Search

BackgroundThe increasing prevalence of obesity necessitates innovative approaches to better understand this health crisis, particularly given its strong connection to chronic diseases such as diabetes, cancer, and cardiovascular conditions. Monitoring dietary behavior is crucial for designing effective interventions that help decrease obesity prevalence and promote healthy lifestyles. However, traditional dietary tracking methods are limited by participant burden and recall bias. Exploring microlevel eating activities, such as meal duration and chewing frequency, in addition to eating episodes, is crucial due to their substantial relation to obesity and disease risk. ObjectiveThe primary objective of the study was to develop an accurate and noninvasive system for automatically monitoring eating and chewing activities using sensor-equipped smart glasses. The system distinguishes chewing from other facial activities, such as speaking and teeth clenching. The secondary objective was to evaluate the system’s performance on unseen test users using a combination of laboratory-controlled and real-life user studies. Unlike state-of-the-art studies that focus on detecting full eating episodes, our approach provides a more granular analysis by specifically detecting chewing segments within each eating episode. MethodsThe study uses OCO optical sensors embedded in smart glasses to monitor facial muscle activations related to eating and chewing activities. The sensors measure relative movements on the skin’s surface in 2 dimensions (X and Y). Data from these sensors are analyzed using deep learning (DL) to distinguish chewing from other facial activities. To address the temporal dependence between chewing events in real life, we integrate a hidden Markov model as an additional component that analyzes the output from the DL model. ResultsStatistical tests of mean sensor activations revealed statistically significant differences across all 6 comparison pairs (P

With the development of technology allowing for a rapid expansion of data science and machine learning in our everyday lives, a significant gap is forming in the global job market where the demand for qualified workers in these fields cannot be properly satisfied. This worrying trend calls for an immediate action in education, where these skills must be taught to students at all levels in an efficient and up-to-date manner. This paper gives an overview of the current state of data science and machine learning education globally and both at the high school and university levels, while outlining some illustrative and positive examples. Special focus is given to vocational education and training (VET), where the teaching of these skills is at its very beginning. Also presented and analysed are survey results concerning VET students in Slovenia, Serbia, and North Macedonia, and their knowledge, interests, and prerequisites regarding data science and machine learning. These results confirm the need for development of efficient and accessible curricula and courses on these subjects in vocational schools.

Arrhythmia detection is a vital task for reducing the mortality rate of cardiovascular diseases. Electrocardiogram (ECG) is a simple and inexpensive tool that can provide valuable information about the heart’s electrical activity and detect arrhythmias. However, manual analysis of ECG signals can be time-consuming and prone to errors. Therefore, machine learning models have been proposed to automate the process and improve the accuracy and efficiency of arrhythmia detection. In this paper, we compare six machine learning models, namely ADA boosting, Gradient Boost, Random Forest, C-Support Vector (SVC), Convolutional Neural Network (CNN), and Long Short-Term Memory Network (LSTM), for arrhythmia detection using ECG data from the MIT-BIH Arrhythmia Database. We evaluate the performance of the models using various metrics, such as accuracy, precision, recall, and F1-score, on different classes of ECG beats. We also use confusion matrices to visualize the errors made by the models. We find that the CNN model is the best performing model overall, achieving accuracy of 95% and F1-score of 84.75%. SVC and LSTM were the second and third best, achieving accuracy of 94% and 93%, respectively. We also discuss the challenges of using ECG data for arrhythmia detection, such as noise, imbalance, and similarity of classes. We suggest some possible ways to overcome these challenges, such as using more advanced preprocessing and resampling techniques, or incorporating domain knowledge and expert feedback into the models.

