- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
[IEEE 2018 IEEE 13th Image, Video, and Multidimensional Signal Processing Workshop (IVMSP) - Aristi Village, Zagorochoria, Greece (2018.6.10-2018.6.12)] 2018 IEEE 13th Image, Video, and Multidimensional Signal Processing Workshop (IVMSP) - Quantitative Evaluation of Salient Deep Neural Network Features Using Random Forests
摘要： The Deep Neural Networks and Deep Convolutional Neural Network have the property of providing multi-scale features at different layers of the network. Combination of these large number of features is one of the attributed reasons for the performance of the Neural Network (NN) on vision problems. This work uses Random Forests to identify robust features at various layers of the NN and evaluates the classification performance of these features in isolation. We propose a method for evaluation of parts of an already trained network using the selection by entropy maximization property of the Random Forests. We define measures for saliency in terms of contribution to the final classification, and evaluate the feature saliency. Simultaneously, a measure to identify the imperativeness of network features for classification is also formalized. The experiments made on a Hand dataset and the MNIST dataset, quantitatively validate various intuitions like the discriminatory nature of the outer layer features.
关键词： Random Forests,Feature Evaluation,CNN,Feature Selection
更新于2025-09-23 15:23:52
-
Investigation on ROI size and location to classify mammograms
摘要： Breast cancer is the major cause of death among women and early detection can lead to a longer survival. Computer Aided Diagnosis (CAD) system helps radiologists in the accurate detection of breast cancer. In medical images a Region of Interest (ROI) is a portion of image which carries the important information related to the diagnosis and it forms the basis for applying shape and texture techniques for cancer detection. Several ROI sizes and locations have been proposed for computer aided diagnosis systems. In the present work various ROI sizes have been used to determine the appropriate ROI size to classify fatty and dense mammograms. Two types of mammograms i.e. fatty and dense are used from the MIAS database. Various texture features have been determined from each ROI size for the analysis of texture characteristics. Fisher discriminant ratio is used to select the most relevant features for classification. Finally linear SVM is used for the purpose of classification. Highest classification accuracy of 96.1% was achieved for ROI size 200×200 pixels.
关键词： classification,breast cancer,digital mammograms,breast tissue,ROI,feature selection
更新于2025-09-23 15:22:29
-
Hypertension Assessment Using Photoplethysmography: A Risk Stratification Approach
摘要： Hypertension is a common chronic cardiovascular disease (CVD). Early screening and diagnosis of hypertension plays a major role in its prevention and in the control of CVDs. Our study discusses the early screening of hypertension while using the morphological features of photoplethysmography (PPG). Numerous morphological features of PPG and its derivative waves were defined and extracted. Six types of feature selection methods were chosen to screen and evaluate these PPG morphological features. The optimal features were comprehensively analyzed in relation to the physiological processes of the cardiovascular circulatory system. Particularly, the intrinsic relation and physiological significance between the formation process of systolic blood pressure (SBP) and PPG morphology features were analyzed in depth. A variety of linear and nonlinear classification models were established for the comparison trials. The F1 scores for the normotension versus prehypertension, normotension and prehypertension versus hypertension, and normotension versus hypertension trials were 72.97%, 81.82%, and 92.31%, respectively. In summary, this study established a PPG characteristic analysis model and established the intrinsic relationship between SBP and PPG characteristics. Finally, the risk stratification of hypertension at different stages was examined and compared based on the optimal feature subset.
关键词： Hypertension,photoplethysmograph,feature selection,systolic blood pressure,risk classification
更新于2025-09-23 15:22:29
-
On the performance improvement of non-cooperative iris biometrics using segmentation and feature selection techniques
摘要： In this work, an improved segmentation methodology and a novel feature selection algorithm are proposed. From the input eye image, iris boundary is identified using Circular Hough Transform. A bounding box is defined using the radius obtained followed by iterative thresholding techniques to eliminate specular reflections, eyelids, eyelashes and pupil region. First-order and second-order statistical features are extracted from the segmented iris. For the first time, the statistical measure, Chi-square value is computed from GLCM as a new novel feature from iris images. Statistical dependency-based backward feature selection (SDBFS) algorithm is used to reduce the feature vector size. By operating on local features in reduced search space, computation complexity of segmentation is reduced with less mislocalisation count and eliminates pupil dilation effects. Results of SDBFS show the usefulness of minimal-useful features. Experimental results conducted on CASIA V1, V3-interval and UBIRIS V1 datasets show that statistical features in non-ideal iris images outperform some of the state-of-the-art methods.
