Accelerometer Sensor Research Articles

Optimization of the machining of metallic additive manufacturing supports: first methodological approach

Metal additive manufacturing is an active field of innovation. However, for laser power bed fusion (LPBF), supports removal is a major constraint. In this technology, supports are strongly welded to the part to tightly maintain it, avoid distortion, and evacuate thermal load. Although supports are usually optimized for manual removal, machining is often necessary, which can affect post-processing productivity. This paper proposes a comprehensive methodological approach to optimize the selection of cutting parameters, cutting tools, and support structure for LPBF. The aim is to help additive manufacturers find supports that reduce machining costs in terms of time and cutting tool degradation, from among the numerous support designs available. This approach can also optimize the design of lattice structures used inside parts. Our results show that among the 11 designs tested, honeycomb and squared pattern grid supports are the most efficiently machined using the 8-teeth tangential milling of the 3 tools tested, with a good post-machined surface roughness and tools’ health. The method considers low magnification optical analysis and an accelerometer sensor, which is easy to use even for small- and medium-sized enterprises. This paper also proposes and analyzes a new kind of porous support using this method.

Evaluating Behavior Recognition Pipeline of Laying Hens Using Wearable Inertial Sensors.

Recently, animal welfare has gained worldwide attention. The concept of animal welfare encompasses the physical and mental well-being of animals. Rearing layers in battery cages (conventional cages) may violate their instinctive behaviors and health, resulting in increased animal welfare concerns. Therefore, welfare-oriented rearing systems have been explored to improve their welfare while maintaining productivity. In this study, we explore a behavior recognition system using a wearable inertial sensor to improve the rearing system based on continuous monitoring and quantifying behaviors. Supervised machine learning recognizes a variety of 12 hen behaviors where various parameters in the processing pipeline are considered, including the classifier, sampling frequency, window length, data imbalance handling, and sensor modality. A reference configuration utilizes a multi-layer perceptron as a classifier; feature vectors are calculated from the accelerometer and angular velocity sensor in a 1.28 s window sampled at 100 Hz; the training data are unbalanced. In addition, the accompanying results would allow for a more intensive design of similar systems, estimation of the impact of specific constraints on parameters, and recognition of specific behaviors.

Mobile and wearable technologies for the analysis of Ten Meter Walk Test: A concise systematic review

Physical issues started to receive more attention due to the sedentary lifestyle prevalent in modern culture. The Ten Meter Walk Test allows measuring the person’s capacity to walk along 10 m and analyzing the advancement of various medical procedures for ailments, including stroke. This systematic review is related to the use of mobile or wearable devices to measure physical parameters while administering the Ten Meter Walk Test for the analysis of the performance of the test. We applied the PRISMA methodology for searching the papers related to the Ten Meter Walk Test. Natural Language Processing (NLP) algorithms were used to automate the screening process. Various papers published in two decades from multiple scientific databases, including IEEE Xplore, Elsevier, Springer, EMBASE, SCOPUS, Multidisciplinary Digital Publishing Institute (MDPI), and PubMed Central were analyzed, focusing on various diseases, devices, features, and methods. The study reveals that chronometer and accelerometer sensors measuring spatiotemporal features are the most pertinent in the Gait characterization of most diseases. Likewise, all studies emphasized the close relation between the quality of the sensor’s data obtained and the system’s ultimate accuracy. In other words, calibration procedures are needed because of the body part where the sensor is worn and the type of sensor. In addition, using ambient sensors providing kinematic and kinetic features in conjunction with wearable sensors and consistently acquiring walking signals can enhance the system’s performance. The most common weaknesses in the analyzed studies are the sample size and the unavailability of continuous monitoring devices for measuring the Ten Meter Walk Test.

