Set Of Distinctive Features Research Articles

Multiview Clustering via Unified and View-Specific Embeddings Learning.

Multiview clustering, which aims at using multiple distinct feature sets to boost clustering performance, has a wide range of applications. A subspace-based approach, a type of widely used methods, learns unified embedding from multiple sources of information and gives a relatively good performance. However, these methods usually ignore data similarity rankings; for example, example A may be more similar to B than C, and such similarity triplets may be more effective in revealing the data cluster structure. Motivated by recent embedding methods for modeling knowledge graph in natural-language processing, this paper proposes to mimic different views as different relations in a knowledge graph for unified and view-specific embedding learning. Moreover, in real applications, it happens so often that some views suffer from missing information, leading to incomplete multiview data. Under such a scenario, the performance of conventional multiview clustering degenerates notably, whereas the method we propose here can be naturally extended for incomplete multiview clustering, which enables full use of examples with incomplete feature sets for model promotion. Finally, we demonstrate through extensive experiments that our method performs better than the state-of-the-art clustering methods.

SIP-FS: a novel feature selection for data representation

Multiple features are widely used to characterize real-world datasets. It is desirable to select leading features with stability and interpretability from a set of distinct features for a comprehensive data description. However, most of existing feature selection methods focus on the predictability (e.g., prediction accuracy) of selected results yet neglect stability. To obtain compact data representation, a novel feature selection method is proposed to improve stability, and interpretability without sacrificing predictability (SIP-FS). Instead of mutual information, generalized correlation is adopted in minimal redundancy maximal relevance to measure the relation between different feature types. Several feature types (each contains a certain number of features) can then be selected and evaluated quantitatively to determine what types contribute to a specific class, thereby enhancing the so-called interpretability of features. Moreover, stability is introduced in the criterion of SIP-FS to obtain consistent results of ranking. We conduct experiments on three publicly available datasets using one-versus-all strategy to select class-specific features. The experiments illustrate that SIP-FS achieves significant performance improvements in terms of stability and interpretability with desirable prediction accuracy and indicates advantages over several state-of-the-art approaches.

Regularized multi-view least squares twin support vector machines

Regularized least squares twin support vector machines are a new nonparallel hyperplane classifier, which can lead to simple and fast algorithms for generating binary classifiers by replacing inequality constraints with equality constraints and implementing the structural risk minimization principle in twin support vector machines. Multi-view learning is an emerging direction in machine learning which aims to exploit distinct views to improve generalization performance from multiple distinct feature sets. Experimental results demonstrate that our proposed methods are effective.

Myeloid-derived suppressor cells coming of age.

Myeloid-derived suppressor cells (MDSCs) are a heterogeneous population of cells generated during a large array of pathologic conditions ranging from cancer to obesity. These cells represent a pathologic state of activation of monocytes and relatively immature neutrophils. MDSCs are characterized by a distinct set of genomic and biochemical features, and can, on the basis of recent findings, be distinguished by specific surface molecules. The salient feature of these cells is their ability to inhibit T cell function and thus contribute to the pathogenesis of various diseases. In this Review, we discuss the origin and nature of these cells; their distinctive features; and their biological roles in cancer, infectious diseases, autoimmunity, obesity and pregnancy.

Multi-view CSPMPR-ELM feature learning and classifying for RGB-D object recognition

In order to fully utilize potential feature information of RGB-D images, current popular algorithms mainly use convolutional neural network (CNN) to execute both feature extraction and classification. Such methods could achieve impressive results but usually on the basis of an extremely huge and complex network. What’s more, since the fully connected layers in CNN form a classical neural network classifier, which is trained by gradient descent-based implementations, the generalization ability is limited and sub-optimal. To address these problems, this paper introduce a multi-view CNN-SPMP-RNN-ELM (MCSPMPR-ELM) model for RGB-D object recognition, which combines the power of MCSPMPR and fast training of ELM. It uses the MCSPMPR algorithm to extract discriminative features from raw RGB images and depth images separately. Then the abstracted features are fed to a nonlinear ELM classifier, which leads to better generalization performance with faster learning speed. At last, co-training is employed to learn from the unlabeled data using the two distinct feature sets by semi-supervised learning method. Experimental results on widely used RGB-D object datasets show that our method achieves competitive performance compared with other state-of-the-art algorithms specifically designed for RGB-D data.

