The efficient Kalman filter has been widely used in recent decades to obtain air navigation information in UAVs. However, for a good performance of the Kalman filter, the model that describes the system dynamics must ...
The efficient Kalman filter has been widely used in recent decades to obtain air navigation information in UAVs. However, for a good performance of the Kalman filter, the model that describes the system dynamics must not contain uncertainties. This paper presents the implementation of a robust Kalman filter to estimate the attitude, velocity, and position of UAVs. The robust filter considers uncertainties in the sensor models. A mathematical structure based on the solution of linear systems synthesizes the predictor-corrector robust estimation algorithm. The main contribution of this study is the proposed QR decomposition based on Givens rotation to solve the linear system. The simulated experiments used sensory data collected in Zürich-Switzerland and ground truth referencing attitude, velocity, and position. The offline simulation results express the effectiveness of the robust Kalman filter for this application, with a reduction of up to 18.9% in the estimation error, in relation to the standard Kalman filter. The proposal to use systolic arrays for numerical solutions has shown promise for implementation in parallel processing platforms, such as FPGAs.
Multivariate time series (MTS) data, when sampled irregularly and asynchronously, often present extensive missing values. Conventional methodologies for MTS analysis tend to rely on temporal embeddings based on timest...
详细信息
The intelligent Internet of Things(IIoT)is one of the key enablers for the digital transformation of traditional industries towards Industry *** services have diversified requirements due to the nature of their commer...
详细信息
The intelligent Internet of Things(IIoT)is one of the key enablers for the digital transformation of traditional industries towards Industry *** services have diversified requirements due to the nature of their commercial and industrial *** various devices in IIoT environments have their unique properties in terms of resource limita-tions,network lifetimes,and application Quali-ty-of-Service(QoS)requirements which affect the performance under such applications ***,IoT devices typically have constrained power,storage,computing,high latency,massive multiple access and communications resources which limit the performance of IIoT for commercial and industrial Use *** the other hand,devices used in IIoT were not initially designed with security in mind and they had been considered *** response to the above challenges,domestic and foreign scholars have gradually carried out research on network architecture,collaborative scheduling strategy,energy supply technology,resource man-agement,and ***,the research on IIoT is still in its infancy,and has not yet formed comprehen-sive and systematic theoretical methods and technical standards.
Microsatellite instability (MSI) is a pivotal genetic marker influencing the efficacy of immunotherapy in colorectal cancer. Traditional MSI examination often requires additional genetic or immunohistochemical tests, ...
详细信息
ISBN:
(数字)9798331518622
ISBN:
(纸本)9798331518639
Microsatellite instability (MSI) is a pivotal genetic marker influencing the efficacy of immunotherapy in colorectal cancer. Traditional MSI examination often requires additional genetic or immunohistochemical tests, whereas histology images, widely available in colorectal cancer diagnosis, offer a valuable alternative for MSI prediction. Although Transformer-based models have demonstrated promising outcomes in predicting MSI from histology images, they are hampered by traditional local attention mechanisms that struggle to capture long-range interdependencies and establish a comprehensive global receptive field. In this study, we introduce DiNAT-MSI, a novel framework for histology-based MSI prediction that incorporates the Dilated Neighborhood Attention Transformer (DiNAT). This model enhances global context recognition and substantially expands receptive fields, all without additional computational burden. Our results demonstrate that DiNAT-MSI achieves a superior patientwise AUROC compared to ResNet18 and Swin Transformer, along with commendable explainability. Our work not only illustrates a more accessible diagnostic tool for leveraging histological data but also underscores the potential of Transformerbased models with sophisticated attention designs in advancing precision medicine for colorectal cancer patients.
This research aims to help the user monitor their heart’s condition and notify other people in case of an emergency due to an abnormal heartbeat (normal heartbeat around 60-100 beats per minute). From the heart rate ...
详细信息
As part of the 2023 PhysioNet Challenge, our team FINDING_MEMO utilized Transformer to predict outcomes using patient EEG data since it excels at dealing with sequential data like EEG. We mainly used the Transformer e...
As part of the 2023 PhysioNet Challenge, our team FINDING_MEMO utilized Transformer to predict outcomes using patient EEG data since it excels at dealing with sequential data like EEG. We mainly used the Transformer encoder block's multi-head self-attention to generate representations from the input and leverage several hidden layers to form the final prediction. Using the latest EEG from every patient, our team achieved the challenge score of 0.42 with the hidden validation set (ranked 36th out of 73 invited teams) and obtained a result of 0.37 (ranked 29th out of 36 qualified teams). Our results show a consistent performance across varying EEG recording durations in both the validation and test set. Our team also had the second-best score when evaluated, with only 12 hours of available recordings in the test set. Such promising results showcase the models' generalizability and clinical potential in predicting outcomes for comatose patients, especially for limited available EEG recordings.
