Built-in Accelerometer Research Articles

Speech enhancement can greatly improve the user experience during phone calls in low signal-to-noise ratio (SNR) scenarios. In this paper, we propose a low-cost, energy-efficient, and environment-independent speech enhancement system, namely AccCall, that improves phone call quality using the smartphone's built-in accelerometer. However, a significant gap remains between the underlying insight and its practical applications, as several critical challenges should be addressed, including efficiency of speech enhancement in cross-user scenario, adaptive system triggering to reduce energy consumption, and lightweight deployment for real-time processing. To this end, we first design Acc-Aided Network (AccNet), a cross-modal deep learning model inherently capable of cross-user generalization through three key components, including cross-modal fusion module, accelerometer-aided (abbreviated as acc-aided) mask generator, the unified loss function. Second, we adopt a machine learning-based approach instead of deep learning to achieve high accuracy in distinguishing call activity states followed by adaptive system triggering, ensuring lower energy consumption and efficient deployment on mobile platforms. Finally, we propose a knowledge-distillation-driven structured pruning framework that optimizes model efficiency while preserving performance. Extensive experiments with 20 participants have been conducted under a user-independent scenario. The results show that AccCall achieves excellent and reliable adaptive triggering performance, and enables substantial real-time improvements in SISDR, SISNR, STOI, PESQ, and WER, demonstrating the superiority of our system in enhancing speech quality and intelligibility for phone calls.

Spinal cord stimulation (SCS) is a treatment option for chronic neuropathic pain conditions when conventional therapies have failed. However, objective and measurable long-term data on the effects of SCS are lacking. This study evaluates changes in objectively recorded mobility and the correlation with patient-reported outcomes in SCS-treated patients with intractable back and/or leg pain following lumbar spine surgery. Fifty patients were enrolled. Baseline mobility was recorded over 4 weeks using an external neurostimulator with a built-in accelerometer. Patients achieving ≥50% pain relief during a subsequent SCS test trial received a permanently implanted stimulator at the same site. Mobility data were extracted at 3, 6, and 12 months and compared with baseline alongside work status, medication usage, and patient-reported outcome measures. Thirty-seven patients received a permanent stimulator, and 32 completed the 12 month follow-up of activity data. Time spent in mobility episodes lasting at least 30 s was 34±27 min/24 hours for SCS-patients at baseline compared with 92±51 min for healthy controls (p=0.009). Mobility increased gradually after SCS, reaching statistical significance at 12 months (p=0.045). The increase was significant in patients with predominant leg pain (35±27 to 54±32 min, p=0.011) but not in those with predominant back pain. Significant improvements were observed in working ability, medication reduction, and self-reported outcomes. Increased mobility correlated significantly with reduction in self-reported disability (p=0.044) and leg pain (p=0.046). The new objective data indicate that SCS has beneficial, long-term effects on mobility in patients with intractable leg pain after spine surgery. NCT04710355.

Perceived stress is prevalent in industrial societies, negatively impacting mental health. Smartphone-based stress management interventions provide accessible alternatives to traditional methods, but their efficacy remains modest, potentially due to limited integration of smartphone sensor technology. The primary aim of this study was to evaluate the efficacy of an 18-day smartphone-based stress management intervention, MT-StressLess with integrated heart rate (HR)-based biofeedback using built-in accelerometer sensors, compared to a waitlist control (WLC) condition. Secondary outcomes included emotion regulation skills, depressive symptoms, overall well-being, usbiality and usage data. As exploratory aims, we investigated whether the MT-StressLess version without HR-based biofeedback was also superior to the WLC condition, and whether the version with HR-based biofeedback provided additional benefits compared to the version without. In a three-arm randomized controlled trial, 166 participants were assigned to MT-StressLess with HR-based biofeedback, MT-StressLess, or the WLC condition. Linear mixed-effects models were used to analyze intervention effects over time (baseline, postintervention, and 1-month follow-up). At postintervention, MT-StressLess with HR-based biofeedback showed significantly greater reductions in perceived stress compared to the WLC condition (d = 0.41, 95% CI [0.03, 0.79]), whereas the version without biofeedback did not differ significantly (d = 0.14, 95% CI [−0.24, 0.51]). No significant differences were observed between the two active conditions (d = 0.29, 95% CI [−0.08, 0.66]). Both active conditions, however, led to significant improvements in the secondary outcomes of emotion regulation skills and well-being compared to the WLC (all ds = −0.58 to −0.27). These patterns persisted at the 1-month follow-up. Usability ratings were high, but overall adherence was moderate. The findings in the main comparison may reflect increased interoceptive awareness and self-regulation. Yet, the limited effects of the core intervention and the biofeedback component also suggest the influence of non-specific factors, such as placebo effects, outcome expectancy and user engagement, which highlights the need to better understand optimal intervention duration, motivation, reinforcement, and more individualized approaches to stress reactivity. Overall, the findings provide preliminary support for the potential of a smartphone-based intervention that includes HR-based biofeedback to reduce perceived stress compared to no intervention. As these interventions are still in their early stages, future research should explore how personalization driven by artificial intelligence and real-time physiological tracking can enhance engagement and efficacy.

