Chinese Clinical Named Entity Recognition Using Multi-Feature Fusion and Multi-Scale Local Context Enhancement

Chinese Clinical Named Entity Recognition(CNER)is a crucial step in extracting medical information and is of great significance in promoting medical informatization.However,CNER poses challenges due to the specificity of clinical terminology,the complexity of Chinese text semantics,and the uncertainty of Chinese entity boundaries.To address these issues,we propose an improved CNER model,which is based on multi-feature fusion and multi-scale local context enhancement.The model simultaneously fuses multi-feature representations of pinyin,radical,Part of Speech(POS),word boundary with BERT deep contextual representations to enhance the semantic representation of text for more effective entity recognition.Furthermore,to address the model’s limitation of focusing just on global features,we incorporate Convolutional Neural Networks(CNNs)with various kernel sizes to capture multi-scale local features of the text and enhance the model’s comprehension of the text.Finally,we integrate the obtained global and local features,and employ multi-head attention mechanism(MHA)extraction to enhance the model’s focus on characters associated with medical entities,hence boosting the model’s performance.We obtained 92.74%,and 87.80%F1 scores on the two CNER benchmark datasets,CCKS2017 and CCKS2019,respectively.The results demonstrate that our model outperforms the latest models in CNER,showcasing its outstanding overall performance.It can be seen that the CNER model proposed in this study has an important application value in constructing clinical medical knowledge graph and intelligent Q&A system.

Guided-YNet: Saliency Feature-Guided Interactive Feature Enhancement Lung Tumor Segmentation Network

Multimodal lung tumor medical images can provide anatomical and functional information for the same lesion.Such as Positron Emission Computed Tomography(PET),Computed Tomography(CT),and PET-CT.How to utilize the lesion anatomical and functional information effectively and improve the network segmentation performance are key questions.To solve the problem,the Saliency Feature-Guided Interactive Feature Enhancement Lung Tumor Segmentation Network(Guide-YNet)is proposed in this paper.Firstly,a double-encoder single-decoder U-Net is used as the backbone in this model,a single-coder single-decoder U-Net is used to generate the saliency guided feature using PET image and transmit it into the skip connection of the backbone,and the high sensitivity of PET images to tumors is used to guide the network to accurately locate lesions.Secondly,a Cross Scale Feature Enhancement Module(CSFEM)is designed to extract multi-scale fusion features after downsampling.Thirdly,a Cross-Layer Interactive Feature Enhancement Module(CIFEM)is designed in the encoder to enhance the spatial position information and semantic information.Finally,a Cross-Dimension Cross-Layer Feature Enhancement Module(CCFEM)is proposed in the decoder,which effectively extractsmultimodal image features through global attention and multi-dimension local attention.The proposed method is verified on the lung multimodal medical image datasets,and the results showthat theMean Intersection overUnion(MIoU),Accuracy(Acc),Dice Similarity Coefficient(Dice),Volumetric overlap error(Voe),Relative volume difference(Rvd)of the proposed method on lung lesion segmentation are 87.27%,93.08%,97.77%,95.92%,89.28%,and 88.68%,respectively.It is of great significance for computer-aided diagnosis.

A Situational Awareness Method for Initial Insulation Fault of Distribution Network Based on Multi-Feature Index Comprehensive Evaluation

Most ground faults in distribution network are caused by insulation deterioration of power equipment.It is difficult to find the insulation deterioration of the distribution network in time,and the development trend of the initial insulation fault is unknown,which brings difficulties to the distribution inspection.In order to solve the above problems,a situational awareness method of the initial insulation fault of the distribution network based on a multi-feature index comprehensive evaluation is proposed.Firstly,the insulation situation evaluation index is selected by analyzing the insulation fault mechanism of the distribution network,and the relational database of the distribution network is designed based on the data and numerical characteristics of the existing distribution management system.Secondly,considering all kinds of fault factors of the distribution network and the influence of the power supply region,the evaluation method of the initial insulation fault situation of the distribution network is proposed,and the development situation of the distribution network insulation fault is classified according to the evaluation method.Then,principal component analysis was used to reduce the dimension of the training samples and test samples of the distribution network data,and the support vector machine(SVM)was trained.The optimal parameter combination of the SVM model was found by the grid search method,and a multi-class SVM model based on 1-v-1 method was constructed.Finally,the trained multi-class SVM was used to predict 6 kinds of situation level prediction samples.The results of simulation examples show that the average prediction accuracy of 6 situation levels is above 95%,and the perception accuracy of 4 situation levels is above 96%.In addition,the insulation maintenance decision scheme under different situation levels is able to be given when no fault occurs or the insulation fault is in the early stage,which can meet the needs of power distribution and inspection for accurately sensing the insulation fault situation.The correctness and effectiveness of this method are verified.

