Search

Bladder urothelial carcinoma is the most common malignant tumor disease in urinary system, and its incidence rate ranks ninth in the world. In recent years, the continuous development of hyperspectral imaging technology has provided a new tool for the auxiliary diagnosis of bladder cancer. In this study, based on microscopic hyperspectral data, an automatic detection algorithm of bladder tumor cells combining color features and shape features is proposed. Support vector machine (SVM) is used to build classification models and compare the classification performance of spectral feature, spectral and shape fusion feature, and the fusion feature proposed in this paper on the same classifier. The results show that the sensitivity, specificity, and accuracy of our classification algorithm based on shape and color fusion features are 0.952, 0.897, and 0.920, respectively, which are better than the classification algorithm only using spectral features. Therefore, this study can effectively extract the cell features of bladder urothelial carcinoma smear, thus achieving automatic, real-time, and noninvasive detection of bladder tumor cells, and then helping doctors improve the efficiency of pathological diagnosis of bladder urothelial cancer, and providing a reliable basis for doctors to choose treatment plans and judge the prognosis of the disease. [ABSTRACT FROM AUTHOR]

Bladder urothelial carcinoma is the most common malignant tumor disease in urinary system, and its incidence rate ranks ninth in the world. In recent years, the continuous development of hyperspectral imaging technology has provided a new tool for the auxiliary diagnosis of bladder cancer. In this study, based on microscopic hyperspectral data, an automatic detection algorithm of bladder tumor cells combining color features and shape features is proposed. Support vector machine (SVM) is used to build classification models and compare the classification performance of spectral feature, spectral and shape fusion feature, and the fusion feature proposed in this paper on the same classifier. The results show that the sensitivity, specificity, and accuracy of our classification algorithm based on shape and color fusion features are 0.952, 0.897, and 0.920, respectively, which are better than the classification algorithm only using spectral features. Therefore, this study can effectively extract the cell features of bladder urothelial carcinoma smear, thus achieving automatic, real-time, and noninvasive detection of bladder tumor cells, and then helping doctors improve the efficiency of pathological diagnosis of bladder urothelial cancer, and providing a reliable basis for doctors to choose treatment plans and judge the prognosis of the disease.

Continuous data scale growth increases energy consumption and operating cost that cannot be ignored in cloud storage systems. Previous studies have shown that analyzing the characteristics of I/O access and mining data features is effective for reasonable data distribution in storage systems. The granularity and criterion of classification are the key factors in determining the data distribution. To decrease energy consumption and operating cost, this paper puts forward a fine-grained framework of the climatic-season-based energy-aware in cloud storage system called CSEA. The framework concludes the following three aspects: (i) data feature mining. CSEA discovers potential data features by analyzing data access to provide help with data classification. (ii) K-means clustering algorithm. CSEA uses an unsupervised data classification algorithm in machine learning to divide data into categories based on seasonal characteristics by gathering real I/O access. (iii) data distribution of fine-grained. On the basis of seasonal features, CSEA fuses regional features to further refine the data distribution granularity to save on energy consumption and operating cost. Simulation experiments using extended CloudSimDisk and the constructed mathematical models indicate that CSEA reduces the energy consumption and operating cost compared with the single data classification standard and coarse-grained data distribution. [ABSTRACT FROM AUTHOR]

The accurate measurement of soil organic matter (SOM) is vital for maintaining soil quality. We present an innovative model for SOM prediction by integrating spectral and profile features. We use PCA, Lasso, and SCARS methods to extract important spectral features and combine them with profile data. This hybrid approach significantly improves SOM prediction across various models, including Random Forest, ExtraTrees, and XGBoost, boosting the coefficient of determination (R2) by up to 26%. Notably, the ExtraTrees model, enriched with PCA-extracted features, achieves the highest accuracy with an R2 of 0.931 and an RMSE of 0.068. Compared with single-feature models, this approach improves the R2 by 17% and 26% for PCA features of full-band spectra and profile features, respectively. Our findings highlight the potential of feature integration, especially the ExtraTrees model with PCA-extracted features and profile features, as a stable and accurate tool for SOM prediction in extensive study areas. [ABSTRACT FROM AUTHOR]