Electronic Health Records (EHRs) are a cornerstone of modern healthcare analytics, offering rich datasets for various disease analyses through advanced deep learning algorithms. However, the pervasive issue of missing...
详细信息
ISBN:
(数字)9798350371499
ISBN:
(纸本)9798350371505
Electronic Health Records (EHRs) are a cornerstone of modern healthcare analytics, offering rich datasets for various disease analyses through advanced deep learning algorithms. However, the pervasive issue of missing values in EHRs significantly hampers the development and performance of these models. Addressing this challenge is crucial for enhancing clinical decision-making and patient care. Existing methods for handling missing data, ranging from simple imputation to more sophisticated approaches, often fall short of capturing the temporal dynamics inherent in EHRs. To bridge this gap, we introduce the Deep Stochastic Time-series Imputation (Deep STI) algorithm, an innovative end-to-end deep learning model that seamlessly integrates a sequence-to-sequence generative network with a prediction network. Deep STI is designed to leverage the observed time-series data in EHRs, learning to infer missing values from the temporal context with high accuracy. We evaluated Deep STI on the liver cancer data from the National Taiwan University Hospital (NTUH), Taiwan. Our results showed that Deep STI achieved better 5-year hepatocellular carcinoma predictions (19.21% in the area under the precision-recall curve) than extreme gradient boosting (18.15%) and Transformer (18.09%). The ablation study also illustrates the efficacy of our generative architecture design compared to regular imputations. This approach not only promises to improve the reliability of disease analysis in the presence of incomplete data but also sets a new standard for utilizing EHRs in predictive healthcare. Our work aims to advance the field of healthcare analytics and open new avenues for research in deep learning applications to EHRs.
Dual-encoder structure successfully utilizes two language-specific encoders (LSEs) for code-switching speech recognition. Because LSEs are initialized by two pre-trained language-specific models (LSMs), the dual-encod...
详细信息
Deep learning has revolutionized medical imaging, offering advanced methods for accurate diagnosis and treatment planning. The BCLC staging system is crucial for staging Hepatocellular Carcinoma (HCC), a high-mortalit...
详细信息
ISBN:
(数字)9798350351552
ISBN:
(纸本)9798350351569
Deep learning has revolutionized medical imaging, offering advanced methods for accurate diagnosis and treatment planning. The BCLC staging system is crucial for staging Hepatocellular Carcinoma (HCC), a high-mortality cancer. An automated BCLC staging system could significantly enhance diagnosis and treatment planning efficiency. However, we found that BCLC staging, which is directly related to the size and number of liver tumors, aligns well with the principles of the Multiple Instance Learning (MIL) framework. To effectively achieve this, we proposed a new preprocessing technique called Masked Cropping and Padding(MCP), which addresses the variability in liver volumes and ensures consistent input sizes. This technique preserves the structural integrity of the liver, facilitating more effective learning. Furthermore, we introduced Re ViT, a novel hybrid model that integrates the local feature extraction capabilities of Convolutional Neural Networks (CNNs) with the global context modeling of Vision Transformers (ViTs). Re ViT leverages the strengths of both architectures within the MIL framework, enabling a robust and accurate approach for BCLC staging. We will further explore the trade-off between performance and interpretability by employing TopK Pooling strategies, as our model focuses on the most informative instances within each bag.
The Barcelona Clinic Liver Cancer (BCLC) staging system plays a crucial role in clinical planning, offering valuable insights for effectively managing hepatocellular carcinoma. Accurate prediction of BCLC stages can s...
详细信息
ISBN:
(数字)9798350371499
ISBN:
(纸本)9798350371505
The Barcelona Clinic Liver Cancer (BCLC) staging system plays a crucial role in clinical planning, offering valuable insights for effectively managing hepatocellular carcinoma. Accurate prediction of BCLC stages can significantly ease the workload on radiologists. However, few datasets are explicitly designed for discerning BCLC stages. Despite the common practice of appending BCLC labels to clinical data within datasets, the inherent imbalance in BCLC distribution is further amplified by the diverse purposes for which datasets are curated. In this study, we aim to develop a BCLC staging system using the advanced Swin Transformer model. Additionally, we explore the integration of two datasets, each originally intended for separate objectives, highlighting the critical challenge of preserving class distribution in practical study designs. This exploration is pivotal for ensuring the applicability of our developed staging system in the designed clinical settings. Our resulting BCLC staging system demonstrates an accuracy of 55.81% (±7.8%), contributing to advancing medical image-based research for predicting BCLC stages.
暂无评论