Search

Microservice-based systems promote agility and rapid business development. Some features, such as fast time-to-market, scalability and optimal response times, have encouraged stakeholders to get more involved in the development and implementation of microservices architectures in order to translate their business vision into the implementation of the architecture. Although some techniques allow the inclusion of the stakeholders' perspective in the design of microservice architectures, few proposals consider such perspectives in the selection and evaluation of technologies that implement microservice architectures. Indeed, the qualities that characterize microservice-based systems strongly depend on the suitable selection of technologies, such as application frameworks and platforms. This article proposes a collaborative technique that includes stakeholders and software architects in the selection and evaluation of application frameworks and platforms to implement microservice-based systems. We evaluated the technique in an industrial case of design and implementation of an Ambient-Assisted Living (AAL) system, which combines microservice architecture and Internet-of-Medical-Things (IoMT) sensors. The case results indicate that the proposed technique supported stakeholders in the pragmatic evaluation of alternative technological solutions. Additionally, it allowed the implementation of an AAL system that satisfies the quality specifications of stakeholders and end-users. This initial study suggests that actively including stakeholders in the implementation of microservice-based systems allows architects to make design decisions that better consider stakeholders viewpoints as well as managing their expectations.

Stress is an increasingly prevalent mental health condition across the world. In Europe, for example, stress is considered one of the most common health problems, and over USD 300 billion are spent on stress treatments annually. Therefore, monitoring, identification and prevention of stress are of the utmost importance. While most stress monitoring is carried out through self-reporting, there are now several studies on stress detection from physiological signals using Artificial Intelligence algorithms. However, the generalizability of these models is only rarely discussed. The main goal of this work is to provide a monitoring proof-of-concept tool exploring the generalization capabilities of Heart Rate Variability-based machine learning models. To this end, two Machine Learning models are used, Logistic Regression and Random Forest to analyze and classify stress in two datasets differing in terms of protocol, stressors and recording devices. First, the models are evaluated using leave-one-subject-out cross-validation with train and test samples from the same dataset. Next, a cross-dataset validation of the models is performed, that is, leave-one-subject-out models trained on a Multi-modal Dataset for Real-time, Continuous Stress Detection from Physiological Signals dataset and validated using the University of Waterloo stress dataset. While both logistic regression and random forest models achieve good classification results in the independent dataset analysis, the random forest model demonstrates better generalization capabilities with a stable F1 score of 61%. This indicates that the random forest can be used to generalize HRV-based stress detection models, which can lead to better analyses in the mental health and medical research field through training and integrating different models.

Thanks to wearable devices joint with AI algorithms, it is possible to record and analyse physiological parameters such as heart rate variability (HRV) in ambulatory environments. The main downside to such setups is the bad quality of recorded data due to movement, noises, and data losses. These errors may considerably alter HRV analysis and should therefore be addressed beforehand, especially if used for medical diagnosis. One widely used method to handle such problems is interpolation, but this approach does not preserve the time dependence of the signal. In this study, we propose a new method for HRV processing including filtering and iterative data imputation using a Gaussian distribution. The particularity of the method is that many physiological aspects are taken into consideration, such as HRV distribution, RR variability, and normal boundaries, as well as time series characteristics. We study the effect of this method on classification using a random forest classifier (RF) and compare it to other data imputation methods including linear, shape-preserving piecewise cubic Hermite (pchip), and spline interpolation in a case study on stress. Features from reconstructed HRV signals of 67 healthy subjects using all four methods were analysed and separately classified by a random forest algorithm to detect stress against relaxation. The proposed method reached a stable F1 score of 61% even with a high percentage of missing data, whereas other interpolation methods reached approximately 54% F1 score for a low percentage of missing data, and the performance drops to about 44% when the percentage is increased. This suggests that our method gives better results for stress classification, especially on signals with a high percentage of missing data.