Copyright of China Rural Water & Hydropower is the property of China Rural Water & Hydropower Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Antiviral peptides (AVPs) are widely found in animals and plants, with high specificity and strong sensitivity to drug-resistant viruses. However, due to the great heterogeneity of different viruses, most of the AVPs have specific antiviral activities. Therefore, it is necessary to identify the specific activities of AVPs on virus types. Most existing studies only identify AVPs, with only a few studies identifying subclasses by training multiple binary classifiers. We develop a two-stage prediction tool named FFMAVP that can simultaneously predict AVPs and their subclasses. In the first stage, we identify whether a peptide is AVP or not. In the second stage, we predict the six virus families and eight species specifically targeted by AVPs based on two multiclass tasks. Specifically, the feature extraction module in the two-stage task of FFMAVP adopts the same neural network structure, in which one branch extracts features based on amino acid feature descriptors and the other branch extracts sequence features. Then, the two types of features are fused for the following task. Considering the correlation between the two tasks of the second stage, a multitask learning model is constructed to improve the effectiveness of the two multiclass tasks. In addition, to improve the effectiveness of the second stage, the network parameters trained through the first-stage data are used to initialize the network parameters in the second stage. As a demonstration, the cross-validation results, independent test results and visualization results show that FFMAVP achieves great advantages in both stages. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Vibration, Measurement & Diagnosis is the property of Nanjing Hangkong Daxue and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Capturing semantics and structure surrounding the target entity pair is crucial for relation extraction. The task is challenging due to the limited semantic elements and structural features of the target entity pair within a sentence. To tackle this problem, this paper introduces an approach that fuses entity-related features under convolutional neural networks and graph convolution neural networks. Our approach combines the unit features of the target entity pair to generate corresponding fusion features and applies the deep learning framework to extract high-order abstract features for relation extraction. Experimental results from three public datasets (ACE05 English, ACE05 Chinese, and SanWen) indicate that the proposed approach achieves F1-scores of 77.70%, 90.12%, and 68.84%, respectively, highlighting its effectiveness and robustness. This paper provides a comprehensive description of the approach and experimental results. [ABSTRACT FROM AUTHOR]

In the field of Automatic Facial Expression Signal Recognition (AFESR) at video communication system, the fusing feature extraction is playing an extremely important role in recognition accuracy. This paper presents a new feature extraction method, Multi-Feature Fusing Local Directional Ternary Pattern (MFF-LDTP) which keeps more feature information and improvs the robustness under the uncontrollable and wild environment for AFESR. Firstly, the MFF-LDTP operator obtains the global feature of facial expression by Principal Components Analysis (PCA). Secondly, the MFF-LDTP enhances traditional Local Directional Ternary Pattern （LDTP）by using a “kirsch mask” to replace the Frei-Chen masks and selects the threshold for facial expression signal recognition. To effectively avoid generating invalid features, the MFF-LDTP extracts the local feature of eye and mouth which are significant regions by ELDTP. Thirdly, The MFF-LDTP final feature vector includes the linear connection of global and local features. The recognition rate for the extended JAFFE database is 96.5%. And the extended JAFFE includes captured sample images under an uncontrollable and wild environment. The experimental results show that the proposed MFF-LDTP achieved significant improvement and outperformed some state-of-the-art methods.

Copyright of Journal of Southeast University (English Edition) is the property of Journal of Southeast University Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The accurate measurement of soil organic matter (SOM) is vital for maintaining soil quality. We present an innovative model for SOM prediction by integrating spectral and profile features. We use PCA, Lasso, and SCARS methods to extract important spectral features and combine them with profile data. This hybrid approach significantly improves SOM prediction across various models, including Random Forest, ExtraTrees, and XGBoost, boosting the coefficient of determination (R2) by up to 26%. Notably, the ExtraTrees model, enriched with PCA-extracted features, achieves the highest accuracy with an R2 of 0.931 and an RMSE of 0.068. Compared with single-feature models, this approach improves the R2 by 17% and 26% for PCA features of full-band spectra and profile features, respectively. Our findings highlight the potential of feature integration, especially the ExtraTrees model with PCA-extracted features and profile features, as a stable and accurate tool for SOM prediction in extensive study areas.

In the field of Automatic Facial Expression Signal Recognition (AFESR) at video communication system, the fusing feature extraction is playing an extremely important role in recognition accuracy. This paper presents a new feature extraction method, Multi-Feature Fusing Local Directional Ternary Pattern (MFF-LDTP) which keeps more feature information and improvs the robustness under the uncontrollable and wild environment for AFESR. Firstly, the MFF-LDTP operator obtains the global feature of facial expression by Principal Components Analysis (PCA). Secondly, the MFF-LDTP enhances traditional Local Directional Ternary Pattern （LDTP）by using a "kirsch mask" to replace the Frei-Chen masks and selects the threshold for facial expression signal recognition. To effectively avoid generating invalid features, the MFF-LDTP extracts the local feature of eye and mouth which are significant regions by ELDTP. Thirdly, The MFF-LDTP final feature vector includes the linear connection of global and local features. The recognition rate for the extended JAFFE database is 96.5%. And the extended JAFFE includes captured sample images under an uncontrollable and wild environment. The experimental results show that the proposed MFF-LDTP achieved significant improvement and outperformed some state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Video anomaly detection is essential to distinguish abnormal events in large volumes of surveillance video and can benefit many fields such as traffic management, public security and failure detection. However, traditional video anomaly detection methods are unable to accurately detect and locate abnormal events in real scenarios, while existing deep learning methods are likely to omit important information when extracting features. In order to avoid omitting important features and improve the accuracy of abnormal event detection and localization, this paper proposes a novel method called Multi Chunk Learning based Skip Connected Convolutional Auto Encoder (MCSCAE). The proposed method improves the accuracy of video anomaly detection by obtaining more vital information. In the data sorting phase, non-uniform chunking is proposed to divide the video frame into several chunks of different sizes to avoid obtaining unnecessary information and omitting crucial information. In order to well reflect the abnormal motion of objects in the video, a new feature, the inter frame flow feature, which is obtained by merging inter frame difference and optical flow features, is proposed to extract motion feature. Moreover, in this paper, skip connection in the auto encoder is utilized during the training phase to reduce the reconstruction error between the original frames and the reconstruction frames, so that the reconstruction error can be used to detect abnormal events during testing. Experience on three public datasets verifies the effectiveness and accuracy of our proposed method. Experimental results show that the proposed method can detect and locate abnormal events outperforms other recent methods significantly. [ABSTRACT FROM AUTHOR]