Design and Simulation of a GSM, Buzzer, and GPS Module-Based Accident Detection System

The average number of automobiles on the roads around the world has increased as cars become more and more accessible. Our lives are now easier because to the technology and infrastructure that are developing quickly. Technology has also increased the frequency of traffic risks and road accidents, which result in significant loss of life and property due to inadequate emergency resources. Accidents wreak havoc on victims, costing them valuable time and money. It has been determined via considerable research that the majority of accidents result in fatalities as a result of poor communication with the relevant medical authorities and the ensuing dearth of prompt medical assistance. In this study, an accelerometer can be applied as a rollover or crash detector for the car both during and after a collision. The vibration sensor can also be employed in research to measure the vibration rates of any vehicle. A serious accident can be identified by keeping an eye on the information from the accelerometer and vibration sensor. The police control center, any rescue team, or the owners of the vehicle are then sent the alert message via the GSM module, together with the latitude and longitude information provided by the GPS module. As a result, as soon as they receive the emergency notification, the police can locate the accident's site and take the appropriate action. When an accident occurs in a remote place and no one is available to report it, this technique may prove to be a lifesaver. By responding quickly, the emergency services can prevent an accident from happening and save a life.

Driver Predicting Behavior Based on Accelerometer and Gyroscope Sensors with K-Means Algorithm Method

The transportation with an increasing population level in Indonesia will also affect the smoothness of traffic. However, with the existence of transportation that is owned by someone, it is often misused in driving. Aggressive driving behavior is a major factor in traffic accidents. As reported AAA Foundation for Traffic Safety, 106,727 dangerous accidents – 55.7 percent of the over past four year period involved drivers engaging in one or more acts of aggressive driving. Therefore, to predict driver behavior, the K-Means algorithm used the Orange Application. Using the driver behavior dataset that has been recorded with Accelerometer and Gyroscope Sensor-based applications, the results obtained where the k value is the number of cluster 1 there are 814 items, cluster 2 has 997 items, cluster 3 has 1273 items. From this test, it was found that proportion of predicted driver behavior with Aggressive qualifications was 96.4%, Normal was 92.2% and from driver behavior with Low qualifications was 74.3%. The accuracy rate of research using the K-Means algorithm to determine predictions is 0.861 or 86.1%. The results of predictions can help prevent accidents or other risks that will occur in the future.

Noise effects analysis on subspace-based damage detection with neural networks

Structural health monitoring (SHM) is nowadays a significant and topical issue in the civil engineering field, whose first-level task is the damage detection job. Recent advances in artificial intelligence (AI) combined with non-destructive assessments based on output-only vibration signals represent the frontier of SHM. The present research study has handled an AI-based multi-class damage classification task on a numerical benchmark beam problem with three different procedures. The main purpose was to investigate the noise effects of the analyzed damage detection procedures simulating real-world accelerometer sensors. The first damage identification method leverages simple statistical features of vibration signals, whereas the second method additionally considers a subspace-based damage indicator. The third method relies on a dataset composed of a specific set of damage indicators. Two deep learning (DL) techniques have been adopted to compare and verify the results, i.e. a multi-layer perceptron (MLP) and a one-dimensional convolutional network (1D-CNN). Three groups of different reasonable signal-to-noise ratio (SNR) levels were set up to simulate micro electro-mechanical system (MEMS) accelerometer sensors in real-world conditions to evaluate noise effects. In a nutshell, the results demonstrated that the DL models based on stochastic subspace identification (SSI) methods have good noise immunity performance for damage detection purposes.

An Alternative System for Assessing Pavement Condition in the Event of an Epidemic: A Case of COVID-19

Maintaining the efficiency of road pavement is essential to achieving the highest road performance and comfort for road users. Pavement monitoring plays a significant role in maintaining the sustainability of road networks. Additionally, assessments have been performed using different equipment and devices or through visual inspections to determine the type and severity of pavement degradation. However, some obstacles may affect the sustainability of road networks by preventing the regular monitoring and maintenance of pavements, such as the COVID-19 pandemic. Due to the COVID-19 pandemic, the construction and management of transportation systems have been affected by economic shut-downs and imposed social restrictions. Road networks have also suffered from neglect and a lack of monitoring and maintenance due to the government’s lockdowns in addition to strict regulations that limit movement on roads and any form of construction, monitoring, inspection, and evaluation to improve road pavement conditions. This research introduces a safe pavement monitoring system using an e-bike to evaluate and predict pavement degradation. An accelerometer sensor and line-scan camera were used to collect pavement vibration data during the e-bike’s movement. The results of the proposed monitoring method showed reliable evaluation outcomes. Moreover, the SVM model showed a significant contribution to detecting and classifying pavement distress.

