Phone Accelerometer Research Articles

IMPROVED PARALLEL BIG DATA CLUSTERING BASED ON K-MEDOIDS AND K-MEANS ALGORITHMS

In recent years, the amount of data created worldwide has grown exponentially. The increase in computational complexity when working with "Big data" leads to the need to develop new approaches for their clustering. The problem of massive data amounts clustering can be solved using parallel processing. Dividing the data into batches helps to perform clustering in a reasonable time. In this case, the reliability of the obtained result for each block will affect the performance of the entire dataset. The main idea of the proposed approach is to apply the k-medoids and k-means algorithms to parallel Big data clustering. The advantage of this hybrid approach is that it is based on the central object in the cluster and is less sensitive to outliers than k-means clustering. Experiments are conducted on real datasets, namely YearPredictionMSD and Phone Accelerometer. The proposed approach is compared with the k-means and MiniBatch k-means algorithms. Experimental results proved that the proposed parallel implementation of k-medoids with the k-means algorithm shows greater accuracy and works faster than the k-means algorithm.

Observing temporary changes in gait using a mobile phone

The purpose of the article is to analyze temporary changes in human gait, the parameters of which are recorded using the accelerometer of a mobile phone in everyday use. The work presents trends in the field of personalized medicine and monitoring the health of employees in the manufacturing sector based on wearable and mobile devices. The features of collecting and processing data on a person’s gait using a mobile phone are presented, which act as a comprehensive assessment of human health parameters. The results of a year-long research of changes in human gait are presented. Daily, weekly and annual trends are identified. The research analyzed mobile phone accelerometer time series representing double steps during gait. When constructing trends, the maximum value of the cross-correlation function of data segments was used. Data segmentation was carried out according to the length of the double step. Based on the results of the research, an assumption is made about the possibility of recording individual characteristics of the functioning of the human musculoskeletal system using a mobile phone and conducting further research in order to accumulate statistical material and identify the relationship between a person’s lifestyle and changes in gait parameters.

A Mobile Based Activity Recog-nition Model

In the last decade, activity recognition (AR) of humans via smart phones became important and attractive subject for scholars and developers in many areas from health care to real-time security systems. In this research, we worked on AR that based on data collected from Android-based smart phone's accelerometers held at waist region while performing different activities (i.e. walking, jogging, climbing stairs, downing stairs, sitting, and standing). To achieve this goal, six classification algorithms were performed: Naïve Bayes (NB), Multi Layer Perceptron (MLP), Bayes Network (BN), Sequential Minimal Optimization (SMO), Kstar, and Decision Tree (DT). Experimental results of the six models were illustrated and analyzed. Comparison results declare that MLP algorithm outperforms other algorithms.

Extraction of individual gait features in mobile phone accelerometer

An algorithm for extracting individual signs of a person’s gait according to the data of a mobile phone accelerometer is considered. The developed algorithm includes the stage of data segmentation, correlation selection of motion patterns, and data clustering procedures. By selecting noisy segments, the quality of data clustering and the extraction of individual features is improved. The results of the algorithm work allow us to refine the existing models of changes in human motor behavior in personalized medicine and security systems. The article also discusses the features of data segmentation and the influence of external factors on the measurement results.

Earthquake Event Recognition on Smartphones Based on Neural Network Models.

Using sensors embedded in smartphones to study earthquake early warning (EEW) technology can effectively reduce the high construction and maintenance costs of traditional EEW systems. However, due to the impact of human activities, it is very difficult to accurately detect seismic events recorded on mobile phones. In this paper, to improve the detection accuracy of earthquakes on mobile phones, we investigated the suitability of different types of neural network models in seismic event detection. Firstly, we collected three-component acceleration records corresponding to human activities in various scenarios such as walking, running, and cycling through our self-developed mobile application. Combined with traditional strong-motion seismic event records fusing typical mobile phone accelerometer self-noise, all records were used for establishing the training and testing dataset. Finally, two types of neural network models, fully connected and convolutional neural networks, were trained, validated, and tested. The results showed that the accuracy rates of the neural network models were all over 98%, and the precision rate for seismic events and the recall rate for non-earthquake events could both reach 99%, indicating that the introduction of neural networks into the earthquake recognition on smartphones can significantly enhance the accuracy of seismic event recognition. Therefore, we can exceedingly reduce the amount of data transmitted to the processing server, further lowering the load on the server processor and effectively increasing the lead time at each target site for an EEW system.

