首页 | 本学科首页   官方微博 | 高级检索  
相似文献
 共查询到20条相似文献,搜索用时 31 毫秒
1.
Liu  Wei  Li  Ding  Su  Hongqi 《Cognitive computation》2021,13(5):1128-1135

Semantic segmentation is a crucial issue in the field of computer vision, and it aims to assign each pixel in an image to a semantic object category. Modern cognitive research has presented that the biological system contains hidden features and explicit features, although they both contain useful information, the hidden features need further processing to make them explicit or clear. Inspired by this theory, a semantic segmentation framework named hierarchical attention network assembling is proposed. Multiple auxilary information of different levels corresponding to the two kinds of features of the cognitive system are exploited. Then we further process the hidden information to make them explicit for the semantic segmentation. While in the traditional methods, limited assistance of the auxiliary tasks with only hidden information is provided. In this study, the attention mechanism is utilized and two auxiliary tasks are introduced as attention modules to give explicit guidance to the semantic segmentation task. Two hierarchical sub-networks—an object-level bounding box attention network and an edge-level boundary attention network together serve as explicit auxiliary tasks, of which the first network driven by the object detection aims to aggrandize the consistency constraint of pixels belonging to the same object, and the second one driven by the boundary detection aims to improve the segmentation accuracy within the boundary regions. With the proposed method, the performance achieves 78.3% mean IOU on PASCAL VOC 2012. The explicit guidance of the two auxiliary tasks can well assist the semantic segmentation task.

  相似文献   

2.
OBJECTIVE: Automatic seizure detection has attracted attention as a method to obtain valuable information concerning the duration, timing, and frequency of seizures. Methods currently used to detect EEG seizures in adults show high false detection rates in neonates because they lack information about specific age-dependent features of normal and pathological EEG and artifacts. This paper describes a novel multistage knowledge-based seizure detection system for newborn infants to identify and classify normal and pathological newborn EEGs as well as seizures with a reduced false detection rate. METHODS: We developed the system in a way to make comprehensive use of spatial and temporal contextual information obtained from multichannel EEGs. The system development consists of six major stages: (i) EEG data collection and bandpass filtering; (ii) automatic artifact detection; (iii) feature extraction from segments of non-seizure and seizure activities; (iv) feature selection via the relevance and redundancy analysis; (v) EEG classification and pattern recognition using a trained multilayer back-propagation neural network; and (v) knowledge-based decision-making to examine each of possible EEG patterns from a multi-channel perspective. The system was developed and tested with the EEG recordings of 10 newborns aged between 39 and 42 weeks. RESULTS: The overall sensitivity, selectivity, and average detection rate of the system were 74%, 70.1%, and 79.7%, respectively. The average false detection of 1.55/h was also achieved by the system with a feature reduction up to 80%. CONCLUSIONS: The expert rule-based decision-making subsystem accompanying the classifier helped to reduce the false detection rate, reject a wide variety of artifacts, and discriminate various patterns of EEG. SIGNIFICANCE: This paper may serve as a guide for the selection of discriminative features to improve the accuracy of conventional seizure detection systems for routine clinical EEG interpretation and brain activity monitoring in newborns especially those hospitalized in the neonatal intensive care units.  相似文献   

3.

