Participative Urban Health and Healthy Aging in the Age of AI

The fast growth of the IoT and the unlimited possibilities in terms of applications and processing brought forth by the 5G which is around the corner is making IoT an active part of the activity of daily living. Those massive architectures become then the target of security issues, broken services, broken hardware or malfunctioning of applications. Moreover, in a system of million connected devices, operating each one of them is impossible making the platform unmaintainable. In this study, we present our attempt to achieve the autonomy of IoT infrastructure and we present some of the existing and recurrent issues undermining the IoT architecture. Then we review existing self-healing techniques that enable a system to be autonomous and solve issues. We also described our IoT platform that targets the self-healing concern. Finally, we point out some recommendations to make an overall reliable, resilient IoT system with cognitive entities for self-management.

We aim to facilitate the daily-life activities of frail or elderly people in collaboration with mobile assistive robots through the means of a digital twin-powered smart home. Being able to quickly and efficiently produce a digital twin of the human user’s environment, can help to further develop personalized assistive solutions. As our first investigation toward this goal, we describe our proof-of-concept “digital twin-driven smart home” implementation. It consists of a virtual representation, robot navigation and environment semantics using open-source software. The initial obtained results on the building process of the digital twin are encouraging and suggest the possibility of integration of digital twin for smart spaces.

Formal method techniques are used to model complex systems as mathematical entities. By building mathematical rigorous models of IoT design patterns, it is possible to verify their properties in a thorough fashion. In this paper, we propose a refinement-based approach for modeling IoT design patterns. It allows the modeling of correct by construction IoT design patterns. It takes advantage of formal methods by the specification of design pattern models with the Event-B method and checking the design correctness. Our goal is to design IoT patterns proven correct by construction to successfully apply them and promote their reuse. Our approach is experimented through pattern examples and we illustrate it with a case study in the health care domain.

The rapid advancement of the Internet of Things (IoT) has reshaped the industrial system, agricultural system, healthcare systems, and even our daily livelihoods, as the number of IoT applications is surging in these fields. Still, numerous challenges are imposed when putting in place such technology at large scale. In a system of millions of connected devices, operating each one of them manually is impossible, making IoT platforms unmaintainable. In this study, we present our attempt to achieve the autonomy of IoT infrastructure by building a platform that targets a dynamic and quick Plug and Play (PnP) deployment of the system at any given location, using predefined pipelines. The platform also supports real-time data processing, which enables the users to have reliable and real-time data visualization in a dynamic dashboard.

In the literature, a wide number of annotation systems in the e-health sector have been implemented. These systems are distinguished by a number of aspects. In fact, each of these systems is based on a different paradigm, resulting in a jumbled and confused vision. The purpose of this study is to categorize medical annotation systems in order to provide a standardized overview. To accomplish this, we combed through twenty years’ worth of scientific literature on annotation systems. Then, we utilized five filters to determine which systems would proceed to the classification phase. The following filters have been chosen: accessible, free, web-based or stand-alone, easily installable, functional, availability of documentation. The classification step is performed on systems that evaluate “true” for all of these filters. This classification is based on three modules: the publication module, the general information module and the functional module. This research gave us the chance to draw attention to the issues that healthcare professionals may face when using these systems in their regular work.

With the rise of the digital age, life has become a lot easier for the vast majority of the population. However, the ever-increasing elderly population has suffered, especially in countries like Pakistan, where limited accessibility to technology, often due to language barriers, hinders elderly from reaping technological benefits. In this paper, an Urdu virtual assistant application is proposed which provides an intuitive and empathetic platform for the elderly in Pakistan that helps them perform essential tasks such as reminding them of their medications, organising their work, getting daily news highlights, and connecting them with their loved ones. It also provides entertainment in the form of user-specified video playlists or by positively engaging them in conversations on various topics.

This study evaluated a smart technology intervention in the home as a support for individuals with severe mental illness. This study recruited 13 participants in a variety of community-based homes. Participants were offered a smartphone, a touchscreen monitor and health devices such as smartwatches, weigh-scales, and automated medication dispensers. Data was exported to the Lawson Integrated DataBase for care providers to monitor/track. Interviews with participants and focus groups with participants and care providers were conducted at baseline, 6-months and 12-months, and survey instruments were used to collect quantitative data about different dimensions of health and social determinants. Descriptive statistics from these outcome measures are presented as the sample size was too small for meaningful statistical inference. Qualitative analyses revealed a high degree of acceptability of the devices and motivation for healthy living, communication and mental health. Health Care Providers also noted improvements to client health. This study proves the feasibility of deploying smart technologies to support individuals with severe mental illness. Future scale-up would further our understanding of their impacts.

