- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
[IEEE 2018 IEEE/ACS 15th International Conference on Computer Systems and Applications (AICCSA) - Aqaba, Jordan (2018.10.28-2018.11.1)] 2018 IEEE/ACS 15th International Conference on Computer Systems and Applications (AICCSA) - Number of Texture Unit as Feature to Breast's Disease Classification from Thermal Images
摘要： This paper presents the use of the Number of Texture Unit as a feature extractor for classification of breast images. The Number of Texture Unit served as the basis for the idealization of the Local Binary Pattern a technique that is widely used in facial recognition. We compared the proposed strategy with the Gray Level Co-occurrence Matrix which is the most used texture analysis technique in the literature. With this work we have been able to show that the combination of the two techniques of feature extraction improves the final result of classification. To perform the tests we used the Support Vectors Machine classifier and obtained a result of 96.15% Area Under the Curve (Receiver Operating Characteristic Curve).
关键词： computer aided diagnosis,machine learning,support vector machine,feature extraction,infrared images,Local Binary Pattern
更新于2025-09-19 17:15:36
-
Evaluation of Machine Learning Approaches to Predict Soil Organic Matter and pH Using vis-NIR Spectra
摘要： Soil organic matter (SOM) and pH are essential soil fertility indictors of paddy soil in the middle-lower Yangtze Plain. Rapid, non-destructive and accurate determination of SOM and pH is vital to preventing soil degradation caused by inappropriate land management practices. Visible-near infrared (vis-NIR) spectroscopy with multivariate calibration can be used to effectively estimate soil properties. In this study, 523 soil samples were collected from paddy ?elds in the Yangtze Plain, China. Four machine learning approaches—partial least squares regression (PLSR), least squares-support vector machines (LS-SVM), extreme learning machines (ELM) and the Cubist regression model (Cubist)—were used to compare the prediction accuracy based on vis-NIR full bands and bands reduced using the genetic algorithm (GA). The coef?cient of determination (R2), root mean square error (RMSE), and ratio of performance to inter-quartile distance (RPIQ) were used to assess the prediction accuracy. The ELM with GA reduced bands was the best model for SOM (SOM: R2 = 0.81, RMSE = 5.17, RPIQ = 2.87) and pH (R2 = 0.76, RMSE = 0.43, RPIQ = 2.15). The performance of the LS-SVM for pH prediction did not differ signi?cantly between the model with GA (R2 = 0.75, RMSE = 0.44, RPIQ = 2.08) and without GA (R2 = 0.74, RMSE = 0.45, RPIQ = 2.07). Although a slight increase was observed when ELM were used for prediction of SOM and pH using reduced bands (SOM: R2 = 0.81, RMSE = 5.17, RPIQ = 2.87; pH: R2 = 0.76, RMSE = 0.43, RPIQ = 2.15) compared with full bands (R2 = 0.81, RMSE = 5.18, RPIQ = 2.83; pH: R2 = 0.76, RMSE = 0.45, RPIQ = 2.07), the number of wavelengths was greatly reduced (SOM: 201 to 44; pH: 201 to 32). Thus, the ELM coupled with reduced bands by GA is recommended for prediction of properties of paddy soil (SOM and pH) in the middle-lower Yangtze Plain.
