• ETRI Journal
• /
• v.44 no.4
• /
• pp.654-671
• /
• 2022

Accidental falls frequently occur during activities of daily living. Although many studies have proposed various accident detection methods, no high-performance accident detection system is available. In this study, we propose a method for integrating data and accident detection algorithms presented in existing studies, collect new data (from two stunt performers and 15 people over age 60) using a developed wearable device, demonstrate new features and related accident detection algorithms, and analyze the performance of the proposed method against existing methods. Comparative analysis results show that the newly defined features extracted reflect more important risk factors than those used in existing studies. Further, although the traditional algorithms applied to integrated data achieved an accuracy (AC) of 79.5% and a false positive rate (FPR) of 19.4%, the proposed accident detection algorithms achieved 97.8% AC and 2.9% FPR. The high AC and low FPR for accidental falls indicate that the proposed method exhibits a considerable advancement toward developing a commercial accident detection system.

• International Journal of Computer Science & Network Security
• /
• v.22 no.12
• /
• pp.212-216
• /
• 2022

Space based constellation network is a kind of ad hoc network in which users are self-organized without center node. In space based constellation network, users are allowed to enter or leave the network at any given time. Thus, the number of active users is an unknown and time-varying parameter, and the performance of the network depends on how accurately this parameter is estimated. The so-called problem of active user identification, which consists of determining the number and identities of users transmitting in space based constellation network is discussed and a novel active user identification method is proposed in this paper. Active user identification code generated by transmitter address code and receiver address code is used to spread spectrum. Subspace-based method is used to process received signal and judgment model is established to identify active users according to the processing results. The proposed method is simulated under AWGN channel, Rician channel and Rayleigh channel respectively. Numerical results indicate that the proposed method obtains at least 1.16dB E_b/N₀ gains compared with reference methods when miss alarm rate reaches 10^-3.

• International Journal of Computer Science & Network Security
• /
• v.22 no.12
• /
• pp.51-56
• /
• 2022

In space based constellation network, users are allowed to enter or leave the network arbitrarily. Hence, the number, identities and transmitted data of active users vary with time and have considerable impacts on the receiver's performance. The so-called problem of multiuser detection means identifying the identity of each active user and detecting the data transmitted by each active user. Traditional methods assume that the number of active users is equal to the maximum number of users that the network can hold. The model of traditional methods are simple and the performance are suboptimal. In this paper a Maximum A Posteriori Probability (MAP) based multiuser detection method is proposed. The proposed method models the activity state of users as Markov chain and transforms multiuser detection into searching optimal path in grid map with BCJR algorithm. Simulation results indicate that the proposed method obtains 2.6dB and 1dB E_b/N₀ gains respectively when activity detection error rate and symbol error rate reach 10^-3, comparing with reference methods.

• International Journal of Computer Science & Network Security
• /
• v.22 no.12
• /
• pp.98-106
• /
• 2022

A condition of the retina known as hypertensive retinopathy (HR) is connected to high blood pressure. The severity and persistence of hypertension are directly correlated with the incidence of HR. To avoid blindness, it is essential to recognize and assess HR as soon as possible. Few computer-aided systems are currently available that can diagnose HR issues. On the other hand, those systems focused on gathering characteristics from a variety of retinopathy-related HR lesions and categorizing them using conventional machine-learning algorithms. Consequently, for limited applications, significant and complicated image processing methods are necessary. As seen in recent similar systems, the preciseness of classification is likewise lacking. To address these issues, a new CAD HR-diagnosis system employing the advanced Deep Dense CNN Learning (DD-CNN) technology is being developed to early identify HR. The HR-diagnosis system utilized a convolutional neural network that was previously trained as a feature extractor. The statistical investigation of more than 1400 retinography images is undertaken to assess the accuracy of the implemented system using several performance metrics such as specificity (SP), sensitivity (SE), area under the receiver operating curve (AUC), and accuracy (ACC). On average, we achieved a SE of 97%, ACC of 98%, SP of 99%, and AUC of 0.98. These results indicate that the proposed DD-CNN classifier is used to diagnose hypertensive retinopathy.

• Nuclear Engineering and Technology
• /
• v.54 no.11
• /
• pp.4322-4328
• /
• 2022

The two-fluid model is widely used to describe two-phase flows in complex systems such as nuclear reactors. Although the two-phase flow was successfully simulated, the standard two-fluid model suffers from an ill-posed nature. There are several remedies for the ill-posedness of the one-dimensional (1D) two-fluid model; among those, artificial viscosity is the focus of this study. Some previous works added artificial diffusion terms to both mass and momentum equations to render the two-fluid model well-posed and demonstrated that this method provided a numerically converging model. However, they did not consider mass conservation, which is crucial for analyzing a closed reactor system. In fact, the total mass is not conserved in the previous models. This study improves the artificial viscosity model such that the 1D incompressible two-fluid model is well-posed, and the total mass is conserved. The water faucet and Kelvin-Helmholtz instability flows were simulated to test the effect of the proposed artificial viscosity model. The results indicate that the proposed artificial viscosity model effectively remedies the ill-posedness of the two-fluid model while maintaining a negligible total mass error.

