Journal articles on the topic 'Discriminative Encoding'
To see the other types of publications on this topic, follow the link: Discriminative Encoding.
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'Discriminative Encoding.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Feng, Lin, Yang Liu, Zan Li, Meng Zhang, Feilong Wang, and Shenglan Liu. "Discriminative bit selection hashing in RGB-D based object recognition for robot vision." Assembly Automation 39, no. 1 (February 4, 2019): 17–25. http://dx.doi.org/10.1108/aa-03-2018-037.
Full textAbstract:
PurposeThe purpose of this paper is to promote the efficiency of RGB-depth (RGB-D)-based object recognition in robot vision and find discriminative binary representations for RGB-D based objects.Design/methodology/approachTo promote the efficiency of RGB-D-based object recognition in robot vision, this paper applies hashing methods to RGB-D-based object recognition by utilizing the approximate nearest neighbors (ANN) to vote for the final result. To improve the object recognition accuracy in robot vision, an “Encoding+Selection” binary representation generation pattern is proposed. “Encoding+Selection” pattern can generate more discriminative binary representations for RGB-D-based objects. Moreover, label information is utilized to enhance the discrimination of each bit, which guarantees that the most discriminative bits can be selected.FindingsThe experiment results validate that the ANN-based voting recognition method is more efficient and effective compared to traditional recognition method in RGB-D-based object recognition for robot vision. Moreover, the effectiveness of the proposed bit selection method is also validated to be effective.Originality/valueHashing learning is applied to RGB-D-based object recognition, which significantly promotes the recognition efficiency for robot vision while maintaining high recognition accuracy. Besides, the “Encoding+Selection” pattern is utilized in the process of binary encoding, which effectively enhances the discrimination of binary representations for objects.
2
Zhao, Yuehua, Jie Ma, Qian Wang, Mao Ye, and Lin Wu. "Encoding discriminative representation for point cloud semantic segmentation." Electronics Letters 57, no. 6 (February 23, 2021): 258–60. http://dx.doi.org/10.1049/ell2.12118.
Full text
3
Bansal, Vipul, Himanshu Buckchash, and Balasubramanian Raman. "Discriminative Auto-Encoding for Classification and Representation Learning Problems." IEEE Signal Processing Letters 28 (2021): 987–91. http://dx.doi.org/10.1109/lsp.2021.3077853.
Full text
4
Sivaraman, Deepa, Jeneetha Jebanazer, and Bhuvaneswari Balasubramanian. "Discriminative analysis of wavelets for efficient medical image compression." Indonesian Journal of Electrical Engineering and Computer Science 30, no. 1 (April 1, 2023): 510. http://dx.doi.org/10.11591/ijeecs.v30.i1.pp510-517.
Full textAbstract:
Critical diagnostic information inferred using state of the artradiology techniques helps radiologists in determining the severity of diseases and hence suggest suitable treatment procedures. As a result, dealing with medical image compression necessitates a trade-off between good perceptual quality and high compression rate. The objective of this work is twofold, i) to investigate the effect of increasing the number of encoding loops on medical image compression parameters, and ii) to determine the most suitable wavelet for medical image compression. Haar, Daubechies, Biorthogonal Demeyer, Coifletand Symlet wavelets are used for comparison. Six different sets of medical images are used for testing and from the results obtained it is observed that increasing the number of encoding loops results in better compression parameters but increasing beyond 9 has no significant effect on compression parameters and thus the optimum choice for the number of encoding loops is 9. From the second analysis it is observed that changing the type of wavelets used has no significant effect on the compression parameters.
5
Liu, Peixin, Xiaofeng Li, Han Liu, and Zhizhong Fu. "Online Learned Siamese Network with Auto-Encoding Constraints for Robust Multi-Object Tracking." Electronics 8, no. 6 (May 28, 2019): 595. http://dx.doi.org/10.3390/electronics8060595.
Full textAbstract:
Multi-object tracking aims to estimate the complete trajectories of objects in a scene. Distinguishing among objects efficiently and correctly in complex environments is a challenging problem. In this paper, a Siamese network with an auto-encoding constraint is proposed to extract discriminative features from detection responses in a tracking-by-detection framework. Different from recent deep learning methods, the simple two layers stacked auto-encoder structure enables the Siamese network to operate efficiently only with small-scale online sample data. The auto-encoding constraint reduces the possibility of overfitting during small-scale sample training. Then, the proposed Siamese network is improved to extract the previous-appearance-next vector from tracklet for better association. The new feature integrates the appearance, previous, and next stage motions of an element in a tracklet. With the new features, an online incremental learned tracking framework is established. It contains reliable tracklet generation, data association to generate complete object trajectories, and tracklet growth to deal with missing detections and to enhance the new feature for tracklet. Benefiting from discriminative features, the final trajectories of objects can be achieved by an efficient iterative greedy algorithm. Feature experiments show that the proposed Siamese network has advantages in terms of both discrimination and correctness. The system experiments show the improved tracking performance of the proposed method.
6
Li, Fuqiang, Tongzhuang Zhang, Yong Liu, and Feiqi Long. "Deep Residual Vector Encoding for Vein Recognition." Electronics 11, no. 20 (October 13, 2022): 3300. http://dx.doi.org/10.3390/electronics11203300.
Full textAbstract:
Vein recognition has been drawing more attention recently because it is highly secure and reliable for practical biometric applications. However, underlying issues such as uneven illumination, low contrast, and sparse patterns with high inter-class similarities make the traditional vein recognition systems based on hand-engineered features unreliable. Recent successes of convolutional neural networks (CNNs) for large-scale image recognition tasks motivate us to replace the traditional hand-engineered features with the superior CNN to design a robust and discriminative vein recognition system. To address the difficulty of direct training or fine-tuning of a CNN with existing small-scale vein databases, a new knowledge transfer approach is formulated using pre-trained CNN models together with a training dataset (e.g., ImageNet) as a robust descriptor generation machine. With the generated deep residual descriptors, a very discriminative model, namely deep residual vector encoding (DRVE), is proposed by a hierarchical design of dictionary learning, coding, and classifier training procedures. Rigorous experiments are conducted with a high-quality hand-dorsa vein database, and superior recognition results compared with state-of-the-art models fully demonstrate the effectiveness of the proposed models. An additional experiment with the PolyU multispectral palmprint database is designed to illustrate the generalization ability.
7
Tavares, Gabriel, and Sylvio Barbon. "Matching business process behavior with encoding techniques via meta-learning: An anomaly detection study." Computer Science and Information Systems, no. 00 (2023): 5. http://dx.doi.org/10.2298/csis220110005t.
Full textAbstract:
Recording anomalous traces in business processes diminishes an event log?s quality. The abnormalities may represent bad execution, security issues, or deviant behavior. Focusing on mitigating this phenomenon, organizations spend efforts to detect anomalous traces in their business processes to save resources and improve process execution. However, in many real-world environments, reference models are unavailable, requiring expert assistance and increasing costs. The con15 siderable number of techniques and reduced availability of experts pose an additional challenge for particular scenarios. In this work, we combine the representational power of encoding with a Meta-learning strategy to enhance the detection of anomalous traces in event logs towards fitting the best discriminative capability be tween common and irregular traces. Our approach creates an event log profile and recommends the most suitable encoding technique to increase the anomaly detetion performance. We used eight encoding techniques from different families, 80 log descriptors, 168 event logs, and six anomaly types for experiments. Results indicate that event log characteristics influence the representational capability of encodings. Moreover, we investigate the process behavior?s influence for choosing the suitable encoding technique, demonstrating that traditional process mining analysis can be leveraged when matched with intelligent decision support approaches.
8
Shakeel, M. Saad, and Kin-Man Lam. "Deep-feature encoding-based discriminative model for age-invariant face recognition." Pattern Recognition 93 (September 2019): 442–57. http://dx.doi.org/10.1016/j.patcog.2019.04.028.
Full text
9
Kim, Yeongbin, Joongchol Shin, Hasil Park, and Joonki Paik. "Real-Time Visual Tracking with Variational Structure Attention Network." Sensors 19, no. 22 (November 9, 2019): 4904. http://dx.doi.org/10.3390/s19224904.