Abstract Accurate and comprehensive nursing documentation is essential to ensure quality patient care. To streamline this process, we present SONAR, a publicly available dataset of nursing activities recorded using inertial sensors in a nursing home. The dataset includes 14 sensor streams, such as acceleration and angular velocity, and 23 activities recorded by 14 caregivers using five sensors for 61.7 hours. The caregivers wore the sensors as they performed their daily tasks, allowing for continuous monitoring of their activities. We additionally provide machine learning models that recognize the nursing activities given the sensor data. In particular, we present benchmarks for three deep learning model architectures and evaluate their performance using different metrics and sensor locations. Our dataset, which can be used for research on sensor-based human activity recognition in real-world settings, has the potential to improve nursing care by providing valuable insights that can identify areas for improvement, facilitate accurate documentation, and tailor care to specific patient conditions.

Abstract This study aimed to evaluate the use of novel optomyography (OMG) based smart glasses, OCOsense, for the monitoring and recognition of facial expressions. Experiments were conducted on data gathered from 27 young adult participants, who performed facial expressions varying in intensity, duration, and head movement. The facial expressions included smiling, frowning, raising the eyebrows, and squeezing the eyes. The statistical analysis demonstrated that: (i) OCO sensors based on the principles of OMG can capture distinct variations in cheek and brow movements with a high degree of accuracy and specificity; (ii) Head movement does not have a significant impact on how well these facial expressions are detected. The collected data were also used to train a machine learning model to recognise the four facial expressions and when the face enters a neutral state. We evaluated this model in conditions intended to simulate real-world use, including variations in expression intensity, head movement and glasses position relative to the face. The model demonstrated an overall accuracy of 93% (0.90 f1-score)—evaluated using a leave-one-subject-out cross-validation technique.

This paper focuses on analyzing the benchmark Diabetes dataset which consists of eight commonly measured characteristics. The goal of the study is to present comparative analysis of six machine learning models that predict diabetes, as well as various preprocessing techniques (under-over sampling, feature standardization). The study investigates various approaches and presents results demonstrating that machine learning algorithms can achieve high accuracy results for diabetes prediction, enabling early detection and better outcomes for patients. The paper shows that ensemble learning methods, such as Extra Trees Classifier and Random Forest Classifier, along with appropriate data pre-processing techniques, can lead to 86% accuracy in diabetes prediction classification problems. The paper highlights the potential for machine learning to play a valuable role in the prediction and management of diabetes, leading to improved quality of life and health outcomes for patients.

The increasing use of Wearable devices opens up the use of a wide range of applications. Using different models, these devices can be of great use in Human Activity Recognition (HAR), where the main goal is to process information obtained from sensors located in them, especially in eHealth. The high volume of data collected by various smart devices in contemporary ML scenarios, leads to higher processing consumption and in many cases results in compromised privacy. These shortcomings could be overcome by using Federated Learning (FL), a learning paradigm that allows for decentralized training of models such that user’s personal data does not need to ever leave their devices, which substantially reduces to possibility of a breach. This paper analyses the behaviour and performances of FL when applied to the context of HAR. The obtained results show that FL can achieve comparable performances to those of centralized Deep Learning, while facilitating improved data privacy and diversity, as well as fostering real-time continuous learning.

BackgroundContinuous assessment of affective behaviors could improve the diagnosis, assessment and monitoring of chronic mental health and neurological conditions such as depression. However, there are no technologies well suited to this, limiting potential clinical applications.AimTo test if we could replicate previous evidence of hypo reactivity to emotional salient material using an entirely new sensing technique called optomyography which is well suited to remote monitoring.MethodsThirty-eight depressed and 37 controls (≥18, ≤40 years) who met a research diagnosis of depression and an age-matched non-depressed control group. Changes in facial muscle activity over the brow (corrugator supercilli) and cheek (zygomaticus major) were measured whilst volunteers watched videos varying in emotional salience.ResultsAcross all participants, videos rated as subjectively positive were associated with activation of muscles in the cheek relative to videos rated as neutral or negative. Videos rated as subjectively negative were associated with brow activation relative to videos judged as neutral or positive. Self-reported arousal was associated with a step increase in facial muscle activation across the brow and cheek. Group differences were significantly reduced activation in facial muscles during videos considered subjectively negative or rated as high arousal in depressed volunteers compared with controls.ConclusionWe demonstrate for the first time that it is possible to detect facial expression hypo-reactivity in adults with depression in response to emotional content using glasses-based optomyography sensing. It is hoped these results may encourage the use of optomyography-based sensing to track facial expressions in the real-world, outside of a specialized testing environment.

