• Journal of the Korean Society of Propulsion Engineers
• /
• v.22 no.4
• /
• pp.61-67
• /
• 2018

High-frequency signals are analyzed at the inlet/outlet pipeline and pump casing during cavitation tests of the LOx pump for liquid rocket engines. Root-mean square values of all data are investigated with respect to cavitation number. The values of synchronous, harmonic, and cavitation instability frequencies are also calculated. Pressure pulsations of the inlet and outlet pipelines are affected by cavitation instabilities. The 3x component (i.e., the blade-passing frequency of the inducer) is predominant in the outlet pulsation sensor. This seems to be related to the fact that the number of impeller blades is a multiple of the number of the inducer blades. The cavitation instability is also measured at the accelerometer of the pump casing.

• Journal of the Regional Association of Architectural Institute of Korea
• /
• v.20 no.6
• /
• pp.47-54
• /
• 2018

The purpose of this study is to verify the long - range measurement performance for practical field application of VDMS. The reliability of the VDMS was verified by comparison with the existing monitoring sensor, GPS, Accelerometer and LDS. It showed the ability to accurately measure the dynamic displacement by tracking a motion of free vibration of target. And using the PSD function of measured data, the results in the frequency domain were also analyzed. We judged that VDMS is able to identify the higher system mode and has sufficient reliability. Based on the reliability verification, we conducted tests for long-distance applicability for actual application of VDMS. The distance from the stationary target model structure was increased by 50m interval, and the maximum distance was set to 400m. From the distance of 150m, the image obtained by the commercial camcorder has an error in the analysis, so the measured displacement comparison was performed between the LDS and the refractor telescope measurement results. In the measurement results of the displacement area of VDMS, the data validity was deteriorated due to the data shift by the external force and the quality degradation of the enlarged image. However, even under the condition that the effectiveness of the displacement measurement data of VDMS is low, the first mode characteristic included in the free vibration of the object is clearly measured. If the influence from the external environment is controlled and stable data is collected, It is judged that reliability of long-distance VDMS can be secured.

• Journal of Biomedical Engineering Research
• /
• v.41 no.6
• /
• pp.247-255
• /
• 2020

Accurate diagnosis of movement disorders is important for providing right patient care at right time. In general, assessment of motor impairment relies on clinical ratings conducted by experienced clinicians. However, this may introduce subjective opinions into scoring the severity of motor impairment. Digital devices such as table PC and smart band with accelerometer can be used for more accurate and objective assessment and possibly helpful for clinicians to make right decision of patient's states. In this study, we introduce quantification algorithms of motor impairment which uses the digital data acquired during four clinical motor tests (Line drawing, Spiral drawing, Nose to finger and Hand flip tests). The step by step procedure of quantifying metrics (Tremor Frequency, Tremor Magnitude, Error Distance, Time, Velocity, Count and Period) are provided with flowchart. The effectiveness of the proposed algorithm is presented with the result from simulated data (normal, normal with tremor and slowness, poor with tremor, poor with tremor and slowness).

• Korean Journal of Applied Biomechanics
• /
• v.31 no.1
• /
• pp.16-23
• /
• 2021

Objective: The purpose of the study was to compare the acceleration and shock attenuation (SA) of the runners with/without low back pain (LBG vs. NLBG) while running at 2.5 m/s, 3.0 m/s, 3.5 m/s and 4.0 m/s. Method: 15 adults without low back pain (age: 23.13±3.46 years, body weight: 70.13±8.94 kg, height: 176.79±3.68 cm, NLBG) and 7 adults with low back pain (age: 27.14±5.81 years, body weight: 73.10±10.74 kg, height: 176.41±3.13 cm, LBG) participated in this study. LBG was recruited through the VAS pain rating scale. All participants ran on an instrumented treadmill (Bertec, USA). Results: The LBG shows statistically greater vertical acceleration at the distal tibia during running at 3.5 m/s and 4.0 m/s and greater shock attenuation from the distal tibia to the head during running at 3.5 m/s compared with the NLBG during running (p<.05). As the speed increased, there was a statistically significant increase in vertical/resultant acceleration and shock attenuation for both groups. Conclusion: The findings indicated that the runners with low back pain (LBG) experience greater impact and shock attenuation compared with non-low back pain group (NLBG) during fast running. However, it is still inconclusive whether high impact on the lower extremity during running is the main cause of low back pain in the population. Thus, it is suggested that the study on low back pain should observe the characteristics of impact during running with individuals' low back pain experience and clinical symptoms.