Full textAbstract:
Online training framework based on discriminative correlation filters for visual tracking has recently shown significant improvement in both accuracy and speed. However, correlation filter-base discriminative approaches have a common problem of tracking performance degradation when the local structure of a target is distorted by the boundary effect problem. The shape distortion of the target is mainly caused by the circulant structure in the Fourier domain processing, and it makes the correlation filter learn distorted training samples. In this paper, we present a structure–attention network to preserve the target structure from the structure distortion caused by the boundary effect. More specifically, we adopt a variational auto-encoder as a structure–attention network to make various and representative target structures. We also proposed two denoising criteria using a novel reconstruction loss for variational auto-encoding framework to capture more robust structures even under the boundary condition. Through the proposed structure–attention framework, discriminative correlation filters can learn robust structure information of targets during online training with an enhanced discriminating performance and adaptability. Experimental results on major visual tracking benchmark datasets show that the proposed method produces a better or comparable performance compared with the state-of-the-art tracking methods with a real-time processing speed of more than 80 frames per second.
10
Rescorla, Robert A. "Elemental and Configural Encoding of the Conditioned Stimulus." Quarterly Journal of Experimental Psychology Section B 56, no. 2b (May 2003): 161–76. http://dx.doi.org/10.1080/02724990244000089.
Full textAbstract:
Five experiments explored the effect of conditioning AB and CD compounds on responding to transfer AD and BC compounds and to elements. These experiments used several conditioning procedures: flavour aversion and instrumental discriminative learning in rats and autoshaping in pigeons. All of the experiments found greater responding to the trained AB and CD than to the transfer AD and BC compounds, a result that agrees with some configural models, but not with an elemental model. All experiments also found greater responding to the transfer AD and BC compounds than to the elements, a result that agrees with elemental, but not configural, models.
11
Norhisham Razali, Mohd, Noridayu Manshor, Alfian Abdul Halin, Norwati Mustapha, and Razali Yaakob. "Fuzzy encoding with hybrid pooling for visual dictionary in food recognition." Indonesian Journal of Electrical Engineering and Computer Science 21, no. 1 (January 1, 2021): 179. http://dx.doi.org/10.11591/ijeecs.v21.i1.pp179-195.
Full textAbstract:
<span>Tremendous number of f food images in the social media services can be exploited by using food recognition for healthcare benefits and food industry marketing. The main challenges in food recognition are the large variability of food appearance that often generates a highly diverse and ambiguous descriptions of local feature. Ironically, the ambiguous descriptions of local feature have triggered information loss in visual dictionary constructions from the hard assignment practices. The current method based on hard assignment and Fisher vector approach to construct visual dictionary have unexpectedly cause errors from the uncertainty problem during visual word assignation. This research proposes a method of combination in soft assignment technique by using fuzzy encoding approach and maximum pooling technique to aggregate the features to produce a highly discriminative and robust visual dictionary across various local features and machine learning classifiers. The local features by using MSER detector with SURF descriptor was encoded by using fuzzy encoding approach. Support vector machine (SVM) with linear kernel was employed to evaluate the effect of fuzzy encoding. The results of the experiments have demonstrated a noteworthy classification performance of fuzzy encoding approach compared to the traditional approach based on hard assignment and Fisher vector technique. The effects of uncertainty and plausibility were minimized along with more discriminative and compact visual dictionary representation.</span>
12
Sarhan, Ahmad. "Run length encoding based wavelet features for COVID-19 detection in X-rays." BJR|Open 3, no. 1 (January 2021): 20200028. http://dx.doi.org/10.1259/bjro.20200028.
Full textAbstract:
Objectives: Introduced in his paper is a novel approach for the recognition of COVID-19 cases in chest X-rays. Methods: The discrete Wavelet transform (DWT) is employed in the proposed system to obtain highly discriminative features from the input chest X-ray image. The selected features are then classified by a support vector machine (SVM) classifier as either normal or COVID-19 cases. The DWT is well-known for its energy compression power. The proposed system uses the DWT to decompose the chest X-ray image into a group of approximation coefficients that contain a small number of high-energy (high-magnitude) coefficients. The proposed system introduces a novel coefficient selection scheme that employs hard thresholding combined with run-length encoding to extract only high-magnitude Wavelet approximation coefficients. These coefficients are utilized as features symbolizing the chest X-ray input image. After applying zero-padding to unify their lengths, the feature vectors are introduced to a SVM which classifies them as either normal or COVID-19 cases. Results: The proposed system yields promising results in terms of classification accuracy, which justifies further work in this direction. Conclusion: The DWT can produce a few features that are highly discriminative. By reducing the dimensionality of the feature space, the proposed system is able to reduce the number of required training images and diminish the space and time complexities of the system. Advances in knowledge: Exploiting and reshaping the approximation coefficients can produce discriminative features representing the input image.
13
Cutellic, Pierre. "Towards encoding shape features with visual event-related potential based brain–computer interface for generative design." International Journal of Architectural Computing 17, no. 1 (March 2019): 88–102. http://dx.doi.org/10.1177/1478077119832465.
Full textAbstract:
This article will focus on abstracting and generalising a well-studied paradigm in visual, event-related potential based brain–computer interfaces, for the spelling of characters forming words, into the visually encoded discrimination of shape features forming design aggregates. After identifying typical technologies in neuroscience and neuropsychology of high interest for integrating fast cognitive responses into generative design and proposing the machine learning model of an ensemble of linear classifiers in order to tackle the challenging features that electroencephalography data carry, it will present experiments in encoding shape features for generative models by a mechanism of visual context updating and the computational implementation of vision as inverse graphics, to suggest that discriminative neural phenomena of event-related potentials such as P300 may be used in a visual articulation strategy for modelling in generative design.
14
Kim, Woong Bin, and Jun-Hyeong Cho. "Encoding of Discriminative Fear Memory by Input-Specific LTP in the Amygdala." Neuron 95, no. 5 (August 2017): 1129–46. http://dx.doi.org/10.1016/j.neuron.2017.08.004.
Full text
15
Son, Chang-Hwan. "Leaf Spot Attention Networks Based on Spot Feature Encoding for Leaf Disease Identification and Detection." Applied Sciences 11, no. 17 (August 28, 2021): 7960. http://dx.doi.org/10.3390/app11177960.
Full textAbstract:
This study proposes a new attention-enhanced YOLO model that incorporates a leaf spot attention mechanism based on regions-of-interest (ROI) feature extraction into the YOLO framework for leaf disease detection. Inspired by a previous study, which revealed that leaf spot attention based on the ROI-aware feature extraction can improve leaf disease recognition accuracy significantly and outperform state-of-the-art deep learning models, this study extends the leaf spot attention model to leaf disease detection. The primary idea is that spot areas indicating leaf diseases appear only in leaves, whereas the background area does not contain useful information regarding leaf diseases. To increase the discriminative power of the feature extractor that is required in the object detection framework, it is essential to extract informative and discriminative features from the spot and leaf areas. To realize this, a new ROI-aware feature extractor, that is, a spot feature extractor was designed. To divide the leaf image into spot, leaf, and background areas, the leaf segmentation module was first pretrained, and then spot feature encoding was applied to encode spot information. Next, the ROI-aware feature extractor was connected to an ROI-aware feature fusion layer to model the leaf spot attention mechanism, and to be joined with the YOLO detection subnetwork. The experimental results confirm that the proposed ROI-aware feature extractor can improve leaf disease detection by boosting the discriminative power of the spot features. In addition, the proposed attention-enhanced YOLO model outperforms conventional state-of-the-art object detection models.
16
Reichle, Joe, and Mary Ward. "Teaching Discriminative Use of an Encoding Electronic Communication Device and Signing Exact English to a Moderately Handicapped Child." Language, Speech, and Hearing Services in Schools 16, no. 1 (January 1985): 58–63. http://dx.doi.org/10.1044/0161-1461.1601.58.