Under the scenario of moving target tracking is very important in the fields of computer vision and research direction, its purpose is to give computer vision, double eye for simulation of the human visual information processing and information feedback process, in the process of the research can obtain the target trajectory information and provide related data for target tracking, The relevant research results of target tracking have been successfully developed in many fields such as human-computer interaction, security monitoring, intelligent monitoring and face recognition. However in the scene moving target vulnerable to disorder interference, light, shade, and scale complex situations, such as the change of the apparent dynamic change in the process of movement target, research can achieve different scenario stable tracking method has important research significance and engineering related events in the field of value, the existing popular nuclear-related filter tracking algorithm was improved, To solve the problem of occlusion and multi-scale change of tracking target, a new tracking algorithm based on multi-feature and multi-scale anti-occlusion is proposed by using kernel correlation filtering method. [ABSTRACT FROM AUTHOR]

Abstract Background At present, the residual film pollution in cotton fields is crucial. The commonly used recycling method is the manual-driven recycling machine, which is heavy and time-consuming. The development of a visual navigation system for the recovery of residual film is conducive, in order to improve the work efficiency. The key technology in the visual navigation system is the cotton stubble detection. A successful cotton stubble detection can ensure the stability and reliability of the visual navigation system. Methods Firstly, it extracts the three types of texture features of GLCM, GLRLM and LBP, from the three types of images of stubbles, residual films and broken leaves between rows. It then builds three classifiers: Random Forest, Back Propagation Neural Network and Support Vector Machine in order to classify the sample images. Finally, the possibility of improving the classification accuracy using the texture features extracted from the wavelet decomposition coefficients, is discussed. Results The experiment proves that the GLCM texture feature of the original image has the best performance under the Back Propagation Neural Network classifier. As for the different wavelet bases, the vertical coefficient texture feature of coif3 wavelet decomposition, combined with the texture feature of the original image, is the feature having the best classification effect. Compared with the original image texture features, the classification accuracy is increased by 3.8%, the sensitivity is increased by 4.8%, and the specificity is increased by 1.2%. Conclusions The algorithm can complete the task of stubble detection in different locations, different periods and abnormal driving conditions, which shows that the wavelet coefficient texture feature combined with the original image texture feature is a useful fusion feature for detecting stubble and can provide a reference for different crop stubble detection.

Speech synthesis and speech conversion and other technologies are gradually becoming the mainstream methods for synthesizing speech, which has potential risks to social stability and national security. To further improve the accuracy of synthesized and converted forged speech detection, three hybrid network models were proposed from the hybrid network model, feature selection, which were based on CNN-RNN-DNN networks, namely CNN-LSTM-DNN, CNN-GRU-DNN and CNN-BiLSTM-DNN. Subsampling can be carried out by the CNN part of the model. The timing problem of speech can be solved by the RNN part, and the classification function can be realized by the DNN part. 20 network layers are contained in each fusion network model. The extracted 6 acoustic features were tested, among which the combination of CNN-LSTM-DNN + MFCC performed the best, with an equal error rate of 5. 79%, which was 28. 43% lower than the B02 baseline system provided by ASVSPoof2019. At the same time, the performance of three fusion networks combined with six characteristics was compared. The results show that the hybrid network model proposed has the advantages of stable performance and high accuracy, besides the MFCC feature and MFCC + LFCC fusion feature is better fit with this fusion network [ABSTRACT FROM AUTHOR]

We propose a feature-fusion network for pose estimation directly from RGB images without any depth information in this study. First, we introduce a two-stream architecture consisting of segmentation and regression streams. The segmentation stream processes the spatial embedding features and obtains the corresponding image crop. These features are further coupled with the image crop in the fusion network. Second, we use an efficient perspective-n-point (E-PnP) algorithm in the regression stream to extract robust spatial features between 3D and 2D keypoints. Finally, we perform iterative refinement with an end-to-end mechanism to improve the estimation performance. We conduct experiments on two public datasets of YCB-Video and the challenging Occluded-LineMOD. The results show that our method outperforms state-of-the-art approaches in both the speed and the accuracy. [ABSTRACT FROM AUTHOR]

