Figure - uploaded by Aishwarya Balakrishnan
Content may be subject to copyright.
![Freezing of gait rating scale in motor examination (MDS-UPDRS) [Copyright 2008 International Parkinson and Movement Disorder Society (MDS). All Rights Reserved. Reproduced with permission of the copyright owner. Further reproduction prohibited without permission].](profile/Aishwarya-Balakrishnan/publication/357842055/figure/tbl2/AS:1131625756786694@1646812013864/Freezing-of-gait-rating-scale-in-motor-examination-MDS-UPDRS-Copyright-2008.png)
Freezing of gait rating scale in motor examination (MDS-UPDRS) [Copyright 2008 International Parkinson and Movement Disorder Society (MDS). All Rights Reserved. Reproduced with permission of the copyright owner. Further reproduction prohibited without permission].
Source publication
Gait analysis, a way of assessing the manner of walking, is considered a significant criterion in diagnosing movement disorder. Various factors contribute to the alterations in gait patterns, of which neurodegenerative related disorders play a major role. Subjects affected by Parkinson's disease (PD) suffer from numerous gait-related disturbances,...
Similar publications
p>While the BLE is very popular for indoor communication, the antenna for the BLE in wearable sensor systems is lack investigation. This work proposes the BLE antenna for a wearable sensor, which is (i) small enough to fit in a compact device and (ii) tolerant against the nearby medium change.</p
A Human-Prosthetic Interface (HPI) serves to estimate and realise the limb pose intended by the human user, using the information obtained from sensors worn by the user. In recent studies, the HPI maps multi-joint limb poses (i.e. coordinated movement of the body and limbs) to the inputs of multiple sensors. This is in contrast to the conventional...
Eutectogels are a new class of soft ion conductive materials that are attracting attention as an alternative to conventional hydrogels and costly ionic liquid gels to build wearable sensors and bioelectrodes. Herein, the first example of mixed ionic and electronic conductive eutectogels showing high adhesion, flexibility, nonvolatility, and reversi...
![Figure 2. Antenna Sensors (a) Meander dipole antenna [20] (b) Sinosidal...](publication/373052137/figure/fig2/AS:11431281180922617@1691756204591/Antenna-Sensors-a-Meander-dipole-antenna-20-b-Sinosidal-dipole-antenna-21-c_Q320.jpg)
![Figure 3. Metamaterial sensors (a) Modulated FSS [36] (b) Spiral...](publication/373052137/figure/fig3/AS:11431281180932495@1691756204848/Metamaterial-sensors-a-Modulated-FSS-36-b-Spiral-resonator-37-c-Surface_Q320.jpg)
![Figure 4. FBG Sensors (a) FBG working principle [45] (b) Vital signs...](publication/373052137/figure/fig4/AS:11431281180922618@1691756205116/FBG-Sensors-a-FBG-working-principle-45-b-Vital-signs-monitoring-46-c-Single-FBG_Q320.jpg)
![Figure 5. Capacitive sensors using (a) porous Ecoflex polymer [56] (b)...](publication/373052137/figure/fig5/AS:11431281180922619@1691756205277/Capacitive-sensors-using-a-porous-Ecoflex-polymer-56-b-embroidery-on-face-mask_Q320.jpg)
This paper provides an overview of flexible and wearable respiration sensors with emphasis on their significance in healthcare applications. The paper classifies these sensors based on their operating frequency distinguishing between high-frequency sensors which operate above 10 MHz and low-frequency sensors. The operating principles of breathing s...
Wearable sensors have made significant progress in sensing physiological and biochemical markers for telehealth. By monitoring vital signs like body temperature, arterial oxygen saturation, and breath rate, wearable sensors provide enormous potential for the early detection of diseases. In recent years, significant advancements have been achieved i...
Citations
... The unprecedented desire for more advanced and smart living leads to the rapid improvement in smart multifunctional wearable devices [1][2][3][4][5]. In this pathway, cutting-edge technologies such as the Internet of Things (IoT) and artificial intelligence (AI) are playing the most significant roles [6][7][8][9][10][11]. Undoubtedly, this rapid expansion significantly enhances the demand for portable adequate power sources. ...