Full textAbstract:
A 13-year-old communicatively and intellectually delayed male was taught to use discriminatively each of two previously acquired augmentative systems that consisted of signing and direct select letter encoding. Procedures used resulted in the use of signs with signers and direct select encoding with nonsigners. The learner's selection of the most appropriate communication modality generalized to new persons and environments.
17
Liu, Xinhai, Zhizhong Han, Fangzhou Hong, Yu-Shen Liu, and Matthias Zwicker. "LRC-Net: Learning discriminative features on point clouds by encoding local region contexts." Computer Aided Geometric Design 79 (May 2020): 101859. http://dx.doi.org/10.1016/j.cagd.2020.101859.
Full text
18
Chen, Dong, Xianghong Li, Fan Hu, P. Takis Mathiopoulos, Shaoning Di, Mingming Sui, and Jiju Peethambaran. "EDPNet: An Encoding–Decoding Network with Pyramidal Representation for Semantic Image Segmentation." Sensors 23, no. 6 (March 17, 2023): 3205. http://dx.doi.org/10.3390/s23063205.
Full textAbstract:
This paper proposes an encoding–decoding network with a pyramidal representation module, which will be referred to as EDPNet, and is designed for efficient semantic image segmentation. On the one hand, during the encoding process of the proposed EDPNet, the enhancement of the Xception network, i.e., Xception+ is employed as a backbone to learn the discriminative feature maps. The obtained discriminative features are then fed into the pyramidal representation module, from which the context-augmented features are learned and optimized by leveraging a multi-level feature representation and aggregation process. On the other hand, during the image restoration decoding process, the encoded semantic-rich features are progressively recovered with the assistance of a simplified skip connection mechanism, which performs channel concatenation between high-level encoded features with rich semantic information and low-level features with spatial detail information. The proposed hybrid representation employing the proposed encoding–decoding and pyramidal structures has a global-aware perception and captures fine-grained contours of various geographical objects very well with high computational efficiency. The performance of the proposed EDPNet has been compared against PSPNet, DeepLabv3, and U-Net, employing four benchmark datasets, namely eTRIMS, Cityscapes, PASCAL VOC2012, and CamVid. EDPNet acquired the highest accuracy of 83.6% and 73.8% mIoUs on eTRIMS and PASCAL VOC2012 datasets, while its accuracy on the other two datasets was comparable to that of PSPNet, DeepLabv3, and U-Net models. EDPNet achieved the highest efficiency among the compared models on all datasets.
19
Bugarel, Marie, Lothar Beutin, Flemming Scheutz, Estelle Loukiadis, and Patrick Fach. "Identification of Genetic Markers for Differentiation of Shiga Toxin-Producing, Enteropathogenic, and Avirulent Strains ofEscherichia coliO26." Applied and Environmental Microbiology 77, no. 7 (February 11, 2011): 2275–81. http://dx.doi.org/10.1128/aem.02832-10.
Full textAbstract:
ABSTRACTShiga toxin-producingEscherichia coli(STEC) O26 is one of the top five enterohemorrhagicE. coli(EHEC) O groups most often associated with hemorrhagic colitis and hemolytic uremic syndrome (HUS) worldwide. STEC O26 is considered to have evolved from enteropathogenic (EPEC) O26 strains through the acquisition of Shiga toxin (Stx)-encoding genes. Our PCR data identified several STEC-like strains expressing all features of STEC except Stx production and carrying remnants of Stx phages that were probably derivatives of EHEC O26. EHEC and EPEC O26 strains phenotypically resemble O26 EHEC-like and apathogenicE. coliO26 strains and are therefore undistinguishable by cultural methods. A clear discrimination between the different O26 groups is required for diagnostics in patients and for control of food safety. To develop an assay for specific detection of EHEC and EHEC-like O26 strains, we used a high-throughput PCR approach for selection of discriminative genetic markers among 33 tested genes mostly encoding type III secretion system effector proteins. The genesECs1822,nleH1-2,nleA,nleC,nleH1-1,nleG,nleG2,nleG6-1,nleG6-2,espJ,espM2,nleG8-2,espG,ent(orespL2),nleB,nleE,efa1, andespBwere detected at different frequencies in O26 EHEC, EHEC-like, and EPEC strains, indicating the possible role of these genes in virulence of human pathogenic O26 strains. TheespKandespNgenes were detected only in EHEC and EHEC-like O26 strains.espKwas present in 99.14% of EHEC and 91.14% of EHEC-like O26 strains and was hence the best candidate as a genetic marker for characterizing these pathogroups. These data were corroborated by a genotyping real-time PCR test based on allelic discrimination of thearcA(aerobic respiratory control protein A) gene. The results indicate that a combination of molecular detection tools for O26wzx(wzxO26),eae-beta,stx,espK, andarcAgenotyping is highly discriminative for clear identification of EHEC and EHEC-likeE. coliO26 strains. This simple diagnostic test might be applicable in hospital service laboratories or public health laboratories to test strains isolated from stools of patients suffering from diarrhea.
20
Mardikoraem, Mehrsa, and Daniel Woldring. "Protein Fitness Prediction Is Impacted by the Interplay of Language Models, Ensemble Learning, and Sampling Methods." Pharmaceutics 15, no. 5 (April 25, 2023): 1337. http://dx.doi.org/10.3390/pharmaceutics15051337.
Full textAbstract:
Advances in machine learning (ML) and the availability of protein sequences via high-throughput sequencing techniques have transformed the ability to design novel diagnostic and therapeutic proteins. ML allows protein engineers to capture complex trends hidden within protein sequences that would otherwise be difficult to identify in the context of the immense and rugged protein fitness landscape. Despite this potential, there persists a need for guidance during the training and evaluation of ML methods over sequencing data. Two key challenges for training discriminative models and evaluating their performance include handling severely imbalanced datasets (e.g., few high-fitness proteins among an abundance of non-functional proteins) and selecting appropriate protein sequence representations (numerical encodings). Here, we present a framework for applying ML over assay-labeled datasets to elucidate the capacity of sampling techniques and protein encoding methods to improve binding affinity and thermal stability prediction tasks. For protein sequence representations, we incorporate two widely used methods (One-Hot encoding and physiochemical encoding) and two language-based methods (next-token prediction, UniRep; masked-token prediction, ESM). Elaboration on performance is provided over protein fitness, protein size, and sampling techniques. In addition, an ensemble of protein representation methods is generated to discover the contribution of distinct representations and improve the final prediction score. We then implement multiple criteria decision analysis (MCDA; TOPSIS with entropy weighting), using multiple metrics well-suited for imbalanced data, to ensure statistical rigor in ranking our methods. Within the context of these datasets, the synthetic minority oversampling technique (SMOTE) outperformed undersampling while encoding sequences with One-Hot, UniRep, and ESM representations. Moreover, ensemble learning increased the predictive performance of the affinity-based dataset by 4% compared to the best single-encoding candidate (F1-score = 97%), while ESM alone was rigorous enough in stability prediction (F1-score = 92%).
21
Jochumsen, Mads, Cecilie Rovsing, Helene Rovsing, Imran Khan Niazi, Kim Dremstrup, and Ernest Nlandu Kamavuako. "Classification of Hand Grasp Kinetics and Types Using Movement-Related Cortical Potentials and EEG Rhythms." Computational Intelligence and Neuroscience 2017 (2017): 1–8. http://dx.doi.org/10.1155/2017/7470864.
Full textAbstract:
Detection of single-trial movement intentions from EEG is paramount for brain-computer interfacing in neurorehabilitation. These movement intentions contain task-related information and if this is decoded, the neurorehabilitation could potentially be optimized. The aim of this study was to classify single-trial movement intentions associated with two levels of force and speed and three different grasp types using EEG rhythms and components of the movement-related cortical potential (MRCP) as features. The feature importance was used to estimate encoding of discriminative information. Two data sets were used. 29 healthy subjects executed and imagined different hand movements, while EEG was recorded over the contralateral sensorimotor cortex. The following features were extracted: delta, theta, mu/alpha, beta, and gamma rhythms, readiness potential, negative slope, and motor potential of the MRCP. Sequential forward selection was performed, and classification was performed using linear discriminant analysis and support vector machines. Limited classification accuracies were obtained from the EEG rhythms and MRCP-components: 0.48±0.05 (grasp types), 0.41±0.07 (kinetic profiles, motor execution), and 0.39±0.08 (kinetic profiles, motor imagination). Delta activity contributed the most but all features provided discriminative information. These findings suggest that information from the entire EEG spectrum is needed to discriminate between task-related parameters from single-trial movement intentions.