The challenges and increasing number of elderly individuals requiring remote monitoring at home highlight the need for technological innovations. This study devised an eHealth mobile application designed to detect abnormal movement behavior and alert caregivers when a lack of movement is detected for an abnormal period. By utilizing the built-in accelerometer of a conventional mobile phone, an application was developed to accurately record movement patterns and identify active and idle states. Fuzzy logic, an artificial intelligence (AI)-inspired paradigm particularly effective for real-time reasoning under uncertainty, was integrated to analyze activity data and generate timely alerts, ensuring rapid response in emergencies. The approach reduced development costs while leveraging the widespread familiarity with mobile phones, facilitating easy adoption. The approach involved collecting real-time accelerometry data, analyzing movement patterns using fuzzy logic-based inferencing, and implementing a rule-based decision system to classify user activity and detect inactivity. This pilot study primarily validated the devised fuzzy logic method and the functional prototype of the mobile application, demonstrating its potential to leverage universal smartphone accelerometers for accessible remote monitoring. Using fuzzy logic, temporal and behavioral symmetry in movement patterns were adapted to detect asymmetric anomalies, e.g., abnormal inactivity or falls. The study is particularly relevant considering lonely individuals found deceased in their homes long after dying. By providing real-time monitoring and proactive alerts, this eHealth solution offers a scalable, cost-effective approach to improving elderly care, enhancing safety, and reducing the risk of unnoticed deaths through fuzzy logic.

Accurate acetabular cup placement using a smartphone-based digital alignment guide in total hip arthroplasty

The prevalence of stroke is high in both males and females, and it rises with age. Stroke often leads to sensor and motor issues, such as hemiparesis affecting one side of the body. Poststroke patients require torso stabilization exercises, but maintaining proper posture can be challenging due to their condition. Our goal was to develop the Postural SmartVest, an affordable wearable technology that leverages a smartphone's built-in accelerometer to monitor sagittal and frontal plane changes while providing visual, tactile, and auditory feedback to guide patients in achieving their best-at-the-time posture during rehabilitation. To design the Postural SmartVest, we conducted brainstorming sessions, therapist interviews, gathered requirements, and developed the first prototype. We used this initial prototype in a feasibility study with individuals without hemiparesis (n=40, average age 28.4). They used the prototype during 1-hour seated sessions. Their feedback led to a second prototype, which we used in a pilot study with a poststroke patient. After adjustments and a kinematic assessment using the Vicon Gait Plug-in system, the third version became the Postural SmartVest. We assessed the Postural SmartVest in a within-subject experiment with poststroke patients (n=40, average age 57.1) and therapists (n=20, average age 31.3) during rehabilitation sessions. Participants engaged in daily activities, including walking and upper limb exercises, without and with app feedback. The Postural SmartVest comprises a modified off-the-shelf athletic lightweight compression tank top with a transparent pocket designed to hold a smartphone running a customizable Android app securely. This app continuously monitors sagittal and frontal plane changes using the built-in accelerometer sensor, providing multisensory feedback through audio, vibration, and color changes. Patients reported high ratings for weight, comfort, dimensions, effectiveness, ease of use, stability, durability, and ease of adjustment. Therapists noted a positive impact on rehabilitation sessions and expressed their willingness to recommend it. A 2-tailed t-test showed a significant difference (P<.001) between the number of the best-at-the-time posture positions patients could maintain in 2 stages, without feedback (mean 13.1, SD 7.12) and with feedback (mean 4.2, SD 3.97), demonstrating the effectiveness of the solution in improving posture awareness. The Postural SmartVest aids therapists during poststroke rehabilitation sessions and assists patients in improving their posture during these sessions.

