Non-Intrusive Load Monitoring (NILM) aims to identify electrical appliances in a household from voltage and current signals, enabling energy efficiency and smart grid applications. This study investigates NILM classification using the PLAID sub-metered dataset, evaluating multiple feature extraction techniques and classification algorithms. The results demonstrate that generic statistical features outperform domain-specific electrical features, including those based on IEEE standards. Feature analysis reveals that transient-state signals generally lead to higher classification accuracy than steady-state signals. However, the best performance is achieved by combining statistical features from both states, specifically by characterizing the steady-state current signal, complemented by its phase shift, and the active-state current signal filtered through nine pass-band filters. Dimensionality reduction further improves classification by enhancing feature relevance. Among the classifiers tested, Random Forest achieves the highest performance, reaching 93% accuracy under optimal conditions. To address dataset imbalance, the Synthetic Minority Over-sampling Technique (SMOTE) was applied. While this technique does not improve overall performance, it enhances classification fairness by improving recognition of underrepresented categories at the cost of a slight decrease in the most populated ones. Learning curve analysis suggests that performance has not yet plateaued, indicating that a larger dataset would further enhance results. These findings highlight key challenges and opportunities in NILM, suggesting that future work should focus on expanding dataset diversity and refining feature extraction methods to improve classification robustness.

In electrical distribution networks an adequate management is key for supporting the deployment of renewable generation sources and microgrids while extracting their maximum potential. Among the existing optimization approaches, stochastic and probabilistic methods are experiencing a growth in their use. However, one of the problems when applying these approaches is the complexity of creating and evaluating the quality of the required stochastic forecasts compared to deterministic forecasts. To mitigate this difficulty, this paper proposes a probabilistic forecasting framework that integrates model creation, their evaluation, and the selection of the best model for predicting. Additionally, two novel methods are proposed for creating scenario sets, and a new metric is defined for evaluating and selecting which model to use. The proposed framework is applied in a case study over a dataset of ten secondary distribution substations from a real distribution network located in Manzanilla (Spain), showing the effect of the selection criteria over the forecasting quality.

As the global adoption of residential battery storage systems paired with local photovoltaic (PV) generation increases, prosumers are increasingly motivated to reduce both their electricity costs and dependence on the grid. This shift highlights the importance of accurately evaluating and predicting the battery's State of Health (SOH) and Remaining Useful Life (RUL). These factors are crucial for determining the operational costs and longevity of battery systems. Traditionally, SOH predictions have relied heavily on detailed measurement data and time-intensive simulations. In response, we introduce a new AI-based approach that simplifies SOH estimation. Our method, named "ML Battery Life Predictor (MLBatLife)," leverages forecasted or historical PV generation data and load consumption patterns to quickly forecast the SOH for various battery configurations. Tested on simulated data, this tool demonstrated a high accuracy, with a coefficient of determination of 0.986 for predictions one day ahead, and an impressively low average error of 0.1% for projections five years into the future. This innovative AI-driven technique offers substantial benefits for evaluating the economic viability and warranty parameters of battery installations in different regions. It provides a valuable resource for both industry stakeholders and energy system planners aiming to assess and anticipate battery health outcomes efficiently.

A comprehensive knowledge of topology is of great importance for the effective operation and maintenance of distribution networks. This paper contributes with a novel data-driven topology identification method for low-voltage distribution networks based on the wavelet transform. The method uses only energy measurements from smart meters, being compatible with the current European smart meter capabilities. The method identifies the feeder and phase topology of single and three-phase customers, even in unbalanced situations. A computationally-efficient methodology to link customers' time-frequency features with their network connection is proposed. The performance of the method is assessed on eleven non-synthetic networks, with a robustness assessment of factors such as network observability, dataset size, measurement errors, and Renewable Energy Sources (RES) penetration. Accuracy rates exceeding 95 % are obtained in most cases, outperforming an energy-conservation approach. A 98 % accuracy can be achieved with a 30-day hourly dataset if at least 80 % of network observability is provided. For lower observability levels, 45 or 60 days of data are needed to reach similar rates. The sensitivity analysis of measurement error demonstrated that it had a negligible influence on the results. The method showed favorable results even in scenarios with high-RES penetration, with accuracy values exceeding 95 %.

The increasing competition in the electric sector is challenging retail companies as they must assign its commercial efforts to attract the most profitable customers. Those are whose energy demand best fit certain target profiles, which usually depend on generation or cost policies. But, even when the demand profile is available, it is in an anonymous way, preventing its association to a particular client. In this paper, we explore a large dataset containing several millions of monthly demand profiles in Spain and use the available information about the associated economic sector and location for an indirect identification of the customers. The distance of the demand profile from the target is used to define a key performance indicator (KPI) which is used as the main driver of the proposed marketing strategy. The combined use of activity and location has been revealed as a powerful tool for indirect identification of customers, as 100,000 customers are uniquely identified, while about 300,000 clients are identifiable in small sets containing 10 or less consumers. To assess the proposed marketing strategy, it has been compared to the random attraction of new clients, showing a reduction of distance from the target of 40% for 10,000 new customers.