Vehicular impact analysis of driving for accidents using on board diagnostic II

A large number of people meet with an accident everyday around the world. One of the leading causes of death is traffic accidents. The reasons behind India's rising number of road accidents contribute to bad driving behavior, poor road design and infrastructure, lack of enforcement of traffic laws. The post accidental investigation report is very important to know the actual reason of collision for the concerned parties and the insurance company and the police. The proposed work effectively extracts interpretable features describing complex driving patterns. It will provide analytical report of the accidents to various parties involved in process. This work analyzes the type and cause of accident. The experiment has been simulated using on board diagnostic II (OBD II) and smart phone accelerometer for post accidental analysis of collision. As the electronic control unit (ECU) does not provide accelerometer sensor, so the smart phone accelerometer has been utilized in conjunction with another parameter of OBD II device. The gravitational force (G-force) values observed from accelerometer sensor along the different axes and speed, acceleration, fuel consumption rate, and are retrieved from OBD II device. The result shows that the parameters recorded are very helpful in finding the actual accidental status of the vehicle.

A 19 day earth tide measurement with a MEMS gravimeter

The measurement of tiny variations in local gravity enables the observation of subterranean features. Gravimeters have historically been extremely expensive instruments, but usable gravity measurements have recently been conducted using MEMS (microelectromechanical systems) sensors. Such sensors are cheap to produce, since they rely on the same fabrication techniques used to produce mobile phone accelerometers. A significant challenge in the development of MEMS gravimeters is maintaining stability over long time periods, which is essential for long term monitoring applications. A standard way to demonstrate gravimeter stability and sensitivity is to measure the periodic elastic distortion of the Earth due to tidal forces—the Earth tides. Here, a 19 day measurement of the Earth tides, with a correlation coefficient to the theoretical signal of 0.975, has been presented. This result demonstrates that this MEMS gravimeter is capable of conducting long-term time-lapse gravimetry, a functionality essential for applications such as volcanology.

Pavement Distress Recognition via Wavelet-Based Clustering of Smartphone Accelerometer Data

The ubiquity of smartphones has led to a variety of studies on how phone accelerometers can be used to assess road pavement quality. The majority of prior studies have emphasized supervised machine learning, assuming the ability to collect labeled data for model development. However, variances in vehicle dynamics and roadway quality, as well as the reliance on data labeling, limit the generalizability, scalability, and reproducibility of these approaches. Here, we propose an unsupervised learning framework that combines Pareto-optimized wavelet featurization and clustering. We first demonstrate the applicability of wavelets as features for dimensionally reduced accelerometer data. Wavelet featurization typically requires significant empirical tuning for optimal featurization. The presented framework automates tuning and selection of wavelet features based on subsequent clustering metrics. These metrics are related to inherent cluster characteristics such as intercluster variance and between-cluster variance. Rather than select a clustering method a priori, the proposed approach optimizes across a variety of clustering algorithms and hyperparameter configurations, again based on a set of clustering metrics. Experimental evaluation shows that the framework is able to detect road pavement distress and distinguish between classes of pavement defects, but that low-cost smartphone sensor data may not be as reliable in discriminating the more nuanced characteristics of pavement distress. This was most notable in the case of cracking, where the type and range of cracking severity caused undesirable cluster separation. The presented framework is general and cost-efficient and opens the way to further research on automatic pavement distress recognition from crowdsourced, low-cost data.

Human Activity Recognition using Machine Learning

Abstract: Nowadays, activity recognition is one of the most popular uses of machine learning algorithms. It's utilized in biomedical engineering, game production, and producing better metrics for sports training, among other things. Data from sensors linked to a person may be used to build supervised machine learning models that predict the activity that the person is doing. We will use data from the UCI Machine Learning Repository in this work. It contains data from the phone's accelerometer, gyroscope, and other sensors, which is used to build supervised prediction models using machine learning techniques like as SVM, Random Forest. This may be used to forecast the person's kind of movement, which is separated into six categories: walking, walking upstairs, walking downstairs, sitting, standing, and lying. We'll use a confusion matrix to compare the accuracy of different models.