Mobility is essential for older adults to keep a good level of socialization, health and well-being. Still, aging is often accompanied by multiple mobility-related challenges. Hence, these mobility limitations make travel and use of public transport a big challenge. Numerous mobility trip planner tools can be found now days. However, they are not adapted to older adults’ needs and preferences. We discuss in this paper our attempt to develop a one-stop platform to help older adults in their mobility where, when, and how they want. We introduce our co-creation approach, our software architecture, as well as our first prototype.

Patients discharged from hospitals following the onset of an acute illness or injury rendered with disabling conditions require systematic medical-based and rehabilitation-focused sports and exercise programs accessible in their communities. This proposal aims to build a data-driven smart health system that allows people with disabilities to continuously improve their health by alleviating modifiable factors, including architectural barriers and related challenges following discharge from an inpatient hospital or rehabilitation course. Our goal is to promote a multi-ministerial data-driven innovative medical exercise system using a digital living lab platform as a testbed program to provide lifestyle exercise and physical education for community-dwelling individuals with disabilities. The pilot program of services will be rendered at the living lab center of the National Rehabilitation Center, equipped with data servers for storing accumulated pertinent information and continuous data acquisition. We envision an encrypted data collection and acquisition system, whereby newly acquired data will be merged with data information from original records of individuals generated during the inpatient hospital course.

Building Energy Management (BEM) and monitoring systems should not only consider HVAC systems and building physics but also human behaviors. These systems could provide information and advice to occupants about the significance of their practices with regard to the current state of a dwelling. It is also possible to provide services such as assistance to the elderly, comfort and health monitoring. For this, an intelligent building must know the daily activities of its residents and the algorithms of the smart environment must track and recognize the activities that the occupants normally perform as part of their daily routine. In the literature, deep learning is one of effective supervised learning model and cost-efficient for real-time HAR, but it still struggles with the quality of training data (missing values in time series and non-annotated event), the variability of data, the data segmentation and the ontology of activities. In this work, recent research works, existing algorithms and related challenges in this field are firstly highlighted. Then, new research directions and solutions (performing fault detection and diagnosis for drift detection, multi-label classification modeling for multi-occupant classification, new indicators for training data quality, new metrics weighted by the number of representations in dataset to handle the issue of missing data and finally language processing for complex activity recognition) are suggested to solve them respectively and to improve this field.

The COVID-19 pandemic has flooded a vast amount of information into the world. To help control this situation, good utilization of the overflow in data is required. However, data come in different forms, posing numerous challenges in subsequent processing. Therefore, a uniform knowledge representation of COVID-19 information is needed, and ontology can play a role. The ontology will model patient healthcare-related data, ranging from symptoms to side effects and medical conditions, and the necessary precautions, especially for healthcare workers, to obtain protection from the COVID-19 virus. We followed Sánchez’s methodology to build the vocabularies, which include current ontology concepts, W3C standards RDF, OWL and SWRL. This work shows promising results that can be applied by different organizations.

The COVID-19 pandemic took a toll on the world’s healthcare infrastructure as well as its social, economic, and psychological well-being. In particular, Italy’s unexpectedly high COVID-19 case and death rate from March to June, 2020, captured headlines due to its speed and virulence. Many governments are currently implementing measures to help contain and slow down the spread of COVID-19. The Social Response to Covid-19 Smart Dashboard was built by researchers at the Metabolism of Cities Living Lab, Center for Human Dynamics in the Mobile Age at San Diego State University and Politecnico di Milano. This dashboard provides an aggregated view of what people in 10 Italian metropolitan cities (Milan, Venice, Turin, Bologna, Florence, Rome, Naples, Bari, Palermo, and Cagliari) tweet during the pandemic by monitoring social media behaviors in the north, center, south, and islands. Moreover, the dashboard is a geo-targeted search tool for Twitter messages to monitor the diffusion of information and social behavior changes which provides an automatic procedure to help researchers to: associate tweets based on geography differences, filter noises such as removing redundant retweets and using machine learning methods to improve precisions, analyze social media data from a spatiotemporal perspective, and visualize social media data in various aspects such as weekly trends, top urls, top retweets, top mentions, and top hashtags. The Social Response to Covid-19 SMART Dashboard provides a useful tool for policy makers, city planners, research organizations, and health officials to monitor real-time societal perceptions using social media.