22
Chiu, Chi-Yue, Ying-Yi Hong, Walter Mischel, and Yuichi Shoda. "Discriminative Facility in Social Competence: Conditional Versus Dispositional Encoding and Monitoring-Blunting of Information." Social Cognition 13, no. 1 (March 1995): 49–70. http://dx.doi.org/10.1521/soco.1995.13.1.49.
Full text
23
Xiao, Guanghua, Huibin Wang, Jie Shen, Zhe Chen, Zhen Zhang, and Xiaomin Ge. "Synergy Factorized Bilinear Network with a Dual Suppression Strategy for Brain Tumor Classification in MRI." Micromachines 13, no. 1 (December 23, 2021): 15. http://dx.doi.org/10.3390/mi13010015.
Full textAbstract:
Automatic brain tumor classification is a practicable means of accelerating clinical diagnosis. Recently, deep convolutional neural network (CNN) training with MRI datasets has succeeded in computer-aided diagnostic (CAD) systems. To further improve the classification performance of CNNs, there is still a difficult path forward with regards to subtle discriminative details among brain tumors. We note that the existing methods heavily rely on data-driven convolutional models while overlooking what makes a class different from the others. Our study proposes to guide the network to find exact differences among similar tumor classes. We first present a “dual suppression encoding” block tailored to brain tumor MRIs, which diverges two paths from our network to refine global orderless information and local spatial representations. The aim is to use more valuable clues for correct classes by reducing the impact of negative global features and extending the attention of salient local parts. Then we introduce a “factorized bilinear encoding” layer for feature fusion. The aim is to generate compact and discriminative representations. Finally, the synergy between these two components forms a pipeline that learns in an end-to-end way. Extensive experiments exhibited superior classification performance in qualitative and quantitative evaluation on three datasets.
24
Wang, Shijie, Haojie Li, Zhihui Wang, and Wanli Ouyang. "Dynamic Position-aware Network for Fine-grained Image Recognition." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 4 (May 18, 2021): 2791–99. http://dx.doi.org/10.1609/aaai.v35i4.16384.
Full textAbstract:
Most weakly supervised fine-grained image recognition (WFGIR) approaches predominantly focus on learning the discriminative details which contain the visual variances and position clues. The position clues can be indirectly learnt by utilizing context information of discriminative visual content. However, this will cause the selected discriminative regions containing some non-discriminative information introduced by the position clues. These analysis motivate us to directly introduce position clues into visual content to only focus on the visual variances, achieving more precise discriminative region localization. Though important, position modelling usually requires significant pixel/region annotations and therefore is labor-intensive. To address this issue, we propose an end-to-end Dynamic Position-aware Network (DP-Net) to directly incorporate the position clues into visual content and dynamically align them without extra annotations, which eliminates the effect of position information for visual variances of subcategories. In particular, the DP-Net consists of: 1) Position Encoding Module, which learns a set of position-aware parts by directly adding the learnable position information into the horizontal/vertical visual content of images; 2) Position-vision Aligning Module, which dynamically aligns both visual content and learnable position information via performing graph convolution on position-aware parts; 3) Position-vision Reorganization Module, which projects the aligned position clues and visual content into the Euclidean space to construct a position-aware feature maps. Finally, the position-aware feature maps are used which is implicitly applied the aligned visual content and position clues for more accurate discriminative regions localization. Extensive experiments verify that DP-Net yields the best performance under the same settings with most competitive approaches, on CUB Bird, Stanford-Cars, and FGVC Aircraft datasets.
25
Govindaraj, Rajiv G., Sathiyamoorthy Subramaniyam, and Balachandran Manavalan. "Extremely-randomized-tree-based Prediction of N6-methyladenosine Sites in Saccharomyces cerevisiae." Current Genomics 21, no. 1 (March 25, 2020): 26–33. http://dx.doi.org/10.2174/1389202921666200219125625.
Full textAbstract:
Introduction: N6-methyladenosine (m6A) is one of the most common post-transcriptional modifications in RNA, which has been related to several biological processes. The accurate prediction of m6A sites from RNA sequences is one of the challenging tasks in computational biology. Several computational methods utilizing machine-learning algorithms have been proposed that accelerate in silico screening of m6A sites, thereby drastically reducing the experimental time and labor costs involved. Methodology: In this study, we proposed a novel computational predictor termed ERT-m6Apred, for the accurate prediction of m6A sites. To identify the feature encodings with more discriminative capability, we applied a two-step feature selection technique on seven different feature encodings and identified the corresponding optimal feature set. Results: Subsequently, performance comparison of the corresponding optimal feature set-based extremely randomized tree model revealed that Pseudo k-tuple composition encoding, which includes 14 physicochemical properties significantly outperformed other encodings. Moreover, ERT-m6Apred achieved an accuracy of 78.84% during cross-validation analysis, which is comparatively better than recently reported predictors. Conclusion: In summary, ERT-m6Apred predicts Saccharomyces cerevisiae m6A sites with higher accuracy, thus facilitating biological hypothesis generation and experimental validations.
26
Teagarden, Mark A., and George V. Rebec. "Subthalamic and Striatal Neurons Concurrently Process Motor, Limbic, and Associative Information in Rats Performing an Operant Task." Journal of Neurophysiology 97, no. 3 (March 2007): 2042–58. http://dx.doi.org/10.1152/jn.00368.2006.
Full textAbstract:
Although the subthalamic nucleus (STN) is commonly assumed to be a relay for striatal (STR) output, anatomical evidence suggests the two structures are connected in parallel, raising the possibility that parallel STN and STR firing patterns mediate behavioral processes. The STR is known to play a role in associative and limbic processes, and although behavioral studies suggest that the STN may do so as well, evaluation of this hypothesis is complicated by a lack of pertinent STN physiological data. We recorded concurrent STN and STR firing patterns in rats learning an operant nose-poke task. Both structures responded in similar proportions to task events including instructive cues, discriminative nose-pokes, and sucrose reinforcement. Neuronal responses to reinforcement comprised phasic excitations preceding reinforcement and inhibitions afterward; the inhibition was attenuated when reinforcement was absent. Reinforcement responses occurred more frequently during later training sessions in which discriminative action was required, suggesting that responses were context-dependent. Nose-pokes were typically preceded by excitations; there also was a nonsignificant trend toward inhibition encoding correct nose-pokes. Sustained changes in firing rate coinciding with specific task events suggested that both nuclei were encoding behavioral sequences; this is the first report of such behavior in the STN. Our findings also reveal complex STN responses to reinforcement. Thus both STN and STR neurons show concurrent involvement in motor, limbic, and associative processes.
27
Butt, Ammar Mohsin, Muhammad Haroon Yousaf, Fiza Murtaza, Saima Nazir, Serestina Viriri, and Sergio A. Velastin. "Agglomerative Clustering and Residual-VLAD Encoding for Human Action Recognition." Applied Sciences 10, no. 12 (June 26, 2020): 4412. http://dx.doi.org/10.3390/app10124412.
Full textAbstract:
Human action recognition has gathered significant attention in recent years due to its high demand in various application domains. In this work, we propose a novel codebook generation and hybrid encoding scheme for classification of action videos. The proposed scheme develops a discriminative codebook and a hybrid feature vector by encoding the features extracted from CNNs (convolutional neural networks). We explore different CNN architectures for extracting spatio-temporal features. We employ an agglomerative clustering approach for codebook generation, which intends to combine the advantages of global and class-specific codebooks. We propose a Residual Vector of Locally Aggregated Descriptors (R-VLAD) and fuse it with locality-based coding to form a hybrid feature vector. It provides a compact representation along with high order statistics. We evaluated our work on two publicly available standard benchmark datasets HMDB-51 and UCF-101. The proposed method achieves 72.6% and 96.2% on HMDB51 and UCF101, respectively. We conclude that the proposed scheme is able to boost recognition accuracy for human action recognition.