Biometric authentication system based on texture features of retinal images

In biometric authentication system, distinct set of characteristic features are used to identify an authorised person. Retina is a stable biometric feature because of its location and unique physiological characteristics. In this paper, we propose a texture feature-based retinal authentication system. Texture features are considered as important features for authentication purpose. These texture features of retina are extracted using local configuration pattern (LCP) and Radon transform technique. The LCP computes the local structural information as well as the microscopic information of the image. Using Radon transform on retinal images, Radon features are extracted which contains the texture information of the blood vessels. A feature vector is formed by combining all theses LCP and Radon features and then fed to a feed-forward artificial neural network (FANN) classifier. This stage checks whether the test image belongs to the authorised person or not. Three general retinal databases DRIVE, HRF, Messidor, and images collected from two local eye hospitals are considered to authenticate a person. Two retinal authentication databases RIDB and VARIA are also used for evaluating the performance of the system. The results obtained show that the system is effective and efficient in authenticating the individuals.

Biometric authentication system based on texture features of retinal images

In biometric authentication system, distinct set of characteristic features are used to identify an authorised person. Retina is a stable biometric feature because of its location and unique physiological characteristics. In this paper, we propose a texture feature-based retinal authentication system. Texture features are considered as important features for authentication purpose. These texture features of retina are extracted using local configuration pattern (LCP) and Radon transform technique. The LCP computes the local structural information as well as the microscopic information of the image. Using Radon transform on retinal images, Radon features are extracted which contains the texture information of the blood vessels. A feature vector is formed by combining all theses LCP and Radon features and then fed to a feed-forward artificial neural network (FANN) classifier. This stage checks whether the test image belongs to the authorised person or not. Three general retinal databases DRIVE, HRF, Messidor, and images collected from two local eye hospitals are considered to authenticate a person. Two retinal authentication databases RIDB and VARIA are also used for evaluating the performance of the system. The results obtained show that the system is effective and efficient in authenticating the individuals.

ОСОБЛИВОСТІ АНТИКОРУПЦІЙНОЇ ЕКСПЕРТИЗИ ЯК ПРАВОВОГО ЗАСОБУ З ПРОТИДІЇ КОРУПЦІЇ В УКРАЇНІ

The scientific research offered to the general public is devoted to the issues of determining the features of anti-corruption expertise as a means of combating corruption. Also, in addition to the completeness and comprehensiveness of the content of the scientific publication, attention is focused on a number of other relevant and noteworthy aspects within the outlined issues. The common views of scientists regarding the understanding of the definitions of "expertise" and "anti-corruption expertise" are studied and analyzed. In order to avoid potential inconsistencies in attempts to formulate the conceptual and categorical apparatus, the relevant provisions of domestic legislation relating to the analyzed area of relations (Laws of Ukraine "On Principles of Prevention and Counteraction to Corruption" of 11.06.2009 No 1506-VI, "On Principles of Prevention and Counteraction of Corruption" dated 07.04.2011 No 3206-VI and "On Prevention of Corruption" dated 14.10.2014 No 1700-VII, "On Forensic Examination" dated 25.02.1994 No 4038-XII, orders of the Ministry of Justice of Ukraine "On approval of the Methodology for conducting anti-corruption expertise" dated 24.04.2017 No 1395/5, National Agency for Prevention of Corruption "On approval of the Methodology for conducting anti-corruption examination by the National Agency for Prevention of Corruption" dated 20.10.2020 No 470/20 and others documents). Based on the results of the research, the author's vision of the features of anti-corruption expertise is proposed. It is noted that this term, like all concepts, has its own characteristic distinctive set of features. The signs of anti-corruption expertise are determined, namely: 1) normative-legal regulation; 2) special purpose; 3) own tasks; 4) a specialized network of inspecting entities; 5) specific objects of inspection; 6) focused on minimizing corruption at the initial (embryonic) stages. An understanding of the purpose, tasks, subjects and objects of anti-corruption expertise is offered. Other debatable aspects are considered, which have significance and semantic load from the point of view of completeness and comprehensiveness of research of anti-corruption expertise in Ukraine.