The past decade has seen substantial growth in the prevalence and capabilities of wearable devices. For instance, recent human activity recognition (HAR) research has explored using wearable devices in applications such as remote monitoring of patients, detection of gait abnormalities, and cognitive disease identification. However, data collection poses a major challenge in developing HAR systems, especially because of the need to store data at a central location. This raises privacy concerns and makes continuous data collection difficult and expensive due to the high cost of transferring data from a user’s wearable device to a central repository. Considering this, we explore the adoption of federated learning (FL) as a potential solution to address the privacy and cost issues associated with data collection in HAR. More specifically, we investigate the performance and behavioral differences between FL and deep learning (DL) HAR models, under various conditions relevant to real-world deployments. Namely, we explore the differences between the two types of models when (i) using data from different sensor placements, (ii) having access to users with data from heterogeneous sensor placements, (iii) considering bandwidth efficiency, and (iv) dealing with data with incorrect labels. Our results show that FL models suffer from a consistent performance deficit in comparison to their DL counterparts, but achieve these results with much better bandwidth efficiency. Furthermore, we observe that FL models exhibit very similar responses to those of DL models when exposed to data from heterogeneous sensor placements. Finally, we show that the FL models are more robust to data with incorrect labels than their centralized DL counterparts.

Abstract Using a novel wearable surface electromyography (sEMG), we investigated induced affective states by measuring the activation of facial muscles traditionally associated with positive (left/right orbicularis and left/right zygomaticus) and negative expressions (the corrugator muscle). In a sample of 38 participants that watched 25 affective videos in a virtual reality environment, we found that each of the three variables examined—subjective valence, subjective arousal, and objective valence measured via the validated video types (positive, neutral, and negative)—sEMG amplitude varied significantly depending on video content. sEMG aptitude from “positive muscles” increased when participants were exposed to positively valenced stimuli compared with stimuli that was negatively valenced. In contrast, activation of “negative muscles” was elevated following exposure to negatively valenced stimuli compared with positively valenced stimuli. High arousal videos increased muscle activations compared to low arousal videos in all the measured muscles except the corrugator muscle. In line with previous research, the relationship between sEMG amplitude as a function of subjective valence was V-shaped.

Sensor-based human activity recognition is becoming ever more prevalent. The increasing importance of distinguishing human movements, particularly in healthcare, coincides with the advent of increasingly compact sensors. A complex sequence of individual steps currently characterizes the activity recognition pipeline. It involves separate data collection, preparation, and processing steps, resulting in a heterogeneous and fragmented process. To address these challenges, we present a comprehensive framework, HARE, which seamlessly integrates all necessary steps. HARE offers synchronized data collection and labeling, integrated pose estimation for data anonymization, a multimodal classification approach, and a novel method for determining optimal sensor placement to enhance classification results. Additionally, our framework incorporates real-time activity recognition with on-device model adaptation capabilities. To validate the effectiveness of our framework, we conducted extensive evaluations using diverse datasets, including our own collected dataset focusing on nursing activities. Our results show that HARE’s multimodal and on-device trained model outperforms conventional single-modal and offline variants. Furthermore, our vision-based approach for optimal sensor placement yields comparable results to the trained model. Our work advances the field of sensor-based human activity recognition by introducing a comprehensive framework that streamlines data collection and classification while offering a novel method for determining optimal sensor placement.

