- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
A Novel Fundus Image Reading Tool for Efficient Generation of a Multi-dimensional Categorical Image Database for Machine Learning Algorithm Training
摘要： Background: We described a novel multi-step retinal fundus image reading system for providing high-quality large data for machine learning algorithms, and assessed the grader variability in the large-scale dataset generated with this system. Methods: A 5-step retinal fundus image reading tool was developed that rates image quality, presence of abnormality, findings with location information, diagnoses, and clinical significance. Each image was evaluated by 3 different graders. Agreements among graders for each decision were evaluated. Results: The 234,242 readings of 79,458 images were collected from 55 licensed ophthalmologists during 6 months. The 34,364 images were graded as abnormal by at-least one rater. Of these, all three raters agreed in 46.6% in abnormality, while 69.9% of the images were rated as abnormal by two or more raters. Agreement rate of at-least two raters on a certain finding was 26.7%–65.2%, and complete agreement rate of all-three raters was 5.7%–43.3%. As for diagnoses, agreement of at-least two raters was 35.6%–65.6%, and complete agreement rate was 11.0%–40.0%. Agreement of findings and diagnoses were higher when restricted to images with prior complete agreement on abnormality. Retinal/glaucoma specialists showed higher agreements on findings and diagnoses of their corresponding subspecialties. Conclusion: This novel reading tool for retinal fundus images generated a large-scale dataset with high level of information, which can be utilized in future development of machine learning-based algorithms for automated identification of abnormal conditions and clinical decision supporting system. These results emphasize the importance of addressing grader variability in algorithm developments.
关键词： Grader,Deep Learning,Reading Tool,Retina Fundus Image,Machine Learning
更新于2025-09-09 09:28:46
-
[IEEE 2018 International Joint Conference on Neural Networks (IJCNN) - Rio de Janeiro (2018.7.8-2018.7.13)] 2018 International Joint Conference on Neural Networks (IJCNN) - STDP Learning of Image Patches with Convolutional Spiking Neural Networks
摘要： Spiking neural networks are motivated from principles of neural systems and may possess unexplored advantages in the context of machine learning. A class of convolutional spiking neural networks is introduced, trained to detect image features with an unsupervised, competitive learning mechanism. Image features can be shared within subpopulations of neurons, or each may evolve independently to capture different features in different regions of input space. We analyze the time and memory requirements of learning with and operating such networks. The MNIST dataset is used as an experimental testbed, and comparisons are made between the performance and convergence speed of a baseline spiking neural network.
关键词： Spiking Neural Networks,Unsupervised Learning,Convolution,STDP,Machine Learning
更新于2025-09-09 09:28:46
-
[IEEE 2018 20th International Conference on Transparent Optical Networks (ICTON) - Bucharest (2018.7.1-2018.7.5)] 2018 20th International Conference on Transparent Optical Networks (ICTON) - Impact of Selected Input Features for Lightpath Feasibility Validation Using Artificial Neural Networks
摘要： The new advents of 5G and Internet of Things (IoT) will impact the traf?c, both in volume and dynamicity, at unprecedented rates. As a result, optical transport networks should become more responsive to the traf?c changes as well as to operate more closely to optimality. Therefore, the implementation of a self-driving network is being proposed as a way to achieve these targets. One of the key challenges in this environment is the automatic provisioning of lightpaths. In order to provision a lightpath, Quality of Transmission (QoT) needs to be estimated, which involves complex and time consuming computations. This work proposes the use of arti?cial neural networks (ANN) to speed up lightpath feasibility validation without performing full validation per request (slow) nor keeping a full database of feasible lightpaths (memory consuming). Moreover, we evaluate the impact of input features selection and number of neurons in the obtained accuracy.
