The Plegma dataset: Domestic appliance-level and aggregate electricity demand with metadata from Greece.

The growing availability of smart meter data has facilitated the development of energy-saving services like demand response, personalized energy feedback, and non-intrusive-load-monitoring applications, all of which heavily rely on advanced machine learning algorithms trained on energy consumption datasets. To ensure the accuracy and reliability of these services, real-world smart meter data collection is crucial. The Plegma dataset described in this paper addresses this need bfy providing whole- house aggregate loads and appliance-level consumption measurements at 10-second intervals from 13 different households over a period of one year. It also includes environmental data such as humidity and temperature, building characteristics, demographic information, and user practice routines to enable quantitative as well as qualitative analysis. Plegma is the first high-frequency electricity measurements dataset in Greece, capturing the consumption behavior of people in the Mediterranean area who use devices not commonly included in other datasets, such as AC and electric-water boilers. The dataset comprises 218 million readings from 88 installed meters and sensors. The collected data are available in CSV format.

Unsupervised Cluster Analysis of Walking Activity Data for Healthy Individuals and Individuals with Lower Limb Amputation.

This is the first investigation to perform an unsupervised cluster analysis of activities performed by individuals with lower limb amputation (ILLAs) and individuals without gait impairment, in free-living conditions. Eight individuals with no gait impairments and four ILLAs wore a thigh-based accelerometer and walked on an improvised route across a variety of terrains in the vicinity of their homes. Their physical activity data were clustered to extract 'unique' groupings in a low-dimension feature space in an unsupervised learning approach, and an algorithm was created to automatically distinguish such activities. After testing three dimensionality reduction methods-namely, principal component analysis (PCA), t-distributed stochastic neighbor embedding (tSNE), and uniform manifold approximation and projection (UMAP)-we selected tSNE due to its performance and stable outputs. Cluster formation of activities via DBSCAN only occurred after the data were reduced to two dimensions via tSNE and contained only samples for a single individual. Additionally, through analysis of the t-SNE plots, appreciable clusters in walking-based activities were only apparent with ground walking and stair ambulation. Through a combination of density-based clustering and analysis of cluster distance and density, a novel algorithm inspired by the t-SNE plots, resulting in three proposed and validated hypotheses, was able to identify cluster formations that arose from ground walking and stair ambulation. Low dimensional clustering of activities has thus been found feasible when analyzing individual sets of data and can currently recognize stair and ground walking ambulation.

Explainability-Informed Feature Selection and Performance Prediction for Nonintrusive Load Monitoring.

With the massive, worldwide, smart metering roll-out, both energy suppliers and users are starting to tap into the potential of higher resolution energy readings for accurate billing, improved demand response, improved tariffs better tuned to users and the grid, and empowering end-users to know how much their individual appliances contribute to their electricity bills via nonintrusive load monitoring (NILM). A number of NILM approaches, based on machine learning (ML), have been proposed over the years, focusing on improving the NILM model performance. However, the trustworthiness of the NILM model itself has hardly been addressed. It is important to explain the underlying model and its reasoning to understand why the model underperforms in order to satisfy user curiosity and to enable model improvement. This can be done by leveraging naturally interpretable or explainable models as well as explainability tools. This paper adopts a naturally interpretable decision tree (DT)-based approach for a NILM multiclass classifier. Furthermore, this paper leverages explainability tools to determine local and global feature importance, and design a methodology that informs feature selection for each appliance class, which can determine how well a trained model will predict an appliance on any unseen test data, minimising testing time on target datasets. We explain how one or more appliances can negatively impact classification of other appliances and predict appliance and model performance of the REFIT-data trained models on unseen data of the same house and on unseen houses on the UK-DALE dataset. Experimental results confirm that models trained with the explainability-informed local feature importance can improve toaster classification performance from 65% to 80%. Additionally, instead of one five-classifier approach incorporating all five appliances, a three-classifier approach comprising a kettle, microwave, and dishwasher and a two-classifier comprising a toaster and washing machine improves classification performance for the dishwasher from 72% to 94% and the washing machine from 56% to 80%.

A Survey on Deep Reinforcement Learning Algorithms for Robotic Manipulation.

Robotic manipulation challenges, such as grasping and object manipulation, have been tackled successfully with the help of deep reinforcement learning systems. We give an overview of the recent advances in deep reinforcement learning algorithms for robotic manipulation tasks in this review. We begin by outlining the fundamental ideas of reinforcement learning and the parts of a reinforcement learning system. The many deep reinforcement learning algorithms, such as value-based methods, policy-based methods, and actor-critic approaches, that have been suggested for robotic manipulation tasks are then covered. We also examine the numerous issues that have arisen when applying these algorithms to robotics tasks, as well as the various solutions that have been put forth to deal with these issues. Finally, we highlight several unsolved research issues and talk about possible future directions for the subject.