The ongoing evolution of Industry 4.0 requires the modernization of automation class laboratories to enrich the capabilities of future automation engineers. Our project aims to revamp the laboratory structure into a Single Source of Truth-based architecture using Local Area Networks, PLCs, and gateways with Unified Namespace technology. The implementation of this technology provides flexibility to the laboratory network, enhancing the quality of high-level services. The communication between operational technology and information technology elements has been improved, resolving issues such as data duplication, missing data due to communication problems, and different input data for services through the use of a Single Source of Truth architecture. The Automation Laboratory implemented the architecture to facilitate teaching at the Escuela Politecnica Superior of the Universidad de Sevilla, where students control a continuous production process.

BACKGROUND:Health care services are undergoing a digital transformation in which the Participatory Health Informatics field has a key role. Within this field, studies aimed to assess the quality of digital tools, including mHealth apps, are conducted. Privacy is one dimension of the quality of an mHealth app. Privacy consists of several components, including organizational, technical, and legal safeguards. Within legal safeguards, giving transparent information to the users on how their data are handled is crucial. This information is usually disclosed to users through the privacy policy document. Assessing the quality of a privacy policy is a complex task and several scales supporting this process have been proposed in the literature. However, these scales are heterogeneous and even not very objective. In our previous study, we proposed a checklist of items guiding the assessment of the quality of an mHealth app privacy policy, based on the General Data Protection Regulation.OBJECTIVE:To refine the robustness of our General Data Protection Regulation-based privacy scale to assess the quality of an mHealth app privacy policy, to identify new items, and to assign weights for every item in the scale.METHODS:A two-round modified eDelphi study was conducted involving a privacy expert panel.RESULTS:After the Delphi process, all the items in the scale were considered "important" or "very important" (4 and 5 in a 5-point Likert scale, respectively) by most of the experts. One of the original items was suggested to be reworded, while eight tentative items were suggested. Only two of them were finally added after Round 2. Eleven of the 16 items in the scale were considered "very important" (weight of 1), while the other 5 were considered "important" (weight of 0.5).CONCLUSION:The Benjumea privacy scale is a new robust tool to assess the quality of an mHealth app privacy policy, providing a deeper and complementary analysis to other scales. Also, this robust scale provides a guideline for the development of high-quality privacy policies of mHealth apps.

Recent developments in machine learning applications are deeply concerned with the poor interpretability of most of these techniques. To gain some insights in the process of designing data-based models it is common to graphically represent the algorithm's results, either in their final or intermediate stage. Specially challenging is the task of plotting multiclass classification results as they involve categorical variables (classes) rather than numeric results. Using the well-known MNIST dataset and a simple neural network as an example, this paper reviews the existing techniques to visualize classification results, from those centered on a particular instance or set of instances, to those representing an overall performance metric. As classification results are commonly summarized in the form of a confusion matrix, special attention is paid to its graphical representation. From this analysis, a new visualization tool is derived, which is presented in two forms: confusion star and confusion gear. The confusion star is centered on the classification errors, while the confusion gear focuses on the classification hits. The proposed visualization tools are also evaluated when facing: (i) balanced and imbalanced classifiers issues; (ii) the problem of representing errors with different orders of magnitude. By using shapes instead of colors to represent the value of each matrix cell, the new tools significantly improve the readability of the confusion matrices. Furthermore, we show how the area enclosed by the confusion stars and gears are directly related to standard classification metrics. The new graphic tools can be also usefully employed to visualize the performances of a sequence of classifiers.

Abstract Nowadays, the health sector is involved in a digital transformation. The use of technological systems supporting in the health care are becoming common among all stakeholders. The COVID-19 pandemic has also accelerated this process increasing the use of digital tools, devices, and services supporting patients in the self-management and/or in the communication with healthcare providers. In such circumstances, mobile health (mHealth) has also experienced a significant growth because of the potential benefits of its use in health self-management. However, the quality of the mHealth solutions is not always high enough reducing its adoption and acceptance. This study is focused on one of the components of the quality of mHealth solutions, privacy, particularly on the fairness of the privacy policies. Following a modified Delphi method, we assessed the robustness of a General Data Protection Regulation-based privacy scale, identified new tentative items to be included, and define weights to items according to their relevance. This Delphi study was conducted in two rounds through two online questionnaires that a selected expert panel filled out. Most of the experts considered all the items defined in the original scale as “important” or “very important” (4 and 5 in a 5-point Likert scale, respectively). An original item was reworded, and two new items were added. Regarding weight assignment, 11 of the 16 items in the scale were considered "very important", so that they were assigned a weight of 1, while the other 5 were considered "important", and were assigned a weight of 0.5. As a result, a new robust scale to assess the fairness of the privacy policy of a mHealth solution is defined. The Benjumea privacy scale is a new tool to assess a key component of privacy, privacy policy, providing a deeper and complementary analysis to other scales that assesses the general quality of mHealth solutions. Also, this robust scale provides a guideline for development of high-quality privacy policies of mHealth solutions.

