The availability of smart meters and IoT technology has opened new opportunities, ranging from monitoring electrical energy to extracting various types of information related to household occupancy, and with the frequency of usage of different appliances. Non-intrusive load monitoring (NILM) allows users to disaggregate the usage of each device in the house using the total aggregated power signals collected from a smart meter that is typically installed in the household. It enables the monitoring of domestic appliance use without the need to install individual sensors for each device, thus minimizing electrical system complexities and associated costs. This paper proposes an NILM framework based on low frequency power data using a convex hull data selection approach and hybrid deep learning architecture. It employs a sliding window of aggregated active and reactive powers sampled at 1 Hz. A randomized approximation convex hull data selection approach performs the selection of the most informative vertices of the real convex hull. The hybrid deep learning architecture is composed of two models: a classification model based on a convolutional neural network trained with a regression model based on a bidirectional long-term memory neural network. The results obtained on the test dataset demonstrate the effectiveness of the proposed approach, achieving F1 values ranging from 0.95 to 0.99 for the four devices considered and estimation accuracy values between 0.88 and 0.98. These results compare favorably with the performance of existing approaches.

Energy-saving schemes are nowadays a major worldwide concern. As the building sector is a major energy consumer, and hence greenhouse gas emitter, research in home energy management systems (HEMS) has increased substantially during the last years. One of the primary purposes of HEMS is monitoring electric consumption and disaggregating this consumption across different electric appliances. Non-intrusive load monitoring (NILM) enables this disaggregation without having to resort in the profusion of specific meters associated with each device. This paper proposes a low-complexity and low-cost NILM framework based on radial basis function neural networks designed by a multi-objective genetic algorithm (MOGA), with design data selected by an approximate convex hull algorithm. Results of the proposed framework on residential house data demonstrate the designed models’ ability to disaggregate the house devices with excellent performance, which was consistently better than using other machine learning algorithms, obtaining F1 values between 68% and 100% and estimation accuracy values ranging from 75% to 99%. The proposed NILM approach enabled us to identify the operation of electric appliances accounting for 66% of the total consumption and to recognize that 60% of the total consumption could be schedulable, allowing additional flexibility for the HEMS operation. Despite reducing the data sampling from one second to one minute, to allow for low-cost meters and the employment of low complexity models and to enable its real-time implementation without having to resort to specific hardware, the proposed technique presented an excellent ability to disaggregate the usage of devices.

Existing hyperchaotic medical image encryption schemes derive all chaotic initial conditions solely from statistical features of deep-learning-segmented anatomical regions, creating a structural chosen-plaintext-attack (CPA) vulnerability: images with similar segmentation statistics yield cipher images from the same keystream, resulting in a Cipher Cross Correlation (CCC) close to unity (experimentally measured at 0.9141). We introduce a semantically conditioned key schedule that binds deep-learning semantic features with cryptographic hash functions to initialise chaotic dynamical systems. As a concrete instantiation, U-Net segmentation statistics and a digest of the whole plaintext image are fused via a nonlinear $$\tanh$$ tanh coupling. The cryptographic guarantees structural CPA resistance, full-image plaintext sensitivity, and an effective key space of $$2^{256}$$ 2 256 derive from the keyed hash component under standard hash assumptions (complexity-theoretic IND-CPA is not claimed), while the U-Net component provides semantic key conditioning , enabling content-aware deployment scenarios such as audit traceability. The framework is drop-in compatible with existing permutation-diffusion pipelines and generalises beyond U-Net and to other semantic extractors and hash primitives. Experiments on six medical imaging datasets across five modalities confirm near-ideal entropy ( $$\approx 7.997$$ ≈ 7.997 bits), NPCR ( $$\approx 99.61\%$$ ≈ 99.61 % ), and UACI ( $$\approx 33.47\%$$ ≈ 33.47 % ), and a reduction of more than three orders of magnitude in adversarial CCC relative to the base architecture, at under 2 ms of additional computation per $$256\!\times \!256$$ 256 × 256 image.

Solar irradiance is a critical factor in solar energy projects, and its unpredictability can hinder the management and efficiency of solar systems. To overcome this challenge, the development of intelligent and accurate forecasting models has become essential. These models play a key role in predicting energy production, optimizing grid operations, and balancing power supply and demand. While there has been extensive research on solar irradiance forecasting, there remains a gap in the literature regarding the analysis of tree-based ensemble learning methods. In contrast, Artificial Neural Network (ANN) models have been extensively studied. Tree-based ensemble learning models are notable for their lower computational cost and effective performance, especially when compared to the more complex structure of ANN models. This paper has three objectives. First, it provides an overview of the critical elements for developing solar irradiance forecasting models, including data characteristics, preprocessing steps, and feature selection for accurate prediction. Second, it provides a comprehensive review of the state of the art in tree-based ensemble learning methods applied to solar irradiance forecasting. Finally, the paper presents a discussion of the research findings and proposes recommendations and potential directions for future research in this area.