How AI Impacts Urban Living and Public Health

Although emerging IoT paradigms in sleep tracking have a substantial contribution to enhancing current healthcare systems, there are several privacy and security considerations that end-users need to consider. End-users can be susceptible to malicious threats when they allow permission to potentially vulnerable or leaky third-party apps. Since the data is migrated to the cloud, it goes over insecure communication channels, all of which have their security concerns. Moreover, there are alternative data violation concerns when the data projects into the proprietor’s cloud storage facility. In this study, we present some of the existing IoT sleep trackers, also we discuss the most common features associated with these sleep trackers. As the majority of end-users are not aware of the privacy and security concerns affiliated with emerging IoT sleep trackers. We review existing solutions that can apply to IoT sleep tracker architecture. Also, we describe a deployed IoT platform that can address these concerns. Finally, we provide some of the recommendations to end-users and service providers to ensure a safer approach while leveraging the IoT sleep tracker in caregiving. This incorporates recommendations for software updates, awareness programs, software installation, and social engineering.

Mild Cognitive Impairment (MICI) symptoms are one of the main issues that contribute, in older people, to the difficulty to live independently, social isolation and loss of autonomy. INFINITy solution provides a set of services aimed to reinforce and support the daily routines of people with MCI for both indoor and outdoor scenarios. A co-design session with end-users were performed in order to better adapt the INFINITy solution to the needs and characteristics of the target beneficiaries. Results show the feedback received form end-users regarding different aspects of the solution such as: functionalities, use cases, and interfaces. The results were useful to improve the INFINITy solution to better address user’s needs and preferences.

Today, numerous factors are causing a demographic change in many countries in the world. This change is producing a nearly balanced society share between the young and aging population. The noticeable increasing aging population is causing different economical, logistical and societal problems. In fact, aging is associated with chronic diseases in addition to physical, psychological, cognitive and societal changes. These changes are considered as indicators of aging peoples’ frailty. It is therefore important to early detected these changes to prevent isolation, sedentary lifestyle, and even diseases in order to delay the frailty period. This paper presents an experiment deployment of an Internet of Thing solution for the continuous monitoring and detection of elderly people’s behavior changes. The objective is to help geriatricians detect sedentary lifestyle and health-related problems at an early stage.

Smart home refers to the independency and comfort that are ensured by remote monitoring and assistive services. Assisting an elderly person requires identifying and accurately predicting his/her normal and abnormal behaviors. Abnormal behaviors observed during the completion of activities of daily living are a good indicator that the person is more likely to have health and behavioral problems that need intervention and assistance. In this paper, we propose a method, based on long short-term memory recurrent neural networks (LSTM), to automatically predicting an elderly person’s abnormal behaviors. Our method allows to model the temporal information expressed in the long sequences collected over time. Our study aims to evaluate the performance of LSTM on identifying and predicting elderly persons abnormal behaviors in smart homes. We experimentally demonstrated, through extensive experiments using a dataset, the suitability and performance of the proposed method in predicting abnormal behaviors with high accuracy. We also demonstrated the superiority of the proposed method compared to the existing state-of-the-art methods.

This paper addresses a new problem of automatic detection of visual attention in older adults based on their driving speed. All state-of-the-art methods try to understand the on-road performance of older adults by means of the Useful Field of View (UFOV) measure. Our method takes advantage of deep learning models such as Long-short Term Memory (LSTM) to automatically extract features from driving speed data for predicting drivers’ visual attention. We demonstrate, through extensive experiments on real dataset, that our method is able to predict the driver’s visual attention based on driving speed with high accuracy.

We discuss in this paper a study of a smart and unobtrusive mattress in a clinical setting on a population with cardiorespiratory problems. Up to recently, the vast majority of studies with unobtrusive sensors are done with healthy populations. The unobtrusive monitoring of the Respiratory Rate (RR) is essential for proposing better diagnoses. Thus, new industrial and research activity on smart mattresses is targeting respiratory rate in an Internet-of-Things (IoT) context. In our work, we are interested in the performances of a microbend fiber optic sensor (FOS) mattress on 81 subjects admitted in the Cardiac Intensive Care Unit (CICU) by estimating the RR from their ballistocardiograms (BCG). Our study proposes a new RR estimator, based on harmonic plus noise models (HNM) and compares it with known estimators such as MODWT and CLIE. The goal is to examine, using a more representative and bigger dataset, the performances of these methods and of the smart mattress in general. Results of applying these three estimators on the BCG show that MODWT is more accurate with an average mean absolute error (MAE) of \(1.97\,\pm \,2.12\;\text {BPM}\). However, the HNM estimator has space for improvements with estimation errors of \(2.91 \pm 4.07\;\text {BPM}\). The smart mattress works well within a standard RR range of 10–20 breaths-per-minute (BPM) but gets less accurate with a bigger range of estimation. These results highlight the need to test these sensors in much more realistic contexts .

