• International Journal of Computer Science & Network Security
• /
• v.22 no.7
• /
• pp.389-396
• /
• 2022

Smartphones are growing more susceptible as technology develops because they contain sensitive data that offers a severe security risk if it falls into the wrong hands. The Android OS includes permissions as a crucial component for safeguarding user privacy and confidentiality. On the other hand, mobile malware continues to struggle with permission misuse. Although permission-based detection is frequently utilized, the significant false alarm rates brought on by the permission-based issue are thought to make it inadequate. The present detection method has a high incidence of false alarms, which reduces its ability to identify permission-based attacks. By using permission features with intent, this research attempted to improve permission-based detection. However, it creates an excessive number of features and increases the likelihood of false alarms. In order to generate the optimal number of features created and boost the quality of features chosen, this research developed an intersection feature approach. Performance was assessed using metrics including accuracy, TPR, TNR, and FPR. The most important characteristics were chosen using the Correlation Feature Selection, and the malicious program was categorized using SVM and naive Bayes. The Intersection Feature Technique, according to the findings, reduces characteristics from 486 to 17, has a 97 percent accuracy rate, and produces 0.1 percent false alarms.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.12
• /
• pp.3991-4007
• /
• 2022

In the public healthcare, a computational system that can automatically and efficiently detect and classify falls from a video sequence has significant potential. With the advancement of deep learning, which can extract temporal and spatial information, has become more widespread. However, traditional 3D CNNs that usually adopt shallow networks cannot obtain higher recognition accuracy than deeper networks. Additionally, some experiences of neural network show that the problem of gradient explosions occurs with increasing the network layers. As a result, an enhanced three-dimensional ResNet-based method for fall detection (3D-ERes-FD) is proposed to directly extract spatio-temporal features to address these issues. In our method, a 50-layer 3D residual network is used to deepen the network for improving fall recognition accuracy. Furthermore, enhanced residual units with four convolutional layers are developed to efficiently reduce the number of parameters and increase the depth of the network. According to the experimental results, the proposed method outperformed several state-of-the-art methods.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.25-27
• /
• 2021

With the recent development of deep learning technology, computer vision-based AI technologies have been studied to analyze the abnormal behavior of objects in image information acquired through CCTV cameras. There are many cases where surveillance cameras are installed in dangerous areas or security areas for crime prevention and surveillance. For this reason, companies are conducting studies to determine major situations such as intrusion, roaming, falls, and assault in the surveillance camera environment. In this paper, we propose a real-time abnormal behavior analysis algorithm using object detection and tracking method.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.516-518
• /
• 2022

In this paper, we introduce a dependence of number of nodes of hidden-layer in fall detection system using Long Short-Term Memory that can detect falls. Its training is carried out using the parameter theta(θ), which indicates the angle formed by the x, y, and z-axis data for the direction of gravity using a 3-axis acceleration sensor. In its learning, validation is performed and divided into training data and test data in a ratio of 8:2, and training is performed by changing the number of nodes in the hidden layer to increase efficiency. When the number of nodes is 128, the best accuracy is shown with Accuracy = 99.82%, Specificity = 99.58%, and Sensitivity = 100%.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.1
• /
• pp.65-70
• /
• 2005

This paper deals with the problem of double-talk (DT) detection in anacoustic echo canceller (AEC). In the DT detection algorithm with correlation coefficient, detection errors occasionally occur because it is hard to set the threshold to distinguish DT from echo path change (EPC). Adaptive filter falls into the situation that it stops updating its filter coefficients when EPC is erroneously considered as DT at the starting-point of EPC. In addition, in case of echo path changing during the DT period, the end-point detection of DT period fails so that the AEC cannot update its filter coefficients for a while even after the DT period ends. To solve these problems, in this paper, we propose a novel AEC that employs an auxiliary filter. We use the idea that though the error signal cannot be estimated using reference signal in case or DT situation but it can be in case or EPC situation. The experimental result verifies that the proposed method could solve the problems caused by DT detection error or echo path change during the DT period.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.1
• /
• pp.77-83
• /
• 2019

Major causes of industrial accidents include falls and gas leak. The existing safety helmet and smart device combination products are focused on convenience, so the functions to prevent such accidents are insufficient. We developed a smart helmet focusing on fall accident detection and gas leak detection. We also developed management system to manage workers efficiently. Its core function is to detect dangerous conditions of employees, to communicate with managers and to confirm the situations of workers. The effectiveness of the combustible gas measurement capability was verified through experiments. However, since a significant amount of power consumption is founded due to continuous operation of the board and the sensor, countermeasures such as replacing with a large capacity battery are required.

