parties, edge or cloud servers, to train their models. This architecture is often impractical due to the high bandwidth requirements, legalization, and privacy vulnerabilities. The Federated Learning (FL) concept has recently emerged as a promising solution for mitigating the problems of unwanted bandwidth loss, data privacy, and legalization. FL can co-train models across distributed clients, such as mobile phones, automobiles, hospitals, and more, through a centralized server, while maintaining data localization. FL can therefore be viewed as a stimulating factor in the EC paradigm as it enables collaborative learning and model optimization. Although the existing surveys have taken into account applications of FL in EC environments, there has not been any systematic survey discussing FL implementation and challenges in the EC paradigm. This paper aims to provide a systematic survey of the literature on the implementation of FL in EC environments with a taxonomy to identify advanced solutions and other open problems. In this survey, we review the fundamentals of EC and FL, then we review the existing related works in FL in EC. Furthermore, we describe the protocols, architecture, framework, and hardware requirements for FL implementation in the EC environment. Moreover, we discuss the applications, challenges, and related existing solutions in the edge FL. Finally, we detail two relevant case studies of applying FL in EC, and we identify open issues and potential directions for future research. We believe this survey will help researchers better understand the connection between FL and EC enabling technologies and concepts.

This paper proposes a customized convolutional neural network for crack detection in concrete structures. The proposed method is compared to four existing deep learning methods based on training data size, data heterogeneity, network complexity, and the number of epochs. The performance of the proposed convolutional neural network (CNN) model is evaluated and compared to pretrained networks, i.e., the VGG-16, VGG-19, ResNet-50, and Inception V3 models, on eight datasets of different sizes, created from two public datasets. For each model, the evaluation considered computational time, crack localization results, and classification measures, e.g., accuracy, precision, recall, and F1-score. Experimental results demonstrated that training data size and heterogeneity among data samples significantly affect model performance. All models demonstrated promising performance on a limited number of diverse training data; however, increasing the training data size and reducing diversity reduced generalization performance, and led to overfitting. The proposed customized CNN and VGG-16 models outperformed the other methods in terms of classification, localization, and computational time on a small amount of data, and the results indicate that these two models demonstrate superior crack detection and localization for concrete structures.

Health monitoring and its related technologies is an attractive research area. The electrocardiogram (ECG) has always been a popular measurement scheme to assess and diagnose cardiovascular diseases (CVDs). The number of ECG monitoring systems in the literature is expanding exponentially. Hence, it is very hard for researchers and healthcare experts to choose, compare, and evaluate systems that serve their needs and fulfill the monitoring requirements. This accentuates the need for a verified reference guiding the design, classification, and analysis of ECG monitoring systems, serving both researchers and professionals in the field. In this paper, we propose a comprehensive, expert-verified taxonomy of ECG monitoring systems and conduct an extensive, systematic review of the literature. This provides evidence-based support for critically understanding ECG monitoring systems’ components, contexts, features, and challenges. Hence, a generic architectural model for ECG monitoring systems is proposed, an extensive analysis of ECG monitoring systems’ value chain is conducted, and a thorough review of the relevant literature, classified against the experts’ taxonomy, is presented, highlighting challenges and current trends. Finally, we identify key challenges and emphasize the importance of smart monitoring systems that leverage new technologies, including deep learning, artificial intelligence (AI), Big Data and Internet of Things (IoT), to provide efficient, cost-aware, and fully connected monitoring systems.

Short term electric load forecasting plays a crucial role for utility companies, as it allows for the efficient operation and management of power grid networks, optimal balancing between production and demand, as well as reduced production costs. As the volume and variety of energy data provided by building automation systems, smart meters, and other sources are continuously increasing, long short-term memory (LSTM) deep learning models have become an attractive approach for energy load forecasting. These models are characterized by their capabilities of learning long-term dependencies in collected electric data, which lead to accurate prediction results that outperform several alternative statistical and machine learning approaches. Unfortunately, applying LSTM models may not produce acceptable forecasting results, not only because of the noisy electric data but also due to the naive selection of its hyperparameter values. Therefore, an optimal configuration of an LSTM model is necessary to describe the electric consumption patterns and discover the time-series dynamics in the energy domain. Finding such an optimal configuration is, on the one hand, a combinatorial problem where selection is done from a very large space of choices; on the other hand, it is a learning problem where the hyperparameters should reflect the energy consumption domain knowledge, such as the influential time lags, seasonality, periodicity, and other temporal attributes. To handle this problem, we use in this paper metaheuristic-search-based algorithms, known by their ability to alleviate search complexity as well as their capacity to learn from the domain where they are applied, to find optimal or near-optimal values for the set of tunable LSTM hyperparameters in the electrical energy consumption domain. We tailor both a genetic algorithm (GA) and particle swarm optimization (PSO) to learn hyperparameters for load forecasting in the context of energy consumption of big data. The statistical analysis of the obtained result shows that the multi-sequence deep learning model tuned by the metaheuristic search algorithms provides more accurate results than the benchmark machine learning models and the LSTM model whose inputs and hyperparameters were established through limited experience and a discounted number of experimentations.

Big Data is an essential research area for governments, institutions, and private agencies to support their analytics decisions. Big Data refers to all about data, how it is collected, processed, and analyzed to generate value-added data-driven insights and decisions. Degradation in Data Quality may result in unpredictable consequences. In this case, confidence and worthiness in the data and its source are lost. In the Big Data context, data characteristics, such as volume, multi-heterogeneous data sources, and fast data generation, increase the risk of quality degradation and require efficient mechanisms to check data worthiness. However, ensuring Big Data Quality (BDQ) is a very costly and time-consuming process, since excessive computing resources are required. Maintaining Quality through the Big Data lifecycle requires quality profiling and verification before its processing decision. A BDQ Management Framework for enhancing the pre-processing activities while strengthening data control is proposed. The proposed framework uses a new concept called Big Data Quality Profile. This concept captures quality outline, requirements, attributes, dimensions, scores, and rules. Using Big Data profiling and sampling components of the framework, a faster and efficient data quality estimation is initiated before and after an intermediate pre-processing phase. The exploratory profiling component of the framework plays an initial role in quality profiling; it uses a set of predefined quality metrics to evaluate important data quality dimensions. It generates quality rules by applying various pre-processing activities and their related functions. These rules mainly aim at the Data Quality Profile and result in quality scores for the selected quality attributes. The framework implementation and dataflow management across various quality management processes have been discussed, further some ongoing work on framework evaluation and deployment to support quality evaluation decisions conclude the paper.