With the widespread dissemination of user-generated content on different web sites, social networks, and online consumer systems such as Amazon, the quantity of opinionated information available on the Internet has been increased. Sentiment analysis of user-generated content is one of the main cognitive computing branches; hence, it has attracted the attention of many scholars in recent years. One of the main tasks of the sentiment analysis is to detect polarity within a text. The existing polarity detection methods mainly focus on keywords and their naïve frequency counts; however, they less regard the meanings and implicit dimensions of the natural concepts. Although background knowledge plays a critical role in determining the polarity of concepts, it has been disregarded in polarity detection methods. This study presents a context-based model to solve ambiguous polarity concepts using commonsense knowledge. First, a model is presented to generate a source of ambiguous sentiment concepts based on SenticNet by computing the probability distribution. Then, the model uses a bag-of-concepts approach to remove ambiguities and semantic augmentation with the ConceptNet handling to overcome lost knowledge. ConceptNet is a large-scale semantic network with a large number of commonsense concepts. In this paper, the point mutual information (PMI) measure is used to select the contextual concepts having strong relationships with ambiguous concepts. The polarity of the ambiguous concepts is precisely detected using positive/negative contextual concepts and the relationship of the concepts in the semantic knowledge base. The text representation scheme is semantically enriched using Numberbatch, which is a word embedding model based on the concepts from the ConceptNet semantic network. In this regard, the cosine similarity metric is used to measure similarity and select a concept from the ConceptNet network for semantic augmentation. Pre-trained concepts vectors facilitate the more effective computation of semantic similarity among the concerned concepts. The proposed model is evaluated by applying a corpus of product reviews, called Semeval. The experimental results revealed an accuracy rate of 82.07%, representing the effectiveness of the proposed model.

  相似文献   

4.
Multiple elastic modules for visual pattern recognition   总被引:4,自引:0,他引:4  
Soheil Shams   《Neural networks》1995,8(9):1439-1453
Fast synaptic plasticity, used to associate topologically ordered features in an input image to those of previously learned objects, has been previously proposed as a possible model for object recognition (von der Malsburg & Bienenstock, 1987, Europhysics Letters, 3(11), 1243–1249). In this paper, it is argued that in addition to rapid link dynamics, fast receptive field size dynamics are necessary to automatically escape from poor local matches and also allow for simultaneous recognition of multiple objects. Furthermore, a feature locking mechanism with a properly designed hysteresis property is needed to handle complex, cluttered, and dynamic scenes. The multiple elastic modules (MEM) model, described in this paper, utilizes newly developed dynamics that locate and recognize a previously learned object based on expected spatial arrangement of local features. The MEM model can be viewed as using a deformable template of an object to search the input scene. Unlike many of the current artificial neural network models, the proposed MEM model attempts to capture many of the functions available in the biological visual system by providing mechanisms for: multi-model feature integration, generation and maintenance of focus of attention, multiresolution hierarchical searching, and top-down expectation driven processing coupled with bottom-up feature activation processing. In addition, the MEM dynamics, unlike similar template matching approaches (Konen et al., 1994, Neural Networks, 7(6/7), 1019–1030; Yuille et al., 1992, International Journal of Computer Vision, 8(2), 99–111), does not converge to false objects when there are no sufficiently familiar objects in the scene. The performance of the MEM model in detection and recognition of objects through a number of computer simulations is demonstrated.  相似文献   

5.
In this paper, we introduce a theoretical basis for a Hadoop-based neural network for parallel and distributed feature selection in Big Data sets. It is underpinned by an associative memory (binary) neural network which is highly amenable to parallel and distributed processing and fits with the Hadoop paradigm. There are many feature selectors described in the literature which all have various strengths and weaknesses. We present the implementation details of five feature selection algorithms constructed using our artificial neural network framework embedded in Hadoop YARN. Hadoop allows parallel and distributed processing. Each feature selector can be divided into subtasks and the subtasks can then be processed in parallel. Multiple feature selectors can also be processed simultaneously (in parallel) allowing multiple feature selectors to be compared. We identify commonalities among the five features selectors. All can be processed in the framework using a single representation and the overall processing can also be greatly reduced by only processing the common aspects of the feature selectors once and propagating these aspects across all five feature selectors as necessary. This allows the best feature selector and the actual features to select to be identified for large and high dimensional data sets through exploiting the efficiency and flexibility of embedding the binary associative-memory neural network in Hadoop.  相似文献   