A Review of Research on Handwritten Chinese Character Recognition with Multi-Feature Fusion

This paper analyzes the progress of handwritten Chinese character recognition technology,from two perspectives:traditional recognition methods and deep learning-based recognition methods.Firstly,the complexity of Chinese character recognition is pointed out,including its numerous categories,complex structure,and the problem of similar characters,especially the variability of handwritten Chinese characters.Subsequently,recognition methods based on feature optimization,model optimization,and fusion techniques are highlighted.The fusion studies between feature optimization and model improvement are further explored,and these studies further enhance the recognition effect through complementary advantages.Finally,the article summarizes the current challenges of Chinese character recognition technology,including accuracy improvement,model complexity,and real-time problems,and looks forward to future research directions.

A Multi-Feature Learning Model with Enhanced Local Attention for Vehicle Re-Identification

Vehicle re-identification(ReID)aims to retrieve the target vehicle in an extensive image gallery through its appearances from various views in the cross-camera scenario.It has gradually become a core technology of intelligent transportation system.Most existing vehicle re-identification models adopt the joint learning of global and local features.However,they directly use the extracted global features,resulting in insufficient feature expression.Moreover,local features are primarily obtained through advanced annotation and complex attention mechanisms,which require additional costs.To solve this issue,a multi-feature learning model with enhanced local attention for vehicle re-identification(MFELA)is proposed in this paper.The model consists of global and local branches.The global branch utilizes both middle and highlevel semantic features of ResNet50 to enhance the global representation capability.In addition,multi-scale pooling operations are used to obtain multiscale information.While the local branch utilizes the proposed Region Batch Dropblock(RBD),which encourages the model to learn discriminative features for different local regions and simultaneously drops corresponding same areas randomly in a batch during training to enhance the attention to local regions.Then features from both branches are combined to provide a more comprehensive and distinctive feature representation.Extensive experiments on VeRi-776 and VehicleID datasets prove that our method has excellent performance.

Classification and Extraction of Urban Land-Use Information from High-Resolution Image Based on Object Multi-features

Urban land provides a suitable location for various economic activities which affect the development of surrounding areas. With rapid industrialization and urbanization, the contradictions in land-use become more noticeable. Urban administrators and decision-makers seek modern methods and technology to provide information support for urban growth. Recently, with the fast development of high-resolution sensor technology, more relevant data can be obtained, which is an advantage in studying the sustainable development of urban land-use. However, these data are only information sources and are a mixture of ＂information＂ and ＂noise＂. Processing, analysis and information extraction from remote sensing data is necessary to provide useful information. This paper extracts urban land-use information from a high-resolution image by using the multi-feature information of the image objects, and adopts an object-oriented image analysis approach and multi-scale image segmentation technology. A classification and extraction model is set up based on the multi-features of the image objects, in order to contribute to information for reasonable planning and effective management. This new image analysis approach offers a satisfactory solution for extracting information quickly and efficiently.

Saliency detection based on superpixels clustering and stereo disparity

Reliable saliency detection can be used to quickly and effectively locate objects in images. In this paper, a novel algorithm for saliency detection based on superpixels clustering and stereo disparity （SDC） is proposed. Firstly, we use an improved superpixels clustering method to decompose the given image. Then, the disparity of each superpixel is computed by a modified stereo correspondence algorithm. Finally, a new measure which combines stereo disparity with color contrast and spatial coherence is defined to evaluate the saliency of each superpixel. From the experiments we can see that regions with high disparity can get higher saliency value, and the saliency maps have the same resolution with the source images, objects in the map have clear boundaries. Due to the use of superpixel and stereo disparity information, the proposed method is computationally efficient and outperforms some state-of-the-art color- based saliency detection methods.

Saliency detection and edge feature matching approach for crater extraction

Craters are salient terrain features on planetary surfaces, and provide useful information about the relative dating of geological unit of planets. In addition, they are ideal landmarks for spacecraft navigation. Due to low contrast and uneven illumination, automatic extraction of craters remains a challenging task. This paper presents a saliency detection method for crater edges and a feature matching algorithm based on edges informa- tion. The craters are extracted through saliency edges detection, edge extraction and selection, feature matching of the same crater edges and robust ellipse fitting. In the edges matching algorithm, a crater feature model is proposed by analyzing the relationship between highlight region edges and shadow region ones. Then, crater edges are paired through the effective matching algorithm. Experiments of real planetary images show that the proposed approach is robust to different lights and topographies, and the detection rate is larger than 90%.