• Journal of Creative Information Culture
• /
• v.7 no.4
• /
• pp.235-242
• /
• 2021

Recently, many human activity recognition(HAR) researches using smartphone sensor data have been studied. HAR can be utilized in various fields, such as life pattern analysis, exercise measurement, and dangerous situation detection. However researches have been focused on recognition of basic human behaviors or efficient battery use. In this paper, exercising activities performed indoors and outdoors were defined and recognized. Data collection and pre-processing is performed to recognize the defined activities by SVM, random forest and gradient boosting model. In addition, the recognition result is determined based on voting class approach for accuracy and stable performance. As a result, the proposed activities were recognized with high accuracy and in particular, similar types of indoor and outdoor exercising activities were correctly classified.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.30 no.1C
• /
• pp.27-35
• /
• 2010

Instrumented steel sheet piles being driven by vibratory pile driver were installed in granular soil deposit and behaviors of the sheet piles were investigated. One of the instrumented steel sheet pile was installed without clutch and the other was installed with clutch. Sheet pile with clutch means that of installed in connection with pre-installed sheet pile. Penetration rates of sheet piles measured from depth measuring drum has shown that interlock friction had great effect on penetration speed of sheet pile. Clutch friction shows irregular distribution along the depths of penetration and its magnitude was estimated as 19.1kN/m. According to the accelerations obtained from accelerometer, it was seen that steel sheet pile behaviored nearly as a rigid body. Efficiency factor of an isolated sheet pile was 0.42 and that of the connected sheet pile was 0.71. Shapes of dynamic load transfer curves obtained from analysis of measuring devices was similar to those suggested by Dierssen.

• Safety and Health at Work
• /
• v.15 no.1
• /
• pp.9-16
• /
• 2024

Background: E-waste workers in Hong Kong are handling an unprecedented amount of e-waste, which contains various neurotoxic chemicals. However, no study has been conducted to evaluate the neurological health status of e-waste workers in Hong Kong. This study aimed to evaluate the prevalence of neurobehavioral alterations and to identify the vulnerable groups among Hong Kong e-waste workers. Methods: We recruited 109 Hong Kong e-waste workers from June 2021 to September 2022. Participants completed standard questionnaires and wore a GENEActiv accelerometer for seven days. Pittsburgh Sleep Quality Index and Questionnaire 16/18 (Q16/18) were used to assess subjective neurobehavioral alterations. The GENEActiv data generated objective sleep and circadian rhythm variables. Workers were grouped based on job designation and entity type according to the presumed hazardous level. Unconditional logistic regression models measured the associations of occupational characteristics with neurobehavioral alterations after adjusting for confounders. Results: While dismantlers/repairers and the workers in entities not funded by the government were more likely to suffer from neurotoxic symptoms in Q18 (adjusted odds ratio: 3.18 [1.18-9.39] and 2.77 [1.10-7.46], respectively), the workers from self-sustained recycling facilities also have poor performances in circadian rhythm. Results also showed that the dismantlers/repairers working in entities not funded by the government had the highest risk of neurotoxic symptoms compared to the lowest-risk group (i.e., workers in government-funded companies with other job designations). Conclusion: This timely and valuable study emphasizes the importance of improving the working conditions for high-risk e-waste workers, especially the dismantlers or repairers working in facilities not funded by the government.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.6
• /
• pp.1478-1499
• /
• 2024

Coronavirus disease (COVID-19) is an infectious disease caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) virus. COVID-19 become an active epidemic disease due to its spread around the globe. The main causes of the spread are through interaction and transmission of the droplets through coughing and sneezing. The spread can be minimized by isolating the susceptible patients. However, it necessitates remote monitoring to check the breathing issues of the patient remotely to minimize the interactions for spread minimization. Thus, in this article, we offer a wearable-IoTs-centered framework for remote monitoring and recognition of the breathing pattern and abnormal breath detection for timely providing the proper oxygen level required. We propose wearable sensors accelerometer and gyroscope-based breathing time-series data acquisition, temporal features extraction, and machine learning algorithms for pattern detection and abnormality identification. The sensors provide the data through Bluetooth and receive it at the server for further processing and recognition. We collect the six breathing patterns from the twenty subjects and each pattern is recorded for about five minutes. We match prediction accuracies of all machine learning models under study (i.e. Random forest, Gradient boosting tree, Decision tree, and K-nearest neighbor. Our results show that normal breathing and Bradypnea are the most correctly recognized breathing patterns. However, in some cases, algorithm recognizes kussmaul well also. Collectively, the classification outcomes of Random Forest and Gradient Boost Trees are better than the other two algorithms.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.163-177
• /
• 2019