6.
Humans can efficiently perceive arbitrary visual objects based on an incremental learning mechanism with selective attention. This paper proposes a new task specific top-down attention model to locate a target object based on its form and color representation along with a bottom-up saliency based on relativity of primitive visual features and some memory modules. In the proposed model top-down bias signals corresponding to the target form and color features are generated, which draw the preferential attention to the desired object by the proposed selective attention model in concomitance with the bottom-up saliency process. The object form and color representation and memory modules have an incremental learning mechanism together with a proper object feature representation scheme. The proposed model includes a Growing Fuzzy Topology Adaptive Resonance Theory (GFTART) network which plays two important roles in object color and form biased attention; one is to incrementally learn and memorize color and form features of various objects, and the other is to generate a top-down bias signal to localize a target object by focusing on the candidate local areas. Moreover, the GFTART network can be utilized for knowledge inference which enables the perception of new unknown objects on the basis of the object form and color features stored in the memory during training. Experimental results show that the proposed model is successful in focusing on the specified target objects, in addition to the incremental representation and memorization of various objects in natural scenes. In addition, the proposed model properly infers new unknown objects based on the form and color features of previously trained objects.  相似文献   

7.
H Kawaguchi  J Fukuda 《Brain research》1992,594(2):284-289
A new co-culture method for observation and identification of synapse formation utilizing dissociated retinal and tectal neurons from 7-day-old chick embryos was developed using a glass apparatus which we named 'Dual Compartment Cell-Allocation Apparatus.' This apparatus enabled us to culture these two types of cells by forming two parallel lanes, each with a dimension of 200 microns by 15 mm and with an interval of 200 microns separating the two lanes, on a collagen-coated cover slip. Infiltration and/or migration of retinal cells into the tectal cell lane was minimal with only 0.15% identified and confirmed with the fluorescence-dye labeling method. Growth of neurites connecting the two lanes was observed within 48 h of culture in a serum-free medium. Double-immunostaining of the culture preparations with anti-neurofilament and anti-synaptophysin antibodies revealed the presence of synaptophysin-hot spots on neurofilament-positive processes connecting the retinal neurons with the tectal neurons, thus confirming the formation of synapses between the neurons of the retinal lane and the neurons of the tectal lane. The dual compartment cell-allocation apparatus has proven itself to be advantageous and useful for studying the formation of synapses between two types of neurons from different origin.  相似文献   

8.
OBJECTIVE: Automatic seizure detection obtains valuable information concerning duration and timing of seizures. Commonly used methods for EEG seizure detection in adults are inadequate for the same task in neonates because they lack the specific age-dependant characteristics of normal and pathological EEG. This paper presents an automatic seizure detection system for newborn with focus on feature selection via relevance and redundancy analysis. METHODS: Two linear correlation-based feature selection methods and the ReliefF method were applied to parameterized EEG data acquired from six neonates aged between 39 and 42 weeks. To evaluate the effectiveness of these methods, features extracted from seizure and non-seizure segments were ranked by these methods. The optimized ranked feature subsets were fed into a backpropagation neural network for classifying. Its performance was used as indicator for the feature selection effectiveness. RESULTS: Results showed an average seizure detection rate of 91%, an average non-seizure detection rate of 95%, an average false rejection rate of 95% and an overall average detection rate of 93% with a false seizure detection rate of 1.17/h. CONCLUSIONS: This good performance in detecting newborn ictal activities has been achieved based on an optimized subset of 30 features determined by the ReliefF-based detector, which corresponds to a reduction of the number of features of up to 75%. SIGNIFICANCE: The presented approach takes into account specific characteristics of normal and pathological EEG. Thus, it can improve the accuracy of conventional seizure detection systems in newborn.  相似文献   

9.
An approach for estimating the number of pedestrians is presented in this paper. The proposed counting framework combines two main pedestrian counting strategies—direct approach and indirect approach—by the use of mixed features and extreme learning machine (ELM). ELM is used to map mixed features to the number of pedestrians. Mixed features consist of holistic low-level features and rectangular local binary pattern (rLBP) features, and rLBP features are new features designed to describe the statistical and structural information of explicit pedestrian detection rectangles. Through mixed features, the information from both direct approach (rLBP features) and indirect approach (low-level features) is used in our algorithm, so we can take full advantage of two counting strategies. The detection rectangles are obtained by the use of the pedestrian detector described in paper “the fastest pedestrian detector in the west" (FPDW) by Dollár et al. Based on integral channel features and soft cascade classifier, FPDW is able to provide outstanding detection results at rapid speed. Experimental results on PETS 2009 datasets show that the proposed counting framework can improve counting accuracy significantly by the combination of two counting strategies. rLBP features are effective to describe the useful information of detection rectangles for regression models, and mixed features are more effective than either of both.  相似文献   