To further extend the applicability of wearable sensors, methods for accurately extracting subtle psychological information from the sensor data are required. However, accessing subjective information in everyday life, such as cognitive load, remains challenging. To bring consensus on methods for cognitive load monitoring, a machine learning challenge is organized. The participants developed machine learning methods for cognitive load classification using wrist-worn physiological sensors’ data, namely heart rate, R-R intervals, skin conductance, and skin temperature. The data from subjects solving cognitive tasks of varying difficulty is used for the challenge. This article presents a systematic comparison and multi-strategic performance evaluation of the thirteen methods submitted to this challenge. A systematic comparison of preprocessing techniques, classification algorithms, and implementation techniques is presented. Performance variations for different task difficulty levels, different subjects, and different experiment periods are evaluated. The results indicate that the most robust methods used multimodal sensor data, classical classification approaches such as decision trees and support vector machines or their ensembles, and Bayesian hyperparameter optimization for hyperparameter tuning. The most accurate models used handcrafted features that are further selected using sequential backward floating search and evaluated using stratified person-aware cross-validation strategy. Moreover, the results indicated better classification performance for specific test subjects, the tasks with the highest difficulty, and in some cases, the time elapsed since the start of the experiment. This dependency is likely due to model overfitting or due to the subjective nature of the psychophysiological process. The intersubject variability in responses is challenging to be captured through objective binary labels for cognitive load, thereby warranting more sophisticated annotation approaches.

Air pollution is becoming a global environmental problem, in both developed and developing countries. It has greatly impacted the health and lives of millions of people, thus increasing mortality rates and pollution induced diseases reports. This paper proposes machine learning methods for predicting the rates of possibly increased air pollution in several areas, by processing the gathered data from multiple weather and air quality meter stations. The data has been gathered over a period of several years including air quality and pollution data and weather data including temperature, humidity and wind characteristics. The development process included feature extraction, feature selection for removing redundancy, and finally training multiple regression models and hyperparameter optimization. Pollutants and air quality index (AQI) were used as target variables, and appropriate regression models were trained. The performed experiments show that XGBoost is the most accurate, achieving MAE of 8.9 for Center, 8.9 for Karpos and 7.3 for Kumanovo municipality for the PM10 pollutant. The improvements over the baseline, Dummy regressor are significant, reducing the MAE for 12 on average.

The Sussex-Huawei Locomotion-Transportation (SHL) Recognition Challenges aim to advance and capture the state-of-the-art in locomotion and transportation mode recognition from smartphone motion (inertial) sensors. The goal of this series of machine learning and data science challenges was to recognize eight locomotion and transportation activities (Still, Walk, Run, Bus, Car, Train, Subway). The three challenges focused on time-independent (SHL 2018), position-independent (SHL 2019) and user-independent (SHL 2020) evaluations, respectively. Overall, we received 48 submissions (out of 93 teams who registered interest) involving 201 scientists over the three years. The survey captures the state-of-the-art through a meta-analysis of the contributions to the three challenges, including approaches, recognition performance, computational requirements, software tools and frameworks used. It was shown that state-of-the-art methods can distinguish with relative ease most modes of transportation, although the differentiating between subtly distinct activities, such as rail transport (Train and Subway) and road transport (Bus and Car) still remains challenging. We summarize insightful methods from participants that could be employed to address practical challenges of transportation mode recognition, for instance, to tackle over-fitting, to employ robust representations, to exploit data augmentation, and to exploit smart post-processing techniques to improve performance. Finally, we present baseline results to compare the three challenges with a unified recognition pipeline and decision window length.