Robust face recognition via hierarchical collaborative representation

Collaborative representation-based classification (CRC) is currently attracting the attention of researchers because it is more effective than conventional representation-based classifiers in recognition tasks. CRC has shown high face recognition accuracy; however, its accuracy is degraded significantly if the number of training faces in each class is small. This is because the accuracy of CRC is only dependent on the results of minimizing the Euclidean distance between a testing face and its approximator in the collaborative subspace of training faces. In this research, we proved that the accuracy of CRC can be improved substantially by minimizing not only the Euclidean distance between a testing face and its approximator but also the Euclidean distances from the approximator to training faces in each class. Consequently, we presented a hierarchical collaborative representation-based classification (HCRC) in which a two-stage classifier is applied for training faces, and the recognition accuracy of the second-stage classifier is significantly improved in comparison to that of the first-stage classifier. Moreover, the recognition rate of our classifier can be considerably increased by using models of discriminative feature extraction. Since noise and illumination are the main factors that cause CRC to be less accurate, we propose combining HCRC with a wide model of local ternary patterns (LTP). This combination enhances the efficiency of face recognition under different illumination and noisy conditions. For dealing with face recognition under variations in pose, expression and illumination, we present a deep convolutional neural network (DCNN) model of discriminative feature learning, which transforms face images into a common set of distinct features. The combination of HCRC with this deep model achieves high recognition rates on challenging face databases. Furthermore both models are optimized to reduce computational costs so that they can be successfully applied for real-world applications of face recognition that are required to run reliably in real time. In addition, we also prove that combining state-of-the-art DCNN models with HCRC results in an significant improvement in face recognition performance. We demonstrate several experiments with challenging face recognition datasets. Our results show that the hierarchical collaborative representation-based classifier with the models significantly outperforms state-of-the-art methods.

Learning Midlevel Auditory Codes from Natural Sound Statistics.

Interaction with the world requires an organism to transform sensory signals into representations in which behaviorally meaningful properties of the environment are made explicit. These representations are derived through cascades of neuronal processing stages in which neurons at each stage recode the output of preceding stages. Explanations of sensory coding may thus involve understanding how low-level patterns are combined into more complex structures. To gain insight into such midlevel representations for sound, we designed a hierarchical generative model of natural sounds that learns combinations of spectrotemporal features from natural stimulus statistics. In the first layer, the model forms a sparse convolutional code of spectrograms using a dictionary of learned spectrotemporal kernels. To generalize from specific kernel activation patterns, the second layer encodes patterns of time-varying magnitude of multiple first-layer coefficients. When trained on corpora of speech and environmental sounds, some second-layer units learned to group similar spectrotemporal features. Others instantiate opponency between distinct sets of features. Such groupings might be instantiated by neurons in the auditory cortex, providing a hypothesis for midlevel neuronal computation.

Novel Feature Set Based on Bayesian Approach for Circuit Breaker Fault Detection

Smart grid is developing rapidly with the promotion of artificial intelligence (AI) technology, and online condition assessment of circuit breaker (CB), as one of the most important facility in power system, is increasingly requested. Owing to most of CB faults can be reflected on its coil current (CC), lots of papers research on the relationship between CC data and CB fault. This paper proposed a new method to get distinctive CC feature set, which achieves better data distinction and has more practical physical meaning. The classification experiments based on the new feature set show that the proposed method can quickly and accurately recognize fault, meanwhile point out the malfunctioning device.

