• Communications for Statistical Applications and Methods
• /
• 제25권2호
• /
• pp.173-184
• /
• 2018

In medical or public health research, it is common to encounter clustered or longitudinal count data that exhibit excess zeros. For example, health care utilization data often have a multi-modal distribution with excess zeroes as well as a multilevel structure where patients are nested within physicians and hospitals. To analyze this type of data, zero-inflated count models with mixed effects have been developed where a count response variable is assumed to be distributed as a mixture of a Poisson or negative binomial and a distribution with a point mass of zeros that include random effects. However, no study has considered a situation where data are also censored due to the finite nature of the observation period or follow-up. In this paper, we present a weighted version of zero-inflated Poisson model with random effects accounting for variable individual follow-up times. We suggested two different types of weight function. The performance of the proposed model is evaluated and compared to a standard zero-inflated mixed model through simulation studies. This approach is then applied to Medicaid data analysis.

• Ocean Systems Engineering
• /
• 제3권2호
• /
• pp.97-122
• /
• 2013

For the optimization design and strength evaluation of the umbilical cable, the calculation of cross section stress is of great importance and very time consuming. To calculate the cross section stress under combined tension and bending loads, a new integrated analytical model of umbilical cable is presented in this paper. Based on the Hook's law, the axial strain of helical components serves as the tensile stress. Considering the effects of friction between helical components, the bending stress is divided into elastic bending stress and friction stress. For the former, the elastic bending stress, the curvature of helical components is deduced; and for the latter, the shear stress before and after the slipping of helical components is determined. This new analytical model is validated by the experimental results of an umbilical cable. Further, this model is applied to estimate the extreme strength and fatigue life of the umbilical cable used in South China Sea.

• Bulletin of the Korean Chemical Society
• /
• 제34권3호
• /
• pp.777-782
• /
• 2013

In order to further reduce the sulfur content in liquid hydrocarbon fuels, a desulfurization process by adsorption for removing dimethyl sulfide (DMS) and propylmercaptan (PM) was investigated. Bentonite adsorbents modified by $CuCl_2$ for the desulfurization of model oil was investigated. The results indicated that the modified bentonite adsorbents were effective for adsorption of DMS and PM. The bentonite adsorbents were characterized by X-ray diffraction (XRD) and thermal analysis (TGA). The acidity was measured by FT-IR spectroscopy. Several factors that influence the desulfurization capability, including loading and calcination temperature, were studied. The maximum sulfur adsorption capacity was obtained at a Cu(II) loading of 15 wt %, and the optimum calcination temperature was $150^{\circ}C$. Spectral shifts of the ${\nu}$(C-S) and ${\nu}$(Cu-S) vibrations of the complex compound obtained by the reaction of $CuCl_2$ and DMS were measured with the Raman spectrum. On the basis of complex adsorption reaction and hybrid orbital theory, the adsorption on modified bentonite occurred via multilayer intermolecular forces and S-M (${\sigma}$) bonds.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제6권9호
• /
• pp.2285-2301
• /
• 2012

Peer-to-Peer (P2P) networks are becoming more and more popular in video content delivery services, such as Video on Demand (VoD). Scalability feature of P2P allows a higher number of simultaneous users at a given server load and bandwidth to use stream service. However, the quality of service (QoS) in these networks is difficult to be guaranteed because of the free-riding problem that nodes download the recourses while never uploading recourses, which degrades the performance of P2P VoD networks. In this paper, a distributed trust model is designed to reduce node's free-riding phenomenon in P2P VoD networks. In this model, the P2P network is abstracted to be a super node hierarchical structure to monitor the reputation of nodes. In order to calculate the reputation of nodes, the Hidden Markov Model (HMM) is introduced in this paper. Besides, a distinction algorithm is proposed to distinguish the free-riders and malicious nodes. The free-riders are the nodes which have a low frequency to free-ride. And the malicious nodes have a high frequency to free-ride. The distinction algorithm takes different measures to response to the request of these two kinds of free-riders. The simulation results demonstrate that this proposed trust model can improve QoS effectively in P2P VoD networks.

• Industrial Engineering and Management Systems
• /
• 제10권2호
• /
• pp.154-160
• /
• 2011

In this paper, a reliability sampling plan under progressively type-1 interval censoring is proposed when the lifetime of products follows the Pareto distribution of second kind. We use the maximum likelihood estimator for the median life and its asymptotic distribution. The cost model is proposed and the design parameters are determined such that the given producer's and the consumer's risks are satisfied. Tables are given and the results are explained with examples.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권12호
• /
• pp.3904-3922
• /
• 2022

As a research hotspot, pedestrian detection has a wide range of applications in the field of computer vision in recent years. However, current pedestrian detection methods have problems such as insufficient detection accuracy and large models that are not suitable for large-scale deployment. In view of these problems mentioned above, a lightweight pedestrian detection and early warning method using a new model called you only look once (Yolov5) is proposed in this paper, which utilizing advantages of Yolov5s model to achieve accurate and fast pedestrian recognition. In addition, this paper also optimizes the loss function of the batch normalization (BN) layer. After sparsification, pruning and fine-tuning, got a lot of optimization, the size of the model on the edge of the computing power is lower equipment can be deployed. Finally, from the experimental data presented in this paper, under the training of the road pedestrian dataset that we collected and processed independently, the Yolov5s model has certain advantages in terms of precision and other indicators compared with traditional single shot multiBox detector (SSD) model and fast region-convolutional neural network (Fast R-CNN) model. After pruning and lightweight, the size of training model is greatly reduced without a significant reduction in accuracy, and the final precision reaches 87%, while the model size is reduced to 7,723 KB.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권4호
• /
• pp.826-842
• /
• 2024

