Feature Space Mapping Research Articles

Embedded Zero-Shot Image Classification Based on Bidirectional Feature Mapping

The zero-shot image classification technique aims to explore the semantic information shared between seen and unseen classes through visual features and auxiliary information and, based on this semantic information, to complete the knowledge migration from seen to unseen classes in order to complete the classification of unseen class images. Previous zero-shot work has either not extracted enough features to express the relationship between the sample classes or has only used a single feature mapping method, which cannot fully explore the information contained in the features and the connection between the visual–semantic features. To address the above problems, this paper proposes an embedded zero-shot image classification model based on bidirectional feature mapping (BFM). It mainly contains a feature space mapping module, which is dominated by a bidirectional feature mapping network and supplemented with a mapping network from visual to category label semantic feature space. Attention mechanisms based on attribute guidance and visual guidance are further introduced to weight the features to reduce the difference between visual and semantic features to alleviate the modal difference problem, and then the category calibration loss is utilized to assign a larger weight to the unseen class to alleviate the seen class bias problem. The BFM model proposed in this paper has been experimented on three public datasets CUB, SUN, and AWA2, and has achieved 71.9%, 62.8%, and 69.3% and 61.6%, 33.2%, and 66.6% accuracies under traditional and generalized zero-sample image classification settings, respectively. The experimental results verify the superiority of the BFM model in the field of zero-shot image classification.

Pre-stack seismic inversion based on model-constrained generative adversarial network

Pre-stack seismic inversion usually uses various traditional algorithms to estimate elastic parameters such as P-wave velocity, S-wave velocity, and density. It is hard to derive accurate elastic parameters due to their non-uniqueness and high dimensionality between elastic parameters and seismic data, the calculation of elastic parameters is inaccurate. Convolutional Neural Networks (CNNs) have high-dimensional feature space mapping capabilities, which are utilized to establish mapping relationships between seismic data and elasticity parameters. However, their effectiveness is greatly affected by label data, and at the same time, due to the lack of enough label data, resulting in a low degree of fitting between prediction results and real data. In addition, conventional seismic inversion methods based on CNNs lack physical model constraints, resulting in low accuracy and poor interpretability of prediction results. We propose a Cycle-consistent Generative Adversarial Network based on a geophysical mechanism (SeisInv-CycleGAN). Deterministic inversion results and labeled data are combined into hybrid geophysical data as a training set of SeisInv-CycleGAN with geophysical constraints. At the same time, the residual (seismic loss) between the seismic data synthesized by forward modeling and the actual data is used as part of the loss function. The SeisInv-CycleGAN does not require building an initial model, and it can achieve higher accuracy in prediction results with a small amount of labeled data.

TF-IDF Vectorization and Clustering for Extractive Text Summarization

Extractive document summarization is a vital technique for condensing large volumes of text while retaining key information. This research introduces a dynamic feature space mapping approach to enhance extractive document summarization, aiming to succinctly encapsulate key information from extensive text volumes. The proposed method involves extracting various document properties like term frequency, sentence length, and position to comprehensively describe content. By employing a mapping function, these features are projected into a dynamic feature space, enhancing summarization efficiency and feature clarity. Clustering similar phrases in this space facilitates easier sentence grouping, aiding summary creation. Leveraging TF-IDF vectorization, the most representative phrases are chosen from each cluster based on importance and diversity. This process culminates in generating a high-quality document summary quickly and systematically. The dynamic mapping method streamlines sentence grouping, systematically capturing essential document attributes. This approach addresses challenges in extractive summarization, contributing significantly to automated text summarization. Its applicability spans domains requiring rapid extraction of information from vast textual data.