The ever-expanding demand for smart, wearable, and self-powered devices raises concerns regarding desirable power supplies. Again, this growing use of smart electronics continuously increases the burden on electronic waste (e-waste). Thus, a suitable power supply composed of environmentally friendly materials and assisted by adequate power density is quite enviable in today’s world. Herein, the designing and fabrication of an agricultural waste rice husk ash (RHA)/poly(vinylidene fluoride) (PVDF)-based flexible triboelectric energy harvesting device are demonstrated. The silica (SiO2)-enriched RHA effectively engineered the microstructure of the bio-compatible PVDF and effectively enhanced the electroactive phase fraction. The proof-of-concept of designing the flexible triboelectric energy harvester (TEH) using RHA/PVDF as a functional layer is studied. The fabricated lightweight, wearable TEH can generate a maximum voltage, current, and power density of ~ 463 V, 30 µAmp, and 1.94 mW.cm⁻², respectively, under repetitive finger imparting. This significantly enhanced output performance of the optimized TEH is attributed to the coupling of the piezoelectric effect with the triboelectric phenomenon inside the device under each cycle of operation. Owing to the good dynamic pressure sensitivity, the device is quite capable of sensing and scavenging energy from the fine motions of fingers as well as other body joints. Finally, the device was used to assemble self-powered smart sensors in order to conduct smart home and smart library operations. The smart switches can operate the smart home electronic appliances wirelessly from the interior/exterior of the room of the respective building. In smart library applications, the signal generated from the smart sensors can convey useful information to the librarian or the users regarding occupied and empty positions of a particular book on a bookshelf. With the bio-degradable nature of the filler, easy processing of the device, excellent biomechanical energy harvesting capability, and efficacy towards IoT applications, this sustainable bio-organic device paves the way towards effective, flexible, self-powered electromechanical systems for next-generation smart artificial intelligence (AI) and Internet of Things (IoT) applications.
Graphical Abstract
... Given the accelerating advancement of flexible and stretchable electronics, characteristics such as robustness, dependability, and longevity of devices have emerged as crucial determinants for their practical application [1][2][3][4][5][6][7][8]. Especially, wearable electronics, including body-attachable devices, repeatedly undergo mechanical deformation during practical usage, so damage to the device is inevitable [9]. ...
... These peaks corresponded to Ti-C, Ti 2+ , Ti 3+ , TiO 2 , and C-Ti-F X at binding energies of 453. 8 The C-C peaks in the C 1 s spectrum were attributed to carbon impurities that resulted from the absence of Ti atoms during the etching process. The F 1 s spectrum exhibited two peaks at 685.06 and 686.09 eV, which were related to C-Ti-F X and AlF X , respectively. ...
For flexible devices to be effectively integrated into long-lasting wearable systems, self-healing properties that can repair the damage are crucial. Although numerous studies have reported on the fabrication of self-healing devices, most still rely on external energy sources, such as heat or light, to initiate the intrinsic healing mechanisms. In this study, we successfully developed a spontaneously self-healing heater (SHH) that eliminates the need for any additional processes. To fabricate the SHH, we employed electrospun polycaprolactone (PCL) fibers, which have a melting point of 60 °C, as the core material. We coated the PCL fibers with Ti3C2TX MXene nanosheets and silver nanowires (AgNWs) to form electrode layers. Although PCL is unsuitable for heaters due to its low melting point, introducing MXene nanosheets as shape-retention barriers enabled the development of a thermally stable MXene/PCL composite that exhibits self-healing capabilities. The AgNW-coated MXene/PCL fibers demonstrated excellent electrical conductivity, with the heater’s temperature increasing proportionally to the applied voltage. The optimized heater achieved excellent flexibility, reaching temperatures above PCL’s melting point with a voltage of only 1–2 V. We repeatedly induced a crack on the heater’s surface and applied a voltage of 1.6 V, resulting in a temperature increase to 61 °C. Remarkably, the crack was autonomously repaired. Even in more severe damage scenarios with a complete cut the sample, the heater successfully rejoined the severed portions without any deterioration. This flexible heater’s inherent autonomous self-healing characteristics liberate users from the burden of trivial component repairs, ultimately enhancing the longevity of wearable devices.
Graphical Abstract
This study presents a flexible heater that demonstrates spontaneous self-healing capabilities during heat generation, eliminating the necessity for additional processes.
... While the authors of [10] for instance propose textile-based sensing elements for long-term gait analysis to improve lowerlimb rehabilitation, in [11] the usage of Wearable Sensors for the assessment of Parkinson's Disease is discussed. ...