关键词： soil organic matter,paddy soil,vis-NIR spectra,pH,machine learning approaches
更新于2025-09-19 17:15:36
-
Development of a Recognition System for Spraying Areas from Unmanned Aerial Vehicles Using a Machine Learning Approach
摘要： Unmanned aerial vehicle (UAV)-based spraying systems have recently become important for the precision application of pesticides, using machine learning approaches. Therefore, the objective of this research was to develop a machine learning system that has the advantages of high computational speed and good accuracy for recognizing spray and non-spray areas for UAV-based sprayers. A machine learning system was developed by using the mutual subspace method (MSM) for images collected from a UAV. Two target lands: agricultural croplands and orchard areas, were considered in building two classifiers for distinguishing spray and non-spray areas. The field experiments were conducted in target areas to train and test the system by using a commercial UAV (DJI Phantom 3 Pro) with an onboard 4K camera. The images were collected from low (5 m) and high (15 m) altitudes for croplands and orchards, respectively. The recognition system was divided into offline and online systems. In the offline recognition system, 74.4% accuracy was obtained for the classifiers in recognizing spray and non-spray areas for croplands. In the case of orchards, the average classifier recognition accuracy of spray and non-spray areas was 77%. On the other hand, the online recognition system performance had an average accuracy of 65.1% for croplands, and 75.1% for orchards. The computational time for the online recognition system was minimal, with an average of 0.0031 s for classifier recognition. The developed machine learning system had an average recognition accuracy of 70%, which can be implemented in an autonomous UAV spray system for recognizing spray and non-spray areas for real-time applications.
关键词： image classifiers,machine learning system,precision agriculture,recognition system,mutual subspace method
更新于2025-09-19 17:15:36
-
Can Multispectral Information Improve Remotely Sensed Estimates of Total Suspended Solids? A Statistical Study in Chesapeake Bay
摘要： Total suspended solids (TSS) is an important environmental parameter to monitor in the Chesapeake Bay due to its effects on submerged aquatic vegetation, pathogen abundance, and habitat damage for other aquatic life. Chesapeake Bay is home to an extensive and continuous network of in situ water quality monitoring stations that include TSS measurements. Satellite remote sensing can address the limited spatial and temporal extent of in situ sampling and has proven to be a valuable tool for monitoring water quality in estuarine systems. Most algorithms that derive TSS concentration in estuarine environments from satellite ocean color sensors utilize only the red and near-infrared bands due to the observed correlation with TSS concentration. In this study, we investigate whether utilizing additional wavelengths from the Moderate Resolution Imaging Spectroradiometer (MODIS) as inputs to various statistical and machine learning models can improve satellite-derived TSS estimates in the Chesapeake Bay. After optimizing the best performing multispectral model, a Random Forest regression, we compare its results to those from a widely used single-band algorithm for the Chesapeake Bay. We find that the Random Forest model modestly outperforms the single-band algorithm on a holdout cross-validation dataset and offers particular advantages under high TSS conditions. We also find that both methods are similarly generalizable throughout various partitions of space and time. The multispectral Random Forest model is, however, more data intensive than the single band algorithm, so the objectives of the application will ultimately determine which method is more appropriate.
关键词： water quality,total suspended solids,ocean color,satellite remote sensing,statistical analysis,Random Forest,Chesapeake Bay,multispectral,machine learning
更新于2025-09-19 17:15:36
-
Classification of Land Cover, Forest, and Tree Species Classes with ZiYuan-3 Multispectral and Stereo Data
摘要： The global availability of high spatial resolution images makes mapping tree species distribution possible for better management of forest resources. Previous research mainly focused on mapping single tree species, but information about the spatial distribution of all kinds of trees, especially plantations, is often required. This research aims to identify suitable variables and algorithms for classifying land cover, forest, and tree species. Bi-temporal ZiYuan-3 multispectral and stereo images were used. Spectral responses and textures from multispectral imagery, canopy height features from bi-temporal stereo imagery, and slope and elevation from the stereo-derived digital surface model data were examined through comparative analysis of six classification algorithms including maximum likelihood classifier (MLC), k-nearest neighbor (kNN), decision tree (DT), random forest (RF), artificial neural network (ANN), and support vector machine (SVM). The results showed that use of multiple source data—spectral bands, vegetation indices, textures, and topographic factors—considerably improved land-cover and forest classification accuracies compared to spectral bands alone, which the highest overall accuracy of 84.5% for land cover classes was from the SVM, and, of 89.2% for forest classes, was from the MLC. The combination of leaf-on and leaf-off seasonal images further improved classification accuracies by 7.8% to 15.0% for land cover classes and by 6.0% to 11.8% for forest classes compared to single season spectral image. The combination of multiple source data also improved land cover classification by 3.7% to 15.5% and forest classification by 1.0% to 12.7% compared to the spectral image alone. MLC provided better land-cover and forest classification accuracies than machine learning algorithms when spectral data alone were used. However, some machine learning approaches such as RF and SVM provided better performance than MLC when multiple data sources were used. Further addition of canopy height features into multiple source data had no or limited effects in improving land-cover or forest classification, but improved classification accuracies of some tree species such as birch and Mongolia scotch pine. Considering tree species classification, Chinese pine, Mongolia scotch pine, red pine, aspen and elm, and other broadleaf trees as having classification accuracies of over 92%, and larch and birch have relatively low accuracies of 87.3% and 84.5%. However, these high classification accuracies are from different data sources and classification algorithms, and no one classification algorithm provided the best accuracy for all tree species classes. This research implies the same data source and the classification algorithm cannot provide the best classification results for different land cover classes. It is necessary to develop a comprehensive classification procedure using an expert-based approach or hierarchical-based classification approach that can employ specific data variables and algorithm for each tree species class.