The rising popularity of wearable activity tracking devices can be attributed to their capacity for gathering and analysing ambient data, which finds utility across numerous applications. In this study, a wearable activity tracking device is developed using the BBC micro:bit development board to identify basic bachata dance steps. Initially, a pair of smart ankle bracelets is crafted, employing the BBC micro:bit board equipped with a built-in accelerometer sensor and a Bluetooth module for transmitting accelerometer data to smartphones. Subsequently, a dataset encompassing six core bachata dance steps synchronized to four beats is created from ten participants to examine the performance of the system. A metric using squared Euclidean distance is applied for the accelerometer raw data to facilitate and standardize the automatic detection of the steps by the system. A user interface, built with Python and Tkinter library, is developed to enable automatic step detection using the accelerometer dataset. The results demonstrated a system accuracy rate of 79.2%.

The automatic e-Call system has become mandatory in the European Union since 2018. This requirement means that all new passenger vehicles released on the European market after this date must be equipped with a digital emergency response service, which automatically notifies emergency services in case of an accident through the Automatic Crash Notification (ACN) system. Since the response of emergency services (police, ambulance, etc.) to such calls is extremely expensive, the task arises of improving the accuracy of such reports by verifying the fact that the accident actually occurred. Nowadays, most car manufacturers determine an emergency by analyzing the information coming from the built-in accelerometer sensors. As a result, quite often sudden braking, which avoids an accident, is mistakenly identified as an emergency and leads to a false call to emergency services. Some car manufacturers equip their high-end vehicles with an automatic collision notification, which mainly monitors the airbag deployment in order to detect a severe collision, and call assistance with the embedded cellular radios. In order to reduce costs some third-party solutions offer the installation of boxes under the hood, wind-screen boxes and/or OBDII dongles with an embedded acceleration sensor, a third-party sim-card as well as a proprietary algorithm to detect bumps. Nevertheless, relying on acceleration data may lead to false predictions: street bumps, holes and bad street conditions trigger false positives, whereas collisions coming from the back while standing still may be classified as normal acceleration. Also acceleration data is not suitable to identify vehicle side impacts. In many cases emergency braking helps to avoid collision, while acceleration data would be very similar to the data observed in case of an accident, resulting in a conclusion that the crash actually occurred. As a result, the average accuracy of those car crash detection algorithms nowadays does not exceed , which is acceptable, yet offers a lot of room for further improvement, since each additional percept of accuracy would provide substantial cost savings. That is why the task of increasing accuracy of collision detection stays urgent. In this article, we will describe an innovative approach to the recognition of car accidents based on the use of convolutional neural networks to classify soundtracks recorded inside the car when road accidents occur, assuming that every crash produces a sound. Recording of the soundtrack inside the car can be implemented both with the help of built-in microphones as well as using the driver's smartphone, hands-free car kits, dash cameras, which would drastically reduce cost of hardware required to solve this task. Also, modern smartphones are equipped with accelerometers, which can serve as a trigger for starting the analysis of the soundtrack using a neural network, which will save the computing resources of the smartphone. Accuracy of the crash detection can be further improved by using multiple sound sources. Modern automobiles may be equipped with various devices capable of recording the audio inside the car, namely: built-in microphone of the hands-free speaking system, mobile phones of the driver and/or passengers, dash-cam recording devices, smart back-view mirrors etc.

Defibrillator shocks and their effect on objective asian patient outcomes: results of the painfree SST clinical trial

The aim of this study was to build and validate an artificial neural network (ANN) algorithm to predict sleep using data from a portable monitor (Biologix system) consisting of a high-resolution oximeter with built-in accelerometer plus smartphone application with snoring recording and cloud analysis. A total of 268 patients with suspected obstructive sleep apnea (OSA) were submitted to standard polysomnography (PSG) with simultaneous Biologix (age: 56±11\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$56\\pm 11$$\\end{document} years; body mass index: 30.9±4.6\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$30.9\\pm 4.6$$\\end{document}kg/m2\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\hbox {kg/m}^{2}$$\\end{document}, apnea-hypopnea index [AHI]: 35±30\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$35\\pm 30$$\\end{document} events/h). Biologix channels were input features for construction an ANN model to predict sleep. A k-fold cross-validation method (k=10) was applied, ensuring that all sleep studies (N=268; 246,265 epochs) were included in both training and testing across all iterations. The final ANN model, evaluated as the mean performance across all folds, resulted in a sensitivity, specificity and accuracy of 91.5%, 71.0% and 86.1%, respectively, for detecting sleep. As compared to the oxygen desaturation index (ODI) from Biologix without sleep prediction, the bias (mean difference) between PSG-AHI and Biologix-ODI with sleep prediction (Biologix-Sleep-ODI) decreased significantly (3.40 vs. 1.02 events/h, p<0.001). We conclude that sleep prediction by an ANN model using data from oximeter, accelerometer, and snoring is accurate and improves Biologix system OSA diagnostic precision.