Prediction of displacement in Reinforced concrete based on artificial neural networks using sensors

Although structural health monitoring (SHM) is widely used in civil engineering, researchers are working to enhance its accuracy. In previous laboratory experiments, four types of sensors, namely force resisting sensor (FSR), piezoelectric sensor (PZS), microelectromechanical system (MEMS) accelerometer sensor, and flex sensor (FLS), were employed to predict load-displacement in Reinforced Concrete (RC) beams subject to monotonic two-point loading. Static loading was performed in the laboratory. The results demonstrated that MEMS sensors outperformed the other three sensors. Consequently, only MEMS sensors were used in the ANN model to predict the error percentage. This study compared the static results of previous experiments to those obtained from an Artificial Neural Network (ANN) model that used the beam's position and load as input parameters to predict displacement. The results revealed that the non-linear ANN model produced positive outcomes. Therefore, SHM is likely to utilize MEMS sensors in various civil engineering applications.

Wheelchair control system with hand movement using accelerometer sensor

Disability is a condition where there is an imbalance of interaction between biological conditions with the surrounding environment, which includes disruption, limited activities, and restrictions on participation. With the increasing population of people with disabilities in walking, either due to congenital physical disabilities, accidents, or motor functions due to aging, the need for wheelchairs increases. In this research, a wheelchair control system with hand movements using an accelerometer sensor was made. The system consists of a transmitter on the back of the hand and a receiver on the wheelchair. In the transmitter's part, MPU-6050 sensor detects hand movements, whereby hand movements can be upward, downward, straight, left tilted, and right tilted. The data from MPU-6050 sensor was processed by Arduino Nano then sent using the nRF24L01 module. In the receiver's part, the data were processed by Arduino Uno which activates the BTS7960 motor drive module and drives the DC motor. The test results show that hand movements with an angle of 45° can move the wheelchair forward, backward, turn right, turn left, and stop at a speed of 2 km/h with a maximum test load of 80 kg.

Continuous User Authentication on Multiple Smart Devices

Recent developments in the mobile and intelligence industry have led to an explosion in the use of multiple smart devices such as smartphones, tablets, smart bracelets, etc. To achieve lasting security after initial authentication, many studies have been conducted to apply user authentication through behavioral biometrics. However, few of them consider continuous user authentication on multiple smart devices. In this paper, we investigate user authentication from a new perspective—continuous authentication on multi-devices, that is, continuously authenticating users after both initial access to one device and transfer to other devices. In contrast to previous studies, we propose a continuous user authentication method that exploits behavioral biometric identification on multiple smart devices. In this study, we consider the sensor data captured by accelerometer and gyroscope sensors on both smartphones and tablets. Furthermore, multi-device behavioral biometric data are utilized as the input of our optimized neural network model, which combines a convolutional neural network (CNN) and a long short-term memory (LSTM) network. In particular, we construct two-dimensional domain images to characterize the underlying features of sensor signals between different devices and then input them into our network for classification. In order to strengthen the effectiveness and efficiency of authentication on multiple devices, we introduce an adaptive confidence-based strategy by taking historical user authentication results into account. This paper evaluates the performance of our multi-device continuous user authentication mechanism under different scenarios, and extensive empirical results demonstrate its feasibility and efficiency. Using the mechanism, we achieved mean accuracies of 99.8% and 99.2% for smartphones and tablets, respectively, in approximately 2.3 s, which shows that it authenticates users accurately and quickly.

Examining gender differences in gait parameters between non-smoker and smoker participants.