The quality of sleep has a significant impact on health and life. This study adopts the structure of hierarchical classification to develop an automatic sleep stage classification system using ballistocardiogram (BCG) signals. A leave-one-subject-out cross validation (LOSO-CS) procedure is used for testing classification performance. Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM), and Deep Neural Networks DNNs are complementary in their modeling capabilities; while CNNs have the advantage of reducing frequency variations, LSTMs are good at temporal modeling. A transfer learning (TL) technique is used to pre-train our CNN model on posture data and then fine-tune it on the sleep stage data. We used a ballistocardiography (BCG) bed sensor to collect both posture and sleep stage data to provide a non-invasive, in-home monitoring system that tracks changes in health of the subjects over time. Polysomnography (PSG) data from a sleep lab was used as the ground truth for sleep stages, with the emphasis on three sleep stages, specifically, awake, rapid eye movement (REM) and non-REM sleep (NREM). Our results show an accuracy of 95.3%, 84% and 93.1% for awake, REM and NREM respectively on a group of patients from the sleep lab.

In this paper, we present a convolutional gated recurrent neural network (CGRNN) to predict epileptic seizures based on features extracted from EEG data that represent the temporal aspect and the frequency aspect of the signal. Using a dataset collected in the Children’s Hospital of Boston, CGRNN can predict epileptic seizures between 35 min and 5 min in advance. Our experimental results indicate that the performance of CGRNN varies between patients. We achieve an average sensitivity of 89% and a mean accuracy of 75.6% for the patients in the data set, with a mean False Positive Rate (FPR) of 1.6 per hour.

Chronic Obstructive Pulmonary Disease (COPD) is a severe lung illness that causes a progressive deterioration in the function and structure of the respiratory system. Recently, COPD became the fifth cause of mortality and the seventh cause of morbidity in Canada. The advancement of context-aware technology creates a new and important opportunity to transform the standard shape of healthcare services into a more dynamic and interactive form. This research project design and validates a rule-based ontology-reasoning framework that provides a context-aware system for COPD patients. The originality of the proposed approach consists in its methodology to prove the efficiency of this model in simulated examples of real-life scenarios based on collaborative data analysis, recognized by specialized medical experts.

This paper presents a deep learning approach for depressive episode detection on mobile devices, called DL4DED. It is based on a convolutional neural network and a long short-term memory network to identify the status of a patient’s voice extracted from spontaneous phone calls. To run DL4DED on mobile devices, two neural network model compression techniques are used: quantization and pruning. DL4DED protects data privacy, since it can be executed on a patient’s smartphone. Our proposal is validated on the DAIC-WOZ database. The obtained results show that the accuracy of DL4DED with model compression is only slightly lower than the accuracy of DL4DED without model compression. Furthermore, our experiments indicate that the power consumption of DL4DED is reasonably low.

People with Spinal cord injuries are having difficulty in health care, and complications cause physical, social and economic losses. In severe cases, complications lead to death and require systematic management. In this study, ICT-based health care service was developed to manage the respiratory function and urinary function of the people with spinal cord injuries and to help adapt to daily living activities and social participation through home visit occupational therapy. A pilot study was conducted with five clients with spinal cord injuries to investigate the effectiveness of the intervention services. As a result, it was confirmed that satisfaction, importance, and difficulty were appropriate. In the future, RCT clinical studies will be needed to diversify intervention services and expand the number of patients.

The overall objective of this research was to develop and test the use of smart technology in delivering safe, effective mental health services before expanding into community homes. A system was created that linked multiple screen devices such as smartphones and tablets and health monitoring devices with a central secure database for data to be funneled and stored for monitoring and tracking. In order to assess the feasibility of this technological innovation, the research team installed equipment in two prototype apartments at two inpatient psychiatric hospitals and in up to eight community homes operated by the Canadian Mental Health Association and London Middlesex Community Housing. The results indicate that most participants found the technology acceptable, and that the system was successfully able to export data securely.