关键词： classification,ZiYuan-3,stereo image,machine learning,tree species
更新于2025-09-19 17:15:36
-
Estimating physical properties from liquid crystal textures via machine learning and complexity-entropy methods
摘要： Imaging techniques are essential tools for inquiring a number of properties from different materials. Liquid crystals are often investigated via optical and image processing methods. In spite of that, considerably less attention has been paid to the problem of extracting physical properties of liquid crystals directly from textures images of these materials. Here we present an approach that combines two physics-inspired image quantifiers (permutation entropy and statistical complexity) with machine learning techniques for extracting physical properties of nematic and cholesteric liquid crystals directly from their textures images. We demonstrate the usefulness and accuracy of our approach in a series of applications involving simulated and experimental textures, in which physical properties of these materials (namely: average order parameter, sample temperature, and cholesteric pitch length) are predicted with significant precision. Finally, we believe our approach can be useful in more complex liquid crystal experiments as well as for probing physical properties of other materials that are investigated via imaging techniques.
关键词： machine learning,physical properties,image analysis,complexity-entropy methods,liquid crystals
更新于2025-09-19 17:15:36
-
Study on driver’s braking intention identification based on functional near-infrared spectroscopy
摘要： Purpose – Cooperative driving refers to a notion that intelligent system sharing controlling with human driver and completing driving task together. One of the key technologies is that the intelligent system can identify the driver’s driving intention in real time to implement consistent driving decisions. The purpose of this study is to establish a driver intention prediction model. Design/methodology/approach – The authors used the NIRx device to measure the cerebral cortex activities for identifying the driver’s braking intention. The experiment was carried out in a virtual reality environment. During the experiment, the driving simulator recorded the driving data and the functional near-infrared spectroscopy (fNIRS) device recorded the changes in hemoglobin concentration in the cerebral cortex. After the experiment, the driver’s braking intention identi?cation model was established through the principal component analysis and back propagation neural network. Findings – The research results showed that the accuracy of the model established in this paper was 80.39 per cent. And, the model could identify the driver’s braking intent prior to his braking operation. Research limitations/implications – The limitation of this study was that the experimental environment was ideal and did not consider the surrounding traf?c. At the same time, other actions of the driver were not taken into account when establishing the braking intention recognition model. Besides, the veri?cation results obtained in this paper could only re?ect the results of a few drivers’ identi?cation of braking intention. Practical implications – This study can be used as a reference for future research on driving intention through fNIRS, and it also has a positive effect on the research of brain-controlled driving. At the same time, it has developed new frontiers for intention recognition of cooperative driving. Social implications – This study explores new directions for future brain-controlled driving and wheelchairs. Originality/value – The driver’s driving intention was predicted through the fNIRS device for the ?rst time.