10.
Feedback connections are a prominent feature of cortical anatomy and are likely to have a significant functional role in neural information processing. We present a neural network model of cortical feedback that successfully simulates neurophysiological data associated with attention. In this domain, our model can be considered a more detailed, and biologically plausible, implementation of the biased competition model of attention. However, our model is more general as it can also explain a variety of other top-down processes in vision, such as figure/ground segmentation and contextual cueing. This model thus suggests that a common mechanism, involving cortical feedback pathways, is responsible for a range of phenomena and provides a unified account of currently disparate areas of research.  相似文献   

11.
Tian  Lulu  Wang  Zidong  Liu  Weibo  Cheng  Yuhua  Alsaadi  Fuad E.  Liu  Xiaohui 《Cognitive computation》2021,13(5):1263-1273

As a popular nondestructive testing (NDT) technique, thermal imaging test demonstrates competitive performance in crack detection, especially for detecting subsurface cracks. In thermal imaging test, the temperature of the crack area is higher than that of the non-crack area during the NDT process. By extracting the features of the thermal image sequences, the temperature curve of each spatial point is employed for crack detection. Nevertheless, the quality of thermal images is influenced by the noises due to the complex thermal environment in NDT. In this paper, a modified generative adversarial network (GAN) is employed to improve the image segmentation performance. To improve the feature extraction ability and alleviate the influence of noises, a penalty term is put forward in the loss function of the conventional GAN. A data preprocessing method is developed where the principle component analysis algorithm is adopted for feature extraction. The data argumentation technique is utilized to guarantee the quantity of the training samples. To validate its effectiveness in thermal imaging NDT, the modified GAN is applied to detect the cracks on the eddy current pulsed thermography NDT dataset.

  相似文献   

12.

In today’s digital era, the use of online social media networks, such as Google, YouTube, Facebook, and Twitter, permits people to generate a massive amount of textual content. The textual content that is produced by people reveals essential information regarding their personality, with psychopathy being among these distinct personality types. This work was aimed at classifying input texts according to the traits of psychopaths and non-psychopaths. Several studies based on traditional techniques, such as the SRPIII technique, using small-sized datasets have been conducted for the detection of psychopathic behavior. However, the purpose of the current study was to build an effective computational model for the detection of psychopaths in the domain of text analytics and computational intelligence. This study was aimed at developing a technique based on a convolutional neural network + long short-term memory (CNN-LSTM) model by using a deep learning approach to detect psychopaths. A convolutional neural network was used to extract local information from a text, while the long short-term memory was used to extract the contextual dependencies of the text. By combining the advantages of convolutional neural network and long short-term memory, the proposed hybrid CNN-LSTM was able to yield a good classification accuracy of 91.67%. Additionally, a large-sized benchmark dataset was acquired for the effective classification of the given input text into psychopath vs. non-psychopath classes, thereby enabling persons with such personality traits to be identified.

  相似文献   

13.
14.
Background: The relationship between object concept domains (living vs. nonliving) and their underlying feature structures is a frequent area of investigation regarding semantic processing in healthy individuals and some individuals with neuropsychological impairment resulting from herpes simplex encephalitis, semantic dementia, and Alzheimer’s disease. However, this relationship has been less well investigated in persons with stroke-aphasia (PWA), even though many treatments for anomia following stroke are predicated on the use of semantic feature cues.

Aims: As part of a larger investigation into the influence of semantic feature processing on naming for PWA, this study examined the ability of PWA to confirm the relations between object concepts and associated semantic features.