In recent years, there has been a significant increase in interest in biometrics due to its wide range of applications, which extend beyond just the security and health industry. In this work, biometric authentication is performed using gait sensory in compliance with new mobile network requirements and with applications in the healthcare sector. The research domain focuses on the development of a gait sensory that can read sensory data from the shoe insole, and transfer it to a connected server. A novel method of transmitting data has been put into effect, which saves 33% of transmitted data while also employing data encryption to enhance security. Afterward, the data is fed to Machine Learning (ML) algorithms in order to identify the human using the shoe. The ML technique for human identification can be used for authentication purposes. The smart insole contains a gait sensory of a pressure-sensitive matrix of 6 columns and 18 rows. A small electrostatic discharge film is placed between rows and columns. The structure of rows, columns, and Electrostatic Discharge (ESD)-films gives 88 sensory points on the insole surface. A Test-case for the project is conducted on a sample of 8 people using a shoe of size 43. Gait data were measured and different ML algorithms were trained and tested to identify the person based on their walking pattern. Although the data set sample is small, it shows promising results regarding identification accuracy.
... Advancements in machine learning technologies have greatly improved the objective and automated assessment of Parkinson's Disease (PD) [4][5][6][7]. Notably, wearable sensor technology has been utilized to measure bradykinesia during finger tapping [8,9], with several of these sensors now available for clinical use [10,11]. The use of machine learning in the assessment of Parkinsonism holds promise for clinical care, potentially providing a more-efficient, extensive, and remote monitoring system. ...
The utilization of Artificial Intelligence (AI) for assessing motor performance in Parkinson’s Disease (PD) offers substantial potential, particularly if the results can be integrated into clinical decision-making processes. However, the precise quantification of PD symptoms remains a persistent challenge. The current standard Unified Parkinson’s Disease Rating Scale (UPDRS) and its variations serve as the primary clinical tools for evaluating motor symptoms in PD, but are time-intensive and prone to inter-rater variability. Recent work has applied data-driven machine learning techniques to analyze videos of PD patients performing motor tasks, such as finger tapping, a UPDRS task to assess bradykinesia. However, these methods often use abstract features that are not closely related to clinical experience. In this paper, we introduce a customized machine learning approach for the automated scoring of UPDRS bradykinesia using single-view RGB videos of finger tapping, based on the extraction of detailed features that rigorously conform to the established UPDRS guidelines. We applied the method to 75 videos from 50 PD patients collected in both a laboratory and a realistic clinic environment. The classification performance agreed well with expert assessors, and the features selected by the Decision Tree aligned with clinical knowledge. Our proposed framework was designed to remain relevant amid ongoing patient recruitment and technological progress. The proposed approach incorporates features that closely resonate with clinical reasoning and shows promise for clinical implementation in the foreseeable future.
... The gait disorders are also important factors affecting the quality of life of PD patients, and walking occupies most of the exercise time in daily life [21], [22]. Therefore, for PD patients with gait disorders, the passive detection of motor performance has been proposed in many studies to achieve long-term monitoring [21], [23]. ...
... The gait disorders are also important factors affecting the quality of life of PD patients, and walking occupies most of the exercise time in daily life [21], [22]. Therefore, for PD patients with gait disorders, the passive detection of motor performance has been proposed in many studies to achieve long-term monitoring [21], [23]. Although the body wearable sensor network can reflect the motor performance of PD patients more comprehensively, using multiple sensors increases the patient burden and may not be feasible for long-term monitoring of patients or management of the disease [24]. ...
Walking detection in the daily life of patients with Parkinson’s disease (PD) is of great significance for tracking the progress of the disease. This study aims to implement an accurate, objective, and passive detection algorithm optimized based on an interpretable deep learning architecture for the daily walking of patients with PD and to explore the most representative spatiotemporal motor features. Five inertial measurement units attached to the wrist, ankle, and waist are used to collect motion data from 100 subjects during a 10-meter walking test. The raw data of each sensor are subjected to the continuous wavelet transform to train the classification model of the constructed 6-channel convolutional neural network (CNN). The results show that the sensor located at the waist has the best classification performance with an accuracy of 98.01%±0.85% and the area under the receiver operating characteristic curve (AUC) of 0.9981±0.0017 under ten-fold cross-validation. The gradient-weighted class activation mapping shows that the feature points with greater contribution to PD were concentrated in the lower frequency band (0.5~3Hz) compared with healthy controls. The visual maps of the 3D CNN show that only three out of the six time series have a greater contribution, which is used as a basis to further optimize the model input, greatly reducing the raw data processing costs (50%) while ensuring its performance (AUC=0.9929±0.0019). To the best of our knowledge, this is the first study to consider the visual interpretation-based optimization of an intelligent classification model in the intelligent diagnosis of PD.
... Parkinson's disease (PD) resulting from nerve damage or death is the second most prevalent neurodegenerative health problem in the world after Alzheimer's (Lu et al. 2020). It was first identified by James Parkinson in 1817 (Balakrishnan et al. 2022). PD occurs as a result of decreased dopamine in the substantia nigra region of the central nervous system, which influences the muscle control mechanism (Xia et al. 2020). ...