Smoking is one of the predictors of decreased cardiopulmonary endurance. Gait disturbance may be due to many reasons, including cardiovascular endurance. This study aimed to determine differences in gait parameters between non-smoker and smoker participants. A cross-sectional design was employed, involving thirty non-smokers and thirty-seven smokers as participants. Detailed interviews were conducted to gather information on smoking habits, status, and history. Gait parameters were measured using a high-quality 3D accelerometer, 3D gyroscope, and barometric pressure sensors (Physilog4 from GaitUp). Anthropometric characteristics were described, and mean values with standard deviations (SD) were calculated. An independent two-tailed t-test was conducted to compare gait parameters between non-smokers and smokers, with statistical significance set at p<0.05. The analysis revealed significant differences in various gait parameters between non-smokers and smokers. Specifically, significant differences were found in cadence (t=9.95, p=0.001), stride length (t=6.85, p=0.001), stride velocity (t=-6.58, p=0.001), stance (t=2.02, p=0.001), swing (t=3.46, p=0.001), foot flat (t=-8.94, p=0.001), pushing (t=3.53, p=0.001), and double support (t=-13.35, p=0.001). However, no significant difference was found between non-smokers and smokers in the loading phase (t=-1.57, p= 0.121). There were significant differences in general and temporal gait parameters between smokers and non-smokers. Gait parameters provide valuable insights for evaluating functional performance and providing objective and quantitative data to assess gait disorders. Future studies should include longitudinal studies with large sample sizes to explore the effects of potential confounders on gait parameters.

Smart Suspenders With Sensors and Machine Learning for Human Activity Monitoring

Most of the Human Activity Recognition (HAR) research focuses on the use of smartphone in-built accelerometer sensors. As accelerometers are location-centric, they measure acceleration signals only at the installation points, increasing the number of sensors required to identify the whole human body activity. They have an inherent property of being noisy, thereby increasing the processing complexity and duration. This paper, for the first time, proposes a body-worn suspender integrated with a strain sensor system that captures the body movement’s periodicity, resulting in less noisy readings with non-localized measurements. The proposed smart suspender system reduces the need for localized sensors to measure complex activities at various points and lessen the pre-processing time for smoothening the noise signals. The system recognizes three simple and eleven complex human activities using machine and deep learning algorithms with best accuracy value of 97.85%. A comparison of the performance between kernel and linear discriminant analysis (KDA and LDA) for this system is made and KDA outperformed LDA across most classifiers.

Advanced Version of Voice for Deaf and Dumb Persons

Abstract: Normal and dumb individuals can naturally communicate with one another using sign language, but people hasn’t comprehend their sign language, they frequently struggle to do so. The major goal of this initiative is to lessen the communication gap between deaf-dumb persons and other people. The suggested device transforms their hand motions into voice that a layperson may comprehend in order to lessen this barrier. Gloves, accelerometer and flex sensors, a microprocessor, a voice module, and a 16x16 LCD display make up this device. To put it simply, the voice module will translate the gestures into real-time speech output, and the display will provide text foreach corresponding gesture. So, this device offers both deaf - dumb and sighted people an effective means of communication.

Evaluation of Cable Tension Using Static and Dynamic Test on R.H. Fisabilillah Cable-Stayed Bridge, Batam-Indonesia

R.H. Bridge Fisabilillah (Bridge I) is a cable-stayed bridge, included in the series of Barelang Bridges (Batam-Rempang-Galang) which were built from 1992 to 1998. With the service life of the bridge reaching 25 years, it is necessary to check the health condition of the bridge structure. Bridge cables are one of the most important elements of a cable-stayed bridge. These cable elements dominantly experience tensile forces when transmitting loads from the decks to the bridge pylons. Cable force inspection methods can be carried out through the direct measurement method (e.g. static test using a lift-off method) and indirect measurement (e.g. dynamic test using accelerometer sensors, electromagnetic/EM sensors, and so on). This study aims to compare the cable tensile force based on the static test (lift-off method) in 2017 against the dynamic test (accelerometer sensors) in 2022. Evaluation of the cable tensile force based on the dynamic test was carried out using the taut string theory and beam string theory approaches. From the study, the two empirical approaches yielded insignificantly different results where a difference in the mean difference of -1,71% was found with a maximum difference of 28,15%. The study also shows an increase in cable force capacity to a maximum of 47,20% UTS (ultimate tensile strength) based on the taut string theory and a maximum of 53.37% UTS based on the beam string theory. This value is greater when compared to the results of the cable force based on the static test (lift-off) in 2017, which was a maximum of 41.64% UTS. It is recommended to carry out further and more comprehensive studies to determine the effect of changes in cable force distribution on the behavior of the structure on the R.H. Fisabilillah Bridge.