As smartphones are getting widely used, human activity recognition (HAR) tasks for recognizing personal activities of smartphone users with multimodal data have been actively studied recently. The research area is expanding from the recognition of the simple body movement of an individual user to the recognition of low-level behavior and high-level behavior. However, HAR tasks for recognizing interaction behavior with other people, such as whether the user is accompanying or communicating with someone else, have gotten less attention so far. And previous research for recognizing interaction behavior has usually depended on audio, Bluetooth, and Wi-Fi sensors, which are vulnerable to privacy issues and require much time to collect enough data. Whereas physical sensors including accelerometer, magnetic field and gyroscope sensors are less vulnerable to privacy issues and can collect a large amount of data within a short time. In this paper, a method for detecting accompanying status based on deep learning model by only using multimodal physical sensor data, such as an accelerometer, magnetic field and gyroscope, was proposed. The accompanying status was defined as a redefinition of a part of the user interaction behavior, including whether the user is accompanying with an acquaintance at a close distance and the user is actively communicating with the acquaintance. A framework based on convolutional neural networks (CNN) and long short-term memory (LSTM) recurrent networks for classifying accompanying and conversation was proposed. First, a data preprocessing method which consists of time synchronization of multimodal data from different physical sensors, data normalization and sequence data generation was introduced. We applied the nearest interpolation to synchronize the time of collected data from different sensors. Normalization was performed for each x, y, z axis value of the sensor data, and the sequence data was generated according to the sliding window method. Then, the sequence data became the input for CNN, where feature maps representing local dependencies of the original sequence are extracted. The CNN consisted of 3 convolutional layers and did not have a pooling layer to maintain the temporal information of the sequence data. Next, LSTM recurrent networks received the feature maps, learned long-term dependencies from them and extracted features. The LSTM recurrent networks consisted of two layers, each with 128 cells. Finally, the extracted features were used for classification by softmax classifier. The loss function of the model was cross entropy function and the weights of the model were randomly initialized on a normal distribution with an average of 0 and a standard deviation of 0.1. The model was trained using adaptive moment estimation (ADAM) optimization algorithm and the mini batch size was set to 128. We applied dropout to input values of the LSTM recurrent networks to prevent overfitting. The initial learning rate was set to 0.001, and it decreased exponentially by 0.99 at the end of each epoch training. An Android smartphone application was developed and released to collect data. We collected smartphone data for a total of 18 subjects. Using the data, the model classified accompanying and conversation by 98.74% and 98.83% accuracy each. Both the F1 score and accuracy of the model were higher than the F1 score and accuracy of the majority vote classifier, support vector machine, and deep recurrent neural network. In the future research, we will focus on more rigorous multimodal sensor data synchronization methods that minimize the time stamp differences. In addition, we will further study transfer learning method that enables transfer of trained models tailored to the training data to the evaluation data that follows a different distribution. It is expected that a model capable of exhibiting robust recognition performance against changes in data that is not considered in the model learning stage will be obtained.

• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.11
• /
• pp.537-542
• /
• 2017

Aggressive driving is a major cause of car accidents. Previous studies have mainly analyzed young driver's aggressive driving tendency, yet they were only done through pure clustering or classification technique of machine learning. However, since elderly people have different driving habits due to their fragile physical conditions, it is necessary to develop a new method such as enhancing the characteristics of driving data to properly analyze aggressive driving of elderly drivers. In this study, acceleration data collected from a smartphone of a driving vehicle is analyzed by a newly proposed ECA(Enhanced Clustering method for Acceleration data) technique, coupled with a conventional clustering technique (K-means Clustering, Expectation-maximization algorithm). ECA selects high-intensity data among the data of the cluster group detected through K-means and EM in all of the subjects' data and models the characteristic data through the scaled value. Using this method, the aggressive driving data of all youth and elderly experiment participants were collected, unlike the pure clustering method. We further found that the K-means clustering has higher detection efficiency than EM method. Also, the results of K-means clustering demonstrate that a young driver has a driving strength 1.29 times higher than that of an elderly driver. In conclusion, the proposed method of our research is able to detect aggressive driving maneuvers from data of the elderly having low operating intensity. The proposed method is able to construct a customized safe driving system for the elderly driver. In the future, it will be possible to detect abnormal driving conditions and to use the collected data for early warning to drivers.