Transportation and locomotion mode recognition from multimodal smartphone sensors is useful for providing just-in-time context-aware assistance. However, the field is currently held back by the lack of standardized datasets, recognition tasks, and evaluation criteria. Currently, the recognition methods are often tested on the ad hoc datasets acquired for one-off recognition problems and with different choices of sensors. This prevents a systematic comparative evaluation of methods within and across research groups. Our goal is to address these issues by: 1) introducing a publicly available, large-scale dataset for transportation and locomotion mode recognition from multimodal smartphone sensors; 2) suggesting 12 reference recognition scenarios, which are a superset of the tasks we identified in the related work; 3) suggesting relevant combinations of sensors to use based on energy considerations among accelerometer, gyroscope, magnetometer, and global positioning system sensors; and 4) defining precise evaluation criteria, including training and testing sets, evaluation measures, and user-independent and sensor-placement independent evaluations. Based on this, we report a systematic study of the relevance of statistical and frequency features based on the information theoretical criteria to inform recognition systems. We then systematically report the reference performance obtained on all the identified recognition scenarios using a machine-learning recognition pipeline. The extent of this analysis and the clear definition of the recognition tasks enable future researchers to evaluate their own methods in a comparable manner, thus contributing to further advances in the field. The dataset and the code are available online. http://www.shl-dataset.org/.

There is growing interest in monitoring gait patterns in people with neurological conditions. The democratisation of wearable inertial sensors has enabled the study of gait in free living environments. One pivotal aspect of gait assessment in uncontrolled environments is the ability to accurately recognise gait instances. Previous work has focused on wavelet transform methods or general machine learning models to detect gait; the former assume a comparable gait pattern between people and the latter assume training datasets that represent a diverse population. In this paper, we argue that these approaches are unsuitable for people with severe motor impairments and their distinct gait patterns, and make the case for a lightweight personalised alternative. We propose an approach that builds on top of a general model, fine-tuning it with personalised data. A comparative proof-of-concept evaluation with general machine learning (NN and CNN) approaches and personalised counterparts showed that the latter improved the overall accuracy in 3.5% for the NN and 5.3% for the CNN. More importantly, participants that were ill-represented by the general model (the most extreme cases) had the recognition of gait instances improved by up to 16.9% for NN and 20.5% for CNN with the personalised approaches. It is common to say that people with neurological conditions, such as Parkinson’s disease, present very individual motor patterns, and that in a sense they are all outliers; we expect that our results will motivate researchers to explore alternative approaches that value personalisation rather than harvesting datasets that are may be able to represent these differences.

Breathing rate is considered one of the fundamental vital signs and a highly informative indicator of physiological state. Given that the monitoring of heart activity is less complex than the monitoring of breathing, a variety of algorithms have been developed to estimate breathing activity from heart activity. However, estimating breathing rate from heart activity outside of laboratory conditions is still a challenge. The challenge is even greater when new wearable devices with novel sensor placements are being used. In this paper, we present a novel algorithm for breathing rate estimation from photoplethysmography (PPG) data acquired from a head-worn virtual reality mask equipped with a PPG sensor placed on the forehead of a subject. The algorithm is based on advanced signal processing and machine learning techniques and includes a novel quality assessment and motion artifacts removal procedure. The proposed algorithm is evaluated and compared to existing approaches from the related work using two separate datasets that contains data from a total of 37 subjects overall. Numerous experiments show that the proposed algorithm outperforms the compared algorithms, achieving a mean absolute error of 1.38 breaths per minute and a Pearson’s correlation coefficient of 0.86. These results indicate that reliable estimation of breathing rate is possible based on PPG data acquired from a head-worn device.