In recent years, with the diversification of malicious code family and the enhancement of confounding countermeasures, traditional detection methods for malicious code are difficult to achieve good classification effect. Therefore, a malicious code family classification model combining attention mechanism is proposed. Firstly, this paper uses the reverse disassembly tool to obtain the features of each section of the malicious sample, and uses visualization technology to convert each section into each channel of RGB color image. Secondly, the channel domain and spatial domain attention mechanism are introduced to build the depthwise separable convolution network based on the mixed domain attention mechanism, and the image texture features of the malicious samples are extracted from the channel and space dimensions. Finally, nine categories of malicious code family are selected to train and test the model. The experimental result shows that the accuracy of the classification of malicious code family by a single section feature is lower than that by fusion feature, which can effectively distinguish various types of malicious code family. Compared with traditional neural network models, the proposed model achieves better classification effect and the classification accuracy of the model reaches 98.38%.

Aiming at the limitation of describing the semantic attributes of target classification, this paper proposes an adaptive weighted fusion feature based zero-sampling image classification algorithm. Firstly, the fusion weights are initialized randomly. Meantime, the semantic vector features and semantic attributes of the text are fused by neural network. Then, particle swarm optimization algorithm is used to optimize the weight of feature fusion. Finally, the features of weighted fusion are regarded as the transfer knowledge of the classification of zero-sampling images. The experimental results show that the classification algorithm based on adaptive weighted fusion for the zero-sampling image has an accuracy rate of 88.9% on the Animals with Attributes (AWA) data set, which illustrates the effectiveness. What's more, the proposed algorithm also improves the stability of the classification model for the zero-sampling image compared with the fusion feature.

Background: At present, the residual film pollution in cotton fields is crucial. The commonly used recycling method is the manual-driven recycling machine, which is heavy and time-consuming. The development of a visual navigation system for the recovery of residual film is conducive, in order to improve the work efficiency. The key technology in the visual navigation system is the cotton stubble detection. A successful cotton stubble detection can ensure the stability and reliability of the visual navigation system. Methods: Firstly, it extracts the three types of texture features of GLCM, GLRLM and LBP, from the three types of images of stubbles, residual films and broken leaves between rows. It then builds three classifiers: Random Forest, Back Propagation Neural Network and Support Vector Machine in order to classify the sample images. Finally, the possibility of improving the classification accuracy using the texture features extracted from the wavelet decomposition coefficients, is discussed. Results: The experiment proves that the GLCM texture feature of the original image has the best performance under the Back Propagation Neural Network classifier. As for the different wavelet bases, the vertical coefficient texture feature of coif3 wavelet decomposition, combined with the texture feature of the original image, is the feature having the best classification effect. Compared with the original image texture features, the classification accuracy is increased by 3.8%, the sensitivity is increased by 4.8%, and the specificity is increased by 1.2%. Conclusions: The algorithm can complete the task of stubble detection in different locations, different periods and abnormal driving conditions, which shows that the wavelet coefficient texture feature combined with the original image texture feature is a useful fusion feature for detecting stubble and can provide a reference for different crop stubble detection. [ABSTRACT FROM AUTHOR]

Labanotation is a widely-used notation system for dance recording. Numerous methods for automatic Labanotation generation from motion capture data have been proposed to save time and human labor. However, dance performance variations, data noises, and difficulties in recognizing long continuous motion sequences limit the performance of existed methods. In this paper, we propose a CRNN-based attention-seq2seq model with fusion features for a robust and effective Labanotation generation.First, we fuse bone feature and Lie group feature to extract not only the information of bones between adjacent joints but also the relative geometry relationships between connected bones. Then, in the proposed seq2seq model, we employ the Convolutional Recurrent Neural Networks (CRNN) to learn the spatial–temporal representation of motion capture data and the attention mechanism to learn good alignments between input motion feature sequences and output symbol sequences. Extensive experiments on real-world datasets show that the proposed method obtains considerable recognition accuracy (90.65% on the LabanSeq16 dataset and 93.29% on the LabanSeq48 dataset), which outperforms state-of-the-art approaches on the task of automatic Labanotation generation. [ABSTRACT FROM AUTHOR]