Methods & Procedures: Fifteen native English-speaking, right-handed individuals with post-stroke-aphasia responded yes or no via button press to feature verification questions designed to probe the relationships between concept domain and feature type and distinctiveness.

Outcomes & Results: PWA were more accurate and quicker to confirm concept–feature relationships when features contained function/action, rather than visual–perceptual information about concepts and when features were distinctive to concepts rather than shared. The truthfulness (i.e., veracity) of concept–feature pairings was demonstrated to differentially affect living versus nonliving concepts. Within domain, only nonliving concepts were verified more accurately and more quickly when pairings were true (rather than false). Between domains, true nonliving concept–feature pairings were more accurately and more quickly verified than true living concept–feature pairings. Also with respect to veracity, correlations were observed between aphasia severity and accuracy and speed of response to false concept–feature pairings.

Conclusions: Findings have implications for the way in which semantic processing is probed with PWA, as well as providing preliminary information regarding responsivity of PWA to differing types of semantic information for living versus nonliving concepts. The fact that PWA demonstrated disproportionate difficulty responding to certain types of semantic information also suggests preliminary implications for the utility of different types of semantic cues in semantically based treatments for word retrieval impairment.  相似文献   

15.
The pathophysiology of major depressive disorder (MDD) has been explored to be highly associated with the dysfunctional integration of brain networks. It is therefore imperative to explore neuroimaging biomarkers to aid diagnosis and treatment. In this study, we developed a spatiotemporal graph convolutional network (STGCN) framework to learn discriminative features from functional connectivity for automatic diagnosis and treatment response prediction of MDD. Briefly, dynamic functional networks were first obtained from the resting‐state fMRI with the sliding temporal window method. Secondly, a novel STGCN approach was proposed by introducing the modules of spatial graph attention convolution (SGAC) and temporal fusion. A novel SGAC was proposed to improve the feature learning ability and special anatomy prior guided pooling was developed to enable the feature dimension reduction. A temporal fusion module was proposed to capture the dynamic features of functional connectivity between adjacent sliding windows. Finally, the STGCN proposed approach was utilized to the tasks of diagnosis and antidepressant treatment response prediction for MDD. Performances of the framework were comprehensively examined with large cohorts of clinical data, which demonstrated its effectiveness in classifying MDD patients and predicting the treatment response. The sound performance suggests the potential of the STGCN for the clinical use in diagnosis and treatment prediction.  相似文献   

16.
Hao  Kangli  Feng  Guorui  Ren  Yanli  Zhang  Xinpeng 《Cognitive computation》2020,12(6):1205-1216

In recent years, iris recognition has been widely used in various fields. As the first step of iris recognition, segmentation accuracy is of great significance to the final recognition. However, iris images exhibit a variety of noise in the real world, which leads to lower segmentation accuracy than the ideal case. To address this problem, this paper proposes an iris segmentation method using feature channel optimization for noisy images. The method for non-ideal environments with noise is more suitable for practical applications. We add dense blocks and dilated convolutional layers to the encoder so that the information gradient flow obtained by different layers can be reused, and the receptive field can be expanded. In the decoder, based on Jensen-Shannon (JS) divergence, we first recalculate the weight of the feature channels obtained from each layer, which enhances the useful information and suppresses the interference information in the noisy environments to boost the segmentation accuracy. The proposed architecture is validated in the CASIA v4.0 interval (CASIA) and IIT Delhi v1.0 datasets (IITD). For CASIA, the mean error rate is 0.78%, and the F-measure value is 98.21%. For IITD, the mean error rate is 0.97%, and the F-measure value is 97.87%. Experimental results show that the proposed method outperforms other state-of-art methods under noisy environments, such as Gaussian blur, Gaussian noise, and salt and pepper noise.

