Mortensenmacgregor3127

Data imbalance is a common phenomenon in machine learning. In the imbalanced data classification, minority samples are far less than majority samples, which makes it difficult for minority to be effectively learned by classifiers A synthetic minority oversampling technique (SMOTE) improves the sensitivity of classifiers to minority by synthesizing minority samples without repetition. However, the process of synthesizing new samples in the SMOTE algorithm may lead to problems such as "noisy samples" and "boundary samples." Based on the above description, we propose a synthetic minority oversampling technique based on Gaussian mixture model filtering (GMF-SMOTE). GMF-SMOTE uses the expected maximum algorithm based on the Gaussian mixture model to group the imbalanced data. Then, the expected maximum filtering algorithm is used to filter out the "noisy samples" and "boundary samples" in the subclasses after grouping. Finally, to synthesize majority and minority samples, we design two dynamic oversampling ratios. Experimental results show that the GMF-SMOTE performs better than the traditional oversampling algorithms on 20 UCI datasets. The population averages of sensitivity and specificity indexes of random forest (RF) on the UCI datasets synthesized by GMF-SMOTE are 97.49% and 97.02%, respectively. In addition, we also record the G-mean and MCC indexes of the RF, which are 97.32% and 94.80%, respectively, significantly better than the traditional oversampling algorithms. More importantly, the two statistical tests show that GMF-SMOTE is significantly better than the traditional oversampling algorithms.Time delay has always been one of the main factors affecting the application performance of neural network (NN) systems, and dynamic performance research of NNs with time delays has been the focus of many scholars in recent years. This article enquires into the exponentially synchronous problem of switched delayed NNs with time delay in the leakage term. Adopting an unusual form from a common switched system, the switching modes of the switched delayed NNs system in this article are dependent on time delays. In the first place, the master, slave, and error NNs models are reconstructed into the switched form by introducing the switched delay idea. Then with the help of the admissible edge-dependent average dwell time (AED-ADT) method and delay-dependent switching adjustment indicators, a novel set of generalized delay-mode-dependent multiple Lyapunov-Krasovskii functionals (MLKFs) is built for analyzing the cases where a state-feedback controller exists and does not exist in the model, and where parts of LKFs may increase during the period when the corresponding subsystems are activated. For these cases, several effective exponential synchronization criteria and switching laws are presented accordingly. At last, the verification of the theoretical results is shown through a few examples.Automatic liver tumor segmentation plays a key role in radiation therapy of hepatocellular carcinoma. In this paper, we propose a novel densely connected U-Net model with criss-cross attention (CC-DenseUNet) to segment liver tumors in computed tomography (CT) images. The dense interconnections in CC-DenseUNet ensure the maximum information flow between encoder layers when extracting intra-slice features of liver tumors. KB0742 Moreover, the criss-cross attention is used in CC-DenseUNet to efficiently capture only the necessary and meaningful non-local contextual information of CT images containing liver tumors. We evaluated the proposed CC-DenseUNet on the LiTS dataset and the 3DIRCADb dataset. Experimental results show that the proposed method reaches the state-of-the-art performance for liver tumor segmentation. We further experimentally demonstrate the robustness of the proposed method on a clinical dataset comprising 20 CT volumes.COVID-19 vaccine distribution route directly impacts the community's mortality and infection rate. Therefore, optimal vaccination dissemination would appreciably lower the death and infection rates. This paper proposes the Epidemic Vulnerability Index (EVI) that quantitatively evaluates the subject's potential risk. Our primary aim for the suggested index is to diminish both infection rate and death rate efficiently. EVI was accordingly designed with clinical factors determining the mortality and social factors incorporating the infection rate. Through statistical COVID-19 patient dataset analysis and social network analysis with an agent-based model that is analogous to a real-world system, we define and experimentally validate the capability of EVI. Our experiments consist of nine vaccination distribution scenarios, including existing indexes which estimate the risk and stochastically proliferate the contagion and vaccine in a 300,000 agent-based graph network. We compared the outcome and variation of the three metrics in the experiments infection case, death case, and death rate. Through this assessment, vaccination by the descending order of EVI has shown to have a significant outcome with an average of 5.0% lower infection cases, 9.4% lower death cases, and 3.5% lower death rate than other vaccine distribution routes.Model-based treatment planning for transcranial ultrasound therapy typically involves mapping the acoustic properties of the skull from an X-ray computed tomography (CT) image of the head. Here, three methods for generating pseudo-CT (pCT) images from magnetic resonance (MR) images were compared as an alternative to CT. A convolutional neural network (U-Net) was trained on paired MR-CT images to generate pCT T images from either T1-weighted or zero-echo time (ZTE) MR images (denoted tCT and zCT, respectively). A direct mapping from ZTE to pCT was also implemented (denoted cCT). When comparing the pCT and ground-truth CT images for the test set, the mean absolute error was 133, 83, and 145 Hounsfield units (HU) across the whole head, and 398, 222, and 336 HU within the skull for the tCT, zCT, and cCT images, respectively. Ultrasound simulations were also performed using the generated pCT images and compared to simulations based on CT. An annular array transducer was used targeting the visual or motor cortex. The mean differences in the simulated focal pressure, focal position, and focal volume were 9.9%, 1.5 mm, and 15.1% for simulations based on the tCT images; 5.7%, 0.6 mm, and 5.7% for the zCT; and 6.7%, 0.9 mm, and 12.1% for the cCT. The improved results for images mapped from ZTE highlight the advantage of using imaging sequences, which improves the contrast of the skull bone. Overall, these results demonstrate that acoustic simulations based on MR images can give comparable accuracy to those based on CT.Simultaneous axial multifocal imaging (SAMI) using a single acoustical transmission was developed to enhance the depth of field. This technique transmits a superposition of axial multifoci waveforms in a single transmission, thus increasing the frame rate. However, since all the waveforms are transmitted at a constant center frequency, there is a tradeoff between attenuation and lateral resolution when choosing a constant frequency for all the axial depths. In this work, we developed an optimized SAMI method by adding frequency dependence to each axial multifocus. By gradually increasing the frequency as a function of the focal depth, this method makes it possible to compensate for the gradually increasing F-number in order to achieve constant lateral resolution across the entire field of view. Alternatively, by gradually decreasing the axial multifoci frequencies as a function of depth, enhanced penetration depth and contrast are obtained. This method, termed frequency multiplexed SAMI (FM-SAMI), is described analytically and validated by resolution and contrast experiments performed on resolution targets, tissue-mimicking phantoms, and ex vivo biological samples. This is the first real-time implementation of a frequency multiplexing approach for axial multifoci imaging that facilitates high-quality imaging at an increased frame rate.