Parkinson's disease (PD) is one of the most widespread neurological disorders associated with nerve damage without definitive treatment. Impairments, such as trembling and slowing down in hand movements are among the first symptoms. For this purpose, in this study, machine learning (ML)-based models were developed by using keyboard keystroke dynamics. According to patients' drug use status, disease severity, and gender, we created 14 different sub-datasets and extracted 378 features using raw keystroke data. We developed alternative models with Support Vector Machines (SVM), k-Nearest Neighbors (kNN), and Random Forest (RF) algorithms. We further used Minimum Redundancy Maximum Relevance (mRmR), RELIEF, sequential forward selection (SFS), and RF feature selection methods to investigate prominent features in distinguishing PD. We developed ML models that jointly use the most popular features of selection algorithms (feature ensemble [FE]) and an ensemble classifier by combining multiple ML algorithms utilizing majority vote (model ensemble [ME]). With 14 different sets, FE and ME models provided accuracy (Acc.) in the range of 91.73 - 100% and 81.08 - 100%, respectively.
... There is very limited work assessing room use in the home setting in people with Parkinson's. However, gait quantification using wearables or smartphones is an area where a significant amount of work has been done (with several systematic reviews such as these [4,7]). Cameras can detect also Parkinsonian gait and some gait features including step length and average walking speed [46]. ...
... Ethical approval. Full approval from NHS Wales Research Ethics Committee 6 was granted on 17 ℎ December 2019, and Health Research Authority and Health and Care Research Wales approval 4 The Random Forest is chosen as a binary classifier; It is not the one used for indoor localisation. confirmed on 14 ℎ January 2020; the research was conducted in accord with the Helsinki Declaration of 1975; written informed consent was gained from all study participants. ...
... living room). It can be seen from Table 2 that the MDCSA 1,4,7 4APS RSSI model has low performance in predicting hallway compared to the full model of MDCSA 1,4,7 . As a consequence, the MDCSA 1,4,7 4APS RSSI model cannot produce in-home gait speed features as competent as the ones produced by the MDCSA 1,4,7 . ...
Parkinson's disease (PD) is a slowly progressive, debilitating neurodegenerative disease which causes motor symptoms including gait dysfunction. Motor fluctuations are alterations between periods with a positive response to levodopa therapy ("on") and periods marked by re-emergency of PD symptoms ("off") as the response to medication wears off. These fluctuations often affect gait speed and they increase in their disabling impact as PD progresses. To improve the effectiveness of current indoor localisation methods, a transformer-based approach utilising dual modalities which provide complementary views of movement, Received Signal Strength Indicator (RSSI) and accelerometer data from wearable devices, is proposed. A sub-objective aims to evaluate whether indoor localisation, including its in-home gait speed features (i.e. the time taken to walk between rooms), could be used to evaluate motor fluctuations by detecting whether the person with PD is taking levodopa medications or withholding them. To properly evaluate our proposed method, we use a free-living dataset where the movements and mobility are greatly varied and unstructured as expected in real-world conditions. 24 participants lived in pairs (consisting of one person with PD, one control) for five days in a smart home with various sensors. Our evaluation on the resulting dataset demonstrates that our proposed network outperforms other methods for indoor localisation. The sub-objective evaluation shows that precise room-level localisation predictions, transformed into in-home gait speed features, produce accurate predictions on whether the PD participant is taking or withholding their medications.
... According to a review of wearable gait detection devices [42], 23 journal papers have used SIMUs on the shank and 25 journal papers have used SIMUs on the foot in an attempt to make SIMUs a popular wearable system for gait analysis. These papers have primarily focused on identifying a user's gait pattern using artificial intelligence (AI) and machine learning (ML) methods, such as artificial neural networks, extreme learning machines, convolutional neural networks, and long short-term memory [43][44][45][46][47], or rulebased algorithms to detect gait phases such as heel strike, toe-off, and swing phase [48][49][50][51][52]. ...
... Other researchers have used IMU systems to quantitatively assess gait [64][65][66][67]. AI has also been applied to assess, evaluate, and extract gait features using IMU systems [43][44][45][46][47]. To the best of our knowledge, there has not been any similar research using an extremely simplified gait detection and assessment system with an associated control algorithm. ...