In the grinding industry, accurate prediction of the mill load is the key to enhancing plant profitability and reducing mill failures. After the condition changes, the model is usually mismatched, and the true label cannot be obtained in time. To solve this problem, we propose a multi-source unsupervised domain adaptation model based on deep learning and fusion features (MUDA_DF), which is suitable for predicting multiple mill load parameters. Considering that the information contained in the data of a single working condition is insufficient to completely cover the information of the unmodeled working condition, we introduce multiple source domains into the model, which can improve the generalization of the model. Since the special features of the source domain also contain useful information, we use the features after the fusion of special features and common features for regression prediction. By designing multiple loss functions, we achieve the prediction of three mill load parameters in unknown operating conditions: material-to-ball volume ratio (MBVR), pulp density (PD), and charge volume ratio (CVR). Experiments were carried out on data sets collected by a laboratory ball mill. Compared with the traditional mill load soft measurement method, the R 2 of this method can reach above 0.9 and the highest can reach 0.99, which proves the effectiveness of this method. • An unsupervised domain-adaptive mill load prediction method is proposed. • Applying multi-source domains to mill load regression prediction. • Applying deep learning to mill load regression prediction. • Extract common and special features simultaneously. [Display omitted] [ABSTRACT FROM AUTHOR]

Cork spot disorder is a common physiological disease that severely affects the quality and yield of the 'Akizuki' pear. In this study, we propose a novel method, Near-infrared spectra and Visual images with Neural Architecture Search (NV-NAS), to achieve a highly accurate diagnosis of cork spot disorder. This method automatically generates fusion features by combining near-infrared spectral and visual image features and then searches for the best-performing model structure. The best result was obtained with near-infrared spectral features preprocessed by first derivatives (FD) and the visual image features extracted by DenseNet121 in the NV-NAS method. On the validation set, the accuracy was 95.5%, and on the test set, the accuracy was 88.2%. Compared to the modeling results of a single feature, the accuracy improved by 26.3% over spectra and by 11.2% over images on the test set. Additionally, in experiments with models of different depths, deep image features were more conducive to feature fusion, with accuracy improvements of 21.7% and 30.1% compared to features from the middle or bottom layers, respectively. The results indicate that the model built on the fusion feature shows high generalization performance and holds significant reference value for the more accurate diagnosis of the 'Akizuki' pear cork spot disorder. • NV-NAS method effectively diagnoses 'Akizuki' pear cork spot disorder. • The model built by the NV-NAS method demonstrates excellent generalization. • The model with fusion data is better than others by the single spectrum or image. [ABSTRACT FROM AUTHOR]

A computer-aided diagnosis (CAD) system based on mammograms enables early breast cancer detection, diagnosis, and treatment. However, the accuracy of the existing CAD systems remains unsatisfactory. This paper explores a breast CAD method based on feature fusion with convolutional neural network (CNN) deep features. First, we propose a mass detection method based on CNN deep features and unsupervised extreme learning machine (ELM) clustering. Second, we build a feature set fusing deep features, morphological features, texture features, and density features. Third, an ELM classifier is developed using the fused feature set to classify benign and malignant breast masses. Extensive experiments demonstrate the accuracy and efficiency of our proposed mass detection and breast cancer classification method.

Copyright of Journal of Frontiers of Computer Science & Technology is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Breast cancer is the most frequently detected tumor that eventually could result in a significant increase in female mortality globally. According to clinical statistics, one woman out of eight is under the threat of breast cancer. Lifestyle and inheritance patterns may be a reason behind its spread among women. However, some preventive measures, such as tests and periodic clinical checks can mitigate its risk thereby, improving its survival chances substantially. Early diagnosis and initial stage treatment can help increase the survival rate. For that purpose, pathologists can gather support from nondestructive and efficient computer-aided diagnosis (CAD) systems. This study explores the breast cancer CAD method relying on multimodal medical imaging and decision-based fusion. In multimodal medical imaging fusion, a deep learning approach is applied, obtaining 97.5% accuracy with a 2.5% miss rate for breast cancer prediction. A deep extreme learning machine technique applied on feature-based data provided a 97.41% accuracy. Finally, decision-based fusion applied to both breast cancer prediction models to diagnose its stages, resulted in an overall accuracy of 97.97%. The proposed system model provides more accurate results compared with other state-of-the-art approaches, rapidly diagnosing breast cancer to decrease its mortality rate. [ABSTRACT FROM AUTHOR]

A fast and nondestructive method for recognizing the severity of wheat Fusarium head blight (FHB) can effectively reduce fungicide use and associated costs in wheat production. This study proposed a feature fusion method based on deep convolution and shallow features derived from the high-resolution digital Red-green-blue (RGB) images of wheat FHB at different disease severity levels. To test the robustness of the proposed method, the RGB images were taken under different influence factors including light condition, camera shooting angle, image resolution, and crop growth period. All images were preprocessed to eliminate background noises to improve recognition accuracy. The AlexNet model parameters trained by the ImageNet 2012 dataset were transferred to the test dataset to extract the deep convolution feature of wheat FHB. Next, the color and texture features of wheat ears were extracted as shallow features. Then, the Relief-F algorithm was used to fuse the deep convolution feature and shallow features as the final FHB features. Finally, the random forest was used to classify and identify the features of different FHB severity levels. Results show that the recognition accuracy of the proposed fusion feature model was higher than those of models using other features in all conditions. The highest recognition accuracy of severity levels was obtained when images were taken under indoor conditions, with high resolution (12 MB pixels), at 90° shooting angle during the crop filling period. The Relief-F algorithm assigned different weights to the features under different influence factors; it made the fused feature model more robust and improved the ability to recognize wheat FHB severity levels using RGB images.