The coronavirus known as COVID-19 is the topic of the hour all over the world. This virus has invaded the world with its invariants, which are characterized by their rapid spread. COVID-19 has impacted the health of people and the economy of countries. For that, laboratories, researchers, and doctors are in a race against time to find a cure for this pandemic. To combat this virus, cutting-edge technologies such as artificial intelligence, cloud computing, and big data have been put in place. In our work, we use Internet of Things (IoT) technology. The use of IoT in an efficient way can lead to detecting infected people and avoiding being contaminated. In this paper, we are interested in the remote medical monitoring of patients who have tested positive for COVID-19. We propose a meta-modeling technique to model the IoT architecture. Then we implement two IoT solutions that permit the remote medical monitoring of patients infected with COVID-19 and the respect of social distancing by instantiating correct models that conform to the proposed meta-model in order to mitigate the COVID-19 outbreak.

For medical treatments, pain is often measured by self-report. However, the current subjective pain assessment highly depends on the patient’s response and is therefore unreliable. In this paper, we propose a physiological-signals-based objective pain recognition method that can extract new features, which have never been discovered in pain detection, from electrodermal activity (EDA) and electrocardiogram (ECG) signals. To discriminate the absence and presence of pain, we establish four classification tasks and build four tree-based classifiers, including Random Forest, Adaptive Boosting (AdaBoost), eXtreme Gradient Boosting (XGBoost), and TabNet. The comparative experiments demonstrate that our method using the EDA and ECG features yields accurate classification results. Furthermore, the TabNet achieves a large accuracy improvement using our ECG features and a classification accuracy of 94.51% using the features selected from the fusion of the two signals.

To improve the QoL of the elderly, it is essential to predict their stress states. In general, the stress state varies from day to day or time to time depending on what activities are performed and how long/strong. However, most existing studies predict the stress state using biometric data and specific activities (e.g., sleep time, exercise time and amount) as explanatory variables, but do not consider all daily living activities. Therefore, it is necessary to predict the stress state by linking various daily living activities and biometric information. In this paper, we propose a method to improve the prediction accuracy of stress estimation by linking daily living activities data and biometric data. Specifically, we construct a machine learning model in which the objective variable is the result of a stress status questionnaire obtained every morning and evening, and the explanatory variables are the types of daily living activities performed in the 24 h prior to the questionnaire and the feature values calculated from the biometric data during each of the performed activities. The results of the evaluation experiments using the one month data collected from five elderly households, show that the proposed method (using per-activity biometric features) improves the prediction accuracy by more than 10% from the baseline methods (with biometric features without considering activities).

This study is preliminary research to develop a smart cradle for women with spinal cord injury. The purpose of this study was to investigate the needs for improvement of the product and important factors related to product development. A focus group interview was conducted with a total of 5 women with spinal cord injury who had experienced parenting after spinal cord injury. After recording all of the focus group interviews, researchers individually analyzed the content and integrated the results. Easy access cradle design for wheelchair users, attachment of wheelchair and cradle when moving at home, an open and lockable door one side of the cradle were required in cradle structures. Electronic height adjustment, bounce mode, children’s motion sensor, and function linked with a smartphone should be reflected in the development of the cradle. This result is meaningful in that it suggests points to be considered in the process of developing an assistive device by reflecting the desire to understand the grievance women with spinal cord injury when parenting.

The wheelchair cushion is one of the intervention methods for preventing pressure ulcers in people with spinal cord injuries. Recently, a customized wheelchair cushion along with off-loading technology that distributes pressure by removing the seat surface in contact with the bony protrusion of the buttocks in the sitting position is attracting attention. In spite of this, they are exposed to the risk of secondary pressure ulcers because they cannot recognize their body pressure distribution and unintended posture changes due to sensory dysfunction. Accordingly, we developed an ICT-based off-loading cushion that can monitor the pressure distribution and pelvis alignment in a sitting position in real-time. People with spinal cord injuries who participated in the pilot study were satisfied with the device and service, and the ICT-based customized off-loading cushion had a positive psychosocial effect on them. We hope that this will contribute to improving the quality of life by preventing pressure ulcers in people with spinal cord injuries.

Some diseases are characterized by persistent deficits in brain activity. Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder. It appears in early childhood and evolves throughout life and needs to be detected early to accelerate the treatment and recovery process. These deficits may be detected using medical imaging techniques. In this paper, we present machine learning algorithms allowing to detect peoples with ASD from normal peoples. We used data from the ABIDE dataset. We tested 3 algorithms: Support Vector Machines (SVM), Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN). The best result was obtained using CNN algorithm with an accuracy equal to 95%.

Magnetic resonance imaging (MRI) has quickly established itself as the reference imaging tool for the management of patients suffering from multiple sclerosis (MS), both for the diagnosis and the follow-up of the evolution and evaluation of the impact of new therapies.