Smart Dimmable LED Lighting Systems.

This paper proposes energy-efficient solutions for the smart light-emitting diode (LED) lighting system, which provides minimal energy consumption while simultaneously satisfying illuminance requirements of the users in a typical office space. In addition to artificial light from dimmable LED lamps, natural daylight coming from external sources, such as windows, is considered as a source of illumination in an indoor environment. In order to reduce total energy consumption, the smart LED system has the possibility to dim LED lamps, resulting in reduced LED output power. Additionally, various LED lamps' functionality, such as semi-angle of the half illuminance and LED tilting, are introduced as an additional parameter to be optimized to achieve greater energy saving of the designed system. In order to properly exploit external lighting, the idea to reduce overall daylight intensity at a users' location is realized by the option to dim the windows with a shading factor. Based on the users' requirements for a minimal and desired level of illumination, the proposed optimization problems can be solved by implementing different optimization algorithms. The obtained solutions are able to give instructions to a smart LED system to manage and control system parameters (LEDs dimming levels, semi-angles of the half illuminance, orientation of LEDs, the shading factor) in order to design total illumination, which ensures minimal energy consumption and users' satisfaction related to illuminance requirements.

Graph-Based Feature Weight Optimisation and Classification of Continuous Seismic Sensor Array Recordings.

Slope instabilities caused by heavy rainfall, man-made activity or earthquakes can be characterised by seismic events. To minimise mortality and infrastructure damage, a good understanding of seismic signal properties characterising slope failures is therefore crucial to classify seismic events recorded from continuous recordings effectively. However, there are limited contributions towards understanding the importance of feature selection for the classification of seismic signals from continuous noisy recordings from multiple channels/sensors. This paper first proposes a novel multi-channel event-detection scheme based on Neyman-Pearson lemma and Multi-channel Coherency Migration (MCM) on the stacked signal across multi-channels. Furthermore, this paper adapts graph-based feature weight optimisation as feature selection, exploiting the signal's physical characteristics, to improve signal classification. Specifically, we alternatively optimise the feature weight and classification label with graph smoothness and semidefinite programming (SDP). Experimental results show that with expert interpretation, compared with the conventional short-time average/long-time average (STA/LTA) detection approach, our detection method identified 614 more seismic events in five days. Furthermore, feature selection, especially via graph-based feature weight optimisation, provides more focused feature sets with less than half of the original number of features, at the same time enhancing the classification performance; for example, with feature selection, the Graph Laplacian Regularisation classifier (GLR) raised the rockfall and slide quake sensitivities to 92% and 88% from 89% and 85%, respectively.

Human Activity Recognition of Individuals with Lower Limb Amputation in Free-Living Conditions: A Pilot Study.

This pilot study aimed to investigate the implementation of supervised classifiers and a neural network for the recognition of activities carried out by Individuals with Lower Limb Amputation (ILLAs), as well as individuals without gait impairment, in free living conditions. Eight individuals with no gait impairments and four ILLAs wore a thigh-based accelerometer and walked on an improvised route in the vicinity of their homes across a variety of terrains. Various machine learning classifiers were trained and tested for recognition of walking activities. Additional investigations were made regarding the detail of the activity label versus classifier accuracy and whether the classifiers were capable of being trained exclusively on non-impaired individuals' data and could recognize physical activities carried out by ILLAs. At a basic level of label detail, Support Vector Machines (SVM) and Long-Short Term Memory (LSTM) networks were able to acquire 77-78% mean classification accuracy, which fell with increased label detail. Classifiers trained on individuals without gait impairment could not recognize activities carried out by ILLAs. This investigation presents the groundwork for a HAR system capable of recognizing a variety of walking activities, both for individuals with no gait impairments and ILLAs.

Individualised Responsible Artificial Intelligence for Home-Based Rehabilitation.

Socioeconomic reasons post-COVID-19 demand unsupervised home-based rehabilitation and, specifically, artificial ambient intelligence with individualisation to support engagement and motivation. Artificial intelligence must also comply with accountability, responsibility, and transparency (ART) requirements for wider acceptability. This paper presents such a patient-centric individualised home-based rehabilitation support system. To this end, the Timed Up and Go (TUG) and Five Time Sit To Stand (FTSTS) tests evaluate daily living activity performance in the presence or development of comorbidities. We present a method for generating synthetic datasets complementing experimental observations and mitigating bias. We present an incremental hybrid machine learning algorithm combining ensemble learning and hybrid stacking using extreme gradient boosted decision trees and k-nearest neighbours to meet individualisation, interpretability, and ART design requirements while maintaining low computation footprint. The model reaches up to 100% accuracy for both FTSTS and TUG in predicting associated patient medical condition, and 100% or 83.13%, respectively, in predicting area of difficulty in the segments of the test. Our results show an improvement of 5% and 15% for FTSTS and TUG tests, respectively, over previous approaches that use intrusive means of monitoring such as cameras.