Human identification based on accelerometer sensors obtained by mobile phone data

In order to achieve secure usage digitally, many different methodologies (i.e., pin code, fingerprint, face recognition) have been employed. In this study, a novel way of user identification, which can be expressed as a biometrical method, has been proposed. The proposed approach was based on the characteristics of mobile phone usage (position changes in carrying, talking, and other actions). To assess and validate the proposed method, a dataset, which consists of millions of data collected from users with the help of accelerometers for several months during their ordinary smartphone usage, was obtained. This large dataset was reduced by randomly taking 3000 samples from each of the 387 devices in the dataset. The arbitrarily selected signals were labeled according to “one against all” (or “one vs. all”) strategies. Extracted features were classified by the k nearest neighbor (kNN) and the randomized neural network (RNN), machine learning methods. It has been seen that behavior-based biometric recognition can be accomplished with mobile phone accelerometer data, with 99.994% success rates for kNN and 99.97% for RNN.

Enhancing human activity recognition using deep learning and time series augmented data

Human activity recognition is concerned with detecting different types of human movements and actions using data gathered from various types of sensors. Deep learning approaches, when applied on time series data, offer promising results over intensive handcrafted feature extraction techniques that are highly reliant on the quality of defined domain parameters. In this paper, we investigate the benefits of time series data augmentation in improving the accuracy of several deep learning models on human activity data gathered from mobile phone accelerometers. More specifically, we compare the performance of the Vanilla, Long-Short Term Memory, and Gated Recurrent Units neural network models on three open-source datasets. We use two time series data augmentation techniques and study their impact on the accuracy of the target models. The experiments show that using gated recurrent units achieves the best results in terms of accuracy and training time followed by the long-short term memory technique. Furthermore, the results show that using data augmentation significantly enhances recognition quality.

Abstract 14892: Mobile Technology Improves Adherence to Cardiac Rehabilitation: A Propensity Score-matched Study

Objective: To examine whether mobile technology improves adherence to cardiac rehabilitation and other outcomes. Methods: We identified enrollees of the cardiac rehabilitation program at Boston Medical Center from 2016-2020 (n=830). Some enrollees used a mobile technology application (Wellframe.com) that provided a customized interactive list of educational content in a progressive manner, used the patient’s smart phone accelerometer to provide daily step counts, and served as a two-way messaging system between the patient and the program staff. Adherence to cardiac rehabilitation was defined as the number of attended prescribed sessions and completion of the program. To evaluate change in the following: exercise capacity, Beck Depression Index (BDI) scores, weight, quality of life scores and Rate Your Plate nutrition scores, we used the generalized estimating equation method. Results: After 2:1 propensity score matching for age, sex, race, education, smoking status, transportation time to cardiac rehabilitation center, qualifying diagnosis, and baseline BDI score, there were 121 enrollees in the group using the Wellframe application as a supplement to the rehabilitation program and 280 enrollees in the Standard rehabilitation group. Enrollees had a mean age of 59 years; 32% were women, and 42% were black. Those in the mobile technology group attended a higher number of prescribed sessions (mean 28 vs. 22), RR: 1.17 (95% CI: 1.04-1.32, p=0.009), were 1.8 times more likely to complete the cardiac rehabilitation program (p=0.01), and had a slightly greater weight loss (lbs) post rehabilitation: -1.71 (95% CI: -0.30, -3.11, p=0.02) as compared to those in the Standard group; other outcomes were similar between the groups (Table 1). Conclusion: In a propensity-matched, racially diverse population, we found that adjunctive use of mobile technology significantly improved adherence to cardiac rehabilitation and number of attended sessions.

A Machine Learning Approach to Estimate Hip and Knee Joint Loading Using a Mobile Phone-Embedded IMU