The treatment of multiple sclerosis does not cure the disease, but it slows its progression and can help to space out attacks. In this paper, tumor segmentation is treated as a problem of classification using the Ant Colony optimization algorithm (ACO) combined with a proposed protocol based on BrainSeg3D tools. Many studies and many existing approaches tend the multiple sclerosis (MS) which is a chronic inflammatory anomaly of the central nervous system.

The aim of this work is to evaluate and to verify the effectiveness of the proposed protocol on a public longitudinal database which contains 20 MS patients. This study is concerned with comparing these results against the ground truth performed by two experts and against other methods namely Dissimilarity Map (DM) creation and segmentation in terms of Dice Similarity Coefficient (DSC).

As the number of people with disabilities continues to increase, difficulties in dressing activities for people with disabilities are also increasing. However, the currently available clothing for the disabled do not satisfy their functional and aesthetic needs. Therefore, this study aims to contribute to vitalizing the development of clothing for the disabled in Korea by collecting domestic study on the development of clothing for the disabled and analyzing them in various areas. Finally, 5 studies were selected. As a result of classifying into 4 areas of body type, considerations, points for improvement, and design, it can be used as basic data for study related to the development of clothing for the disabled.

With life expectancy growing rapidly over the past century, societies are being increasingly faced with a need to find smart living solutions for elderly care and active ageing. The e-VITA project, which is a joint European (H2020) and Japanese (MIC) funded project, is based on an innovative approach to virtual coaching that addresses the crucial domains of active and healthy ageing. In this paper we describe the role of spoken dialogue technology in the project. Requirements for the virtual coach were elicited through a process of participatory design in workshops, focus groups, and living labs, and a number of use cases were identified for development using the open-source RASA framework. Knowledge Graphs are used as a shared representation within the system, enabling an integration of multimodal data, context, and domain knowledge.

Smart Home Technology (SHT) as assistive technology (AT) is becoming an important active research field in the field of rehabilitation. For this purpose, Home Modification (HM) is one of the most common ways to improve the quality of life of the Persons with physical disabilities (PwPD). In this context, we propose a new Smart Home-based Home Modification Program (SHbHM) to improve the quality of life for PwPD. Our method simply uses Bluetooth or extends to Wi-Fi and Zigbee networks. A pilot study was conducted with five PwPD at home to investigate the effectiveness of the program. The reported results show a high quality of life, and the occupational performance and satisfaction are greatly improved, indicating that it is an efficient alternative.

Wearing a mask is an effective measure that prevents the spread of respiratory droplets into the air and thereby curtails the dissemination of coronavirus. Unfortunately, despite the proven effectiveness, the idea of wearing a face mask has difficulty being accepted by part of the population. To address this significant health concern, we present a monitoring system that automatically detects whether a mask is put appropriately over a face. The system annotates the videos that are provided by cameras. In this article, we present a comparative study of machine learning models (i.e., SVM, RNN, LSTM, CNN, auto-encoder, MobileNetV2, Net-B3, VGG-16, VGG-19, Resnet-152).

An integral part in the comprehensive care of HIV and a significant health service is contraception, however research carried out to evaluate the perception and utilization of contraception among HIV positive men are few. This research aim to determine the knowledge, perception and uptake of contraception among HIV positive male patients at Saye-Zaria. This was a descriptive, cross-sectional study with collection of quantitative data through questionnaire and qualitative data with Focused group discussion (FGD). The majority (85.1%) of respondents have heard about contraception, most had good perception, and only 61.9% of the respondents have ever used contraception. There was a significant association between level of education and perception. In conclusion there was high knowledge, low usage and poor acceptance of contraception. Therefore, the government should put adequate policies in place to encourage male involvement in the utilization of contraception.

This paper presents AcousticPAD, a contactless and robust handwriting recognition system that extends the input and interactions beyond the touchscreen using acoustic signals, thus very useful under the impact of the COVID-19 epidemic. To achieve this, we carefully exploit acoustic pulse signals with high accuracy of time of fight (ToF) measurements. Then we employ trilateration localization method to capture the trajectory of handwriting in air. After that, we incorporate a data augmentation module to enhance the handwriting recognition performance. Finally, we customize a back propagation neural network that leverages augmented image dataset to train a model and recognize the acoustic system generated handwriting characters. We implement AcousticPAD prototype using cheap commodity acoustic sensors, and conduct extensive real environment experiments to evaluate its performance. The results validate the robustness of AcousticPAD, and show that it supports 10 digits and 26 English letters recognition at high accuracies.

The presented demonstrated working tools in the initial version constitute the foundation of the novel ALS and MS management and monitoring, leveraging extended IoT sensing and emerging instruments infrastructure, and a basis for integration of more advanced and effective AI models (in development) for disease progression prediction, patient stratification and ambiental exposure assessment.