Design of Earthquake Warning Alarm Using Accelerometer Sensor Based on Internet of Things

Earthquake is natural event due to release of energy suddenly from within that creates seismic waves. The vibrations are usually caused by movement of earth's plates. It cannot be predicted when they are coming. Therefore, need to build an early warning system. It is for anticipation of save the community when an earthquake occurs. It provides solutions to minimize the impact of earthquake events. This system uses accelerometer sensor and arduino nano as a main controller and it is accompanied by Blynk application. This works for sent notification via smartphone. This tool has been successfully designed with manual testing to be able to see the sensitivity of earthquake sensor made. Accelerometer sensor works is using Tilt Method. Accelerometer sensor will tilt on surface as parable of earthquake. Accelerometer sensor will send vibration signal when earthquake occurs. Signal processing is done by Arduino nano as the main controller in system. If the signal is received by sensor then value of earthquake will be displayed on LCD screen. Status of earthquake was separated into 4 levels such as standby, alert, dangerous, dangerous and dangerous. After earthquake value appears on the LCD screen and the status is known then buzzer will sound. It indicates that the earthquake warning alarm is properly functioning. Next, NodeMCU also sends information to Blynk application, which is used as a notification and monitoring of earthquake conditions. Buzzer will sound as a warning alarm to notify peoples to save themselves. This sensor has three output coordinate points, namely X, Y, Z, which have analog values ​​on Arduino Nano. This analog value can be converted into Richter Scale. Based on experimental results, an analog value is 100 – 400.

Health monitoring of ultra high fiber performance reinforced concrete communication tower using machine learning algorithms

Within the last decades, the needed for communication towers has accelerated with the requirements for effective communication, especially for radio, radar, and television. The complexity configuration of the tower and limit access to the structure body especially inner part of the tower with hollow section is led the health monitoring of tower as the main challenging issue to maintenance during its function. The change of natural frequencies can be considered as one of the prevalent damage detection methods in structural assessment procedures. Therefore, the main aim of present research is to develop health monitoring system for Ultra High Fiber Performance Reinforced Concrete (UHPFRC) communication tower based on frequency domain response. Since the frequency data of tower is mostly noisy and interpreting of frequency in different modes in variant case of tower damage. The hybrid algorithm based on the Adaboost, Bagging and RUSBoost algorithms are implemented to identify the damage in the UHPFRC communication tower using frequency domain data. The training samples for the algorithm are obtained from a finite element simulation and full-scale experiment testing is also performed to generate the testing samples. The finite element simulation dynamic frequency results are verified through conducting a full-scale experimental test on 30 m height UHPFRC communication tower. For this propose, frequency Response Functions (FRF’s), for healthy and damaged structures were obtained by exciting of tower by an impact hammer and the acceleration response recorded by three accelerometers sensors attached in suitable positions. The developed hybrid algorithm to identifying the damage is tested and verified by considering the part of tower segments 2–3 and conducting experimental testing on the healthy structure as well as a damaged structure which caused using dynamic actuator. The testing results proved the accuracy of the developed optimized hybrid algorithm to identify damage in the tower structure in variant condition.

TN-GAN-Based Pet Behavior Prediction through Multiple-Dimension Time-Series Augmentation.