关键词： transport networks,arti?cial neural networks,machine learning,Quality of Transmission
更新于2025-09-09 09:28:46
-
Noninvasive diagnostic imaging using machine-learning analysis of nanoresolution images of cell surfaces: Detection of bladder cancer
摘要： We report an approach in diagnostic imaging based on nanoscale-resolution scanning of surfaces of cells collected from body fluids using a recent modality of atomic force microscopy (AFM), subresonance tapping, and machine-leaning analysis. The surface parameters, which are typically used in engineering to describe surfaces, are used to classify cells. The method is applied to the detection of bladder cancer, which is one of the most common human malignancies and the most expensive cancer to treat. The frequent visual examinations of bladder (cytoscopy) required for follow-up are not only uncomfortable for the patient but a serious cost for the health care system. Our method addresses an unmet need in noninvasive and accurate detection of bladder cancer, which may eliminate unnecessary and expensive cystoscopies. The method, which evaluates cells collected from urine, shows 94% diagnostic accuracy when examining five cells per patient’s urine sample. It is a statistically significant improvement (P < 0.05) in diagnostic accuracy compared with the currently used clinical standard, cystoscopy, as verified on 43 control and 25 bladder cancer patients.
关键词： diagnostic imaging,cancer diagnostics,atomic force microscopy,machine learning,noninvasive methods
更新于2025-09-09 09:28:46
-
Automated leaf disease detection in different crop species through image features analysis and One Class Classifiers
摘要： The presented approach demonstrates an automated way of crop disease identification on various leaf sample images corresponding to different crop species employing Local Binary Patterns (LBPs) for feature extraction and One Class Classification for classification. The proposed methodology uses a dedicated One Class Classifier for each plant health condition including, healthy, downy mildew, powdery mildew and black rot. The algorithms trained on vine leaves have been tested in a variety of crops achieving a very high generalization behavior when tested in other crops. An original algorithm proposing conflict resolution between One Class Classifiers provides the correct identification when ambivalent data examples possibly belong to one or more conditions. A total success rate of 95% is achieved for the total for the 46 plant-condition combinations tested.
关键词： Computer vision,Machine learning,Local descriptors,Crop health status,Precision agriculture
更新于2025-09-09 09:28:46
-
Improving accuracy of interatomic potentials: more physics or more data? A case study of silica
摘要： In this paper we test two strategies to improving the accuracy of machine-learning potentials, namely adding more fitting parameters thus making use of large volumes of available quantum-mechanical data, and adding a charge-equilibration model to account for ionic nature of the SiO2 bonding. To that end, we compare Moment Tensor Potentials (MTPs) and MTPs combined with the charge-equilibration (QEq) model (MTP+QEq) fitted to a density functional theory dataset of α-quartz SiO2-based structures. In order to make a meaningful comparison, in addition to the accuracy, we assess the uncertainty of predictions of each potential. It is shown that adding the QEq model to MTP does not make any improvement over the MTP potential alone, while adding more parameters does improve the accuracy and uncertainty of its predictions.
关键词： machine-learning interatomic potentials,Moment Tensor Potential,charge-equilibration model,uncertainty quantification
更新于2025-09-09 09:28:46
-
Rationalizing Perovskites Data for Machine Learning and Materials Design
摘要： Machine learning has been recently used for novel perovskite designs, owing to the availability of large amount of perovskite formability data. Trustworthy results should be based on the valid and reliable data that can reveal the nature of materials as much as possible. In this study, a procedure has been developed to identify the formability of perovskites for all the compounds with the stoichiometry of ABX3 and (A′A′′)(B′B′′)X6, that exist in experiments and are stored in the database of Materials Projects. Our results have enriched data of perovskite formability in a large extent and corrected the possible errors of previous data in ABO3 compounds. Furthermore, machine learning with multiple models approach have identified the A2B′B′′O6 compounds that have suspicious formability results in current experimental data. Therefore, further experimental validation experiments are called for. This work paves a way for cleaning perovskite formability data for reliable machine learning work in future.