• Advances in environmental research
• /
• v.12 no.1
• /
• pp.17-40
• /
• 2023

This article presents studies of the adsorption process in a continuous system of fluoride solutions at a concentration of 30 mg/L using a bone char packed in fixed-bed columns, as well as regeneration studies in the same system using HNO₃, HCl and NaOH at 0.01, 0.1 and 1 M. The Thomas Model, Artificial Neural Networks (ANNs), Numerical Integration and Mass Transfer Zone were used for the modeling of asyemmetrical breakthrough curves obtained from the fluoride adsorption on bone char. The maximum adsorption capacity of the breakthrough curves was estimated, and various design parameters of the columns were obtained for the different operating conditions. Results showed that an improvement in the modeling capabilities of the Thomas model can be obtained using ANNs. Moreover, ANNs are useful for determining reasonable and accurate design parameters of packed-bed adsorption columns. This modeling approach can be useful for the process system engineering of dynamic adsorption systems involved in the field of water treatment and purification. It is important to highlight that the obtained results indicate that, when using HCl or HNO₃ at a concentration of 0.1 M, a large number of adsorption-desorption cycles are obtained and, therefore, the highest values of adsorption capacity, which leads to a reduction in operation costs.

• Journal of Environmental Science International
• /
• v.32 no.6
• /
• pp.441-451
• /
• 2023

This study examines the changes in environmental resource perception and residential areas on Jeju Island. This study focuses on Jeju Island, which has prepared a legal framework for the total amount of environmental resources. The study identifies Jeju residents and non-provincial citizens, analyzes the differences between them, and suggests the future direction of the total amount system for environmental resources. This study aims to provide essential data necessary for successfully implementing the assigned environmental resources. This will contribute to sustainable growth and preserving valuable environmental resources in an era where environmental importance is increasing. The findings indicate that both Jeju residents and non-provincial citizens are satisfied with the current environmental resources on the island. However, when comparing past and current environmental resources, Jeju residents generally indicated lower satisfaction over time, whereas non-provincial citizens perceived an improvement over time. While overall satisfaction with the natural and local environment remains high, there is a notable increase in perception regarding the ecological value of plants, wildlife, wetlands, and Gotjawal areas compared to the past. These findings emphasize the importance of incorporating these high-priority components into the total environmental resource system for future consideration.

• Structural Engineering and Mechanics
• /
• v.87 no.3
• /
• pp.231-242
• /
• 2023

A novel combinatorial type-2 adaptive neuro-fuzzy inference system (T2-ANFIS) and robust proportional integral derivative (PID) control framework for intelligent vibration mitigation of uncertain structural system is introduced. The fuzzy logic controllers (FLCs), are designed independently of the mathematical model of the system. The type-1 FLCs, have a limited ability to reduce the effect of uncertainty, due to their fuzzy sets with a crisp degree of membership. In real applications, the consequent part of the fuzzy rules is uncertain. The type-2 FLCs, are robust to the fuzzy rules and the process parameters due to the fuzzy degree of membership functions and footprint of uncertainty (FOU). The adaptivity of the proposed method is provided with the optimum tuning of the parameters using the neural network training algorithms. In our approach, the PID control force is obtained using the generalized type-2 neuro-fuzzy in such a way that the stability and robustness of the controller are guaranteed. The robust performance and stability of the presented framework are demonstrated in a numerical study for an eleven-story seismically-excited building structure combined with an active tuned mass damper (ATMD). The results indicate that the introduced type-2 neuro-fuzzy PID control scheme is effective to attenuate plant states in the presence of the structured and unstructured uncertainties, compared to the conventional, type-1 FLC, type-2 FLC, and type-1 neuro-fuzzy PID controllers.

• The Journal of Information Systems
• /
• v.32 no.3
• /
• pp.1-17
• /
• 2023

Purpose The proliferation of data on the internet has created a need for innovative methods to analyze user satisfaction data. Traditional survey methods are becoming inadequate in dealing with the increasing volume and diversity of data, and new methods using unstructured internet data are being explored. While numerous comment-based user satisfaction studies have been conducted, only a few have explored user satisfaction through video and audio data. Multimodal sentiment analysis, which integrates multiple modalities, has gained attention due to its high accuracy and broad applicability. Design/methodology/approach This study uses multimodal sentiment analysis to analyze user satisfaction of iPhone and Samsung products through online videos. The research reveals that the combination model integrating multiple data sources showed the most superior performance. Findings The findings also indicate that price is a crucial factor influencing user satisfaction, and users tend to exhibit more positive emotions when content with a product's price. The study highlights the importance of considering multiple factors when evaluating user satisfaction and provides valuable insights into the effectiveness of different data sources for sentiment analysis of product reviews.

• Geomechanics and Engineering
• /
• v.37 no.2
• /
• pp.167-178
• /
• 2024

The natural frequency shift under cyclic environmental loads is a key issue in the design of monopile-based offshore wind power turbines because of their dynamic sensitivity. Existing evidence reveals that the natural frequency shift of the turbine system in sand is related to the varying foundation stiffness, which is caused by soil deformation around the monopile under cyclic loads. Therefore, it is an urgent need to investigate the effect of soil deformation on the system frequency. In the present paper, three generalized geometric models that can describe soil deformation under two-way cyclic loads are proposed. On this basis, the cycling-induced changes in soil parameters around the monopile are quantified. A theoretical approach considering three-spring foundation stiffness is employed to calculate the natural frequency during cycling. Further, a parametric study is conducted to describe and evaluate the frequency shift characteristics of the system under different conditions of sand relative density, pile slenderness ratio and pile-soil relative stiffness. The results indicate that the frequency shift trends are mainly affected by the pile-soil relative stiffness. Following the relevant conclusions, a design optimization is proposed to avoid resonance of the monopile-based wind turbines during their service life.