相关参考文献
注意:仅列出部分参考文献,下载原文获取全部文献信息。
Review
Computer Science, Theory & Methods
Shervin Minaee et al.
Summary: This article provides a comprehensive review of over 150 deep learning-based models for text classification developed in recent years. It discusses their technical contributions, similarities, and strengths, as well as summarizes popular datasets used for text classification. The article also includes a quantitative analysis of the performance of different deep learning models on popular benchmarks and discusses future research directions.
ACM COMPUTING SURVEYS
(2022)
Article
Multidisciplinary Sciences
Agus Hasan et al.
Summary: This study proposes a new method to estimate the time-varying effective reproduction number of COVID-19. It utilizes a discrete-time stochastic augmented compartmental model and a two-stage estimation method with a low pass filter to remove short term fluctuations. The method does not require serial interval information and is comparable to common approaches.
SCIENTIFIC REPORTS
(2022)
Article
Medicine, General & Internal
Nillmani et al.
Summary: This study proposes a deep learning AI-based automatic multiclass detection and classification of pneumonia from chest X-ray images. The method accurately identifies the types of pneumonia by analyzing chest X-ray images, achieving high accuracy and sensitivity.
Article
Medicine, General & Internal
Happy Nkanta Monday et al.
Summary: Chest X-ray is a useful method for COVID-19 evaluation, and a computer-aided diagnosis approach using AI can reduce clinician burden. This study proposes a super-resolutionbased Siamese wavelet multi-resolution CNN called COVID-SRWCNN for COVID-19 classification. By reconstructing high-resolution images and learning high-level features, the proposed model achieves high accuracy and useful performance for COVID-19 screening.
Article
Computer Science, Interdisciplinary Applications
Panagiotis Marentakis et al.
Summary: This study investigated the classification of NSCLC into AC and SCC using different techniques, with LSTM + Inception showing superior performance and outperforming expert evaluations.
MEDICAL & BIOLOGICAL ENGINEERING & COMPUTING
(2021)
Article
Computer Science, Artificial Intelligence
Rajeev Kumar Singh et al.
Summary: The article introduces a novel deep learning solution using chest X-rays for rapid triaging of COVID-19 patients, addressing the issue of scarce testing resources for COVID-19 detection.
NEURAL COMPUTING & APPLICATIONS
(2021)
Article
Chemistry, Analytical
Hammam Alshazly et al.
Summary: This paper utilizes deep learning models and visualization techniques to conduct experiments on SARS-CoV-2 CT-scan and COVID19-CT datasets, achieving rapid and accurate diagnosis of COVID-19 infected individuals.
Article
Radiology, Nuclear Medicine & Medical Imaging
Shuai Wang et al.
Summary: This study utilized artificial intelligence to extract radiological features from CT images of COVID-19, achieving timely and accurate diagnosis of the disease, demonstrating the feasibility of using AI for disease control.
EUROPEAN RADIOLOGY
(2021)
Article
Computer Science, Artificial Intelligence
Aras M. Ismael et al.
Summary: COVID-19 is a novel virus that has led to a global pandemic, with daily increases in cases and deaths. Deep learning approaches, including deep feature extraction and fine-tuning of pretrained convolutional neural networks, show potential in detecting COVID-19 based on chest X-ray images.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Multidisciplinary Sciences
Jungsik Noh et al.
Summary: The study found that under-ascertainment of COVID-19 cases is universal, with actual cumulative cases estimated to be 5-20 times greater than confirmed cases in some countries. Their machine learning framework showed reliability in estimating the number of infections.
Article
Agriculture, Multidisciplinary
Aanis Ahmad et al.
Summary: This study evaluates the performance of three different pre-trained image classification models for classifying early season weeds and assesses an object detection model for locating and identifying weed species. The results show VGG16 as the best performing image classification model, with PyTorch showing faster training times and higher accuracies. The object detection model can locate and identify multiple weeds within a single image.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2021)
Article
Computer Science, Artificial Intelligence
Shaw-Hwa Lo et al.
Summary: The study introduces a novel interaction-based convolutional neural network (ICNN) that uses a model-free influence score to extract valuable information directly from images. By replacing traditional pretrained filters with important variable sets determined by the influence score, the model achieved a state-of-the-art prediction performance of 99.8% on a real-world dataset without sacrificing interpretability.