A fast and nondestructive method for recognizing the severity of wheat Fusarium head blight (FHB) can effectively reduce fungicide use and associated costs in wheat production. This study proposed a feature fusion method based on deep convolution and shallow features derived from the high-resolution digital Red-green-blue (RGB) images of wheat FHB at different disease severity levels. To test the robustness of the proposed method, the RGB images were taken under different influence factors including light condition, camera shooting angle, image resolution, and crop growth period. All images were preprocessed to eliminate background noises to improve recognition accuracy. The AlexNet model parameters trained by the ImageNet 2012 dataset were transferred to the test dataset to extract the deep convolution feature of wheat FHB. Next, the color and texture features of wheat ears were extracted as shallow features. Then, the Relief-F algorithm was used to fuse the deep convolution feature and shallow features as the final FHB features. Finally, the random forest was used to classify and identify the features of different FHB severity levels. Results show that the recognition accuracy of the proposed fusion feature model was higher than those of models using other features in all conditions. The highest recognition accuracy of severity levels was obtained when images were taken under indoor conditions, with high resolution (12 MB pixels), at 90° shooting angle during the crop filling period. The Relief-F algorithm assigned different weights to the features under different influence factors; it made the fused feature model more robust and improved the ability to recognize wheat FHB severity levels using RGB images. [ABSTRACT FROM AUTHOR]

High-frequency electroencephalography (EEG) signals play an important role in research on human emotions. However, the different network patterns under different emotional states in the high gamma band (50–80 Hz) remain unclear. In this paper, we investigate different emotional states using functional network analysis on various frequency bands. We constructed multiple functional networks on different frequency bands and performed functional network analysis and time–frequency analysis on these frequency bands to determine the significant features that represent different emotional states. Furthermore, we verified the effectiveness of these features by using them in emotion recognition. Our experimental results revealed that the network connections in the high gamma band with significant differences among the positive, neutral, and negative emotional states were much denser than the network connections in the other frequency bands. The connections mainly occurred in the left prefrontal, left temporal, parietal, and occipital regions. Moreover, long-distance connections with significant differences among the emotional states were observed in the high frequency bands, particularly in the high gamma band. Additionally, high gamma band fusion features derived from the global efficiency, network connections, and differential entropies achieved the highest classification accuracies for both our dataset and the public dataset. These results are consistent with literature and provide further evidence that high gamma band EEG signals are more sensitive and effective than the EEG signals in other frequency bands in studying human affective perception.

As a high-level function of the human brain, emotion is the external manifestation of people's psychological characteristics. The emotion has a great impact on people's personality and mental health. At the same time, emotion classification from electroencephalogram (EEG) signals have attracted much attention. To improve the precision of EEG-based emotion recognition, we proposed a fused feature extraction method to complete the classification of three emotions (neutral, happiness, and sadness). The standardized movie clips were selected to induce the corresponding emotion and the EEG response of 10 participants is collected by Emotiv EPOC. This paper systematically compared two kinds of EEG features (power spectrum and wavelet energy entropy) and their fusion for emotion classification. To reduce the dimension of fused features, we used principal component analysis (PCA) for dimensionality reduction and feature selection. The support vector machine (SVM) classifier and the relevance vector machines (RVM) classifier were utilized for emotion recognition respectively. From experimental results, we found that the fusion of two kinds of features outperformed a single feature for emotion classification by both the SVM classifier and the RVM classifier, and the averaged classification accuracy was 89.17% and 91.18%, respectively. [ABSTRACT FROM AUTHOR]

For the task of time-series data classification (TSC), some methods directly classify raw time-series (TS) data. However, certain sequence features are not evident in the time domain and the human brain can extract visual features based on visualization to classify data. Therefore, some researchers have converted TS data to image data and used image processing methods for TSC. While human perceptionconsists of a combination of human senses from different aspects, existing methods only use sequence features or visualization features. Therefore, this paper proposes a framework for TSC based on fusion features (TSC-FF) of sequence features extracted from raw TS and visualization features extracted from Area Graphs converted from TS. Deep learning methods have been proven to be useful tools for automatically learning features from data; therefore, we use long short-term memory with an attention mechanism (LSTM-A) to learn sequence features and a convolutional neural network with an attention mechanism (CNN-A) for visualization features, in order to imitate the human brain. In addition, we use the simplest visualization method of Area Graph for visualization features extraction, avoiding loss of information and additional computational cost. This article aims to prove that using deep neural networks to learn features from different aspects and fusing them can replace complex, artificially constructed features, as well as remove the bias due to manually designed features, in order to avoid the limitations of domain knowledge. Experiments on several open data sets show that the framework achieves promising results, compared with other methods. [ABSTRACT FROM AUTHOR]