关键词： backward feature selection,chi-square value,grey level co-occurrence matrix,iris recognition,GLCM,statistical dependency,Circular Hough Transform,segmentation
更新于2025-09-23 15:22:29
-
Using PPG Signals and Wearable Devices for Atrial Fibrillation Screening
摘要： Cardiovascular diseases are the primary cause of deaths in the world. Atrial fibrillation (AF) is the most common type of cardiac arrhythmia. Due to its high prevalence and associated risks, early detection of AF is an important objective for healthcare systems worldwide. The growing demand for medical assistance implies increased expenses, which could be limited by implementing ambulatory monitoring techniques based on wearable devices, thus reducing the number of people requiring observation in hospitals. One of the main challenges in this context is related to the large amount of data from patients to be analyzed, which points to the suitability of using computational intelligence techniques for it. The selection of the features to be extracted from data plays a key role in order for any classifier of heart rhythm to provide good results in this regard. This paper demonstrates that it is possible to achieve an accurate detection of AF using a very low number of relatively simple features extracted from photoplethysmographic signals, enabling the use of affordable wearable devices (with scarce processing and data storage resources) with this purpose over long periods of time. This fact has been validated in experiments using data from real patients under medical supervision.
关键词： Atrial fibrillation,photoplethysmography,wearable devices,ambulatory screening,feature selection
更新于2025-09-23 15:22:29
-
[IEEE 2019 URSI Asia-Pacific Radio Science Conference (AP-RASC) - New Delhi, India (2019.3.9-2019.3.15)] 2019 URSI Asia-Pacific Radio Science Conference (AP-RASC) - Physics based Device Modeling of GaN High Electron Mobility Transistor (HEMT) for Terahertz Applications
摘要： Scanning laser ophthalmoscopes (SLOs) can be used for early detection of retinal diseases. With the advent of latest screening technology, the advantage of using SLO is its wide field of view, which can image a large part of the retina for better diagnosis of the retinal diseases. On the other hand, during the imaging process, artefacts such as eyelashes and eyelids are also imaged along with the retinal area. This brings a big challenge on how to exclude these artefacts. In this paper, we propose a novel approach to automatically extract out true retinal area from an SLO image based on image processing and machine learning approaches. To reduce the complexity of image processing tasks and provide a convenient primitive image pattern, we have grouped pixels into different regions based on the regional size and compactness, called superpixels. The framework then calculates image based features reflecting textural and structural information and classifies between retinal area and artefacts. The experimental evaluation results have shown good performance with an overall accuracy of 92%.
关键词： retinal artefacts extraction,Feature selection,retinal image analysis,scanning laser ophthalmoscope (SLO)
更新于2025-09-23 15:19:57
-
[ACM Press the 2nd International Conference - Chengdu, China (2018.06.16-2018.06.18)] Proceedings of the 2nd International Conference on Advances in Image Processing - ICAIP '18 - Feature-Grouping-Based Two Steps Feature Selection Algorithm in Software Defect Prediction
摘要： In order to improve the effect of software defect prediction, many algorithms including feature selection, have been proposed. Based on Wrapper and Filter hybrid framework, a feature-grouping-based feature selection algorithm is proposed in this paper. The algorithm is composed of two steps. In the first step, in order to remove the redundant features, we group the features according to the redundancy between the features. The symmetry uncertainty is used as the constant indicator of the correlation and the FCBF-based grouping algorithm is used to group the features. In the second step, a subset of the features are selected from each group to form the final subset of features. Many classical methods select the representative feature from each group. We consider that when the number of intra-group features is large, the representative features are not enough to reflect the information in this group. Therefore, we require that at least one feature be selected within each group, in this step, the PSO algorithm is used for Searching Randomly from each group. We tested on the open source NASA and PROMISE data sets. Using three kinds of classifier. Compared to the other methods tested in this article, our method the predictive performance of 30 sets of results on 10 data sets. Compared with the algorithms without feature selection, the AUC values of this method in the Logistic regression, Naive Bayesian, and K-neighbor classifiers are improved by 5.94% and 4.69% And 8.05%. The FCBF algorithm can also be regarded as a kind of first performing feature grouping. Compared with the FCBF algorithm, the AUC values of this method are improved by 4.78%, 6.41% and 4.4% on the basis of Logistic regression, Naive Bayes and K-neighbor. We can also see that for the FCBF-based grouping algorithm, it could be better to choose a characteristic cloud from each group than to choose a representative one.