Hierarchical Visual Attention Model for Saliency Detection Inspired by Avian Visual Pathways

Visual attention is a mechanism that enables the visual system to detect potentially important objects in complex environment. Most computational visual attention models are designed with inspirations from mammalian visual systems.However, electrophysiological and behavioral evidences indicate that avian species are animals with high visual capability that can process complex information accurately in real time. Therefore,the visual system of the avian species, especially the nuclei related to the visual attention mechanism, are investigated in this paper. Afterwards, a hierarchical visual attention model is proposed for saliency detection. The optic tectum neuron responses are computed and the self-information is used to compute primary saliency maps in the first hierarchy. The "winner-takeall" network in the tecto-isthmal projection is simulated and final saliency maps are estimated with the regularized random walks ranking in the second hierarchy. Comparison results verify that the proposed model, which can define the focus of attention accurately, outperforms several state-of-the-art models.This study provides insights into the relationship between the visual attention mechanism and the avian visual pathways. The computational visual attention model may reveal the underlying neural mechanism of the nuclei for biological visual attention.

Identification Method of Gas-Liquid Two-phase Flow Regime Based on Image Multi-feature Fusion and Support Vector Machine

The knowledge of flow regime is very important for quantifying the pressure drop, the stability and safety of two-phase flow systems. Based on image multi-feature fusion and support vector machine, a new method to identify flow regime in two-phase flow was presented. Firstly, gas-liquid two-phase flow images including bub- bly flow, plug flow, slug flow, stratified flow, wavy flow, annular flow and mist flow were captured by digital high speed video systems in the horizontal tube. The image moment invariants and gray level co-occurrence matrix texture features were extracted using image processing techniques. To improve the performance of a multiple classifier system, the rough sets theory was used for reducing the inessential factors. Furthermore, the support vector machine was trained by using these eigenvectors to reduce the dimension as flow regime samples, and the flow regime intelligent identification was realized. The test results showed that image features which were reduced with the rough sets theory could excellently reflect the difference between seven typical flow regimes, and successful training the support vector machine could quickly and accurately identify seven typical flow regimes of gas-liquid two-phase flow in the horizontal tube. Image multi-feature fusion method provided a new way to identify the gas-liquid two-phase flow, and achieved higher identification ability than that of single characteristic. The overall identification accuracy was 100%, and an estimate of the image processing time was 8 ms for online flow regime identification.

A Multi-Feature Weighting Based K-Means Algorithm for MOOC Learner Classification

Massive open online courses(MOOC)have recently gained worldwide attention in the field of education.The manner of MOOC provides a new option for learning various kinds of knowledge.A mass of data miming algorithms have been proposed to analyze the learner’s characteristics and classify the learners into different groups.However,most current algorithms mainly focus on the final grade of the learners,which may result in an improper classification.To overcome the shortages of the existing algorithms,a novel multi-feature weighting based K-means(MFWK-means)algorithm is proposed in this paper.Correlations between the widely used feature grade and other features are first investigated,and then the learners are classified based on their grades and weighted features with the proposed MFWK-means algorithm.Experimental results with the Canvas Network Person-Course(CNPC)dataset demonstrate the effectiveness of our method.Moreover,a comparison between the new MFWK-means and the traditional K-means clustering algorithm is implemented to show the superiority of the proposed method.

Method for pests detecting in stored grain based on spectral residual saliency edge detection

Pests detecting is an important research subject in grain storage field.In the past decades,many edge detection methods have been applied to the edge detection of stored grain pests.Although some of them can realize the stored grain pests detecting,precision and robustness are not good enough.Spectral residual(SR)saliency edge detection defines the logarithmic spectrumof image as novelty part of the image information.The remaining spectrumis converted to the airspace to obtain edge detection results.SR algorithm is completely based on frequency domain processing.It not only can effectively simplify the target detection algorithm,but also can improve the effectiveness of target recognition.The experimental results show that the edge results of stored grain pests detected by SR method are effective and stable.

Vehicle Detection Based on Visual Saliency and Deep Sparse Convolution Hierarchical Model

Traditional vehicle detection algorithms use traverse search based vehicle candidate generation and hand crafted based classifier training for vehicle candidate verification.These types of methods generally have high processing times and low vehicle detection performance.To address this issue,a visual saliency and deep sparse convolution hierarchical model based vehicle detection algorithm is proposed.A visual saliency calculation is firstly used to generate a small vehicle candidate area.The vehicle candidate sub images are then loaded into a sparse deep convolution hierarchical model with an SVM-based classifier to perform the final detection.The experimental results demonstrate that the proposed method is with 94.81% correct rate and 0.78% false detection rate on the existing datasets and the real road pictures captured by our group,which outperforms the existing state-of-the-art algorithms.More importantly,high discriminative multi-scale features are generated by deep sparse convolution network which has broad application prospects in target recognition in the field of intelligent vehicle.