Technological devices such as smartphones can be utilized in tracking various human activities or movements through built-in accelerometers and gyroscopes. Data obtained from these inertial sensors can be utilized in various applications to assist people, including healthcare, human-computer interaction, and sports. As a result, further developments in the effective classification of time series data through machine and deep learning is highly valued and actively pursued. In this study, the transformer model, a deep learning architecture designed for sequential data such as natural language processing (NLP), has been utilized for analysis of time-series motion readings from wearable accelerometers. The transformer model in this study has been refined by incorporating a Long Short-Term Memory (LSTM) recurrent neural network (RNN) architecture. By leveraging the HAR70+ dataset with a wide range of activities, the modified transformer model in this study obtained a best accuracy of 95.85%, demonstrating that it can match the performance of state-of-the-art wearable activity recognition methods using Deep Neural Networks (DNN) and LSTM. Hence, the findings presented in this study suggest the future relevance of improved transformer or deep learning models to enhance the quality of life for seniors.

This review reports on the use of sensors in wheelchair sports to monitor and analyze performance during match and training time. With rapid advancements in electronics and related technologies, understanding performance metrics in wheelchair sports is essential. We reviewed nine studies using various sensor types, including electric motors, inertial measurement units, miniaturized data loggers with magnetic reed switches, and smartphones with inbuilt accelerometers and gyroscopes, operating at frequencies from 8 Hz to 1200 Hz. These studies measured parameters such as angular and translational velocities, distance, number of starts/pushes, and other performance indicators in sports such as basketball, rugby, tennis, and racing. Despite differences in sport types and methodologies, most studies found sensor-derived data effective for assessment of performance. Future developments and research in this field should focus on multi-sensor systems that could provide real-time match analysis and deeper insights into performance metrics. Overall, sensor technologies show significant potential for improving wheelchair sport performance diagnostics, contributing to better athlete training and future wheelchair design, and enhancing competitive outcomes. This review emphasizes the need for continued innovation and standardization in applying sensor technologies in wheelchair sports.

Safety and accessibility of sidewalks are key aspects for the comfortable living of residents in an area, but their effective monitoring is a challenging and financially demanding process. This article analyzes the collaboration between the city of Košice, the Technical University of Košice, and the company ANTIK in testing the utilization of existing infrastructure of shared scooters to assess the quality and accessibility of sidewalks using their built-in accelerometer and GPS module. The results indicate that it is possible to utilize them and identify problematic areas, but the experiment revealed technological obstacles that require solutions before widespread deployment. The outcome could be an automatic update of the city’s accessibility map and dynamic monitoring of the condition of sidewalks and roads, thereby streamlining monitoring processes and improving the overall accessibility of urban infrastructure.

This paper aims to present and analyse the acceleration data inside an aircraft during a parabolic flight. The data used were obtained during the flight from the automatic recordings of the aircraft and from a portable data logger with a built-in 3-axis accelerometer connected to a graphic calculator. There is good agreement between the accelerations obtained by the two methods. Based on the altitude data collected during each parabolic manoeuvre performed by the aircraft, it was possible to estimate the gravity of Mars and the Moon, as well as the values of the acceleration of gravity during the moments of microgravity. The analysis presented can also help to improve the understanding of the concepts of inertial forces and the equivalence between gravity and acceleration.

Abstract A mobile phone application, referred to as SMARTdynamics, was developed to take site readings of the dynamic response of a cable-stayed highway bridge and a three-span plate girder railway bridge by making use of built-in accelerometers. The application allows to determine key dynamic properties including natural frequencies, displacements, and damping ratios. SMARTdynamics includes a novel feature for smartphone accelerometers: the ability to control the sensor remotely with automated application feedback, allowing to record the dynamic response at specific times and with precision. The aim of the study was to determine the reliability of smartphone accelerometers, establish the effectiveness of mobile phone usage in the bridges and civil structures industry, and demonstrate that the derivation of more realistic dynamic properties can offer benefits in determining less conservative structural capacities. Acceleration readings were taken for a cable-stayed highway bridge to determine the tension force within the stay cables. The obtained results confirmed the viability of mobile phone ac-celerometers as a serious asset management tool. Site readings were also taken to determine the dynamic amplification factors of plate girder railway bridges and revealed a mean average reduction of 40% in the real dynamic increment factor when compared with values derived from codes of practice. The study confirmed that moving towards a realistic approach to bridge structural assessments with user-friendly and cost-effective tools can have tangible benefits and should be considered as a viable alternative to traditional methods.