关键词： Machine learning,Driving intention identi?cation,fNIRS,Cooperative driving
更新于2025-09-19 17:15:36
-
[IEEE 2018 7th European Workshop on Visual Information Processing (EUVIP) - Tampere, Finland (2018.11.26-2018.11.28)] 2018 7th European Workshop on Visual Information Processing (EUVIP) - deimeq - A Deep Neural Network Based Hybrid No-reference Image Quality Model
摘要： Current no reference image quality assessment models are mostly based on hand-crafted features (signal, computer vision, ... ) or deep neural networks. Using DNNs for image quality prediction leads to several problems, e.g. the input size increase processing time is restricted; higher resolutions will and memory consumption. Large inputs are handled by image patching and aggregation a quality score. In a pure patching approach connections between the sub-images are getting lost. Also, a huge dataset is required for training a DNN from scratch, though only small datasets with annotations are available. We provide a hybrid solution (deimeq) to predict image quality using DNN feature extraction combined with random forest models. Firstly, deimeq uses a pre-trained DNN for feature extraction in a hierarchical sub-image approach, this avoids a huge training dataset. Further, our proposed sub-image approach circumvents a pure patching, because of hierarchical connections between the sub-images. Secondly, deimeq can be extended using signal-based features from state-of-the art models. To evaluate our approach, we choose a strict cross-dataset evaluation with the Live-2 and TID2013 datasets with several pre-trained DNNs. Finally, we show that deimeq and variants of it perform better or similar than other methods.
关键词： Machine learning,Image quality,Image analysis
更新于2025-09-19 17:15:36
-
A learning-based automatic segmentation and quantification method on left ventricle in gated myocardial perfusion SPECT imaging: A feasibility study
摘要： Background. The performance of left ventricular (LV) functional assessment using gated myocardial perfusion SPECT (MPS) relies on the accuracy of segmentation. Current methods require manual adjustments that are tedious and subjective. We propose a novel machine-learning-based method to automatically segment LV myocardium and measure its volume in gated MPS imaging without human intervention. Methods. We used an end-to-end fully convolutional neural network to segment LV myocardium by delineating its endocardial and epicardial surface. A novel compound loss function, which encourages similarity and penalizes discrepancy between prediction and training dataset, is utilized in training stage to achieve excellent performance. We retrospectively investigated 32 normal patients and 24 abnormal patients, whose LV myocardial contours automatically segmented by our method were compared with those delineated by physicians as the ground truth. Results. The results of our method demonstrated very good agreement with the ground truth. The average DSC metrics and Hausdorff distance of the contours delineated by our method are larger than 0.900 and less than 1 cm, respectively, among all 32 + 24 patients of all phases. The correlation coefficient of the LV myocardium volume between ground truth and our results is 0.910 ± 0.061 (P < 0.001), and the mean relative error of LV myocardium volume is -1.09 ± 3.66%. Conclusion. These results strongly indicate the feasibility of our method in accurately quantifying LV myocardium volume change over the cardiac cycle. The learning-based segmentation method in gated MPS imaging has great promise for clinical use.
关键词： Myocardial perfusion,machine learning,segmentation,SPECT
更新于2025-09-19 17:15:36
-
[IEEE 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA) - Orlando, FL, USA (2018.12.17-2018.12.20)] 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA) - Fine Object Detection in Automated Solar Panel Layout Generation
摘要： A solar panel layout is a diagram of a roof, with the roof edges and obstacles marked. Currently, the user has to manually draw boundary over each obstacle in a tedious and meticulous manner. In this work, we have built a framework using the existing object detection models. We have leveraged the power of traditional edge detection algorithms, fusing with the cutting-edge machine learning based object detection frameworks. This fusion results in a framework capable of detecting objects to their exact edges. Thus, the boundary of each obstacle in a solar panel can be generated automatically with the edge pixel count variation of less than 25% compared to the ground truth.
关键词： machine learning,object detection,edge detection
更新于2025-09-19 17:15:36