This paper addresses the issue of the evaluation of technological devices for digital accessibility for people with disabilities or loss of autonomy. It builds on the work of a multidisciplinary consortium that has been set up at the national level to develop and propose a multidimensional evaluation and observation methodology based on an integrative co-design approach. The main qualitative and quantitative methods used by the partners in the field of digital accessibility are presented. Crossing the two methods from use contexts is essential to model and qualify behaviours in digital accessibility. The implementation of the methodology is illustrated by a pre-study on five volunteers in a smart home environment.

Internet of Things (IoT) is a domain that includes embedded devices connected to a network and used in multiple applications such as: transport, telecommunications, medicine, industrial field and many others. Medical Connected Devices are IoT devices and have their origins in wireless sensor networks and extend this concept by proposing applications in which embedded devices connected to the Internet help automate user tasks. Thus, IoT devices are imagined in multiple applications, from home scenarios (smart home) to clinical scenarios. Considering that IoT devices impact the medical practice and patient life, there is a pressing need for security mechanisms. Security is considered one of the most important IoT characteristics, but it is not considered a key factor influencing acceptance rate. Medical IoT devices are an attractive target for attackers, as they operate with private user data and can be used as an attack vector (for example, for DoS attacks). The peculiarity of the IoT context is that a security breach can endanger human lives or privacy, as well as causing economic damage. Another particular feature of the Medical IoT context is the difficulty of designing security solutions, due to the multiple limitations of the devices, including: hardware and software limitations, lack of input-output modules, installation scenarios and more. Given these particularities of IoT devices and adding the multitude of software and hardware platforms, along with the lack of standardization, there is a pressing need for new security solutions. Without complying with basic cyber security standards, many medical IoT manufacturers focus exclusively on the features of the devices they sell. In many cases, they do not check for vulnerabilities in the final version of the product, nor for the corresponding applications through which the product can be controlled. It could be negligence, but a more likely explanation is that this approach reduces production costs and speeds up product placement. In any case, this affects buyers who are likely to suffer financial consequences or lose sensitive information when hackers start exploiting the flaws.

Background: Evidence Based Medicine (EBM) represents the use of the best latest evidence obtained by systematic search together with personal clinical experience and patient values. Clinical evidences are quantified by a number of indicators. R is a free and powerful environment for statistical computing and graphics, used mainly in command line interface. The aim of this work was to create an extension for R Commander to offer a graphical user interface to calculate the most used EBM indicators. Materials and Methods: The extension was created in R and then tested in R 3.1.1 and R Commander 2.1-1. Results: The extension was successfully created and was named RcmdrPlugin.EBM, being available for download on Comprehensive R Archive Network servers. The extension creates a new menu called EBM, which offers an interface to calculate the following indicators with their confidence intervals: diagnosis (sensitivity, specificity, diagnostic accuracy, Youden’s index, positive/negative likelihood ratio, positive/negative predictive value, number needed to diagnose), therapeutic (absolute risk reduction, relative risk reduction, odds ratio, relative risk, number needed to treat/harm), prognostic (attributable risk, relative risk, odds ratio). Conclusion: It is now easy to compute EBM indicators in R, with the graphical user interface extension of R Commander.

We developed an instrument which can ensure a quick and easy dialogue between the physicians of the Oncology Institute and family physicians. The platform we chose was Simple Machines Forum (abbreviated as SMF), a free Internet forum (BBS - Bulletin Board System) application. The purpose of this article is not to detail the software platform, but to emphasize the facilities and advantages of using this solution in the medical community.

One of the principal issues in any university community is the lack of communication between community categories – leadership, administration, teaching staff and students. Sometimes is important to know in a short time the opinion of one particular group, without investing a lot of resources and without being extremely formal. The aim of this study was to test if an open-source platform – Moodle – can be used for quick surveys inside the Faculty of Medicine, UMF “Iuliu Hatieganu” Cluj-Napoca community. For this, on existing Moodle platform was installed one specific survey instrument – a questionnaire module and a survey containing a real life issue to the students of Faculty of Medicine was launched. The researchers have focused on how the specific problems of a survey - preparing of the survey, the survey process and the analysis of the results can be handle in Moodle. The pilot survey was a success; the conclusion of the study was that Moodle can be used as on-line survey instrument for that community.

