• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.11
• /
• pp.1649-1654
• /
• 2021

In this paper, we introduce a regularization of long short-term memory (LSTM) based fall detection system using TensorFlow that can detect falls that can occur in the elderly. Fall detection uses data from a 3-axis acceleration sensor attached to the body of an elderly person and learns about a total of 7 behavior patterns, each of which is a pattern that occurs in daily life, and the remaining 3 are patterns for falls. During training, a normalization process is performed to effectively reduce the loss function, and the normalization performs a maximum-minimum normalization for data and a L2 regularization for the loss function. The optimal regularization conditions of LSTM using several falling parameters obtained from the 3-axis accelerometer is explained. When normalization and regularization rate λ for sum vector magnitude (SVM) are 127 and 0.00015, respectively, the best sensitivity, specificity, and accuracy are 98.4, 94.8, and 96.9%, respectively.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.2
• /
• pp.127-133
• /
• 2021

A recent study of people physically falling focused on analyzing the motions of the falls using a recurrent neural network (RNN) and a deep learning approach to get good results from detecting 2D human poses from a single color image. In this paper, we investigate a detection method for estimating the position of the head and shoulder keypoints and the acceleration of positional change using the skeletal keypoints information extracted using PoseNet from an image obtained with a low-cost 2D RGB camera, increasing the accuracy of judgments about the falls. In particular, we propose a fall detection method based on the characteristics of post-fall posture in the fall motion-analysis method. A public data set was used to extract human skeletal features, and as a result of an experiment to find a feature extraction method that can achieve high classification accuracy, the proposed method showed a 99.8% success rate in detecting falls more effectively than a conventional, primitive skeletal data-use method.

• Journal of information and communication convergence engineering
• /
• v.22 no.2
• /
• pp.139-144
• /
• 2024

In this study, four types of fall detection systems - designed with YOLOPose, principal component analysis (PCA), convolutional neural network (CNN), and long short-term memory (LSTM) architectures - were developed and compared in the detection of everyday falls. The experimental dataset encompassed seven types of activities: walking, lying, jumping, jumping in activities of daily living, falling backward, falling forward, and falling sideways. Keypoints extracted from YOLOPose were entered into the following architectures: RAW-LSTM, PCA-LSTM, RAW-PCA-LSTM, and PCA-CNN-LSTM. For the PCA architectures, the reduced input size stemming from a dimensionality reduction enhanced the operational efficiency in terms of computational time and memory at the cost of decreased accuracy. In contrast, the addition of a CNN resulted in higher complexity and lower accuracy. The RAW-LSTM architecture, which did not include either PCA or CNN, had the least number of parameters, which resulted in the best computational time and memory while also achieving the highest accuracy.

• JSTS:Journal of Semiconductor Technology and Science
• /
• v.14 no.6
• /
• pp.706-711
• /
• 2014

A low power 6-bit flash ADC that uses an input voltage range detection algorithm is described. An input voltage level detector circuit has been designed to overcome the disadvantages of the flash ADC which consume most of the dynamic power dissipation due to comparators array. In this work, four digital input voltage range detectors are employed and each input voltage range detector generates the specific clock signal only if the input voltage falls between two adjacent reference voltages applied to the detector. The specific clock signal generated by the detector is applied to turn the corresponding latched comparators on and the rest of the comparators off. This ADC consumes 68.82 mW with a single power supply of 1.2V and achieves 4.3 effective number of bits for input frequency up to 1 MHz at 500 MS/s. Therefore it results in 4.6 pJ/step of Figure of Merit (FoM). The chip is fabricated in 0.13-um CMOS process.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.24 no.5
• /
• pp.733-739
• /
• 1987

In this paper, variable threshold detection with weighted pulse code modulation-encoded signals transmitted over Gaussian channels has been investigated. Each bit in the \ulcornerlaw PCM word is weighted according to its significance in the transmitter. It the output falls into the erasure zone, the regenerated sample replaced by interpolation or prediction. To overall system signal to noise ratio for BPSK/PCM speech signals of this technique has been found. When the input signal level was -17 db, the gains in overall signal s/n compared to weighted PCM and variable threshold detection were 5 db and 3 db, respectively. Computer simulation was performed generating signals by computer. The simulation was in resonable agreement with our theoretical prediction.