Improving the Efficiency of Automatic Cardiac Arrhythmias Classification by a Novel Patient-Specific Feature Space Mapping

Improving the Efficiency of Automatic Cardiac Arrhythmias Classification by a Novel Patient-Specific Feature Space Mapping

Adaptive active subspace-based metamodeling for high-dimensional reliability analysis

To address the challenges of reliability analysis in high-dimensional probability spaces, this paper proposes a new metamodeling method that couples active subspace, heteroscedastic Gaussian process, and active learning. The active subspace is leveraged to identify low-dimensional salient features of a high-dimensional computational model. A surrogate computational model is built in the low-dimensional feature space by a heteroscedastic Gaussian process. Active learning adaptively guides the surrogate model training toward the critical region that significantly contributes to the failure probability. A critical trait of the proposed method is that the three main ingredients–active subspace, heteroscedastic Gaussian process, and active learning–are coupled to adaptively optimize the feature space mapping in conjunction with the surrogate modeling. This coupling empowers the proposed method to accurately solve nontrivial high-dimensional reliability problems via low-dimensional surrogate modeling. Finally, numerical examples of a high-dimensional nonlinear function and structural engineering applications are investigated to verify the performance of the proposed method.

MIPA-ResGCN: a multi-input part attention enhanced residual graph convolutional framework for sign language recognition

Sign language (SL) is used as primary mode of communication by individuals who experience deafness and speech disorders. However, SL creates an inordinate communication barrier as most people are not acquainted with it. To solve this problem, many technological solutions using wearable devices, video, and depth cameras have been put forth. The ubiquitous nature of cameras in contemporary devices has resulted in the emergence of sign language recognition (SLR) using video sequence as a viable and unobtrusive substitute. Nonetheless, the utilization of SLR methods based on visual features, commonly known as appearance-based methods, presents notable computational complexities. In response to these challenges, this study introduces an accurate and computationally efficient pose-based approach for SLR. Our proposed approach comprises three key stages: pose extraction, handcrafted feature generation, and feature space mapping and recognition. Initially, an efficient off-the-shelf pose extraction algorithm is employed to extract pose information of various body parts of a subject captured in a video. Then, a multi-input stream has been generated using handcrafted features, i.e., joints, bone lengths, and bone angles. Finally, an efficient and lightweight residual graph convolutional network (ResGCN) along with a novel part attention mechanism, is proposed to encode body's spatial and temporal information in a compact feature space and recognize the signs performed. In addition to enabling effective learning during model training and offering cutting-edge accuracy, the proposed model significantly reduces computational complexity. Our proposed method is assessed on five challenging SL datasets, WLASL-100, WLASL-300, WLASL-1000, LSA-64, and MINDS-Libras, achieving state-of-the-art (SOTA) accuracies of 83.33 %, 72.90 %, 64.92 %, 100± 0 %, and 96.70± 1.07 %, respectively. Compared to previous approaches, we achieve superior performance while incurring a lower computational cost.

A New Lightweight Script Independent Scene Text Style Transfer Network

Scene text style transfer without a language barrier is an open challenge for the video and scene text recognition community because this plays a vital role in poster, web design, augmenting character images, and editing characters to improve scene text recognition performance and usability. This work presents a new model, called Script Independent Scene Text Style Transfer Network (SISTSTNet), for extracting scene characters and transferring text style simultaneously. The SISTSTNet performs mapping in language-independent feature space for transferring style. It is designed based on a Style Parameter Network and Target Encoder Network through lightweight MobileNetv3 convolutional and residual blocks to capture the style and shape to generate target characters. Similarly, a generative model is explored through the Visual Geometry Group (VGG) network for character replacement. The SISTSTNet is flexible and works on different languages and arbitrary examples in a neat and unified fashion. The experimental results on images in various languages, namely, English, Chinese, Hindi, Russian, Japanese, Arabic, Greek, and Bengali and cross-language validation demonstrate the effectiveness of the proposed method. The performance of the method is superior compared to the state-of-the-art methods in terms of quality measures, language independence, shape-preserving, and efficiency. The code and dataset will be released to the public to support reproducibility.

TESPDA-SEI: Tensor embedding substructure preserving domain adaptation for specific emitter identification

For the specific emitter identification (SEI) with few or no labels, domain adaptation make the model respond quickly with the help of empirical information. However, the more extreme case is that there are so few labeled samples in the source domain that it is difficult to train an excellent recognition model. In fact, it is more valuable to make full use of these limited label information. This work aims at proposing an unsupervised domain adaptation (UDA)-based method to accommodate the typical case of no labels in the target domain and small samples in the source domain when new devices are first introduced. The basic principle is to learn tensor embedding shared feature space and preserving inter-class substructure, which perform feature space mapping under the joint source and target domain led by mapping error minimize in the source domain. Specifically, this tensor embedding substructure preserving domain adaptation (TESPDA) consist of three parts, tensor invariant subspace learning, substructure preserving feature space mapping and pseudo-label prediction, which are used to learn inter-class substructure after tensor space mapping and identify the predict labels for the target domain. Finally, experiments are conducted on the real-word ADS-B dataset to demonstrate the effectiveness of the TESPDA method.