Hip osteoarthritis patients exhibit changes in kinematics and kinetics that affect joint loading. Monitoring this load can provide valuable information to clinicians. For example, a patient's joint loading measured across different activities can be used to determine the amount of exercise that the patient needs to complete each day. Unfortunately, current methods for measuring joint loading require a lab environment which most clinicians do not have access to. This study explores employing machine learning to construct a model that can estimate joint loading based on sensor data obtained solely from a mobile phone. In order to learn such a model, we collected a dataset from 10 patients with hip osteoarthritis who performed multiple repetitions of nine different exercises. During each repetition, we simultaneously recorded 3D motion capture data, ground reaction force data, and the inertial measurement unit data from a mobile phone attached to the patient's hip. The 3D motion and ground reaction force data were used to compute the ground truth joint loading using musculoskeletal modeling. Our goal is to estimate the ground truth loading value using only the data captured by the sensors of the mobile phone. We propose a machine learning pipeline for learning such a model based on the recordings of a phone's accelerometer and gyroscope. When evaluated for an unseen patient, the proposed pipeline achieves a mean absolute error of 29% for the left hip and 36% for the right hip. While our approach is a step in the direction of using a minimal number of sensors to estimate joint loading outside the lab, developing a tool that is accurate enough to be applicable in a clinical context still remains an open challenge. It may be necessary to use sensors at more than one location in order to obtain better estimates.

The Role of Paracetamol (acetaminophen) in the Reduction of Tremor in Parkinson’s Disease – a Case Study

Parkinson’s disease (PD) affects millions of people. Tremor is a common symptom. Treatment with levodopa can reduce tremor but is associated with “off periods” when the tremor returns as the dose wear off. The association of levodopa with neurotoxicity needs to be managed. This case study demonstrates the potential role of paracetamol (acetaminophen) in reducing tremor by extending the duration of levodopa efficacy. The case study aimed to confirm visual observations of tremor reduction associated with paracetamol medication. It utilised a mobile phone accelerometer and a software application to monitor the tremor of a subject with PD. The data produced provided information on frequency and variations in the intensity of the tremor. It was found that paracetamol alone does not appear to be effective at reducing tremor. The results show that paracetamol can reduce tremor in subjects during the period when their levodopa dose is usually wearing off particularly in the case of tremor concurrent with arm pain. There have been previous reports of a role for paracetamol or more particularly one of its metabolites, N-acetyl-p-benzoquinonimine, (NAPQI) in inhibiting pain signals in the spinal column. This could partly explain the theoretical basis for the reduction in tremor in this case.

Weighted consensus clustering and its application to Big data

The aim of this study is the development of a weighted consensus clustering that assigns weights to single clustering methods using the purity utility function. In the case of Big data that does not contain labels, the utility function based on the Davies-Bouldin index is proposed in this paper. The Banknote authentication, Phishing, Diabetic, Magic04, Credit card clients, Covertype, Phone accelerometer, and NSL-KDD datasets are used to assess the efficiency of the proposed consensus approach. The proposed approach is evaluated using the Euclidean, Minkowski, squared Euclidean, cosine, and Chebychev distance metrics. It is compared with single clustering algorithms (DBSCAN, OPTICS, CLARANS, k-means, and shared nearby neighbor clustering). The experimental results show the effectiveness of the proposed approach to the Big data clustering in comparison to single clustering methods. The proposed weighted consensus clustering using the squared Euclidean distance metric achieves the highest accuracy, which is a very promising result for Big data clustering. It can be applied to expert systems to help experts make group decisions based on several alternatives. The paper also provides directions for future research on consensus clustering in this area.

Monitoring Patient Recovery After THA or TKA Using Mobile Technology.

Smartphones offer the possibility of assessing recovery of mobility after total hip or knee arthroplasty (THA or TKA) passively and reliably, as well as facilitating the collection of patient-reported outcome measures (PROMs) with greater frequency. We investigated the feasibility of using mobile technology to collect daily step data and biweekly PROMs to track recovery after total joint arthroplasty. Pre- and post-operative daily steps were recorded in prospectively enrolled patients (128 THA and 139 TKA) via an app, which uses the phone's accelerometer. During 6-month follow-up, patients also completed PROMs (the pain numeric rating scale, the Hip Disability and Osteoarthritis Outcome Score Joint Replacement [HOOS JR] and the Knee Injury and Osteoarthritis Outcome Score Joint Replacement [KOOS JR]), and HOOS or KOOS JR quality of life domain via a mobile-enabled web link. At least 6months of follow-up was completed by 65% for THA and 68% for TKA patients. Reasons for non-completion included time commitment, phone battery, app issues, and health complications. Responses from 78% of requested PROMs were returned with 96% of patients returning at least one post-operative PROM. Step data were available from 92% of days from malepatients and 86% of days from female patients. The most robust recovery occurred early, within the first 2months. The groups with higher pre-operative steps were more likely to recover their maximum daily steps at an earlier time point. Correlations between step counts and PROMs scores were modest. Assessing large amounts of post-TKA and post-THA step data using mobile technology is feasible. Completion rates were good, making the technology very useful for collecting frequent PROMs. Being unable to ensure that patients always carried their phones limited our analysis of the step counts.