BACKGROUND Cancer patients are increasingly using mobile health (mHealth) apps to take control of their health. Many studies have explored their efficiency, content, usability, and adherence; however, these apps have created a new set of privacy challenges, as they store personal and sensitive data. OBJECTIVE The purpose of this study was to refine and evaluate a scale based on the General Data Protection Regulation and assess the fairness of privacy policies of mHealth apps. METHODS Based on the experience gained from our previous work, we redefined some of the items and scores of our privacy scale. Using the new version of our scale, we conducted a case study in which we analyzed the privacy policies of cancer Android apps. A systematic search of cancer mobile apps was performed in the Spanish version of the Google Play website. RESULTS The redefinition of certain items reduced discrepancies between reviewers. Thus, use of the scale was made easier, not only for the reviewers but also for any other potential users of our scale. Assessment of the privacy policies revealed that 29% (9/31) of the apps included in the study did not have a privacy policy, 32% (10/31) had a score over 50 out of a maximum of 100 points, and 39% (12/31) scored fewer than 50 points. CONCLUSIONS In this paper, we present a scale for the assessment of mHealth apps that is an improved version of our previous scale with adjusted scores. The results showed a lack of fairness in the mHealth app privacy policies that we examined, and the scale provides developers with a tool to evaluate their privacy policies.

Privacy is a major concern for breast cancer patients. When patients use mobile health applications (mHealth apps), many sensitive data are handled by the application developers. General Data Protection Regulation (GDPR) arises as a solution to privacy issues. In this paper, we analyze the privacy policy of a sample of mHealth apps for breast cancer patients, developing a scale to check if GDPR is complied. Despite privacy is a key factor in the adoption of the use of mHealth apps, the low level of compliance with the GDPR of the analyzed applications was quite surprising. Thus, application developers must be concerned about this matter.

The use of mobile devices has undergone rapid growth in recent years. However, on some occasions, security has been neglected when developing applications. SSL/TLS has been used for years to secure communications although it is not a vulnerability-free protocol. One of the most common vulnerabilities is SSL pinning bypassing. This paper first describes some security controls to help protect against SSL pinning bypassing. Subsequently, some existing methods for bypassing are presented and two new methods are defined. We performed some experiments to check the use of security controls in widely used applications, and applied SSL pinning bypassing methods. Finally, we created an applicability framework, relating the implemented security controls and the methods that are applicable. This framework provides a guideline for pentesters and app developers.

Privatisation of public services education is a key feature of the Global Education Reform Movement (GERM), where policy convictions, ideas, and strategies are integral to the “spreading and mutating” of reforms. While there are important projects that seek to describe and explain major changes to restructuring, ownership and funding, what has not been given sufficient attention is the role of the private in privatisation. By private, we mean the decisions and choices regarding educational services of (a) individuals and families and (b) school providers, and how issues that have traditionally been in the public domain (e.g. through government systems, on the agendas of local community/municipal schools) are no longer there (e.g. government systems have been dismantled and replaced with new providers, and local community/municipal schools either no longer exist or provide “safety nets” for those who fail in the market). What we intend focusing on is depoliticised privatism, where the role of the private in the supply and demand for school places illuminates a shift in the identification and addressing of educational matters from the politicised public to the depoliticised private domain. We report specifically on intellectual and empirical work regarding how supply and demand works in the provision of education services in Chile, particularly by looking at how those who own and work in schools view current reforms.

The application of machine learning techniques to sound signals requires the previous characterization of said signals. In many cases, their description is made using cepstral coefficients that represent the sound spectra. In this paper, the performance in obtaining cepstral coefficients by two integral transforms, Discrete Fourier Transform (DFT) and Discrete Cosine Transform (DCT), are compared in the context of processing anuran calls. Due to the symmetry of sound spectra, it is shown that DCT clearly outperforms DFT, and decreases the error representing the spectrum by more than 30%. Additionally, it is demonstrated that DCT-based cepstral coefficients are less correlated than their DFT-based counterparts, which leads to a significant advantage for DCT-based cepstral coefficients if these features are later used in classification algorithms. Since the DCT superiority is based on the symmetry of sound spectra and not on any intrinsic advantage of the algorithm, the conclusions of this research can definitely be extrapolated to include any sound signal.