Dynamics of Governance in IS Outsourced ERP Implementation : Case-based Exploratory Study

New paradigm has been emerging in a way firms utilizing information and communication technology (I & CT) and corresponding business process innovation in order to maintain firms’ competitive advantage since early 90’s. Those are said to be Enterprise Resource Planning (ERP) system and Business Process Reengineering (BPR) or Process Innovation (PI). In contrast to traditional methodology for developing in-house corporate information system (CIS), there need to develop new breed of methodology for ERP implementation for two reasons. One is distinctive set of features of ERP system; and, the other is the way and governance structure of working in ERP implementation. Regarding the governance structure, firms tend to work with consulting firms for ERP implementation since it is on its early stage in lifecycle. There has been a log of studies done in ERP implementation. Most of the previous studies concerned about implementation methodology and implementation impacts on firm’s performance and competitiveness. As firms used to work with outsourced consulting firm for their ERP implementation, there has been a few studies how to effectively and efficiently work with outsourced firm in ERP implementation. In our study, we borrowed Huber, Fisher, Dibbern and Hirschheim’s (2013-2014) process model and applied the model in ERP implementation. Firstly, we matched the three adaptation triggers along with ERP implementation process. Secondly, we observed the dynamics of governance types during the implementation process. Lastly, we proposed adaptation outcomes focusing on the ERP implementation process by exploring a well-known Korea company in its ERP implementation.

Melanotic MiT family translocation neoplasms: Expanding the clinical and molecular spectrum of this unique entity of tumors

MiT family translocation tumors are a group of neoplasms characterized by translocations involving MiT family transcription factors. The translocation renal cell carcinomas, TFE3 (Xp11.2) and TFEB (t6;11) are known members of this family. Melanotic Xp11 translocation renal cancer is a more recently described entity. To date only 14 cases have been described. It is characterized by a distinct set of features including a nested epithelioid morphology, melanin pigmentation, labeling for markers of melanocytic differentiation, lack of labeling for markers of renal tubular differentiation, predominance in a younger age population and association with aggressive clinical behavior. There are noted similarities between that entity and TFE3 associated PEComas. There are no cases reported of equivalent melanotic TFEB translocation renal cancer. We report 2 rare cases of melanotic translocation renal neoplasms. The first is a melanotic TFE3 translocation renal cancer with an indolent clinical course, occurring in a patient more than 3-decades older than the usual average age in which such tumors have been described. The other case is, to our knowledge, the first reported melanotic TFEB translocation cancer of the kidney. Both cases exhibit the same H&E morphology as previously reported in melanotic translocation renal cancers and label accordingly with HMB45 and Melan-A. While the TFE3 melanotic tumor lacked any evidence of renal tubular differentiation, the TFEB melanotic cancer exhibited some staining for renal tubular markers. Based on the unique features noted above, these two cases expand the clinical and molecular spectrum of the melanotic translocation renal cancers.

Analysis of phonocardiogram signals through proactive denoising using novel self-discriminant learner.

Phonocardiogram (PCG) records heart sound and murmurs, which contains significant information of cardiac health. Analysis of PCG signal has the potential to detect abnormal cardiac condition. However, the presence of noise and motion artifacts in PCG hinders the accuracy of clinical event detection. Thus, noise detection and elimination are crucial to ensure accurate clinical analysis. In this paper, we present a robust denoising technique, Proclean that precisely detects the noisy PCG signal through pattern recognition, and statistical learning. We propose a novel self-discriminant learner that ensures to obtain distinct feature set to distinguish clean and noisy PCG signals without human-in-loop. We demonstrate that our proposed denoising leads to higher accuracy in subsequent clinical analytics for medical investigation. Our extensive experimentations with publicly available MIT-Physionet datasets show that we achieve more than 85% accuracy for noisy PCG signal detection. Further, we establish that physiological abnormality detection improves by more than 20%, when our proposed denoising mechanism is applied.