Intelligent Vehicle Speed Controlling and Pothole Detection System

Speed is the single largest killer on India’s roads. The higher the speed, the greater the impact and the more the chances of grievous injury and death. This is why speed management is something which needs to be seriously considered. Here is an approach to build a system which reduces the number of accidents due to driver’s negligence of over speeding. We are proposing a Dynamic Speed Limiter with the help of machine learning algorithm which will help in reducing the accidents caused due to over speeding and rash driving of vehicles on road. The proposed system set the maximum speed of vehicle with the help of sign board available on the roads which define the safe driving speed of vehicle for that area or road. Also to solve the potholes we are using ML algorithm and mobile phone accelerometer to detect the potholes, accelerometer vibrations are set. After detecting the vibrations, the location (i.e. longitude and latitude) is marked on the GPS, commuters will get information about potholes.

Classification of Human Gait: Swing and Stance Phases using Sum-Vector Analysis

Recent advances in low-cost wearable sensors with methodologies, have opened up a promising future for gait analysis. By providing patient analysis with gait disorders from clinics to common people the analysis requires some form of précised user input. The purpose of this study was to develop a computationally low-cost methodology that could evaluate the performance of different sensor configurations and to study the effect of locomotion mode for swing and stance using kinematic data from hip, knee and ankle extracted using mobile phone accelerometers. The method involved features translated as sum vectors and then using a simple neural network where gait data was normalized and classified the swing or stance. Sum-vector neural network-based method allowed a significantly higher test accuracy compared to the other machine learning algorithms. As an extended gait analysis model focusing predictive applications and implementations that need faster computations, the method could classify the gait kinetic and kinematics of human lower limb more optimally.

Multimode Pedestrian Dead Reckoning Gait Detection Algorithm Based on Identification of Pedestrian Phone Carrying Position

Pedestrian dead reckoning (PDR) is an essential technology for positioning and navigation in complex indoor environments. In the process of PDR positioning and navigation using mobile phones, gait information acquired by inertial sensors under various carrying positions differs from noise contained in the heading information, resulting in excessive gait detection deviation and greatly reducing the positioning accuracy of PDR. Using data from mobile phone accelerometer and gyroscope signals, this paper examined various phone carrying positions and switching positions as the research objective and analysed the time domain characteristics of the three-axis accelerometer and gyroscope signals. A principal component analysis algorithm was used to reduce the dimension of the extracted multidimensional gait feature, and the extracted features were random forest modelled to distinguish the phone carrying positions. The results show that the step detection and distance estimation accuracy in the gait detection process greatly improved after recognition of the phone carrying position, which enhanced the robustness of the PDR algorithm.

Assessment of Ultra-Short Heart Variability Indices Derived by Smartphone Accelerometers for Stress Detection.

Body acceleration due to heartbeat-induced reaction forces can be measured as mobile phone accelerometer (m-ACC) signals. Our aim was to test the feasibility of using m-ACC to detect changes induced by stress by ultra-short heart rate variability (USV) indices (standard deviation of normal-to-normal interval—SDNN and root mean square of successive differences—RMSSD). Sixteen healthy volunteers were recruited; m-ACC was recorded while in supine position, during spontaneous breathing at rest conditions (REST) and during one minute of mental stress (MS) induced by arithmetic serial subtraction task, simultaneous with conventional electrocardiogram (ECG). Beat occurrences were extracted from both ECG and m-ACC and used to compute USV indices using 60, 30 and 10 s durations, both for REST and MS. A feasibility of 93.8% in the beat-to-beat m-ACC heart rate series extraction was reached. In both ECG and m-ACC series, compared to REST, in MS the mean beat duration was reduced by 15% and RMSSD decreased by 38%. These results show that short term recordings (up to 10 s) of cardiac activity using smartphone’s accelerometers are able to capture the decrease in parasympathetic tone, in agreement with the induced stimulus.