Selecting the proper performance metric constitutes a key issue for most classification problems in the field of machine learning. Although the specialized literature has addressed several topics regarding these metrics, their symmetries have yet to be systematically studied. This research focuses on ten metrics based on a binary confusion matrix and their symmetric behaviour is formally defined under all types of transformations. Through simulated experiments, which cover the full range of datasets and classification results, the symmetric behaviour of these metrics is explored by exposing them to hundreds of simple or combined symmetric transformations. Cross-symmetries among the metrics and statistical symmetries are also explored. The results obtained show that, in all cases, three and only three types of symmetries arise: labelling inversion (between positive and negative classes); scoring inversion (concerning good and bad classifiers); and the combination of these two inversions. Additionally, certain metrics have been shown to be independent of the imbalance in the dataset and two cross-symmetries have been identified. The results regarding their symmetries reveal a deeper insight into the behaviour of various performance metrics and offer an indicator to properly interpret their values and a guide for their selection for certain specific applications.

•Imbalance coefficient fosters measuring imbalance.•Geometric Mean and Bookmaker Informedness constitute the best unbiased metrics.•Matthews Correlation Coefficient is the best option for error consideration.•The concept of Class Balance Accuracy can be extended to other metrics.

This paper describes a multiagent architecture integrated system designed to supervise infrastructures in solar farms. The system enables monitoring the environment by means of sensor networks that are in charge of collecting data. It is designed using a hybrid model composed of an inference engine and an ontology. The former makes the system intelligent, while the latter structures knowledge. We have also developed a tool to configure and use the multiagent system in a simple and intuitive way.

A common problem in solar farms is to predict when accumulators stop working optimally and start losing efficiency. This paper proposes and describes how to use Bayesian networks together with expert systems to predict this moment by using a telecontrol multiagent system for monitoring solar farms with distributed sensors, which was developed in a previous work. To this end, a Bayesian network model and its implementation are proposed. The resulting system meets the requirements of telecontrol systems (reliability, flexibility, and response time), yields a solution for the prediction of lifespan batteries, and provides the multiagent system with autonomous intelligent capabilities and integrated learning.

The reduction in size, power consumption and price of many sensor devices has enabled the deployment of many sensor networks that can be used to monitor and control several aspects of various habitats. More specifically, the analysis of sounds has attracted a huge interest in urban and wildlife environments where the classification of the different signals has become a major issue. Various algorithms have been described for this purpose, a number of which frame the sound and classify these frames, while others take advantage of the sequential information embedded in a sound signal. In the paper, a new algorithm is proposed that, while maintaining the frame-classification advantages, adds a new phase that considers and classifies the score series derived after frame labelling. These score series are represented using cepstral coefficients and classified using standard machine-learning classifiers. The proposed algorithm has been applied to a dataset of anuran calls and its results compared to the performance obtained in previous experiments on sensor networks. The main outcome of our research is that the consideration of score series strongly outperforms other algorithms and attains outstanding performance despite the noisy background commonly encountered in this kind of application.

Several biological research studies have shown that the number of individuals of certain species of anurans in a specific geographical region, and the evolution of this number over time, can be used as an indicator of climate change. To detect the presence of anurans, Wireless Sensor Networks (WSNs) are usually deployed with the aim of obtaining bio-acoustic information in a set covering numerous locations. However, the identification of the anuran species from a huge number of recordings usually involves an overwhelming task that has to be undertaken by expert and intelligent systems. Previous studies into this issue have proposed several classification techniques with a common approach: they all take into account the sequential characteristic of sounds by considering syllables or other kinds of vocal segments. In noisy sounds, as it is usually the case in recordings made in natural habitats, segmentation of the signal is no straightforward task and may cause low classification accuracy. To override this problem, a new non-sequential approach is proposed in this paper. It is based on considering very small pieces of sounds (frames) each of which is then classified without considering preceding or subsequent information. Up to nine frame-based classifiers are explored in this paper and their performances are compared to the most commonly used sequential classifier: the Hidden Markov Model (HMM). Additionally, for featuring the frames, many choices have been described, although the application of the Mel Frequency Cepstral Coefficients (MFCCs) has probably become the most common method. In this work, an alternative methodology is suggested: the use of a set of MPEG-7 parameters, which offers a normalized solution with a much greater semantic content. The experimental results have shown that the proposed method clearly outperforms the HMM, thereby showing the non-sequential classification of anuran sounds to be feasible. From among the algorithms tested, the decision-tree classifier has shown the best performance with an overall classification success rate of 87.30%, which is an especially striking result considering that the analyzed sounds were affected by a decidedly noisy background. (C) 2017 The Authors. Published by Elsevier Ltd.