Electroencephalogram (EEG) analysis has been widely used in the diagnosis of stroke diseases for its low cost and noninvasive characteristics. In order to classify the EEG signals of stroke patients with cerebral infarction and cerebral hemorrhage, this paper proposes a novel EEG stroke signal classification method. This method has two highlights. The first is that a multi-feature fusion method is given by combining wavelet packet energy, fuzzy entropy and hierarchical theory. The second highlight is that a suitable classification model based on ensemble classifier is constructed for perfectly classification stroke signals. Entropy is an accessible way to measure information and uncertainty of time series. Many entropy-based methods have been developed these years. By comparing with the performances of permutation entropy, sample entropy, approximate entropy in measuring the characteristic of stroke patient's EEG signals, it can be found that fuzzy entropy has best performance in characterization stroke EEG signal. By combining hierarchical theory, wavelet packet energy and fuzzy entropy, a multi-feature fusion method is proposed. The method first calculates wavelet packet energy of EEG stroke signal, then extracts hierarchical fuzzy entropy feature by combining hierarchical theory and fuzzy entropy. The experimental results show that, compared with the fuzzy entropy feature, the classification accuracy based on the fusion feature of wavelet packet energy and hierarchical fuzzy entropy is much higher than benchmark methods. It means that the proposed multi-feature fusion method based on stroke EEG signal is an efficient measure in classifying ischemic and hemorrhagic stroke. Support vector machine (SVM), decision tree and random forest are further used as the stroke signal classification models for classifying ischemic stroke and hemorrhagic stroke. Experimental results show that, based on the proposed multi-feature fusion method, the ensemble method of random forest can get the best classification performance in accuracy among three models. [ABSTRACT FROM AUTHOR]

• The main contributions of this paper can be summarized as follows. • A local-global feature-preserving fusion method is proposed, where the fused features capture both detail edge and abstract information of the image. • A sample clustering criterion based on fusion features is proposed to obtain the cluster centers. • A sample clustering domain adaptation method is proposed to learn the semantic correlations and fine-grained information for breast histopathology image classification. Deep learning has been widely applied to the diagnosis of breast cancer. Most deep learning models require a large number of labeled samples for training, but a large number of datasets with detailed labels is impractical. Therefore, exploring the methods to accurately classify unlabeled data remains a crucial area of research. In this paper, a deep sample clustering unsupervised domain adaptation method based on deep fusion feature is proposed for breast histopathology image classification. Deep multi-level fusion feature has a strong ability to capture image information, allowing for accurate characterization of the structural features of cells, thus improving the clustering performance. Next, based on the criterion of adaptive clustering of samples, the similarity between different clustering centers in the source and target domains is adjusted jointly. Finally, the classification results were achieved by the nearest neighbor relationship between the clustering centers and samples in the target domain. The proposed method was tested on three different breast cancer datasets. The prediction results of all patches were aggregated to obtain the classification accuracy of the histopathological image. The experimental results demonstrate that the proposed method achieves high classification accuracy and has the potential for application in clinical settings. [ABSTRACT FROM AUTHOR]

• Relationship between dynamic data and thermal imaging is analyzed. • Monitoring principle based on the fusion of dynamic and thermal imaging is proposed. • Dynamic features of revolute pair is extracted from calculated dynamic parameter. • Thermal image features of revolute pair is extracted by convolutional neural network. • Experiment platform is built to verify the effectiveness of fusion monitoring model. The revolute pair is an essential structure. The running of the revolute pair with clearance leads to energy loss due to collision. Partial energy loss is distributed in the form of heat energy. This provides the possibility for using thermal imaging to determine the clearance size of the revolute pair. A clearance monitoring method for revolute pairs fusing dynamic and thermal image features is proposed. The penetration depth and energy loss caused by collision are calculated as dynamic data, and dynamic features are extracted from the dynamic data by a multilayer perceptron. The convolutional block attention module embedded with a convolutional neural network is used to extract thermal imaging features. Clearance monitoring of revolute pairs is conducted based on fusion features of dynamic features and thermal image features. The experimental results on the test bench for revolute pair clearance show that the revolute pair clearance monitoring method based on fusion features can effectively monitor the revolute pair clearance. [ABSTRACT FROM AUTHOR]