28
SCHWARTZ, WILLIAM ROBSON, and HELIO PEDRINI. "IMPROVED FRACTAL IMAGE COMPRESSION BASED ON ROBUST FEATURE DESCRIPTORS." International Journal of Image and Graphics 11, no. 04 (October 2011): 571–87. http://dx.doi.org/10.1142/s0219467811004251.
Full textAbstract:
Fractal image compression is one of the most promising techniques for image compression due to advantages such as resolution independence and fast decompression. It exploits the fact that natural scenes present self-similarity to remove redundancy and obtain high compression rates with smaller quality degradation compared to traditional compression methods. The main drawback of fractal compression is its computationally intensive encoding process, due to the need for searching regions with high similarity in the image. Several approaches have been developed to reduce the computational cost to locate similar regions. In this work, we propose a method based on robust feature descriptors to speed up the encoding time. The use of robust features provides more discriminative and representative information for regions of the image. When the regions are better represented, the search for similar parts of the image can be reduced to focus only on the most likely matching candidates, which leads to reduction on the computational time. Our experimental results show that the use of robust feature descriptors reduces the encoding time while keeping high compression rates and reconstruction quality.
29
Grandi, Laura Clara, and Stefania Bruni. "Social Touch: Its Mirror-like Responses and Implications in Neurological and Psychiatric Diseases." NeuroSci 4, no. 2 (May 26, 2023): 118–33. http://dx.doi.org/10.3390/neurosci4020012.
Full textAbstract:
What is the significance of a touch encoded by slow-conducted unmyelinated C-tactile (CT) fibers? It is the so-called affiliative touch, which has a fundamental social impact. In humans, it has been demonstrated that the affiliative valence of this kind of touch is encoded by a dedicated central network, not involved in the encoding of discriminative touch, namely, the “social brain”. Moreover, CT-related touch has significant consequences on the human autonomic system, not present in the case of discriminative touch, which does not involve CT fibers as the modulation of vagal tone. In addition, CT-related touch provokes central effects as well. An interesting finding is that CT-related touch can elicit “mirror-like responses” since there is evidence that we would have the same perception of a caress regardless of whether it would be felt or seen and that the same brain areas would be activated. Information from CT afferents in the posterior insular cortex likely provides a basis for encoding observed caresses. We also explored the application of this kind of touch in unphysiological conditions and in premature newborns. In the present literature review, we aim to (1) examine the effects of CT-related touch at autonomic and central levels and (2) highlight CT-related touch and mirror networks, seeking to draw a line of connection between them. Finally, the review aims to give an overview of the involvement of the CT system in some neurologic and psychiatric diseases.
30
Chen, Fuzan, Harris Wu, Runliang Dou, and Minqiang Li. "A high-dimensional classification approach based on class-dependent feature subspace." Industrial Management & Data Systems 117, no. 10 (December 4, 2017): 2325–39. http://dx.doi.org/10.1108/imds-11-2016-0491.
Full textAbstract:
Purpose The purpose of this paper is to build a compact and accurate classifier for high-dimensional classification. Design/methodology/approach A classification approach based on class-dependent feature subspace (CFS) is proposed. CFS is a class-dependent integration of a support vector machine (SVM) classifier and associated discriminative features. For each class, our genetic algorithm (GA)-based approach evolves the best subset of discriminative features and SVM classifier simultaneously. To guarantee convergence and efficiency, the authors customize the GA in terms of encoding strategy, fitness evaluation, and genetic operators. Findings Experimental studies demonstrated that the proposed CFS-based approach is superior to other state-of-the-art classification algorithms on UCI data sets in terms of both concise interpretation and predictive power for high-dimensional data. Research limitations/implications UCI data sets rather than real industrial data are used to evaluate the proposed approach. In addition, only single-label classification is addressed in the study. Practical implications The proposed method not only constructs an accurate classification model but also obtains a compact combination of discriminative features. It is helpful for business makers to get a concise understanding of the high-dimensional data. Originality/value The authors propose a compact and effective classification approach for high-dimensional data. Instead of the same feature subset for all the classes, the proposed CFS-based approach obtains the optimal subset of discriminative feature and SVM classifier for each class. The proposed approach enhances both interpretability and predictive power for high-dimensional data.
31
Millar, W. S., C. G. Weir, and G. Supramaniam. "The Relationship Between Encoding, Discriminative Capacities and Perinatal Risk Status in 4?12-Month Old Infants." Journal of Child Psychology and Psychiatry 32, no. 3 (March 1991): 473–88. http://dx.doi.org/10.1111/j.1469-7610.1991.tb00325.x.
Full text
32
Poyart, Claire, Gilles Quesnes, and Patrick Trieu-Cuot. "Sequencing the Gene Encoding Manganese-Dependent Superoxide Dismutase for Rapid Species Identification of Enterococci." Journal of Clinical Microbiology 38, no. 1 (January 2000): 415–18. http://dx.doi.org/10.1128/jcm.38.1.415-418.2000.
Full textAbstract:
ABSTRACT Simple PCR and sequencing assays that utilize a single pair of degenerate primers were used to characterize a 438-bp-long DNA fragment internal ( sodA int ) to the sodA gene encoding the manganese-dependent superoxide dismutase in 19 enterococcal type strains ( Enterococcus avium , Enterococcus casseliflavus , Enterococcus cecorum , Enterococcus columbae , Enterococcus dispar , Enterococcus durans , Enterococcus faecalis , Enterococcus faecium , Enterococcus flavescens , Enterococcus gallinarum , Enterococcus hirae , Enterococcus malodoratus , Enterococcus mundtii , Enterococcus pseudoavium , Enterococcus raffinosus , Enterococcus saccharolyticus , Enterococcus seriolicida , Enterococcus solitarius , and Enterococcus sulfureus ). Sequence analysis of the sodA int fragments enabled reliable identification of 18 enterococcal species, including E. casseliflavus-E. flavescens and E. gallinarum . The sodA int fragments of E. casseliflavus and E. flavescens were almost identical (99.5% sequence identity), which suggests that they should be associated in a single species. Our results confirm that the sodA gene constitutes a more discriminative target sequence than 16S rRNA gene in differentiating closely related bacterial species.
33
Su, Yanzhou, Jian Cheng, Haiwei Bai, Haijun Liu, and Changtao He. "Semantic Segmentation of Very-High-Resolution Remote Sensing Images via Deep Multi-Feature Learning." Remote Sensing 14, no. 3 (January 23, 2022): 533. http://dx.doi.org/10.3390/rs14030533.
Full textAbstract:
Currently, an increasing number of convolutional neural networks (CNNs) focus specifically on capturing contextual features (con. feat) to improve performance in semantic segmentation tasks. However, high-level con. feat are biased towards encoding features of large objects, disregard spatial details, and have a limited capacity to discriminate between easily confused classes (e.g., trees and grasses). As a result, we incorporate low-level features (low. feat) and class-specific discriminative features (dis. feat) to boost model performance further, with low. feat helping the model in recovering spatial information and dis. feat effectively reducing class confusion during segmentation. To this end, we propose a novel deep multi-feature learning framework for the semantic segmentation of VHR RSIs, dubbed MFNet. The proposed MFNet adopts a multi-feature learning mechanism to learn more complete features, including con. feat, low. feat, and dis. feat. More specifically, aside from a widely used context aggregation module for capturing con. feat, we additionally append two branches for learning low. feat and dis. feat. One focuses on learning low. feat at a shallow layer in the backbone network through local contrast processing, while the other groups con. feat and then optimizes each class individually to generate dis. feat with better inter-class discriminative capability. Extensive quantitative and qualitative evaluations demonstrate that the proposed MFNet outperforms most state-of-the-art models on the ISPRS Vaihingen and Potsdam datasets. In particular, thanks to the mechanism of multi-feature learning, our model achieves an overall accuracy score of 91.91% on the Potsdam test set with VGG16 as a backbone, performing favorably against advanced models with ResNet101.