Efficient blood pressure (BP) monitoring in everyday contexts stands as a substantial public health challenge that has garnered considerable attention from both industry and academia. Commercial mobile phones have emerged as a promising tool for BP measurement, benefitting from their widespread popularity, portability, and ease of use. Most mobile phone-based systems leverage a combination of the built-in camera and LED to capture photoplethysmography (PPG) signals, which can be used to infer BP by analyzing the blood flow characteristics. However, due to low Signal-to-Noise (SNR), various factors such as finger motion, improper finger placement, skin tattoos, or fluctuations in environmental lighting can distort the PPG signal. These distortions consequentially affect the performance of BP estimation. In this paper, we introduce a novel sensing system that utilizes the built-in accelerometer of a mobile phone to capture seismocardiography (SCG) signals, enabling accurate BP measurement. Our system surpasses previous mobile phone-based BP measurement systems, offering advantages such as high SNR, ease of use, and power efficiency. We propose a triple-stage noise reduction scheme, integrating improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN), recursive least squares (RLS) adaptive filter, and soft-thresholding, to effectively reconstruct high-quality heartbeat waveforms from initially contaminated raw SCG signals. Moreover, we introduce a data augmentation technique encompassing normalization coupled with temporal-sliding, effectively augmenting the diversity of the training sample set. To enable battery efficiency on smartphone, we propose a resource-efficient deep learning model that incorporates resource-efficient convolution, shortcut connections, and Huber loss. We conduct extensive experiments with 70 volunteers, comprising 35 healthy individuals and 35 individuals diagnosed with hypertension, under a user-independent setting. The excellent performance of our system demonstrates its capacity for robust and accurate daily BP measurement.

Assessment of symptom severity in psychotic disorder patients based on heart rate variability and accelerometer mobility data

In recent years, the continuous progress of wireless communication and sensor technology has enabled sensors to be better integrated into mobile devices. Therefore, sensor-based Human Activity Recognition (HAR) has attracted widespread attention among researchers, especially in the fields of wearable technology and ubiquitous computing. In these applications, mobile devices’ built-in accelerometers and gyroscopes have been typically used for human activity recognition. However, devices such as smartphones were placed in users’ pockets and not fixed to their bodies, and the resulting changes in the orientation of the sensors due to users’ habits or external forces can lead to a decrease in the accuracy of activity recognition. Unfortunately, there is currently a lack of publicly available datasets specifically designed to address the issue of device angle change. The contributions of this study are as follows. First, we constructed a dataset with eight different sensor placement angles using accelerometers and gyroscopes as a prerequisite for the subsequent research. Second, we introduced the Madgwick algorithm to extract quaternion mode features and alleviate the impact of angle changes on recognition performance by fusing raw accelerometer data and quaternion mode features. The resulting study provides a comprehensive analysis. On the one hand, we fine-tuned ResNet and tested its stability on our dataset, achieving a recognition accuracy of 97.13%. We included two independent experiments, one for user-related scenarios and the other for user-independent scenarios. In addition, we validated our research results on two publicly available datasets, demonstrating that our method has good generalization performance.

An ensemble maximal feature subset selection for smartphone based human activity recognition

Currently, wearable technology is an emerging trend that offers remarkable access to our data through smart devices like smartphones, watches, fitness trackers and textiles. As such, wearable devices can enable health monitoring without disrupting our daily routines. In clinical settings, electrocardiograms (ECGs) and photoplethysmographies (PPGs) are used to monitor heart and respiratory behaviors. In more practical settings, accelerometers can be used to estimate the heart rate when they are attached to the chest. They can also help filter out some noise in ECG signals from movement. In this work, we compare the heart rate data extracted from the built-in accelerometer of a commercial smart pen equipped with sensors (STABILO's DigiPen) to standard ECG monitor readouts. We demonstrate that it is possible to accurately predict the heart rate from the smart pencil. The data collection is carried out with eight volunteers writing the alphabet continuously for five minutes. The signal is processed with a Butterworth filter to cut off noise. We achieve a mean-squared error (MSE) better than 6.685 × 10-3 comparing the DigiPen's computed Δt (time between pulses) with the reference ECG data. The peaks' timestamps for both signals all maintain a correlation higher than 0.99. All computed heart rates (HR =60Δt) from the pen accurately correlate with the reference ECG signals.