The feature-weighted receptive field: an interpretable encoding model for complex feature spaces

We introduce the feature-weighted receptive field (fwRF), an encoding model designed to balance expressiveness, interpretability and scalability. The fwRF is organized around the notion of a feature map—a transformation of visual stimuli into visual features that preserves the topology of visual space (but not necessarily the native resolution of the stimulus). The key assumption of the fwRF model is that activity in each voxel encodes variation in a spatially localized region across multiple feature maps. This region is fixed for all feature maps; however, the contribution of each feature map to voxel activity is weighted. Thus, the model has two separable sets of parameters: “where” parameters that characterize the location and extent of pooling over visual features, and “what” parameters that characterize tuning to visual features. The “where” parameters are analogous to classical receptive fields, while “what” parameters are analogous to classical tuning functions. By treating these as separable parameters, the fwRF model complexity is independent of the resolution of the underlying feature maps. This makes it possible to estimate models with thousands of high-resolution feature maps from relatively small amounts of data. Once a fwRF model has been estimated from data, spatial pooling and feature tuning can be read-off directly with no (or very little) additional post-processing or in-silico experimentation.We describe an optimization algorithm for estimating fwRF models from data acquired during standard visual neuroimaging experiments. We then demonstrate the model’s application to two distinct sets of features: Gabor wavelets and features supplied by a deep convolutional neural network. We show that when Gabor feature maps are used, the fwRF model recovers receptive fields and spatial frequency tuning functions consistent with known organizational principles of the visual cortex. We also show that a fwRF model can be used to regress entire deep convolutional networks against brain activity. The ability to use whole networks in a single encoding model yields state-of-the-art prediction accuracy. Our results suggest a wide variety of uses for the feature-weighted receptive field model, from retinotopic mapping with natural scenes, to regressing the activities of whole deep neural networks onto measured brain activity.

Developmental changes in the critical information used for facial expression processing

Facial expression recognition skills are known to improve across childhood and adolescence, but the mechanisms driving the development of these important social abilities remain unclear. This study investigates directly whether there are qualitative differences in child and adult processing strategies for these emotional stimuli. With a novel adaptation of the Bubbles reverse-correlation paradigm (Gosselin & Schyns, 2001), we added noise to expressive face stimuli and presented sub-sets of randomly sampled information from each image at different locations and spatial frequency bands across experimental trials. Results from our large developmental sample: 71 young children (6 –9years), 69 older children (10–13years) and 54 adults, uniquely reveal profiles of strategic information-use for categorisations of fear, sadness, happiness and anger at all ages. All three groups relied upon a distinct set of key facial features for each of these expressions, with fine-tuning of this diagnostic information (features and spatial frequency) observed across developmental time. Reported variability in the developmental trajectories for different emotional expressions is consistent with the notion of functional links between the refinement of information-use and processing ability.

Analyzing the Adoption and Cascading Process of OSN-Based Gifting Applications

To achieve growth in the user base of online social networks--(OSN) based applications, word-of-mouth diffusion mechanisms, such as user-to-user invitations, are widely used. This article characterizes the adoption and cascading process of OSN-based applications that grow via user invitations. We analyze a detailed large-scale dataset of a popular Facebook gifting application, iHeart, that contains more than 2 billion entries of user activities generated by 190 million users during a span of 64 weeks. We investigate (1) how users invite their friends to an OSN-based application, (2) how application adoption of an individual user can be predicted, (3) what factors drive the cascading process of application adoptions, and (4) what are the good predictors of the ultimate cascade sizes. We find that sending or receiving a large number of invitations does not necessarily help to recruit new users to iHeart. We also find that the average success ratio of inviters is the most important feature in predicting an adoption of an individual user, which indicates that the effectiveness of inviters has strong predictive power with respect to application adoption. Based on the lessons learned from our analyses, we build and evaluate learning-based models to predict whether a user will adopt iHeart. Our proposed model that utilizes additional activity information of individual users from other similar types of gifting applications can achieve high precision (83%) in predicting adoptions in the target application (i.e., iHeart). We next identify a set of distinctive features that are good predictors of the growth of the application adoptions in terms of final population size. We finally propose a prediction model to infer whether a cascade of application adoption will continue to grow in the future based on observing the initial adoption process. Results show that our proposed model can achieve high precision (over 80%) in predicting large cascades of application adoptions. We believe our work can give an important implication in resource allocation of OSN-based product stakeholders, for example, via targeted marketing.