34
Lim, King-Ting, Rohani Yasin, Chew-Chieng Yeo, Savithri Puthucheary, and Kwai-Lin Thong. "Characterization of Multidrug Resistant ESBL-ProducingEscherichia coliIsolates from Hospitals in Malaysia." Journal of Biomedicine and Biotechnology 2009 (2009): 1–10. http://dx.doi.org/10.1155/2009/165637.
Full textAbstract:
The emergence ofEscherichia colithat produce extended spectrumβ-lactamases (ESBLs) and are multidrug resistant (MDR) poses antibiotic management problems. Forty-sevenE. coliisolates from various public hospitals in Malaysia were studied. All isolates were sensitive to imipenem whereas 36 were MDR (resistant to 2 or more classes of antibiotics). PCR detection using gene-specific primers showed that 87.5% of the ESBL-producingE. coliharbored theblaTEMgene. Other ESBL-encoding genes detected wereblaOXA,blaSHV, andblaCTX-M. Integron-encoded integrases were detected in 55.3% of isolates, with class 1 integron-encodedintI1integrase being the majority. Amplification and sequence analysis of the5′CS region of the integrons showed known antibiotic resistance-encoding gene cassettes of various sizes that were inserted within the respective integrons. Conjugation and transformation experiments indicated that some of the antibiotic resistance genes were likely plasmid-encoded and transmissible. All 47 isolates were subtyped by PFGE and PCR-based fingerprinting using random amplified polymorphic DNA (RAPD), repetitive extragenic palindromes (REPs), and enterobacterial repetitive intergenic consensus (ERIC). These isolates were very diverse and heterogeneous. PFGE, ERIC, and REP-PCR methods were more discriminative than RAPD in subtyping theE. coliisolates.
35
Gheisari, Soheila, Daniel Catchpoole, Amanda Charlton, Zsombor Melegh, Elise Gradhand, and Paul Kennedy. "Computer Aided Classification of Neuroblastoma Histological Images Using Scale Invariant Feature Transform with Feature Encoding." Diagnostics 8, no. 3 (August 28, 2018): 56. http://dx.doi.org/10.3390/diagnostics8030056.
Full textAbstract:
Neuroblastoma is the most common extracranial solid malignancy in early childhood. Optimal management of neuroblastoma depends on many factors, including histopathological classification. Although histopathology study is considered the gold standard for classification of neuroblastoma histological images, computers can help to extract many more features some of which may not be recognizable by human eyes. This paper, proposes a combination of Scale Invariant Feature Transform with feature encoding algorithm to extract highly discriminative features. Then, distinctive image features are classified by Support Vector Machine classifier into five clinically relevant classes. The advantage of our model is extracting features which are more robust to scale variation compared to the Patched Completed Local Binary Pattern and Completed Local Binary Pattern methods. We gathered a database of 1043 histologic images of neuroblastic tumours classified into five subtypes. Our approach identified features that outperformed the state-of-the-art on both our neuroblastoma dataset and a benchmark breast cancer dataset. Our method shows promise for classification of neuroblastoma histological images.
36
Behera, Ardhendu, Zachary Wharton, Pradeep R. P. G. Hewage, and Asish Bera. "Context-aware Attentional Pooling (CAP) for Fine-grained Visual Classification." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 2 (May 18, 2021): 929–37. http://dx.doi.org/10.1609/aaai.v35i2.16176.
Full textAbstract:
Deep convolutional neural networks (CNNs) have shown a strong ability in mining discriminative object pose and parts information for image recognition. For fine-grained recognition, context-aware rich feature representation of object/scene plays a key role since it exhibits a significant variance in the same subcategory and subtle variance among different subcategories. Finding the subtle variance that fully characterizes the object/scene is not straightforward. To address this, we propose a novel context-aware attentional pooling (CAP) that effectively captures subtle changes via sub-pixel gradients, and learns to attend informative integral regions and their importance in discriminating different subcategories without requiring the bounding-box and/or distinguishable part annotations. We also introduce a novel feature encoding by considering the intrinsic consistency between the informativeness of the integral regions and their spatial structures to capture the semantic correlation among them. Our approach is simple yet extremely effective and can be easily applied on top of a standard classification backbone network. We evaluate our approach using six state-of-the-art (SotA) backbone networks and eight benchmark datasets. Our method significantly outperforms the SotA approaches on six datasets and is very competitive with the remaining two.
37
BHATTARAI, N. R., J. C. DUJARDIN, S. RIJAL, S. DE DONCKER, M. BOELAERT, and G. VAN DER AUWERA. "Development and evaluation of different PCR-based typing methods for discrimination ofLeishmania donovaniisolates from Nepal." Parasitology 137, no. 6 (January 29, 2010): 947–57. http://dx.doi.org/10.1017/s0031182009991752.
Full textAbstract:
SUMMARYIntroduction.Leishmania donovani, the causative agent of visceral leishmaniasis in the Indian subcontinent, has been reported to be genetically homogeneous. In order to support ongoing initiatives to eliminate the disease, highly discriminative tools are required for documenting the parasite population and dynamics.Methods.Thirty-four clinical isolates ofL.donovanifrom Nepal were analysed on the basis of size and restriction endonuclease polymorphisms of PCR amplicons from kinetoplast minicircle DNA, 5 nuclear microsatellites, and nuclear loci encoding glycoprotein 63, cysteine proteinase B, and hydrophilic acylated surface protein B. We present and validate a procedure allowing standardized analysis of kDNA fingerprint patterns.Results.Our results show that parasites are best discriminated on the basis of kinetoplast minicircle DNA (14 genotypes) and 1 microsatellite defining 7 genotypes, while the remaining markers discriminated 2 groups or were monomorphic. Combination of all nuclear markers revealed 8 genotypes, while extension with kDNA data yielded 18 genotypes.Conclusion.We present tools that allow discrimination of closely relatedL.donovanistrains circulating in the Terai region of Nepal. These can be used to study the micro-epidemiology of parasite populations, determine the geographical origin of infections, distinguish relapses from re-infection, and monitor the spread of particular variants.
38
Dai, Xili, Shengbang Tong, Mingyang Li, Ziyang Wu, Michael Psenka, Kwan Ho Ryan Chan, Pengyuan Zhai, et al. "CTRL: Closed-Loop Transcription to an LDR via Minimaxing Rate Reduction." Entropy 24, no. 4 (March 25, 2022): 456. http://dx.doi.org/10.3390/e24040456.
Full textAbstract:
This work proposes a new computational framework for learning a structured generative model for real-world datasets. In particular, we propose to learn a Closed-loop Transcriptionbetween a multi-class, multi-dimensional data distribution and a Linear discriminative representation (CTRL) in the feature space that consists of multiple independent multi-dimensional linear subspaces. In particular, we argue that the optimal encoding and decoding mappings sought can be formulated as a two-player minimax game between the encoder and decoderfor the learned representation. A natural utility function for this game is the so-called rate reduction, a simple information-theoretic measure for distances between mixtures of subspace-like Gaussians in the feature space. Our formulation draws inspiration from closed-loop error feedback from control systems and avoids expensive evaluating and minimizing of approximated distances between arbitrary distributions in either the data space or the feature space. To a large extent, this new formulation unifies the concepts and benefits of Auto-Encoding and GAN and naturally extends them to the settings of learning a both discriminative and generative representation for multi-class and multi-dimensional real-world data. Our extensive experiments on many benchmark imagery datasets demonstrate tremendous potential of this new closed-loop formulation: under fair comparison, visual quality of the learned decoder and classification performance of the encoder is competitive and arguably better than existing methods based on GAN, VAE, or a combination of both. Unlike existing generative models, the so-learned features of the multiple classes are structured instead of hidden: different classes are explicitly mapped onto corresponding independent principal subspaces in the feature space, and diverse visual attributes within each class are modeled by the independent principal components within each subspace.