• Journal of Ocean Engineering and Technology
• /
• v.35 no.1
• /
• pp.91-97
• /
• 2021

Marine accidents caused by ships have brought about economic and social losses as well as human casualties. Most of these accidents are caused by small and medium-sized ships and are due to their poor conditions and insufficient equipment compared with larger vessels. Measures are quickly needed to improve the conditions. This paper discusses a video-integrated collision prediction and fall detection system to support the safe navigation of small- and medium-sized ships. The system predicts the collision of ships and detects falls by crew members using the CCTV, displays the analyzed integrated information using automatic identification system (AIS) messages, and provides alerts for the risks identified. The design consists of an object recognition algorithm, interface module, integrated display module, collision prediction and fall detection module, and an alarm management module. For the basic research, we implemented a deep learning algorithm to recognize the ship and crew from images, and an interface module to manage messages from AIS. To verify the implemented algorithm, we conducted tests using 120 images. Object recognition performance is calculated as mAP by comparing the pre-defined object with the object recognized through the algorithms. As results, the object recognition performance of the ship and the crew were approximately 50.44 mAP and 46.76 mAP each. The interface module showed that messages from the installed AIS were accurately converted according to the international standard. Therefore, we implemented an object recognition algorithm and interface module in the designed collision prediction and fall detection system and validated their usability with testing.

• Journal of the Institute of Convergence Signal Processing
• /
• v.21 no.2
• /
• pp.86-91
• /
• 2020

As the number of elderly people living alone increases, the frequency of fall accidents is also increasing. Falls are a threat to the health of older adults and can reduce their ability to remain independent. To solve this problem, we need real-time technology to recognize and respond to the critical condition of the elderly living alone. Therefore, this paper proposes a modified fall detection algorithm based on YOLO-KCF that can check one of the emergency situations in real time for the elderly living alone. YOLO can detect not only the detection of objects, but also the behavior of objects, namely stand and fall. Therefore, this paper can detect fall using the ratio of change of boundary box between stand and falling situation, and this algorithm can improve the shortcomings of KCF.

• Journal of Biomedical Engineering Research
• /
• v.44 no.6
• /
• pp.384-391
• /
• 2023

Among the elderly, fatal injuries and deaths are significantly attributed to falls. Therefore, a pre-impact fall detection system is necessary for injury prevention. In this study, a robust threshold-based algorithm was proposed for pre-impact fall detection, reducing false positives in highly dynamic daily-living movements. The algorithm was validated using public datasets (KFall and FARSEEING) that include the real-world elderly fall. A 6-axis IMU sensor (Movella Dot, Movella, Netherlands) was attached to S2 of 20 healthy adults (aged 22.0±1.9years, height 164.9±5.9cm, weight 61.4±17.1kg) to measure 14 activities of daily living and 11 fall movements at a sampling frequency of 60Hz. A 5Hz low-pass filter was applied to the IMU data to remove high-frequency noise. Sum vector magnitude of acceleration and angular velocity, roll, pitch, and vertical velocity were extracted as feature vector. The proposed algorithm showed an accuracy 98.3%, a sensitivity 100%, a specificity 97.0%, and an average lead-time 311±99ms with our experimental data. When evaluated using the KFall public dataset, an accuracy in adult data improved to 99.5% compared to recent studies, and for the elderly data, a specificity of 100% was achieved. When evaluated using FARSEEING real-world elderly fall data without separate segmentation, it showed a sensitivity of 71.4% (5/7).

• Maxillofacial Plastic and Reconstructive Surgery
• /
• v.42
• /
• pp.22.1-22.6
• /
• 2020

Introduction: Facial fractures (FFs) occur after high- and low-energy trauma; differences in associated injuries and outcomes have not been well articulated. Objective: To compare the epidemiology, management, and outcomes of patients suffering FFs from high-energy and low-energy mechanisms. Methods: We conducted a 6-year retrospective local trauma registry analysis of adults aged 18-55 years old that suffered a FF treated at the Santa Barbara Cottage Hospital. Fracture patterns, concomitant injuries, procedures, and outcomes were compared between patients that suffered a high-energy mechanism (HEM: motor vehicle crash, bicycle crash, auto versus pedestrian, falls from height > 20 feet) and those that suffered a low-energy mechanism (LEM: assault, ground-level falls) of injury. Results: FFs occurred in 123 patients, 25 from an HEM and 98 from an LEM. Rates of Le Fort (HEM 12% vs. LEM 3%, P = 0.10), mandible (HEM 20% vs. LEM 38%, P = 0.11), midface (HEM 84% vs. LEM 67%, P = 0.14), and upper face (HEM 24% vs. LEM 13%, P = 0.217) fractures did not significantly differ between the HEM and LEM groups, nor did facial operative rates (HEM 28% vs. LEM 40%, P = 0.36). FFs after an HEM event were associated with increased Injury Severity Scores (HEM 16.8 vs. LEM 7.5, P <0.001), ICU admittance (HEM 60% vs. LEM 13.3%, P <0.001), intracranial hemorrhage (ICH) (HEM 52% vs. LEM 15%, P <0.001), cervical spine fractures (HEM 12% vs. LEM 0%, P = 0.008), truncal/lower extremity injuries (HEM 60% vs. LEM 6%, P <0.001), neurosurgical procedures for the management of ICH (HEM 54% vs. LEM 36%, P = 0.003), and decreased Glasgow Coma Score on arrival (HEM 11.7 vs. LEM 14.2, P <0.001). Conclusion: FFs after HEM events were associated with severe and multifocal injuries. FFs after LEM events were associated with ICH, concussions, and cervical spine fractures. Mechanism-based screening strategies will allow for the appropriate detection and management of injuries that occur concomitant to FFs. Type of study: Retrospective cohort study. Level of evidence: Level III.