Diabetic kidney disease is an important complication of type 2 diabetes mellitus (T2DM) and has an economic impact in growth due to the increasing prevalence of T2DM. Identification of diabetic kidney disease risk factors is a priority for both the patient and the healthcare system. The aim of our study was to rank the risk factors using VIKOR method applied on a database with patients with T2DM. Data from 53 T2DM patients were analyzed with VIKOR method. 18 possible risk factors were taken in consideration as alternatives and four separate criteria of renal function: two for albumin excretion – quantified as urinary albumin/creatinine ratio (UACR) and two for GFR (glomerular filtration rate). In the top of the VIKOR method hierarchy was serum adiponectin followed by triglycerides, systolic blood pressure, duration of diabetes and age. Malondialdehyde and HDL-cholesterol influenced chronic kidney disease as protective factors (18th, respective 17th position in the hierarchy). VIKOR method brought new information about the similarity between the positions of some factors in the hierarchy.

In this study, a bound-constrained optimization algorithm is applied for estimating physiological data (pulse and breathing rate) of human body using 60 GHz Doppler radar, by detecting displacements induced by breathing and the heartbeat of a human subject. The influence of mutual phasing between the two movements is analyzed in a theoretical framework and the application of optimization algorithms is proved to be able to accurately detect both breathing and heartbeat rates, despite intermodulation effects between them. Different optimization procedures are compared and shown to be more robust to receiver noise and artifacts of random body motion than a direct spectrum analysis. In case of a large-scale constrained bound, a parallel optimization procedure executed in subranges is proposed to realize accurate detection in a reduced span of time.

This paper addresses the development of a new technique in the sleep analysis domain. Sleep is defined as a periodic physiological state during which vigilance is suspended and reactivity to external stimulations diminished. We sleep on average between six and nine hours per night and our sleep is composed of four to six cycles of about 90 min each. Each of these cycles is composed of a succession of several stages of sleep that vary in depth. Analysis of sleep is usually done via polysomnography. This examination consists of recording, among other things, electrical cerebral activity by electroencephalography (EEG), ocular movements by electrooculography (EOG), and chin muscle tone by electromyography (EMG). Recordings are made mostly in a hospital, more specifically in a service for monitoring the pathologies related to sleep. The readings are then interpreted manually by an expert to generate a hypnogram, a curve showing the succession of sleep stages during the night in 30s epochs. The proposed method is based on the follow-up of the thermal signature that makes it possible to classify the activity into three classes: “awakening,” “calm sleep,” and “restless sleep”. The contribution of this non-invasive method is part of the screening of sleep disorders, to be validated by a more complete analysis of the sleep. The measure provided by this new system, based on temperature monitoring (patient and ambient), aims to be integrated into the tele-medicine platform developed within the framework of the Smart-EEG project by the SYEL–SYstèmes ELectroniques team. Analysis of the data collected during the first surveys carried out with this method showed a correlation between thermal signature and activity during sleep. The advantage of this method lies in its simplicity and the possibility of carrying out measurements of activity during sleep and without direct contact with the patient at home or hospitals.

Exergames have been proposed as a potential tool to improve the current practice of musculoskeletal rehabilitation. Inertial or optical motion capture sensors are commonly used to track the subject’s movements. However, the use of these motion capture tools suffers from the lack of accuracy in estimating joint angles, which could lead to wrong data interpretation. In this study, we proposed a real time quaternion-based fusion scheme, based on the extended Kalman filter, between inertial and visual motion capture sensors, to improve the estimation accuracy of joint angles. The fusion outcome was compared to angles measured using a goniometer. The fusion output shows a better estimation, when compared to inertial measurement units and Kinect outputs. We noted a smaller error (3.96°) compared to the one obtained using inertial sensors (5.04°). The proposed multi-sensor fusion system is therefore accurate enough to be applied, in future works, to our serious game for musculoskeletal rehabilitation.