关键词： Intra-group feature selection,PSO.,FCBF-based grouping algorithm,Software defect prediction,Feature grouping
更新于2025-09-19 17:15:36
-
Quantitative Analysis of Cadmium Content in Tomato Leaves Based on Hyperspectral Image and Feature Selection
摘要： In order to ensure that safe and healthy tomatoes can be provided to people, a method for quantitative determination of cadmium content in tomato leaves based on hyperspectral imaging technology was put forward in this study. Tomato leaves with seven cadmium stress gradients were studied. Hyperspectral images of all samples were firstly acquired by the hyperspectral imaging system, then the spectral data were extracted from the hyperspectral images. To simplify the model, three algorithms of competitive adaptive reweighted sampling (CARS), variable combination population analysis (VCPA) and bootstrapping soft shrinkage (BOSS) were used to select the feature wavelengths ranging from 431 to 962 nm. Final results showed that BOSS can improve prediction performance and greatly reduce features when compared with the other two selection methods. The BOSS model got the best accuracy in calibration and prediction with R2c of 0.9907 and RMSEC of 0.4257mg/kg, R2p of 0.9821, and RMSEP of 0.6461 mg/kg. Hence, the method of hyperspectral technology combined with the BOSS feature selection is feasible for detecting the cadmium content of tomato leaves, which can potentially provide a new method and thought for cadmium content detection of other crops.
关键词： Regression model,Feature selection,Tomato leaves,Hyperspectral image technology,Non-destructive analysis
更新于2025-09-19 17:15:36
-
[IEEE 2019 14th IEEE Conference on Industrial Electronics and Applications (ICIEA) - Xi'an, China (2019.6.19-2019.6.21)] 2019 14th IEEE Conference on Industrial Electronics and Applications (ICIEA) - Photovoltaic consumption in distribution network considering shiftable load
摘要： In this paper, a joint feature selection and parameter estimation algorithm is presented for hidden Markov models (HMMs) and hidden semi-Markov models (HSMMs). New parameters, feature saliencies, are introduced to the model and used to select features that distinguish between states. The feature saliencies represent the probability that a feature is relevant by distinguishing between state-dependent and state-independent distributions. An expectation maximization algorithm is used to calculate maximum a posteriori estimates for model parameters. An exponential prior on the feature saliencies is compared with a beta prior. These priors can be used to include cost in the model estimation and feature selection process. This algorithm is tested against maximum likelihood estimates and a variational Bayesian method. For the HMM, four formulations are compared on a synthetic data set generated by models with known parameters, a tool wear data set, and data collected during a painting process. For the HSMM, two formulations, maximum likelihood and maximum a posteriori, are tested on the latter two data sets, demonstrating that the feature saliency method of feature selection can be extended to semi-Markov processes. The literature on feature selection speci?cally for HMMs is sparse, and non-existent for HSMMs. This paper ?lls a gap in the literature concerning simultaneous feature selection and parameter estimation for HMMs using the EM algorithm, and introduces the notion of selecting features with respect to cost for HMMs.
关键词： maximum a posteriori estimation.,hidden Markov models,hidden semi-Markov models,Feature selection
更新于2025-09-19 17:13:59
-
[IEEE 2019 International Topical Meeting on Microwave Photonics (MWP) - Ottawa, ON, Canada (2019.10.7-2019.10.10)] 2019 International Topical Meeting on Microwave Photonics (MWP) - Free Carrier Plasma GeSn Modulator for Mid-Infrared Integrated Microwave Photonics
摘要： Scanning laser ophthalmoscopes (SLOs) can be used for early detection of retinal diseases. With the advent of latest screening technology, the advantage of using SLO is its wide field of view, which can image a large part of the retina for better diagnosis of the retinal diseases. On the other hand, during the imaging process, artefacts such as eyelashes and eyelids are also imaged along with the retinal area. This brings a big challenge on how to exclude these artefacts. In this paper, we propose a novel approach to automatically extract out true retinal area from an SLO image based on image processing and machine learning approaches. To reduce the complexity of image processing tasks and provide a convenient primitive image pattern, we have grouped pixels into different regions based on the regional size and compactness, called superpixels. The framework then calculates image based features reflecting textural and structural information and classifies between retinal area and artefacts. The experimental evaluation results have shown good performance with an overall accuracy of 92%.
关键词： retinal artefacts extraction,Feature selection,retinal image analysis,scanning laser ophthalmoscope (SLO)
更新于2025-09-19 17:13:59