关键词： Perovskites,Energy Conversion and Storage,Machine Learning,Plasmonics and Optoelectronics,Materials Design
更新于2025-09-09 09:28:46
-
[IEEE 2018 IEEE 13th International Scientific and Technical Conference on Computer Sciences and Information Technologies (CSIT) - Lviv, Ukraine (2018.9.11-2018.9.14)] 2018 IEEE 13th International Scientific and Technical Conference on Computer Sciences and Information Technologies (CSIT) - Machine-Learning Identification of Extragalactic Objects in the Optical-Infrared All-Sky Surveys
摘要： We present new fully-automatic classification model to select extragalactic objects within astronomical photometric catalogs. Construction of the our classification model is based on the three important procedures: 1) data representation to create feature space; 2) building hypersurface in feature space to limit range of features (outliers detection); 3) building hyperplane separating extragalactic objects from the galactic ones. We trained our model with 1.7 million objects (1.4 million galaxies and quasars, 0.3 million stars). The application of the model is presented as a photometric catalog of 38 million extragalactic objects, identified in the WISE and Pan-STARRS catalogs cross-matched with each other.
关键词： machine learning,classification,data mining,support vector machines,neural networks
更新于2025-09-09 09:28:46
-
Estimation of paddy rice leaf area index using machine learning methods based on hyperspectral data from multi-year experiments
摘要： The performance of three machine learning methods (support vector regression, random forests and artificial neural network) for estimating the LAI of paddy rice was evaluated in this study. Traditional univariate regression models involving narrowband NDVI with optimized band combinations as well as linear multivariate calibration partial least squares regression models were also evaluated for comparison. A four year field-collected dataset was used to test the robustness of LAI estimation models against temporal variation. The partial least squares regression and three machine learning methods were built on the raw hyperspectral reflectance and the first derivative separately. Two different rules were used to determine the models’ key parameters. The results showed that the combination of the red edge and NIR bands (766 nm and 830 nm) as well as the combination of SWIR bands (1114 nm and 1190 nm) were optimal for producing the narrowband NDVI. The models built on the first derivative spectra yielded more accurate results than the corresponding models built on the raw spectra. Properly selected model parameters resulted in comparable accuracy and robustness with the empirical optimal parameter and significantly reduced the model complexity. The machine learning methods were more accurate and robust than the VI methods and partial least squares regression. When validating the calibrated models against the standalone validation dataset, the VI method yielded a validation RMSE value of 1.17 for NDVI(766,830) and 1.01 for NDVI(1114,1190), while the best models for the partial least squares, support vector machine and artificial neural network methods yielded validation RMSE values of 0.84, 0.82, 0.67 and 0.84, respectively. The RF models built on the first derivative spectra with mtry = 10 showed the highest potential for estimating the LAI of paddy rice.
关键词： paddy rice,machine learning,remote sensing,leaf area index,hyperspectral data
更新于2025-09-09 09:28:46
-
Reconstructing granular particles from X-ray computed tomography using the TWS machine learning tool and the level set method
摘要： X-ray computed tomography (CT) has emerged as the most prevalent technique to obtain three-dimensional morphological information of granular geomaterials. A key challenge in using the X-ray CT technique is to faithfully reconstruct particle morphology based on the discretized pixel information of CT images. In this work, a novel framework based on the machine learning technique and the level set method is proposed to segment CT images and reconstruct particles of granular geomaterials. Within this framework, a feature-based machine learning technique termed Trainable Weka Segmentation is utilized for CT image segmentation, i.e., to classify material phases and to segregate particles in contact. This is a fundamentally different approach in that it predicts segmentation results based on a trained classifier model that implicitly includes image features and regression functions. Subsequently, an edge-based level set method is applied to approach an accurate characterization of the particle shape. The proposed framework is applied to reconstruct three-dimensional realistic particle shapes of the Mojave Mars Simulant. Quantitative accuracy analysis shows that the proposed framework exhibits superior performance over the conventional watershed-based method in terms of both the pixel-based classification accuracy and the particle-based segmentation accuracy. Using the reconstructed realistic particles, the particle-size distribution is obtained and validated against experiment sieve analysis. Quantitative morphology analysis is also performed, showing promising potentials of the proposed framework in characterizing granular geomaterials.
关键词： Machine learning,Shape reconstruction,3D particle morphology,X-ray computed tomography,Level set
更新于2025-09-09 09:28:46