Averaging Is Probably Not the Optimum Way of Aggregating Parameters in Federated Learning.

Federated learning is a decentralized topology of deep learning, that trains a shared model through data distributed among each client (like mobile phones, wearable devices), in order to ensure data privacy by avoiding raw data exposed in data center (server). After each client computes a new model parameter by stochastic gradient descent (SGD) based on their own local data, these locally-computed parameters will be aggregated to generate an updated global model. Many current state-of-the-art studies aggregate different client-computed parameters by averaging them, but none theoretically explains why averaging parameters is a good approach. In this paper, we treat each client computed parameter as a random vector because of the stochastic properties of SGD, and estimate mutual information between two client computed parameters at different training phases using two methods in two learning tasks. The results confirm the correlation between different clients and show an increasing trend of mutual information with training iteration. However, when we further compute the distance between client computed parameters, we find that parameters are getting more correlated while not getting closer. This phenomenon suggests that averaging parameters may not be the optimum way of aggregating trained parameters.

Building a Graph Signal Processing Model Using Dynamic Time Warping for Load Disaggregation.

Building on recent unsupervised Non-intrusive load monitoring (NILM) algorithms that use graph Laplacian regularization (GLR) and achieve state-of-the-art performance, in this paper, we propose a novel unsupervised approach to design an underlying graph to model the correlation within time-series smart meter measurements. We propose a variable-length data segmentation approach to extract potential events, assign all measurements associated with an identified event to each graph node, employ dynamic time warping to define the adjacency matrix of the graph, and propose a robust cluster labeling approach. Our simulation results on four different datasets show up to 10% improvement in classification performance over competing approaches.

Evaluation of Home-Based Rehabilitation Sensing Systems with Respect to Standardised Clinical Tests.

With increased demand for tele-rehabilitation, many autonomous home-based rehabilitation systems have appeared recently. Many of these systems, however, suffer from lack of patient acceptance and engagement or fail to provide satisfactory accuracy; both are needed for appropriate diagnostics. This paper first provides a detailed discussion of current sensor-based home-based rehabilitation systems with respect to four recently established criteria for wide acceptance and long engagement. A methodological procedure is then proposed for the evaluation of accuracy of portable sensing home-based rehabilitation systems, in line with medically-approved tests and recommendations. For experiments, we deploy an in-house low-cost sensing system meeting the four criteria of acceptance to demonstrate the effectiveness of the proposed evaluation methodology. We observe that the deployed sensor system has limitations in sensing fast movement. Indicators of enhanced motivation and engagement are recorded through the questionnaire responses with more than 83 % of the respondents supporting the system's motivation and engagement enhancement. The evaluation results demonstrate that the deployed system is fit for purpose with statistically significant ( ϱ c > 0 . 99 , R 2 > 0 . 94 , I C C > 0 . 96 ) and unbiased correlation to the golden standard.

On-chip Fourier-transform spectrometers and machine learning: a new route to smart photonic sensors.

Miniaturized silicon photonics spectrometers capable of detecting specific absorption features have great potential for mass market applications in medicine, environmental monitoring, and hazard detection. However, state-of-the-art silicon spectrometers are limited by fabrication imperfections and environmental conditions, especially temperature variations, since uncontrolled temperature drifts of only 0.1°C distort the retrieved spectrum precluding the detection and classification of the absorption features. Here we present a new strategy that exploits the robustness of machine learning algorithms to signal imperfections, enabling recognition of specific absorption features in a wide range of environmental conditions. We combine on-chip spatial heterodyne Fourier-transform spectrometers and supervised learning to classify different input spectra in the presence of fabrication errors, without temperature stabilization or monitoring. We experimentally show the differentiation of four different input spectra under an uncontrolled 10°C range of temperatures, about $ 100\times $100× increase in operational range, with a success rate up to 82.5% using state-of-the-art support vector machines and artificial neural networks.

An electrical load measurements dataset of United Kingdom households from a two-year longitudinal study.

Smart meter roll-outs provide easy access to granular meter measurements, enabling advanced energy services, ranging from demand response measures, tailored energy feedback and smart home/building automation. To design such services, train and validate models, access to data that resembles what is expected of smart meters, collected in a real-world setting, is necessary. The REFIT electrical load measurements dataset described in this paper includes whole house aggregate loads and nine individual appliance measurements at 8-second intervals per house, collected continuously over a period of two years from 20 houses. During monitoring, the occupants were conducting their usual routines. At the time of publishing, the dataset has the largest number of houses monitored in the United Kingdom at less than 1-minute intervals over a period greater than one year. The dataset comprises 1,194,958,790 readings, that represent over 250,000 monitored appliance uses. The data is accessible in an easy-to-use comma-separated format, is time-stamped and cleaned to remove invalid measurements, correctly label appliance data and fill in small gaps of missing data.