Saliency detection of infrared image based on region covariance and global feature

In order to better represent infrared target features under different environments, a saliency detection method based on region covariance and global feature is proposed. Firstly, the region covariance features on different scale spaces and different image regions are extracted and transformed into sigma features,then combined with central position feature, the local salient map is generated. Next, a global salient map is generated by gray contrast and density estimation. Finally, the saliency detection result of infrared images is obtained by fusing the local and global salient maps. The experimental results show that the salient map of the proposed method has complete target features and obvious edges,and the proposed method is better than the state of art method both qualitatively and quantitatively.

Real-time object segmentation based on convolutional neural network with saliency optimization for picking

This paper concerns the problem of object segmentation in real-time for picking system. A region proposal method inspired by human glance based on the convolutional neural network is proposed to select promising regions, allowing more processing is reserved only for these regions. The speed of object segmentation is significantly improved by the region proposal method.By the combination of the region proposal method based on the convolutional neural network and superpixel method, the category and location information can be used to segment objects and image redundancy is significantly reduced. The processing time is reduced considerably by this to achieve the real time. Experiments show that the proposed method can segment the interested target object in real time on an ordinary laptop.

Rate Control Algorithm of Wireless Video Based on Visual Saliency Map Model

In order to further improve the efficiency of video compression, we introduce a perceptual characteristics of Human Visual System (HVS) to video coding, and propose a novel video coding rate control algorithm based on human visual saliency model in H.264/AVC. Firstly, we modifie Itti's saliency model. Secondly, target bits of each frame are allocated through the correlation of saliency region between the current and previous frame, and the complexity of each MB is modified through the saliency value and its Mean Absolute Difference (MAD) value. Lastly, the algorithm was implemented in JVT JM12.2. Simulation results show that, comparing with traditional rate control algorithm, the proposed one can reduce the coding bit rate and improve the reconstructed video subjective quality, especially for visual saliency region. It is very suitable for wireless video transmission.

The detection method of low-rate DoS attack based on multi-feature fusion

As a new type of Denial of Service(DoS)attacks,the Low-rate Denial of Service(LDoS)attacks make the traditional method of detecting Distributed Denial of Service Attack(DDoS)attacks useless due to the characteristics of a low average rate and concealment.With features extracted from the network traffic,a new detection approach based on multi-feature fusion is proposed to solve the problem in this paper.An attack feature set containing the Acknowledge character(ACK)sequence number,the packet size,and the queue length is used to classify normal and LDoS attack traffics.Each feature is digitalized and preprocessed to fit the input of the K-Nearest Neighbor(KNN)classifier separately,and to obtain the decision contour matrix.Then a posteriori probability in the matrix is fused,and the fusion decision index D is used as the basis of detecting the LDoS attacks.Experiments proved that the detection rate of the multi-feature fusion algorithm is higher than those of the single-based detection method and other algorithms.

Smoke root detection from video sequences based on multi-feature fusion

Smoke detection is the most commonly used method in early warning of fire and is widely used in forest detection.Most existing smoke detection methods contain empty spaces and obstacles which interfere with detection and extract false smoke roots.This study developed a new smoke roots search algorithm based on a multi-feature fusion dynamic extraction strategy.This determines smoke origin candidate points and region based on a multi-frame discrete confidence level.The results show that the new method provides a more complete smoke contour with no background interference,compared to the results using existing methods.Unlike video-based methods that rely on continuous frames,an adaptive threshold method was developed to build the judgment image set composed of non-consecutive frames.The smoke roots origin search algorithm increased the detection rate and significantly reduced false detection rate compared to existing methods.

No-reference blur assessment method based on gradient and saliency

To evaluate the quality of blurred images effectively,this study proposes a no-reference blur assessment method based on gradient distortion measurement and salient region maps.First,a Gaussian low-pass filter is used to construct a reference image by blurring a given image.Gradient similarity is included to obtain the gradient distortion measurement map,which can finely reflect the smallest possible changes in textures and details.Second,a saliency model is utilized to calculate image saliency.Specifically,an adaptive method is used to calculate the specific salient threshold of the blurred image,and the blurred image is binarized to yield the salient region map.Block-wise visual saliency serves as the weight to obtain the final image quality.Experimental results based on the image and video engineering database,categorial image quality database,and camera image database demonstrate that the proposed method correlates well with human judgment.Its computational complexity is also relatively low.

Place recognition based on saliency for topological localization

Based on salient visual regions for mobile robot navigation in unknown environments, a new place recognition system was presented. The system uses monocular camera to acquire omni-directional images of the environment where the robot locates. Salient local regions are detected from these images using center-surround difference method, which computes opponencies of color and texture among multi-scale image spaces. And then they are organized using hidden Markov model (HMM) to form the vertex of topological map. So localization, that is place recognition in our system, can be converted to evaluation of HMM. Experimental results show that the saliency detection is immune to the changes of scale, 2D rotation and viewpoint etc. The created topological map has smaller size and a higher ratio of recognition is obtained.