understanding women's attitudes towards female genital mutilation is an important step towards eliminating this practice. We used the 2016 Ethiopia Demographic and Health Survey (EDHS) data set to examine the relationship between wealth index, and previous history of circumcision on women's opinions whether female genital mutilation (FGM) should be continued or stopped in Ethiopia.

Data from 6984 women aged 15-49 years were extracted from the 2016 Ethiopia EDHS data set. Multivariable logistic regression analysis was performed to analyse the data.

In this study, women with a higher level of education and wealth index were more likely to support the cessation of FGM. However, circumcised women (AOR 0.22; 95% CI 0.15-0.32), women from the Afar region (AOR 0.34; 95% CI 0.22-0.50), Somali region (AOR 0.42; 95% CI 0.27-0.65), and Dire Dawa region (AOR 0.51; 95% CI 0.32-0.83) were less likely to support discontinuation of FGM.

The present study revealed that wealth index, education level, history of circumcision, and regional variation are associated with women's attitude towards discontinuation of the practice of FGM in Ethiopia. Empowering women in terms of socioeconomic status and education can change attitudes and might help prevent female genital mutilation in the future. Furthermore, interventions targeting FGM practices should focus on regional variance in order to have a meaningful impact on reducing this harmful cultural practice in Ethiopia.

The present study revealed that wealth index, education level, history of circumcision, and regional variation are associated with women's attitude towards discontinuation of the practice of FGM in Ethiopia. Empowering women in terms of socioeconomic status and education can change attitudes and might help prevent female genital mutilation in the future. Furthermore, interventions targeting FGM practices should focus on regional variance in order to have a meaningful impact on reducing this harmful cultural practice in Ethiopia.A clear understanding of how human brain networks reflect task performance has been lacking, in part due to methodological difficulties. A new study combines the temporal resolution of EEG, MRI source localization, and multivariate modeling to address this need.

In vivo dosimetry is a quality assurance tool that provides post-treatment measurement of the absorbed dose as delivered to the patient. This dosimetry compares the prescribed and measured dose delivered to the target volume. In this study, a tissue-equivalent water phantom provided the simulation of the human environment. The skin and entrance doses were measured using GafChromic EBT2 film for a Theratron® Equinox Cobalt-60 teletherapy machine.

We examined the behaviors of unencapsulated films and custom-made film encapsulation. Films were cut to 1 cm × 1 cm, calibrated, and used to assess skin dose depositions and entrance dose. We examined the response of the film for variations in field size, source to skin distance (SSD), gantry angle and wedge angle.

The estimated uncertainty in EBT2 film for absorbed dose measurement in phantom was ±1.72%. Comparison of the measurements of the two film configurations for the various irradiation parameters were field size (p = 0.0193, α = 0.05, n = 11), gantry angle (p = 0.