The transition toward Healthcare Industry 5.0 requires personalized, intelligent, and privacy-preserving solutions. Additionally, the proliferation of home monitoring in the current Healthcare 4.0 framework has been embracing the challenge for invasiveness/privacy issues brought by home monitoring sensors and devices, potentially forsaking the conceived human-centric attributes of Smart Healthcare Industry 5.0. At the intersection of Healthcare Industry 5.0 and secured home monitoring, we propose a multi-service non-invasive solution for distributed home monitoring. A new infrastructure based on Fiber Bragg Grating (FBG) accelerometers is designed, realizing non-invasive/high-privacy distributed home monitoring by solely monitoring floor vibrations. To achieve home monitoring based on the low-dimensional data collected by FBG accelerometers, a multi-class hierarchical support vector machinebased algorithm (H-SVM) is proposed, which achieves simultaneous multi-service classification with FBG noise/interference mitigation. Moreover, an enhanced time difference of arrival (TDoA)-based algorithm (E-TDoA) is proposed for real-time localization of users, with the enhanced accuracy specifically based on FBG-collected data. Experimental results show an overall accuracy of 93.62% for multi-service classification, with a low processing time of 4.1 ms, meanwhile comprising a localization accuracy of 0.715 m (sufficient for home monitoring multi-service delivery).

The transition toward Healthcare Industry 5.0 requires personalized, intelligent, and privacy-preserving solutions. Additionally, the proliferation of home monitoring in the current Healthcare 4.0 framework has been embracing the challenge for invasiveness/privacy issues brought by home monitoring sensors and devices, potentially forsaking the conceived human-centric attributes of Smart Healthcare Industry 5.0. At the intersection of Healthcare Industry 5.0 and secured home monitoring, we propose a multiservice noninvasive solution for distributed home monitoring. A new infrastructure based on fiber bragg grating (FBG) accelerometers is designed, realizing noninvasive/high-privacy distributed home monitoring by solely monitoring floor vibrations. To achieve home monitoring based on the low-dimensional data collected by FBG accelerometers, a multiclass hierarchical support vector machine (H-SVM)-based algorithm is proposed, which achieves simultaneous multiservice classification with FBG noise/interference mitigation. Moreover, an enhanced time difference of arrival (TDoA)-based algorithm (enhanced the TDoA-based algorithm) is proposed for real-time localization of users, with the enhanced accuracy specifically based on FBG-collected data. Experimental results show an overall accuracy of 93.62% for multiservice classification, with a low processing time of 4.1 ms, meanwhile comprising a localization accuracy of 0.715 m (sufficient for home monitoring multiservice delivery).

In this paper, it is proposed an indoor localization system, relying on multiplexed fiber Bragg grating (FBG)-based accelerometers, targeting the activity levels monitoring of elders living alone. From the proposed consumer sensing system, floor vibration patterns generated by walking with high precision and reliability, were obtained. An indoor localization algorithm is also newly proposed, specifically customized to the localization system formed by the mesh of FBG-based accelerometers. Experimental setup is conducted, and an average root mean square (RMS) error of 0.285 m and a variance of 0.019 m2 were obtained, revealing that the proposed localization methodology delivers a reliable localization estimative, considering that typical foot size is about 0.200 m or greater. Compared with the conventional indoor localization technologies, this presents high accuracy, high reliability, and high privacy. Therefore, the proposed FBG-based localization system is a non-invasive consumer Internet-of-Things (CIoT)-based solution for smart healthcare, which provides low-complexity and high-privacy data for indoor localization.

According to the World Health Organization, there are about 2.3 million new annual breast cancer (BC) cases. Knowing that after surgery BC survivors (BCSs) frequently report a decrease on their muscle activity and a reduction on their fine motor skills, it is fundamental that the rehabilitation process starts right after surgery, focusing on the upper limb function recovery. One of the faculties commonly affected during the treatment, is the handgrip capacity. Its rehabilitation process requires a close monitoring of the typically prescribed exercises, which is most often done based on qualitative observation, provided only during the physical therapy sessions. The capacity to quantitatively evaluate the rehabilitation process, both from home or in a clinic scenario, represents an added value to the rehabilitation process for the medical staff and for the BCS itself. Targeting the improvement of the BCS rehabilitation process, it is proposed a low-cost plastic optical fiber (POF) sensor for handgrip force monitoring during the performance of exercises designed for its rehabilitation. The tool designed presented a sensitivity of (-7 ± 1) m V/N, demonstrating a good performance during the execution of different handspring exercises and the capacity to evaluate the maximum effort from different subjects, for the same exercise.