Cueing and feedback training can be effective in maintaining or improving gait in individuals with Parkinson's disease. We previously designed a rehabilitation assist device that can detect and classify a user's gait at only the swing phase of the gait cycle, for the ease of data processing. In this study, we analyzed the impact of various factors in a gait detection algorithm on the gait detection and classification rate (GDCR). We collected acceleration and angular velocity data from 25 participants (1 male and 24 females with an average age of 62 ± 6 years) using our device and analyzed the data using statistical methods. Based on these results, we developed an adaptive GDCR control algorithm using several equations and functions. We tested the algorithm under various virtual exercise scenarios using two control methods, based on acceleration and angular velocity, and found that the acceleration threshold was more effective in controlling the GDCR (average Spearman correlation −0.9996, p < 0.001) than the gyroscopic threshold. Our adaptive control algorithm was more effective in maintaining the target GDCR than the other algorithms (p < 0.001) with an average error of 0.10, while other tested methods showed average errors of 0.16 and 0.28. This algorithm has good scalability and can be adapted for future gait detection and classification applications.
... Wearable sensors are widely employed for their lightweight, non-invasive, and real-time monitoring-supported abilities. 14 They provide objective, accurate, and reproducible measurements that can complement the use of traditional methods. 15 Based on data collected from wearable sensors, machine learning methods were applied for the detection of pathologies. ...
Objective
Neurodegenerative diseases affect millions of families around the world, while various wearable sensors and corresponding data analysis can be of great support for clinical diagnosis and health assessment. This systematic review aims to provide a comprehensive overview of the existing research that uses wearable sensors and features for the diagnosis of neurodegenerative diseases.
Methods
A systematic review was conducted of studies published between 2015 and 2022 in major scientific databases such as Web of Science, Google Scholar, PubMed, and Scopes. The obtained studies were analyzed and organized into the process of diagnosis: wearable sensors, feature extraction, and feature selection.
Results
The search led to 171 eligible studies included in this overview. Wearable sensors such as force sensors, inertial sensors, electromyography, electroencephalography, acoustic sensors, optical fiber sensors, and global positioning systems were employed to monitor and diagnose neurodegenerative diseases. Various features including physical features, statistical features, nonlinear features, and features from the network can be extracted from these wearable sensors, and the alteration of features toward neurodegenerative diseases was illustrated. Moreover, different kinds of feature selection methods such as filter, wrapper, and embedded methods help to find the distinctive indicator of the diseases and benefit to a better diagnosis performance.
Conclusions
This systematic review enables a comprehensive understanding of wearable sensors and features for the diagnosis of neurodegenerative diseases.
... Ionic conductors (ICs) with superior mechanical properties, excellent electrical conductivity, and self-healing ability are commonly applied in wearable electronic skins, soft robotics, and flexible transistors [1][2][3][4]. Hydrogels and ionic liquid-based ionogels are considered promising candidates for IC fabrication [5,6]. However, the rapid evaporation of water from hydrogels under ambient conditions and the leakage of ionic liquids from ionogels subjected to mechanical forces negatively affect their mechanical performance and electrical conductivity in various environments [7,8]. ...
With the rapid development of wearable devices, the fabrication of strong and tough ionic conductors for multifunctional wearable sensors has become crucial. However, developing ionic conductors with high mechanical strength and elasticity, excellent toughness, satisfactory conductivity, and self-healing is extremely difficult owing to their inherent structural design contradictions. Herein, we propose a lignin mediated biomimetic multiphase structure integrated with a multiple noncovalent interaction strategy to simultaneously increase the strength and toughness of ionic conductors without compromising their conductivity and self-healing ability. The in situ self-assembly of modified lignin to generate nanosphere structures as dynamic chemical crosslinkers realized the construction of a soft–hard multiphase. Furthermore, the charged lignosulfonate positively promoted the conductivity of ionic conductors, eliminating the traditionally observed negative effect of high crosslinking density on the conductivity. This, combined with multiple noncovalent interactions in the soft and hard phases, synergistically contributed to the impressive properties. The synthesized ionic conductors exhibited impressive mechanical properties corresponding to a maximum tensile strength of 7.14 MPa and maximum toughness of 23.3 MJ/m³, excellent elasticity, high conductivity, and good solvent resistance. More importantly, the conductors maintained the self-healing ability despite the excellent mechanical properties. The high-performance strain and pressure sensors manufactured from these materials demonstrated satisfactory sensitivity (S = 0.358–0.653), relatively fast response (386 ms), and long-term reliability (1300 cycles). This work overcomes the challenge of integrating several important but contradictory properties of ionic conductors and paves the way for the fabrication of sustainable and multifunctional wearable sensors suitable for harsh environments.
Graphical Abstract
Summary Ultra-strong, stretchable lignin-based ionic conductors with multiscale biomimetic design for sustainable and multifunctional wearable pressure and strain sensors.