Comparing six pixel-wise classifiers for tropical rural land cover mapping using four forms of fully polarimetric SAR data

ABSTRACTThis study evaluates four commonly used forms of synthetic aperture radar (SAR) data for land-cover classification in tropical rural areas. The backscatter coefficient of linearly polarized L-band SAR was compared to two distinctive feature sets derived from Eigen-based and model-based decompositions. The performance of six classifiers available in Orfeo Toolbox (OTB), that is, Bayes, artificial neural networks (ANNs), Support Vector Machine (SVM), decision trees, Random Forests (RFs), and gradient boosting trees (GBTs), was investigated to distinguish five and seven land-cover classes, with particular attention given to several types of woody vegetation: forest, mixed garden, rubber, oil palm, and tea plantations. Classifiers reacted differently to ingested forms of SAR data, and careless use of data input yielded a negative impact. The results showed that SVM provided the highest overall accuracy although the performance was not significantly better than the others. Tuning the parameters, however, significantly improved the accuracy of ANN and SVM, while RF and GBT did not respond well. Responses of two SVM parameters (cost and kernel type) fluctuated somewhat, which required further attention. ANN accuracy was improved when the number of neurons in the hidden layer was set between 10 and 12. We found that accuracy imbalance existed between designated land-cover classes, especially in woody vegetation. Imbalance can partially be reduced by tuning specific classifiers. We showed that classifier tuning can lead to significantly improved accuracy, especially for classes having medium or low accuracies. This research also demonstrated that freely available toolkits such as OTB and QGIS can be beneficial for mapping activities in developing countries, achieving a reasonable accuracy if the classification parameters are tuned properly.

Polycyclic Aromatic Hydrocarbons in Protoplanetary Disks around Herbig Ae/Be and T Tauri Stars

Abstract A distinct set of broad emission features at 3.3, 6.2, 7.7, 8.6, 11.3, and 12.7 μm, is often detected in protoplanetary disks (PPDs). These features are commonly attributed to polycyclic aromatic hydrocarbons (PAHs). We model these emission features in the infrared spectra of 69 PPDs around 14 T Tauri and 55 Herbig Ae/Be stars in terms of astronomical PAHs. For each PPD, we derive the size distribution and the charge state of the PAHs. We then examine the correlations of the PAH properties (i.e., sizes and ionization fractions) with the stellar properties (e.g., stellar effective temperature, luminosity, and mass). We find that the characteristic size of the PAHs tends to correlate with the stellar effective temperature ( ) and interpret this as the preferential photodissociation of small PAHs in systems with higher of which the stellar photons are more energetic. In addition, the PAH size shows a moderate correlation with the red-ward wavelength shift of the 7.7 μm PAH feature that is commonly observed in disks around cool stars. The ionization fraction of PAHs does not seem to correlate with any stellar parameters. This is because the charging of PAHs depends on not only the stellar properties (e.g., , luminosity) but also their spatial distribution in the disks. The marginally negative correlation between PAH size and stellar age suggests that continuous replenishment of PAHs via the outgassing of cometary bodies and/or the collisional grinding of planetesimals and asteroids is required to maintain the abundance of small PAHs against complete destruction by photodissociation.

“Subject-predicate predicate sentences” in modern Mandarin Chinese: A Cardiff Grammar approach

AbstractThis study investigates “subject-predicate predicate sentences” (“S-P P sentences”) in modern Mandarin Chinese from a Cardiff Grammar approach with the aim of answering three main questions: (i) What is/are the functional syntactic structure(s) of the sentences to be considered in the study? (ii) What is/are the semantic motivation(s) for the structure(s)? (iii) What is/are the contextual constraints on the structure(s)? The study is guided by three basic principles: (a) language is multifunctional; (b) meaning is primary while form is the realization of meaning; and (c) different strands of meaning are realized by a single syntactic structure. Further, the study utilizes the concepts of Theme and Subject within the Cardiff Grammar in order to analyze and discuss the generally acknowledged seven types of “S-P P sentences”. The results show that only one type is truly S-P P and another type only in one sense, whereas no other types can be categorized as such. All the syntactic structures are conditioned by a different set of distinctive semantic features and contextual factors.