Background: Blood pressure (BP) measurements have been used widely in clinical and private environments. Recently, the use of ECG monitors has proliferated; however, they are not enabled with BP estimation. We have developed a method for BP estimation using only electrocardiogram (ECG) signals. Methods: Raw ECG data are filtered and segmented, and, following this, a complexity analysis is performed for feature extraction. Then, a machine-learning method is applied, combining a stacking-based classification module and a regression module for building systolic BP (SBP), diastolic BP (DBP), and mean arterial pressure (MAP) predictive models. In addition, the method allows a probability distribution-based calibration to adapt the models to a particular user. Results: Using ECG recordings from 51 different subjects, 3129 30-s ECG segments are constructed, and seven features are extracted. Using a train-validation-test evaluation, the method achieves a mean absolute error (MAE) of 8.64 mmHg for SBP, 18.20 mmHg for DBP, and 13.52 mmHg for the MAP prediction. When models are calibrated, the MAE decreases to 7.72 mmHg for SBP, 9.45 mmHg for DBP and 8.13 mmHg for MAP. Conclusion: The experimental results indicate that, when a probability distribution-based calibration is used, the proposed method can achieve results close to those of a certified medical device for BP estimation.

Chronic heart failure (CHF) affects over 26 million of people worldwide, and its incidence is increasing by 2% annually. Despite the significant burden that CHF poses and despite the ubiquity of sensors in our lives, methods for automatically detecting CHF are surprisingly scarce, even in the research community. We present a method for CHF detection based on heart sounds. The method combines classic Machine-Learning (ML) and end-to-end Deep Learning (DL). The classic ML learns from expert features, and the DL learns from a spectro-temporal representation of the signal. The method was evaluated on recordings from 947 subjects from six publicly available datasets and one CHF dataset that was collected for this study. Using the same evaluation method as a recent PhysoNet challenge, the proposed method achieved a score of 89.3, which is 9.1 higher than the challenge's baseline method. The method's aggregated accuracy is 92.9% (error of 7.1%); while the experimental results are not directly comparable, this error rate is relatively close to the percentage of recordings labeled as “unknown” by experts (9.7%). Finally, we identified 15 expert features that are useful for building ML models to differentiate between CHF phases (i.e., in the decompensated phase during hospitalization and in the recompensated phase) with an accuracy of 93.2%. The proposed method shows promising results both for the distinction of recordings between healthy subjects and patients and for the detection of different CHF phases. This may lead to the easier identification of new CHF patients and the development of home-based CHF monitors for avoiding hospitalizations.

This paper proposes a system for the early automatic recognition of health problems that manifest themselves in distinctive form of gait. Purpose of the system is to prolong the autonomous living of the elderly at home. When the system identifies a health problem, it automatically notifies a physician and provides an explanation of the automatic diagnosis. The gait of the elderly user is captured using a motion-capture system, which consists of body-worn tags and wall-mounted sensors. The positions of the tags are acquired by the sensors and the resulting time series of position coordinates are analyzed with machine-learning algorithms in order to recognize a specific health problem. Novel semantic features based on medical knowledge for training a machine-learning classifier are proposed in this paper. The classifier classifies the user’s gait into: 1) normal, 2) with hemiplegia, 3) with Parkinson’s disease, 4) with pain in the back and 5) with pain in the leg. The studies of 1) the feasibility of automatic recognition and 2) the impact of tag placement and noise level on the accuracy of the recognition of health problems are presented. The experimental results of the first study (12 tags, no noise) showed that the k-nearest neighbors and neural network algorithms achieved classification accuracies of 100%. The experimental results of the second study showed that classification accuracy of over 99% is achievable using several machine-learning algorithms and 8 or more tags with up to 15 mm standard deviation of noise. The results show that the proposed approach achieves high classification accuracy and can be used as a guide for further studies in the increasingly important area of Ambient Assisted Living. Since the system uses semantic features and an artificial-intelligence approach to interpret the health state, provides a natural explanation of the hypothesis and is embedded in the domestic environment of the elderly person; it is an example of the semantic ambient media for Ambient Assisted Living.

Ambient intelligence (AmI) is intrinsically and thoroughly connected with artificial intelligence (AI). Some even say that it is, in essence, AI in the environment. AI, on the other hand, owes its success to the phenomenal development of the informat

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.

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).