As 5G and AI continue to develop, there has been a significant surge in the healthcare industry. The COVID-19 pandemic has posed immense challenges to the global health system. This study proposes an FL-supported edge computing model based on federated learning (FL) for predicting clinical outcomes of COVID-19 patients during hospitalization. The model aims to address the challenges posed by the pandemic, such as the need for sophisticated predictive models, privacy concerns, and the non-IID nature of COVID-19 data. The model utilizes the FATE framework, known for its privacy-preserving technologies, to enhance predictive precision while ensuring data privacy and effectively managing data heterogeneity. The model's ability to generalize across diverse datasets and its adaptability in real-world clinical settings are highlighted by the use of SHAP values, which streamline the training process by identifying influential features, thus reducing computational overhead without compromising predictive precision. The study demonstrates that the proposed model achieves comparable precision to specific machine learning models when dataset sizes are identical and surpasses traditional models when larger training data volumes are employed. The model's performance is further improved when trained on datasets from diverse nodes, leading to superior generalization and overall performance, especially in scenarios with insufficient node features. The integration of FL with edge computing contributes significantly to the reliable prediction of COVID-19 patient outcomes with greater privacy. The research contributes to healthcare technology by providing a practical solution for early intervention and personalized treatment plans, leading to improved patient outcomes and efficient resource allocation during public health crises.

• Smart Structures and Systems
• /
• 제21권5호
• /
• pp.571-582
• /
• 2018

Track irregularities of high-speed Maglev lines have significant influence on ride comfort. Their adjustment is of key importance in the daily maintenance of these lines. In this study, an adjustment method is proposed and track irregularities analysis is performed. This study considers two modules: an inspection module and a vehicle-guideway coupling vibration analysis module. In the inspection module, an inertial reference method is employed for field-measurements of the Shanghai high-speed Maglev demonstration line. Then, a partial filtering, integration method, resampling method, and designed elliptic filter are employed to analyze the detection data, which reveals the required track irregularities. In the analysis module, a vehicle-guideway interaction model and an electromagnetic interaction model were developed. The influence of the measured line irregularities is considered for the calculations of the electromagnetic force. Numerical integration method was employed for the calculations. Based on the actual field detection results and analysis using the numerical model, a threshold analysis method is developed. Several irregularities modalities with different girder end's deviations were considered in the simulations. The inspection results indicated that long-wavelength irregularities with larger girder end's deviations were the dominant irregularities. In addition, the threshold analysis of the girder end's deviation shows that irregularities that have a deviation amplitude larger than 6 mm and certain modalities (e.g., M- and N-shape) are unfavorable. These types of irregularities should be adjusted during the daily maintenance.

• 분석과학
• /
• 제8권4호
• /
• pp.731-738
• /
• 1995

Toxic air pollutants are investigated in a petrochemical industrial park in Taiwan by using a movable open path FTIR. The results show the qualitative and quantitative analysis of emission gases from plants, and also provide the emission rate of different compounds. More than twenty compounds under usual operation are found from this industrial park. The concentration variation with time can be correlated exactly with wind direction. It means that by changing the measuring points, the source of emission can be unambiguously identified. An EPA proved PAL model is applied to estimate the emission rate of either a point or an area source. Local atmospheric stability is determined by releasing the $SF_6$ tracer. The origins of errors come mainly from the uncertainty of source's configuration and the variation of meteorological condition. Through the continuous measurement (half an hour base in this study) of OP-FTIR sensor, the maximum value of emission rate and the annual amount of emission can be derived. The emission rate of the measured toxic gases are derived by the model technique and the results show that the emission amount are in the order of ten to hundred tons per year.

• Steel and Composite Structures
• /
• 제33권3호
• /
• pp.357-373
• /
• 2019

Steel storage racks are slender structures whose overall behavior and the capacity depend largely on the flexural behavior of the base-plate to upright connections and on the behavior of beam-to-column connections. The base-plate upright connection assembly details, anchor bolt position in particular, associated with the high-rise steel storage racks differ from those of normal height steel storage racks. Since flexural behavior of high-rise rack base connection is hitherto unavailable, this investigation experimentally establishes the flexural behavior of base-plate upright connections of high-rise steel storage racks. This investigation used an enhanced test setup and considered nine groups of three identical tests to investigate the influence of factors such as axial load, base plate thickness, anchor bolt size, bracket length, and upright thickness. The test observations show that the base-plate assembly may significantly influence the overall behavior of such connections. A rigid plate analytical model and an elastic plate analytical model for the overall rotations stiffness of base-plate upright connections with concentric anchor bolts were constructed, and were found to give better predictions of the initial stiffness of such connections. Analytical model based parametric studies highlight and quantify the interplay of components and provide a means for efficient maximization of overall rotational stiffness of concentrically anchor bolted high-rise rack base-plate upright connections.