Multicriteria ranking of workplaces regarding working conditions in a mining company.

Ranking of workplaces with respect to working conditions is very significant for each company. It indicates the positions where employees are most exposed to adverse effects resulting from the working environment, which endangers their health. This article presents the results obtained for 12 different production workplaces in the copper mining and smelting complex RTB Bor - 'Veliki Krivelj' open pit, based on six parameters measured regularly which defined the following working environment conditions: air temperature, light, noise, dustiness, chemical hazards and vibrations. The ranking of workplaces has been performed by PROMETHEE/GAIA. Additional optimization of workplaces is done by PROMETHEE V with the given limits related to maximum permitted values for working environment parameters. The obtained results indicate that the most difficult workplace is on the excavation location (excavator operator). This method can be successfully used for solving similar kinds of problems, in order to improve working conditions.

User-action-driven view and rate scalable multiview video coding.

We derive an optimization framework for joint view and rate scalable coding of multi-view video content represented in the texture plus depth format. The optimization enables the sender to select the subset of coded views and their encoding rates such that the aggregate distortion over a continuum of synthesized views is minimized. We construct the view and rate embedded bitstream such that it delivers optimal performance simultaneously over a discrete set of transmission rates. In conjunction, we develop a user interaction model that characterizes the view selection actions of the client as a Markov chain over a discrete state-space. We exploit the model within the context of our optimization to compute user-action-driven coding strategies that aim at enhancing the client's performance in terms of latency and video quality. Our optimization outperforms the state-of-the-art H.264 SVC codec as well as a multi-view wavelet-based coder equipped with a uniform rate allocation strategy, across all scenarios studied in our experiments. Equally important, we can achieve an arbitrarily fine granularity of encoding bit rates, while providing a novel functionality of view embedded encoding, unlike the other encoding methods that we examined. Finally, we observe that the interactivity-aware coding delivers superior performance over conventional allocation techniques that do not anticipate the client's view selection actions in their operation.

Onboard low-complexity compression of solar stereo images.

We propose an adaptive distributed compression solution using particle filtering that tracks correlation, as well as performing disparity estimation, at the decoder side. The proposed algorithm is tested on the stereo solar images captured by the twin satellites system of NASA's Solar TErrestrial RElations Observatory (STEREO) project. Our experimental results show improved compression performance w.r.t. to a benchmark compression scheme, accurate correlation estimation by our proposed particle-based belief propagation algorithm, and significant peak signal-to-noise ratio improvement over traditional separate bit-plane decoding without dynamic correlation and disparity estimation.

Two-terminal video coding.

Following recent works on the rate region of the quadratic Gaussian two-terminal source coding problem and limit-approaching code designs, this paper examines multiterminal source coding of two correlated, i.e., stereo, video sequences to save the sum rate over independent coding of both sequences. Two multiterminal video coding schemes are proposed. In the first scheme, the left sequence of the stereo pair is coded by H.264/AVC and used at the joint decoder to facilitate Wyner-Ziv coding of the right video sequence. The first I-frame of the right sequence is successively coded by H.264/AVC Intracoding and Wyner-Ziv coding. An efficient stereo matching algorithm based on loopy belief propagation is then adopted at the decoder to produce pixel-level disparity maps between the corresponding frames of the two decoded video sequences on the fly. Based on the disparity maps, side information for both motion vectors and motion-compensated residual frames of the right sequence are generated at the decoder before Wyner-Ziv encoding. In the second scheme, source splitting is employed on top of classic and Wyner-Ziv coding for compression of both I-frames to allow flexible rate allocation between the two sequences. Experiments with both schemes on stereo video sequences using H.264/AVC, LDPC codes for Slepian-Wolf coding of the motion vectors, and scalar quantization in conjunction with LDPC codes for Wyner-Ziv coding of the residual coefficients give a slightly lower sum rate than separate H.264/AVC coding of both sequences at the same video quality.

Fast algorithm for distortion-based error protection of embedded image codes.

We consider a joint source-channel coding system that protects an embedded bitstream using a finite family of channel codes with error detection and error correction capability. The performance of this system may be measured by the expected distortion or by the expected number of correctly decoded source bits. Whereas a rate-based optimal solution can be found in linear time, the computation of a distortion-based optimal solution is prohibitive. Under the assumption of the convexity of the operational distortion-rate function of the source coder, we give a lower bound on the expected distortion of a distortion-based optimal solution that depends only on a rate-based optimal solution. Then, we propose a local search (LS) algorithm that starts from a rate-based optimal solution and converges in linear time to a local minimum of the expected distortion. Experimental results for a binary symmetric channel show that our LS algorithm is near optimal, whereas its complexity is much lower than that of the previous best solution.