Scientific advances build on reproducible researches which need publicly available benchmark data sets. The computer vision and speech recognition communities have led the way in establishing benchmark data sets. There are much less data sets available in mobile computing, especially for rich locomotion and transportation analytics. This paper presents a highly versatile and precisely annotated large-scale data set of smartphone sensor data for multimodal locomotion and transportation analytics of mobile users. The data set comprises seven months of measurements, collected from all sensors of four smartphones carried at typical body locations, including the images of a body-worn camera, while three participants used eight different modes of transportation in the south-east of the U.K., including in London. In total, 28 context labels were annotated, including transportation mode, participant's posture, inside/outside location, road conditions, traffic conditions, presence in tunnels, social interactions, and having meals. The total amount of collected data exceed 950 GB of sensor data, which corresponds to 2812 h of labeled data and 17 562 km of traveled distance. We present how we set up the data collection, including the equipment used and the experimental protocol. We discuss the data set, including the data curation process, the analysis of the annotations, and of the sensor data. We discuss the challenges encountered and present the lessons learned and some of the best practices we developed to ensure high quality data collection and annotation. We discuss the potential applications which can be developed using this large-scale data set. In particular, we present how a machine-learning system can use this data set to automatically recognize modes of transportations. Many other research questions related to transportation analytics, activity recognition, radio signal propagation and mobility modeling can be addressed through this data set. The full data set is being made available to the community, and a thorough preview is already published.

Abstract We present the concept of an Intelligent Assistant Carer system for the elderly, designed to help with active aging and to facilitate the interactions with carers. The system is modular, allowing the users to choose the appropriate functions according to their needs, and is built on an open platform in order to make it compatible with third-party products and services. Currently, the system consists of a wearable device (a smartwatch) and an internet portal that manages the data and takes care of the interactions between the user, the carers, and the support services. We present in detail one of the modules, i.e., fall detection, and the results of a pilot study for the system on 150 users over the course of 3 months.

With the development of technology allowing for a rapid expansion of data science and machine learning in our everyday lives, a significant gap is forming in the global job market where the demand for qualified workers in these fields cannot be properly satisfied. This worrying trend calls for an immediate action in education, where these skills must be taught to students at all levels in an efficient and up-to-date manner. This paper gives an overview of the current state of data science and machine learning education globally and both at the high school and university levels, while outlining some illustrative and positive examples. Special focus is given to vocational education and training (VET), where the teaching of these skills is at its very beginning. Also presented and analysed are survey results concerning VET students in Slovenia, Serbia, and North Macedonia, and their knowledge, interests, and prerequisites regarding data science and machine learning. These results confirm the need for development of efficient and accessible curricula and courses on these subjects in vocational schools.

Understanding people’s eating habits plays a crucial role in interventions promoting a healthy lifestyle. This requires objective measurement of the time at which a meal takes place, the duration of the meal, and what the individual eats. Smartwatches and similar wrist-worn devices are an emerging technology that offers the possibility of practical and real-time eating monitoring in an unobtrusive, accessible, and affordable way. To this end, we present a novel approach for the detection of eating segments with a wrist-worn device and fusion of deep and classical machine learning. It integrates a novel data selection method to create the training dataset, and a method that incorporates knowledge from raw and virtual sensor modalities for training with highly imbalanced datasets. The proposed method was evaluated using data from 12 subjects recorded in the wild, without any restriction about the type of meals that could be consumed, the cutlery used for the meal, or the location where the meal took place. The recordings consist of data from accelerometer and gyroscope sensors. The experiments show that our method for detection of eating segments achieves precision of 0.85, recall of 0.81, and F1-score of 0.82 in a person-independent manner. The results obtained in this study indicate that reliable eating detection using in the wild recorded data is possible with the use of wearable sensors on the wrist.

Falls are a significant threat to the health and independence of elderly people and represent an enormous burden on the healthcare system. Successfully predicting falls could be of great help, yet this requires a timely and accurate fall risk assessment. Gait abnormalities are one of the best predictive signs of underlying locomotion conditions and precursors of falls. The advent of wearable sensors and wrist-worn devices provides new opportunities for continuous and unobtrusive monitoring of gait during daily activities, including the identification of unexpected changes in gait. To this end, we present in this paper a novel method for determining gait abnormalities based on a wrist-worn device and a deep neural network. It integrates convolutional and bidirectional long short-term memory layers for successful learning of spatiotemporal features from multiple sensor signals. The proposed method was evaluated using data from 18 subjects, who recorded their normal gait and simulated abnormal gait while wearing impairment glasses. The data consist of inertial measurement unit (IMU) sensor signals obtained from smartwatches that the subjects wore on both wrists. Numerous experiments showed that the proposed method provides better results than the compared methods, achieving 88.9% accuracy, 90.6% sensitivity, and 86.2% specificity in the detection of abnormal walking patterns using data from an accelerometer, gyroscope, and rotation vector sensor. These results indicate that reliable fall risk assessment is possible based on the detection of walking abnormalities with the use of wearable sensors on a wrist.