Hand movements can be severely affected due to certain medical conditions such as stroke, or as a side effect from the treatments for other diseases such as breast cancer. Here, we propose a solution based on optical fiber Bragg gratings (FBGs) for the monitoring of rehabilitation exercises to recover the hand fine skills, the fingers strength and the precision of movements. The developed sensor was initially calibrated to force, and a value of 18.16 pm/N was obtained for its sensitivity. The sensor was tested for handgrip exercises of precision, oppositional, and lateral pinches, and the results obtained are in accordance with literature, which proved the sensors potential for monitoring this type of exercises during physical therapies. This solution can be further integrated with the Internet of Things (IoT) health systems for a remote digital health solution, as a facilitator for the physical therapies to be performed remotely from the patient's home.

Facing the increasing aging of the world population, it is important to develop new non-invasive systems that do not require any action from the user, allowing their monitoring, with privacy guarantee. This will contribute to diminish the burdens associated with the elderly people care. In this work it is presented a system based on optical fiber Fabry-Perot interferometer (FPI) accelerometers, placed on the floor of an indoor environment, to recognize human falls. Both the sensor production method and the acquisition system are cheaper than commercial ones, available for this purpose. In addition, the proposed system comprises real time data acquisition and processing, representing a promising low-cost solution for the elders indoor monitoring by external entities, by enabling its implementation in apps that alerts the caregivers.

Considering that fall accidents are one of the leading causes of non-natural death of elders, it is crucial to design and to implement home’ fall detection systems. Current home monitoring systems are targeting this challenge, pursuing non-invasive, low latency, and simplified fall detection algorithms. Therefore, in this paper, edge-enabled non-wearable and non-invasive fall detection system is proposed. Concretely, outperforming the conventional invasive/privacy-sensitive fall detection technologies, the proposed system comprises four photonic-based accelerometers solely relying on the fiber Bragg grating (FBG) technology, which monitor the vibrations induced by the body impact in the platform by the Bragg wavelength shifts. A newly-developed support vector machine-based multi-class fall detection algorithm is proposed, based on the data collected by the accelerometers. Moreover, feasibility analysis of the proposed fall detection algorithm also reveals the possibility of fall prediction, given the slipping as the pre-falling phenomenon. Experimental results showcase that the proposed fall detection algorithm achieves overall accuracy up to 96.5%, with average processing time achieved as 21.3 ms, indicating the sufficiency to provide high quality of experience (QoE) fall detection services. Besides, fall prediction based on the pre-falling case study of slipping is discussed, revealing that fall can be predicted~197.5 ms beforehand, which is sufficient for further fall prevention (e.g., airbag).

Numerous studies have been carried out aiming to improve wheelchair users' quality of life. Based on the muscle effort evaluation during their daily activities, wheelchair users can adopt different postures to reduce their effort. However, most of the current solutions for muscle effort assessment are affected by uncontrolled factors. Here, a solution immune to these factors is proposed. The system, based on six fiber Bragg gratings embedded in epoxy resin, was distributed on both arms of six wheelchair users' volunteers. The arms' muscle effort was estimated through the fiber Bragg grating's wavelength shift, which was related with the epoxy resin deformation during some of the wheelchair users' daily movements, such as horizontal plane locomotion (using different wheelchair hand movement patterns), ramp up and down, and dips. The slightest hand clearance, in relation to the rim (pattern A), implies smaller sensor deformations and, therefore, a lower effort. Comparing to pattern A, volunteer 5 increased 17% its effort in pattern B and 27% in pattern D, in the left bicep sensor. Also, ramp displacements require higher muscle effort, in relation to the horizontal plane. Of all the exercises performed, dips involve the most intense arms' muscle effort (volunteer 5 had an 82% deformation increase, comparing to pattern A, in the left bicep sensor). The developed system revealed promising results, providing deeper knowledge about the muscle effort during daily movements. Based on this information they can adopt different postures, resulting in minor muscle fatigue, and consequently an improvement of their quality of life.

A fiber Bragg gratings (FBGs) based system, constituted by six sensors, for wheelchair users muscle effort monitoring was proposed. Each sensor consists in one FBG embedded in epoxy resin, which was secured to Kinesio tape through a 3D printed connection system. After the approval of the Ethics and Deontology Committee and the Data Protection Officer of the University of Aveiro (Portugal), the sensors were implemented to evaluate wheelchair users muscle effort. The sensors were placed on the biceps, deltoids, and triceps (three sensors in each arm) of four wheelchairs users' volunteers, which were asked to perform several exercises. The arms' muscle effort required was estimated through the FBGs wavelength shift, which was related with the deformation of the epoxy resin during some of the wheelchair users' daily movements: varying the typical used hand patterns on horizontal plane (pattern A, B and D); vertical and inclined dips; and going up and down a ramp. The results reveal that on the horizontal plane, the movement characterized by minor hand swings in relation to the wheelchair rim (pattern A), requires a smaller muscle effort, and the dips were the exercise requested to wheelchair users which demand the highest and most sudden muscle effort applied in the arms. The proposed system may be used to monitor and quantify the muscle effort related to any movement, aiding on the choice of techniques to promote the reduction of the muscle fatigue, and therefore contributing to the improvement of wheelchair user quality of life.