Article
Computer Science, Artificial Intelligence
Matteo Pennisi et al.
Summary: The study introduces an AI-powered pipeline for automated COVID-19 detection and lesion categorization from CT scans, achieving comparable results with expert radiologists. Prior lung and lobe segmentation significantly enhances the classification performance of the model by over 6 percent points.
ARTIFICIAL INTELLIGENCE IN MEDICINE
(2021)
Review
Physics, Multidisciplinary
Wei Chen et al.
Summary: This paper discusses the importance of automated heart sound classification in the diagnosis of cardiovascular diseases and the current application and challenges of deep learning methods in this field. The study focuses on analyzing CNN and RNN methods developed over the past five years, with the goal of improving the accuracy of heart sound classification.
Article
Computer Science, Artificial Intelligence
Sen Jia et al.
Summary: With the advancement of deep learning technology, there is a growing focus on building deep learning models for HSI classification with few labeled samples, utilizing methods such as transfer learning, active learning, and few-shot learning. The results of the research indicate that the fusion of deep learning methods and related techniques can effectively address the issues of small-sample sets in HSI classification.
Article
Chemistry, Analytical
Iam Palatnik de Sousa et al.
Summary: The study demonstrates that applying Explainable Artificial Intelligence Methods to COVID CT-Scan classifiers can help identify biases from spurious artifacts and improve classification accuracy. Evaluation of different neural network architectures shows that some are more susceptible to biases while others are more robust. However, despite high performance metrics, the explanation methods can highlight biases present in the networks.
Article
Multidisciplinary Sciences
Jie Hou et al.
Summary: This research developed a new diagnosis platform using a deep convolutional neural network (DCNN) to assist radiologists in distinguishing COVID-19 pneumonia from non-COVID-19 pneumonia based on chest X-ray analysis. The explainable method in the DCNN helps achieve higher prediction accuracy, with an average accuracy above 96%, and has the potential for large-scale rapid screening of COVID-9.
SCIENTIFIC REPORTS
(2021)
Article
Health Care Sciences & Services
Md Manjurul Ahsan et al.
Summary: The COVID-19 global pandemic posed significant challenges in healthcare, with patient isolation driven by PCR testing initially challenged by lower availability and higher costs in developing countries. Researchers proposed COVID-19 patient screening using Chest CT and X-ray results, alongside AI and deep learning for higher diagnostic accuracy. Various models were tested, with MobileNetV2 showing the best performance and VGG16 excelling in X-ray datasets, supported by previous academic literature highlighting the effectiveness of these methods in COVID-19 diagnoses.
Article
Computer Science, Artificial Intelligence
Alex J. DeGrave et al.
Summary: Recent deep learning systems to detect COVID-19 from chest radiographs may rely on confounding factors rather than medical pathology, leading to accuracy issues when tested in new hospitals. The approach to obtain training data for these AI systems introduces a nearly ideal scenario for learning spurious shortcuts, raising concerns in medical-imaging AI. Evaluation of models on external data is insufficient to ensure reliance on medically relevant pathology, highlighting the importance of explainable AI for clinical deployment of machine-learning healthcare models.
NATURE MACHINE INTELLIGENCE
(2021)
Article
Engineering, Multidisciplinary
Xiaowei Xu et al.
Article
Psychiatry
Dandan Chen et al.
GENERAL HOSPITAL PSYCHIATRY
(2020)
Article
Computer Science, Artificial Intelligence
Hema Shekar Basavegowda et al.
CAAI TRANSACTIONS ON INTELLIGENCE TECHNOLOGY
(2020)
Article
Computer Science, Information Systems
Somasis Roy et al.
MULTIMEDIA TOOLS AND APPLICATIONS
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Sudipta Roy et al.
IMAGE ANALYSIS AND RECOGNITION (ICIAR 2019), PT II
(2019)
Article
Engineering, Electrical & Electronic
Sudipta Roy et al.
IETE JOURNAL OF RESEARCH
(2017)
Article
Computer Science, Interdisciplinary Applications
Seyedali Mirjalili et al.
ADVANCES IN ENGINEERING SOFTWARE
(2016)