This study introduces two datasets for multimodal research on cognitive load inference and personality traits. Different to other datasets in Affective Computing, which disregard participants’ personality traits or focus only on emotions, stress, or cognitive load from one specific task, the participants in our experiments performed seven different tasks in total. In the first dataset, 23 participants played a varying difficulty (easy, medium, and hard) game on a smartphone. In the second dataset, 23 participants performed six psychological tasks on a PC, again with varying difficulty. In both experiments, the participants filled personality trait questionnaires and marked their perceived cognitive load using NASA-TLX after each task. Additionally, the participants’ physiological response was recorded using a wrist device measuring heart rate, beat-to-beat intervals, galvanic skin response, skin temperature, and three-axis acceleration. The datasets allow multimodal study of physiological responses of individuals in relation to their personality and cognitive load. Various analyses of relationships between personality traits, subjective cognitive load (i.e., NASA-TLX), and objective cognitive load (i.e., task difficulty) are presented. Additionally, baseline machine learning models for recognizing task difficulty are presented, including a multitask learning (MTL) neural network that outperforms single-task neural network by simultaneously learning from the two datasets. The datasets are publicly available to advance the field of cognitive load inference using commercially available devices.

Short-term load forecasting is integral to the energy planning sector. Various techniques have been employed to achieve effective operation of power systems and efficient market management. We present a scalable system for day-ahead household electrical energy consumption forecasting, named HousEEC. The proposed forecasting method is based on a deep residual neural network, and integrates multiple sources of information by extracting features from (i) contextual data (weather, calendar), and (ii) the historical load of the particular household and all households present in the dataset. Additionally, we compute novel domain-specific time-series features that allow the system to better model the pattern of energy consumption of the household. The experimental analysis and evaluation were performed on one of the most extensive datasets for household electrical energy consumption, Pecan Street, containing almost four years of data. Multiple test cases show that the proposed model provides accurate load forecasting results, achieving a root-mean-square error score of 0.44 kWh and mean absolute error score of 0.23 kWh, for short-term load forecasting for 300 households. The analysis showed that, for hourly forecasting, our model had 8% error (22 kWh), which is 4 percentage points better than the benchmark model. The daily analysis showed that our model had 2% error (131 kWh), which is significantly less compared to the benchmark model, with 6% error (360 kWh).

Although wearable accelerometers can successfully recognize activities and detect falls, their adoption in real life is low because users do not want to wear additional devices. A possible solution is an accelerometer inside a wrist device/smartwatch. However, wrist placement might perform poorly in terms of accuracy due to frequent random movements of the hand. In this paper we perform a thorough, large-scale evaluation of methods for activity recognition and fall detection on four datasets. On the first two we showed that the left wrist performs better compared to the dominant right one, and also better compared to the elbow and the chest, but worse compared to the ankle, knee and belt. On the third (Opportunity) dataset, our method outperformed the related work, indicating that our feature-preprocessing creates better input data. And finally, on a real-life unlabeled dataset the recognized activities captured the subject’s daily rhythm and activities. Our fall-detection method detected all of the fast falls and minimized the false positives, achieving 85% accuracy on the first dataset. Because the other datasets did not contain fall events, only false positives were evaluated, resulting in 9 for the second, 1 for the third and 15 for the real-life dataset (57 days data).