39
Wu, Lulu, Hong Liu, Bing Yang, and Runwei Ding. "An Adaptive Method Based on Multiscale Dilated Convolutional Network for Binaural Speech Source Localization." Complexity 2020 (December 30, 2020): 1–7. http://dx.doi.org/10.1155/2020/5819624.
Full textAbstract:
Most binaural speech source localization models perform poorly in unprecedentedly noisy and reverberant situations. Here, this issue is approached by modelling a multiscale dilated convolutional neural network (CNN). The time-related crosscorrelation function (CCF) and energy-related interaural level differences (ILD) are preprocessed in separate branches of dilated convolutional network. The multiscale dilated CNN can encode discriminative representations for CCF and ILD, respectively. After encoding, the individual interaural representations are fused to map source direction. Furthermore, in order to improve the parameter adaptation, a novel semiadaptive entropy is proposed to train the network under directional constraints. Experimental results show the proposed method can adaptively locate speech sources in simulated noisy and reverberant environments.
40
Tang, Yuzhu, Pinglv Yang, Zeming Zhou, Delu Pan, Jianyu Chen, and Xiaofeng Zhao. "Improving cloud type classification of ground-based images using region covariance descriptors." Atmospheric Measurement Techniques 14, no. 1 (January 29, 2021): 737–47. http://dx.doi.org/10.5194/amt-14-737-2021.
Full textAbstract:
Abstract. The distribution and frequency of occurrence of different cloud types affect the energy balance of the Earth. Automatic cloud type classification of images continuously observed by the ground-based imagers could help climate researchers find the relationship between cloud type variations and climate change. However, by far it is still a huge challenge to design a powerful discriminative classifier for cloud categorization. To tackle this difficulty, in this paper, we present an improved method with region covariance descriptors (RCovDs) and the Riemannian bag-of-feature (BoF) method. RCovDs model the correlations among different dimensional features, which allows for a more discriminative representation. BoF is extended from Euclidean space to Riemannian manifold by k-means clustering, in which Stein divergence is adopted as a similarity metric. The histogram feature is extracted by encoding RCovDs of the cloud image blocks with a BoF-based codebook. The multiclass support vector machine (SVM) is utilized for the recognition of cloud types. The experiments on the ground-based cloud image datasets show that a very high prediction accuracy (more than 98 % on two datasets) can be obtained with a small number of training samples, which validate the proposed method and exhibit the competitive performance against state-of-the-art methods.
41
Meng, Yao, and Long Liu. "A Deep Learning Approach for a Source Code Detection Model Using Self-Attention." Complexity 2020 (September 16, 2020): 1–15. http://dx.doi.org/10.1155/2020/5027198.
Full textAbstract:
With the development of deep learning, many approaches based on neural networks are proposed for code clone. In this paper, we propose a novel source code detection model At-biLSTM based on a bidirectional LSTM network with a self-attention layer. At-biLSTM is composed of a representation model and a discriminative model. The representation model firstly transforms the source code into an abstract syntactic tree and splits it into a sequence of statement trees; then, it encodes each of the statement trees with a deep-first traversal algorithm. Finally, the representation model encodes the sequence of statement vectors via a bidirectional LSTM network, which is a classical deep learning framework, with a self-attention layer and outputs a vector representing the given source code. The discriminative model identifies the code clone depending on the vectors generated by the presentation model. Our proposed model retains both the syntactics and semantics of the source code in the process of encoding, and the self-attention algorithm makes the classifier concentrate on the effect of key statements and improves the classification performance. The contrast experiments on the benchmarks OJClone and BigCloneBench indicate that At-LSTM is effective and outperforms the state-of-art approaches in source code clone detection.
42
Timmermann, Lars, Markus Ploner, Katrin Haucke, Frank Schmitz, Rüdiger Baltissen, and Alfons Schnitzler. "Differential Coding of Pain Intensity in the Human Primary and Secondary Somatosensory Cortex." Journal of Neurophysiology 86, no. 3 (September 1, 2001): 1499–503. http://dx.doi.org/10.1152/jn.2001.86.3.1499.
Full textAbstract:
The primary (SI) and secondary (SII) somatosensory cortices have been shown to participate in human pain processing. However, in humans it is unclear how SI and SII contribute to the encoding of nociceptive stimulus intensity. Using magnetoencephalography (MEG) we recorded responses in SI and SII in eight healthy humans to four different intensities of selectively nociceptive laser stimuli delivered to the dorsum of the right hand. Subjects' pain ratings correlated highly with the applied stimulus intensity. Activation of contralateral SI and bilateral SII showed a significant positive correlation with stimulus intensity. However, the type of dependence on stimulus intensity was different for SI and SII. The relation between SI activity and stimulus intensity resembled an exponential function and matched closely the subjects' pain ratings. In contrast, SII activity showed an S-shaped function with a sharp increase in amplitude only at a stimulus intensity well above pain threshold. The activation pattern of SI suggests participation of SI in the discriminative perception of pain intensity. In contrast, the all-or-none–like activation pattern of SII points against a significant contribution of SII to the sensory-discriminative aspects of pain perception. Instead, SII may subserve recognition of the noxious nature and attention toward painful stimuli.
43
Spratling, M. W. "Unsupervised Learning of Generative and Discriminative Weights Encoding Elementary Image Components in a Predictive Coding Model of Cortical Function." Neural Computation 24, no. 1 (January 2012): 60–103. http://dx.doi.org/10.1162/neco_a_00222.
Full textAbstract:
A method is presented for learning the reciprocal feedforward and feedback connections required by the predictive coding model of cortical function. When this method is used, feedforward and feedback connections are learned simultaneously and independently in a biologically plausible manner. The performance of the proposed algorithm is evaluated by applying it to learning the elementary components of artificial and natural images. For artificial images, the bars problem is employed, and the proposed algorithm is shown to produce state-of-the-art performance on this task. For natural images, components resembling Gabor functions are learned in the first processing stage, and neurons responsive to corners are learned in the second processing stage. The properties of these learned representations are in good agreement with neurophysiological data from V1 and V2. The proposed algorithm demonstrates for the first time that a single computational theory can explain the formation of cortical RFs and also the response properties of cortical neurons once those RFs have been learned.
44
Weng, Zhengkui, Zhipeng Jin, Shuangxi Chen, Quanquan Shen, Xiangyang Ren, and Wuzhao Li. "Attention-Based Temporal Encoding Network with Background-Independent Motion Mask for Action Recognition." Computational Intelligence and Neuroscience 2021 (March 29, 2021): 1–16. http://dx.doi.org/10.1155/2021/8890808.
Full textAbstract:
Convolutional neural network (CNN) has been leaping forward in recent years. However, the high dimensionality, rich human dynamic characteristics, and various kinds of background interference increase difficulty for traditional CNNs in capturing complicated motion data in videos. A novel framework named the attention-based temporal encoding network (ATEN) with background-independent motion mask (BIMM) is proposed to achieve video action recognition here. Initially, we introduce one motion segmenting approach on the basis of boundary prior by associating with the minimal geodesic distance inside a weighted graph that is not directed. Then, we propose one dynamic contrast segmenting strategic procedure for segmenting the object that moves within complicated environments. Subsequently, we build the BIMM for enhancing the object that moves based on the suppression of the not relevant background inside the respective frame. Furthermore, we design one long-range attention system inside ATEN, capable of effectively remedying the dependency of sophisticated actions that are not periodic in a long term based on the more automatic focus on the semantical vital frames other than the equal process for overall sampled frames. For this reason, the attention mechanism is capable of suppressing the temporal redundancy and highlighting the discriminative frames. Lastly, the framework is assessed by using HMDB51 and UCF101 datasets. As revealed from the experimentally achieved results, our ATEN with BIMM gains 94.5% and 70.6% accuracy, respectively, which outperforms a number of existing methods on both datasets.
45
Chen, Chonghao, Jianming Zheng, and Honghui Chen. "Knowledge-Enhanced Graph Attention Network for Fact Verification." Mathematics 9, no. 16 (August 15, 2021): 1949. http://dx.doi.org/10.3390/math9161949.