Behavioral prediction modeling applies statistical techniques for classifying, recognizing, and predicting behavior using various data. However, performance deterioration and data bias problems occur in behavioral prediction. This study proposed that researchers conduct behavioral prediction using text-to-numeric generative adversarial network (TN-GAN)-based multidimensional time-series augmentation to minimize the data bias problem. The prediction model dataset in this study used nine-axis sensor data (accelerometer, gyroscope, and geomagnetic sensors). The ODROID N2+, a wearable pet device, collected and stored data on a web server. The interquartile range removed outliers, and data processing constructed a sequence as an input value for the predictive model. After using the z-score as a normalization method for sensor values, cubic spline interpolation was performed to identify the missing values. The experimental group assessed 10 dogs to identify nine behaviors. The behavioral prediction model used a hybrid convolutional neural network model to extract features and applied long short-term memory techniques to reflect time-series features. The actual and predicted values were evaluated using the performance evaluation index. The results of this study can assist in recognizing and predicting behavior and detecting abnormal behavior, capacities which can be applied to various pet monitoring systems.

Transfer Learning Approach for Indoor Localization with Small Datasets

Indoor pedestrian localization has been the subject of a great deal of recent research. Various studies have employed pedestrian dead reckoning, which determines pedestrian positions by transforming data collected through sensors into pedestrian gait information. Although several studies have recently applied deep learning to moving object distance estimations using naturally collected everyday life data, this data collection approach requires a long time, resulting in a lack of data for specific labels or a significant data imbalance problem for specific labels. In this study, to compensate for the problems of the existing PDR, a method based on transfer learning and data augmentation is proposed for estimating moving object distances for pedestrians. Consistent high-performance moving object distance estimation is achieved using only a small training dataset, and the problem of the concentration of training data only on labels within a certain range is solved using window warping and scaling methods. The training dataset consists of the three-axes values of the accelerometer sensor and the pedestrian’s movement speed calculated based on GPS coordinates. All data and GPS coordinates are collected through the smartphone. A performance evaluation of the proposed moving pedestrian distance estimation system shows a high distance error performance of 3.59 m with only approximately 17% training data compared to other moving object distance estimation techniques.

Toward Real-Time, Robust Wearable Sensor Fall Detection Using Deep Learning Methods: A Feasibility Study

Real-time fall detection using a wearable sensor remains a challenging problem due to high gait variability. Furthermore, finding the type of sensor to use and the optimal location of the sensors are also essential factors for real-time fall-detection systems. This work presents real-time fall-detection methods using deep learning models. Early detection of falls, followed by pneumatic protection, is one of the most effective means of ensuring the safety of the elderly. First, we developed and compared different data-segmentation techniques for sliding windows. Next, we implemented various techniques to balance the datasets because collecting fall datasets in the real-time setting has an imbalanced nature. Moreover, we designed a deep learning model that combines a convolution-based feature extractor and deep neural network blocks, the LSTM block, and the transformer encoder block, followed by a position-wise feedforward layer. We found that combining the input sequence with the convolution-learned features of different kernels tends to increase the performance of the fall-detection model. Last, we analyzed that the sensor signals collected by both accelerometer and gyroscope sensors can be leveraged to develop an effective classifier that can accurately detect falls, especially differentiating falls from near-falls. Furthermore, we also used data from sixteen different body parts and compared them to determine the better sensor position for fall-detection methods. We found that the shank is the optimal position for placing our sensors, with an F1 score of 0.97, and this could help other researchers collect high-quality fall datasets.

Thermoelectric energy harvesting for wireless onboard rail condition monitoring

ABSTRACT A thermoelectric energy harvesting device is evaluated to power a bearing health monitoring system. Unlike wayside equipment, the new system is an onboard wireless solution utilizing accelerometer and temperature sensors to assess the bearing condition continuously. The harvesting system consists of two thermoelectric generator modules with aluminium heat sinks, a switching boost converter, a battery management circuit, and a lithium rechargeable battery. The performance of the harvester is validated on an AAR class bearing mounted on a laboratory tester, with load and speed simulating common freight routes of up to 896 miles. The energy harvested varies with operating conditions, and data is presented showing the effect of load and speed. Over a realistic route, the net energy harvested is more than double that needed to indefinitely power a Bluetooth Low Energy sensor. The critical design parameters are the ratio of open-circuit voltage to the temperature difference for the thermoelectric module, and the cold start voltage of the boost converter.