  相似文献   

17.
Recently released large-scale neuron morphological data has greatly facilitated the research in neuroinformatics. However, the sheer volume and complexity of these data pose significant challenges for efficient and accurate neuron exploration. In this paper, we propose an effective retrieval framework to address these problems, based on frontier techniques of deep learning and binary coding. For the first time, we develop a deep learning based feature representation method for the neuron morphological data, where the 3D neurons are first projected into binary images and then learned features using an unsupervised deep neural network, i.e., stacked convolutional autoencoders (SCAEs). The deep features are subsequently fused with the hand-crafted features for more accurate representation. Considering the exhaustive search is usually very time-consuming in large-scale databases, we employ a novel binary coding method to compress feature vectors into short binary codes. Our framework is validated on a public data set including 58,000 neurons, showing promising retrieval precision and efficiency compared with state-of-the-art methods. In addition, we develop a novel neuron visualization program based on the techniques of augmented reality (AR), which can help users take a deep exploration of neuron morphologies in an interactive and immersive manner.  相似文献   

18.
In most actual autonomous guided vehicles (AGV), path finding and navigational control systems are usually implemented using images captured by cameras mounted on the vehicles. This paper presents and discusses a lane boundary detection technique that is necessary for the task of autonomous driving. In this paper, a new method called vector fuzzy connectedness (VFC) is presented to detect and estimate road lane boundaries. First, a preprocessed technique is used to obtain a skeleton image. Based on the result, the curvatures of the left and right lane boundaries are estimated, and the control points are found by the VFC method. Finally, the non-uniform b-spline (NUBS) interpolation method is introduced to construct the road lane boundaries. The proposed VFC method integrates the vector concept and fuzzy connectedness into the lane boundary detection algorithm. As shown in the example results, the proposed method can extract various road lane shapes and types from real road frames even under complex road environments. For navigation tasks, it is necessary to determine the position of the vehicle relative to the road. These results prove that the proposed detection method can assist in a number of actual AGV assistant applications. In the future, some intelligent techniques will be applied to test the AGV system with obstacle avoidance conditions on real world roads.  相似文献   

19.
The general purpose dimensionality reduction method should preserve data interrelations at all scales. Additional desired features include online projection of new data, processing nonlinearly embedded manifolds and large amounts of data. The proposed method, called RBF-NDR, combines these features.RBF-NDR is comprised of two modules. The first module learns manifolds by utilizing modified topology representing networks and geodesic distance in data space and approximates sampled or streaming data with a finite set of reference patterns, thus achieving scalability. Using input from the first module, the dimensionality reduction module constructs mappings between observation and target spaces. Introduction of specific loss function and synthesis of the training algorithm for Radial Basis Function network results in global preservation of data structures and online processing of new patterns.The RBF-NDR was applied for feature extraction and visualization and compared with Principal Component Analysis (PCA), neural network for Sammon’s projection (SAMANN) and Isomap. With respect to feature extraction, the method outperformed PCA and yielded increased performance of the model describing wastewater treatment process. As for visualization, RBF-NDR produced superior results compared to PCA and SAMANN and matched Isomap. For the Topic Detection and Tracking corpus, the method successfully separated semantically different topics.  相似文献   

20.
Commercially available mini-gels for sodium dodecyl sulphate (SDS)-PAGE and Western blotting are limited both by the number of lanes that can be loaded per gel and the minimum amount of protein per lane that must be loaded. Here we describe a method for loading protein samples onto existing commercially available mini-gels that allows loading of 50 or more lanes per gel. The enhanced sensitivity of the method allows Western blotting with sub-microgram quantities of protein. Samples are loaded onto filter paper strips mounted on a plastic backing sheet, and film-wrapped strips on a separate dummy loader interdigitate with the sample strips, creating a physical barrier to lateral diffusion. The sample loader sandwich is placed on top of the stacking gel, and is compatible with all commercially available SDS-PAGE systems. Comparison of 15-lane mini-gels with 30-lane micro-loader strips reveals up to a 10-fold increase in sensitivity with the new method. Using 50- and 66-lane micro-loaders, sub-microgram quantities of protein produce reliable and quantifiable signal by Western blotting. Manipulation of the ionic conditions within dummy loader strips provides a mechanism for enhancing lateral resolution, allowing for the possibility of further miniaturization.  相似文献   

设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号