• Journal of Trauma and Injury
• /
• v.19 no.1
• /
• pp.54-58
• /
• 2006

Purpose: The committee on trauma of the american college of surgeons, in its manual resources for optimal care of the injured patients involved in falls from less than 20 feet need not be taken to trauma centers. Because triage criteria dictate less urgency for low-level falls, this classification scheme has demerits for early detection and treatment of serious problems in the emergency room. Methods: A prospective analysis was conducted of 182 patients treated for fall-related trauma from June 2003 to March 2004. Falls were classified as group A (<3 m), group B (${\geq}3m$, <6 m), and group C (${\geq}6m$). Collected data included the patient's age, gender, site and height of fall, surface fallen upon, body area of first impact, body regions of injuries, Glasgow Coma Scale (GCS), Revised Trauma Score (RTS), and Injury Severity Score (ISS). Results: The 182 patients were classified as group A (105) 57.7%, group B (61) 33.5%, and group C (16) 8.8%. There was a weak positive correlation between the height of fall and the patients' ISS in the three groups (p<0.001). There were significant differences in GCS (p=0.017), RTS (p=0.034), and ISS (p=0.007) between group A and B. In cases that the head was the initial impact area of the body, the GCS (p<0.001) and the RTS (p=0.002) were lower, but the ISS (p<0.001) was higher than it was for other type of injuries. Hard surfaces as an impact surface type, had an influence on the GCS (p<0.001) and the ISS (p=0.025). Conclusion: To simply categorize patients who fall over 6 meters as severely injured patients doesn't have much meaning, and though patients may have fallen less than 6 meters, they should be categorized by using the dynamics (impact surface type, initial body - impact area) of their fall.

• International Journal of Internet, Broadcasting and Communication
• /
• v.12 no.4
• /
• pp.83-92
• /
• 2020

A recent study to determine the fall is focused on analyzing fall motions using a recurrent neural network (RNN), and uses a deep learning approach to get good results for detecting human poses in 2D from a mono color image. In this paper, we investigated the improved detection method to estimate the position of the head and shoulder key points and the acceleration of position change using the skeletal key points information extracted using PoseNet from the image obtained from the 2D RGB low-cost camera, and to increase the accuracy of the fall judgment. In particular, we propose a fall detection method based on the characteristics of post-fall posture in the fall motion analysis method and on the velocity of human body skeleton key points change as well as the ratio change of body bounding box's width and height. The public data set was used to extract human skeletal features and to train deep learning, GRU, and as a result of an experiment to find a feature extraction method that can achieve high classification accuracy, the proposed method showed a 99.8% success rate in detecting falls more effectively than the conventional primitive skeletal data use method.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.391-393
• /
• 2021

In this paper, we introduce a long short-term memory (LSTM)-based fall detection system using TensorFlow that can detect falls occurring in the elderly in daily living. 3-axis accelerometer data are aggregated for fall detection, and then three types of parameter are calculated. 4 types of activity of daily living (ADL) and 3 types of fall situation patterns are classified. The parameterized data applied to LSTM. Learning proceeds until the Loss value becomes 0.5 or less. The results are calculated for each parameter θ, SVM, and GSVM. The best result was GSVM, which showed Sensitivity 98.75%, Specificity 99.68%, and Accuracy 99.28%.

• Journal of Sensor Science and Technology
• /
• v.33 no.1
• /
• pp.18-23
• /
• 2024

Humanoid robots, designed to interact in human environments, require stable mobility to ensure safety. When a humanoid robot falls, it causes damage, breakdown, and potential harm to the robot. Therefore, fall detection is critical to preventing the robot from falling. Prevention of falling of a humanoid robot requires an operator controlling a crane. For efficient and safe walking control experiments, a system that can replace a crane operator is needed. To replace such a crane operator, it is essential to detect the falling conditions of humanoid robots. In this study, we propose falling detection methods using Convolution Neural Network (CNN) model. The image data of a humanoid robot are collected from various angles and environments. A large amount of data is collected by dividing video data into frames per second, and data augmentation techniques are used. The effectiveness of the proposed CNN model is verified by the experiments with the humanoid robot MAX-E1.

• Journal of East-West Nursing Research
• /
• v.28 no.2
• /
• pp.122-131
• /
• 2022

Purpose: This study aimed to identify the factors related to fear of falling (FOF) in different age groups from community-dwelling mid to late-adults. Methods: To identify the factors related to FOF, data of 162,684 adults over 45 years of age from 2019 Community Health Survey was analyzed using logistic regression with complex samples. Results: Factors related to FOF found in all age groups were sex, previous experience of falls, physical activity levels over moderate intensity, subjective health status, number of chronic diseases, stress, depression, and cognitive decline. In the 45-64 age group, the FOF was significantly higher in the groups of low education level and low monthly household income. In the 65-74 and over 75 age groups, the FOF was significantly higher in the groups of not living with spouse and walking not practiced. Conclusion: We suggests that understanding of risk factors and early detection of fall risk patients in each age group are necessary to establish and apply tailored fall prevention programs for prevention and management of the FOF in community-dwelling mid to late-adults.