Within the EU-funded Pulse project, we are implementing a data analytic platform designed to provide public health decision makers with advanced approaches to jointly analyze maps and geospatial information with health care data and air pollution measurements. In this paper we describe a component of such platform, designed to couple deep learning analysis of geospatial images of cities and some healthcare and behavioral indexes collected by the 500 cities US project, showing that, in New York City, urban landscape significantly correlates with the access to healthcare services.

Ambient Assisted Living (AAL) environments encompass technical systems and the Internet of Things (IoT) tools to support seniors in their daily routines. They aim to enable seniors to live independently and safely for as long as possible when faced declining physical or cognitive capacities. This work presents the design, development and deployment of an AAL system in the context of smart cities. The proposed architecture is based on microservices and software components. We examined the requirements and specifications of AAL systems in smart homes, in efforts to describe and evaluate how they would be transposable in the case of smart cities. The system has been tested and evaluated in the laboratory; it has been deployed in real life settings within city and is still in use by five elderly people.

Recent research allows envisioning what kind of sensory devices could be used for drivers’ navigation in the future, particularly for older adults. Population all around the world is aging, older adults will be more on the road. In this paper, we present a contact-less navigation system dedicated to this category of people based on a mobile head-up display. The aim of this system is to preserve their mobility in order to promote their autonomy and daily social activities. To do so, we interviewed older drivers to design a driving assistance system and we assessed the system under real road conditions (N = 34) with measurement of older drivers’ mental workload and the adequacy of users’ expectations. We emphasize the need to combine both measures of mental workload. The contribution aims at providing a richer understanding of how older people experience navigation technologies and to discuss the design recommendations of digital devices for older people.

We consider a smart phone scenario with a number of apps used by a user. The app usage data provides information about the user behavior, which can be used to identify the user demographics and interest and in turn is used to find similar users. In this paper, we propose a method to generate a latent space user embedding using the user app usage data, which is a dense low-dimensional representation of the user. This representation is used for low latency user similarity computation and acts as the user feature representation in user demographics prediction models.

Air pollution in one of the main problems that big cities have nowadays. Traffic congestion, heaters, industrial activities, among others produce large quantities of Particulate Matter (PM) that have harmful effects on citizens’ health. This paper presents the design, development and initial validation of a wearable device for the detection of PM concentration, with communication capacity via WiFi and Bluetooth Low Energy and an end user interface. The results are promising due to the high accuracy of measurements collected by the developed device. This solution is a step forward in empowering citizens to prevent being exposed to high levels of air pollution and is the beginning of what could be a macro-network of air quality sensors within a Smart City.

The High connectivity among devices within the Internet-of-Things facilitates two-way flow of information throughout the infrastructure reaching homes and the consumers targeting broader energy goals. Our proposal encompasses consumers cooperating in response to utility supply conditions, i.e., electricity available from renewable sources. Such a smart and green community of consumers autonomously adapts its energy consumption by enabling a local aggregator to (1) integrate their demand into a common view and, (2) re-schedule the community demand given the renewable energy supply and the consumers’ demand time preferences. In this paper, we evaluate the developed scheduling algorithm using benchmark data to validate our proposal implementation over existent technology.

In future, smart home and smart living applications will enrich daily life. These applications are aware of their context, use artificial intelligence (AI) and are therefore able to recognize common use cases reliably and adapt these use cases individually with the current user in mind. This paper describes a concept for such an AI-based platform. The presented platform approach considers different stakeholders, e.g. the housing industry, service providers and tenants.

Active mobility is a way of keeping oneself in a good health, although it may cause some discomfort. Globally, and specifically in Singapore context, several elements can influence our decisions. The choice of the right time for active mobility depends not only on available vehicles but also on the weather and the air quality. Popular fitness trackers motivate users by a daily step count goal. At the same time, open data, bus arrival times or shared bicycles availability help optimise the planning of the active mobility. Given these elements, a personalised mobile application was designed in order to facilitate the mobility choice. The paper describes how this application was constructed. It focuses on the use of semantic web reasoning for the integration of all factors and the recommendation inference. The outcome of the ongoing deployment with 36 participants is presented.