Full textAbstract:
Fact verification aims to evaluate the authenticity of a given claim based on the evidence sentences retrieved from Wikipedia articles. Existing works mainly leverage the natural language inference methods to model the semantic interaction of claim and evidence, or further employ the graph structure to capture the relation features between multiple evidences. However, previous methods have limited representation ability in encoding complicated units of claim and evidences, and thus cannot support sophisticated reasoning. In addition, a limited amount of supervisory signals lead to the graph encoder could not distinguish the distinctions of different graph structures and weaken the encoding ability. To address the above issues, we propose a Knowledge-Enhanced Graph Attention network (KEGA) for fact verification, which introduces a knowledge integration module to enhance the representation of claims and evidences by incorporating external knowledge. Moreover, KEGA leverages an auxiliary loss based on contrastive learning to fine-tune the graph attention encoder and learn the discriminative features for the evidence graph. Comprehensive experiments conducted on FEVER, a large-scale benchmark dataset for fact verification, demonstrate the superiority of our proposal in both the multi-evidences and single-evidence scenarios. In addition, our findings show that the background knowledge for words can effectively improve the model performance.
46
Wieczorek, Kinga, and Jacek Osek. "Genetic diversity of Campylobacter jejuni isolated from the poultry food chain." Journal of Veterinary Research 63, no. 1 (March 1, 2019): 35–40. http://dx.doi.org/10.2478/jvetres-2019-0012.
Full textAbstract:
AbstractIntroduction:Campylobacter jejuniis one of the most frequently reported causes of foodborne bacterial enteric disease worldwide. The main source of these microorganisms is contaminated food, especially of poultry origin. There are several molecular methods for differentiation ofCampylobacterisolates at the subgenus level, and one of these isporA-typing based on the sequencing of the major outer-membrane protein (MOMP) encoding gene. The aim of the study was to test the molecular relationship ofC. jejunistrains isolated at different points along the poultry food chain and assess the population structure of the isolates.Material and Methods:A total of 451C. jejuniwere used in the study, and a DNA fragment of 630 bp of the MOMP encoding gene was amplified and sequenced.Results:One hundred and ten sequence types were identified, with 69 (62.7%) unique to the isolates' origin and 30 not present in the database. The most prevalent nucleotide variant 1 was detected in 37 (8.2%) strains. These isolates were identified in all poultry sources tested, especially in faeces (15 isolates) but also in poultry carcasses and meat (11 isolates in each).Conclusion:TheporAtyping method was highly discriminative forC. jejuniof poultry origin since the Simpson's diversity index (D) achieved a value of 0.876, indicating considerable diversity in the bacterial population tested. The method may be further used for epidemiological investigation purposes.
47
Mingote, Victoria, Antonio Miguel, Alfonso Ortega, and Eduardo Lleida. "Supervector Extraction for Encoding Speaker and Phrase Information with Neural Networks for Text-Dependent Speaker Verification." Applied Sciences 9, no. 16 (August 11, 2019): 3295. http://dx.doi.org/10.3390/app9163295.
Full textAbstract:
In this paper, we propose a new differentiable neural network with an alignment mechanism for text-dependent speaker verification. Unlike previous works, we do not extract the embedding of an utterance from the global average pooling of the temporal dimension. Our system replaces this reduction mechanism by a phonetic phrase alignment model to keep the temporal structure of each phrase since the phonetic information is relevant in the verification task. Moreover, we can apply a convolutional neural network as front-end, and, thanks to the alignment process being differentiable, we can train the network to produce a supervector for each utterance that will be discriminative to the speaker and the phrase simultaneously. This choice has the advantage that the supervector encodes the phrase and speaker information providing good performance in text-dependent speaker verification tasks. The verification process is performed using a basic similarity metric. The new model using alignment to produce supervectors was evaluated on the RSR2015-Part I database, providing competitive results compared to similar size networks that make use of the global average pooling to extract embeddings. Furthermore, we also evaluated this proposal on the RSR2015-Part II. To our knowledge, this system achieves the best published results obtained on this second part.
48
Yang, Yang, Yurui Huang, Weili Guo, Baohua Xu, and Dingyin Xia. "Towards Global Video Scene Segmentation with Context-Aware Transformer." Proceedings of the AAAI Conference on Artificial Intelligence 37, no. 3 (June 26, 2023): 3206–13. http://dx.doi.org/10.1609/aaai.v37i3.25426.
Full textAbstract:
Videos such as movies or TV episodes usually need to divide the long storyline into cohesive units, i.e., scenes, to facilitate the understanding of video semantics. The key challenge lies in finding the boundaries of scenes by comprehensively considering the complex temporal structure and semantic information. To this end, we introduce a novel Context-Aware Transformer (CAT) with a self-supervised learning framework to learn high-quality shot representations, for generating well-bounded scenes. More specifically, we design the CAT with local-global self-attentions, which can effectively consider both the long-term and short-term context to improve the shot encoding. For training the CAT, we adopt the self-supervised learning schema. Firstly, we leverage shot-to-scene level pretext tasks to facilitate the pre-training with pseudo boundary, which guides CAT to learn the discriminative shot representations that maximize intra-scene similarity and inter-scene discrimination in an unsupervised manner. Then, we transfer contextual representations for fine-tuning the CAT with supervised data, which encourages CAT to accurately detect the boundary for scene segmentation. As a result, CAT is able to learn the context-aware shot representations and provides global guidance for scene segmentation. Our empirical analyses show that CAT can achieve state-of-the-art performance when conducting the scene segmentation task on the MovieNet dataset, e.g., offering 2.15 improvements on AP.
49
Liu, Yue, Wenxuan Tu, Sihang Zhou, Xinwang Liu, Linxuan Song, Xihong Yang, and En Zhu. "Deep Graph Clustering via Dual Correlation Reduction." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 7 (June 28, 2022): 7603–11. http://dx.doi.org/10.1609/aaai.v36i7.20726.
Full textAbstract:
Deep graph clustering, which aims to reveal the underlying graph structure and divide the nodes into different groups, has attracted intensive attention in recent years. However, we observe that, in the process of node encoding, existing methods suffer from representation collapse which tends to map all data into the same representation. Consequently, the discriminative capability of the node representation is limited, leading to unsatisfied clustering performance. To address this issue, we propose a novel self-supervised deep graph clustering method termed Dual Correlation Reduction Network (DCRN) by reducing information correlation in a dual manner. Specifically, in our method, we first design a siamese network to encode samples. Then by forcing the cross-view sample correlation matrix and cross-view feature correlation matrix to approximate two identity matrices, respectively, we reduce the information correlation in the dual-level, thus improving the discriminative capability of the resulting features. Moreover, in order to alleviate representation collapse caused by over-smoothing in GCN, we introduce a propagation regularization term to enable the network to gain long-distance information with the shallow network structure. Extensive experimental results on six benchmark datasets demonstrate the effectiveness of the proposed DCRN against the existing state-of-the-art methods. The code of DCRN is available at https://github.com/yueliu1999/DCRN and a collection (papers, codes and, datasets) of deep graph clustering is shared at https://github.com/yueliu1999/Awesome-Deep-Graph-Clustering on Github.
50
Danon, Dov, Moab Arar, Daniel Cohen-Or, and Ariel Shamir. "Image resizing by reconstruction from deep features." Computational Visual Media 7, no. 4 (April 27, 2021): 453–66. http://dx.doi.org/10.1007/s41095-021-0216-x.
Full textAbstract:
AbstractTraditional image resizing methods usually work in pixel space and use various saliency measures. The challenge is to adjust the image shape while trying to preserve important content. In this paper we perform image resizing in feature space using the deep layers of a neural network containing rich important semantic information. We directly adjust the image feature maps, extracted from a pre-trained classification network, and reconstruct the resized image using neural-network based optimization. This novel approach leverages the hierarchical encoding of the network, and in particular, the high-level discriminative power of its deeper layers, that can recognize semantic regions and objects, thereby allowing maintenance of their aspect ratios. Our use of reconstruction from deep features results in less noticeable artifacts than use of imagespace resizing operators. We evaluate our method on benchmarks, compare it to alternative approaches, and demonstrate its strengths on challenging images.