This research proposes an improved particle filter tracking algorithm based on SGA (the adaptive genetic algorithm supervised by population convergence). In order to improve the robustness and efficiency of the particle filter tracker in various tracking scenarios, this study proposes an adaptive feature selection strategy based on Harris corner detection, SIFT features and colour features. In addition, the tracking frame scale of the traditional target tracking algorithm is fixed in the tracking process, which leads to many problems such as more invalid features and lower positioning accuracy. To solve these problems, this study proposes an adaptive tracking frame scale adjustment model based on the spatial position of particles. Furthermore, considering that the scale adaptive model cannot accurately reflect the target rotation deformation, this paper proposes an adaptive tracking frame scale and direction adjustment model based on the covariance descriptors to accurately track the rotation of the target and further reduce the invalid features of the rectangle frame. The extensive empirical evaluations on the benchmark dataset (OTB2015) and VOT2016 dataset demonstrate that the proposed method is very promising for the various challenging scenarios. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Zhengzhou University (Natural Science Edition) is the property of Journal of Zhengzhou University (Natural Science Edition) Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Lithium-ion battery state of health estimation is an important task for electric vehicles. However, the uncertainty and complexity of operating conditions pose significant challenges for state of health estimation. In this paper, a state of health estimation method with dynamic operating conditions generalization is developed. The equivalent circuit model parameters are kept unchanged, and the voltage is predicted based on the equivalent circuit model of initial aging point. The integral voltage error is extracted as an indicator of battery aging, and feature fusion is achieved by combining the feature of dynamic operating conditions. By cross-validation under dynamic operating conditions, the fused features are input into a back propagation neural network to achieve accurate estimation of state of health. At the same time, the voltage error reference baseline and pseudo-state of charge interval that affect the accuracy of the model estimation are discussed. After selecting the appropriate voltage error reference baseline and pseudo-state of charge interval, the mean absolute errors of the state of health estimation obtained on the dynamic operating conditions are all around 1%. The proposed state of health estimation method has low computational requirements, eliminates the dependence on the accuracy of state of charge , and can achieve generalization of multiple dynamic operating conditions, making it potentially applicable in actual vehicle applications. • The method achieves generalized SOH estimation under multiple dynamic conditions. • Proposed feature fusion combines battery operating and aging features. • SOH estimation based on dynamic discharge processes has been implemented. • The proposed SOH estimation method eliminates the dependency on SOC accuracy. [ABSTRACT FROM AUTHOR]

To solve the existing problems of low recognition rate and noise problem in radar signal recognition,the fusion feature extraction method of time-frequency image and the random forest classifier is applied to the identification of radar signals.The radar signal time-frequency image was firstly extracted the shape features and texture features to anstitute fusion characteristics,into and then input fusioncharacteristics radom forest classifier recognition of the signal classification was realized.The results of simulation experiments for eight kinds of common radar signals to recognition show that recognition accuracy of the method proposed can be achieved more than 90% in SNR -2 dB,so it also verify the effectiveness of the method.

For the task of time-series data classification (TSC), some methods directly classify raw time-series (TS) data. However, certain sequence features are not evident in the time domain and the human brain can extract visual features based on visualization to classify data. Therefore, some researchers have converted TS data to image data and used image processing methods for TSC. While human perceptionconsists of a combination of human senses from different aspects, existing methods only use sequence features or visualization features. Therefore, this paper proposes a framework for TSC based on fusion features (TSC-FF) of sequence features extracted from raw TS and visualization features extracted from Area Graphs converted from TS. Deep learning methods have been proven to be useful tools for automatically learning features from data; therefore, we use long short-term memory with an attention mechanism (LSTM-A) to learn sequence features and a convolutional neural network with an attention mechanism (CNN-A) for visualization features, in order to imitate the human brain. In addition, we use the simplest visualization method of Area Graph for visualization features extraction, avoiding loss of information and additional computational cost. This article aims to prove that using deep neural networks to learn features from different aspects and fusing them can replace complex, artificially constructed features, as well as remove the bias due to manually designed features, in order to avoid the limitations of domain knowledge. Experiments on several open data sets show that the framework achieves promising results, compared with other methods.

Water body extraction is a hot research topic in remote sensing applications. Using panchromatic optical remote sensing images to extract water bodies is a challenging task, because these images have one level of gray information, variable imaging conditions, and complex scene information. Refined water body extraction from optical panchromatic images often experiences serious under- or over- segmentation problems. In this paper, for producing refined water body extraction results from optical panchromatic images, we propose a fusion feature multi-scale pooling for Markov modeling method. Markov modeling includes two aspects: label field initialization and feature field establishment. These two aspects are jointly created by the fusion feature multi-scale pooling process, and this process is proposed to enhance the feature difference between water bodies and land cover. Then, the greedy algorithm in the iteration conditional method is used to extract refined water bodies according to the rebuilt Markov initial label and feature fields. Finally, to prove the effectiveness of proposed method, extensive experiments were used with collected 2.5m SPOT 5 and 1m GF-2 optical panchromatic images and evaluation indexes (precision, recall, overall accuracy, kappa coefficient and boundary detection ratios) to demonstrate that our proposed method can produce more refined water body extraction results than the state-of-the-art methods. The global and local refined indexes are improved by about 7% and 10%, respectively.