Hybridized model selection with Gifi system for categorical data using the genetic algorithm and information complexity

In the cross-disciplinary fields of social and behavioral sciences, biology, e-commerce, econometrics, medical data mining, and in engineering applications the available data are mostly composed of many categorical, continuous, and mixed data types with both categorical and continuous variables. Modeling such data structures creates many challenges and difficulties in terms of the underlying probability distributional assumptions to model. This paper proposes a novel categorical regression (CATREG) model using optimal scaling technique in Gifi system to resolve the current existing problem by transforming the categorical data to a continuous data and then performing the analysis of the data in the new transformed Gifi space. Such transformation preserves the scaling properties of the original variables without loss of any information and mapping is one-to-one and onto, unlike the kernel mapping in feature space in machine learning. We introduce a hybridized model selection via the information complexity (ICOMP) criterion along with the genetic algorithm (GA) in CATREG model and provide interpretable results. Two real numerical examples are provided to study the effects of the cell phone usage on the sleep patterns of individuals, and a second example is based on building a predictive model of e-commerce for new car market. In both of these numerical examples subset selection of the best predictor variables are determined to build an optimal predictive model. Our results show the efficiency and the versatility of the proposed new approach.

TripletGO: Integrating Transcript Expression Profiles with Protein Homology Inferences for Gene Function Prediction

Gene Ontology (GO) has been widely used to annotate functions of genes and gene products. Here, we proposed a new method, TripletGO, to deduce GO terms of protein-coding and non-coding genes, through the integration of four complementary pipelines built on transcript expression profile, genetic sequence alignment, protein sequence alignment, and naïve probability. TripletGO was tested on a large set of 5754 genes from 8 species (human, mouse, Arabidopsis, rat, fly, budding yeast, fission yeast, and nematoda) and 2433 proteins with available expression data from the third Critical Assessment of Protein Function Annotation challenge (CAFA3). Experimental results show that TripletGO achieves function annotation accuracy significantly beyond the current state-of-the-art approaches. Detailed analyses show that the major advantage of TripletGO lies in the coupling of a new triplet network-based profiling method with the feature space mapping technique, which can accurately recognize function patterns from transcript expression profiles. Meanwhile, the combination of multiple complementary models, especially those from transcript expression and protein-level alignments, improves the coverage and accuracy of the final GO annotation results. The standalone package and an online server of TripletGO are freely available at https://zhanggroup.org/TripletGO/.

Unsupervised adversarial domain adaptive for fault detection based on minimum domain spacing

The deep learning model has gradually matured in the detection of mechanical faults. However, due to the changes in the mechanical operating environment and the application of new sensors in real work, the effect of the training model is not ideal in field applications. The key of this problem is the deviation of feature space mapping between training source domain and application target domain. This paper proposes an unsupervised adversarial domain adaptive fault diagnosis transfer learning model based on the minimum domain spacing to reduce the deviation. In adversarial network training, by training the weight parameters of the classifier, some features extracted by the composed classifier are added to the feature distribution of the target domain through weight changes, which reduces the feature distribution difference between the source domain and the target domain. It is reflected on the reduction of the maximum mean difference distance (MMD) between the two domains, and the fitting features of the data distribution are improved. Finally, through two experimental platforms of rolling bearing and planetary gearbox dataset, the results of six diagnostic tasks show that the new model reduces the amount of parameters by 33.66% and keeps accuracy more than 99% compared with the DANN model under the condition.

Deep Learning Using Synthetic Seismic Data by Fourier Domain Adaptation in Seismic Structure Interpretation

Deep learning is a data-driven technique that demands network models trained using big datasets. In seismic structure interpretation, it is very difficult, time-consuming, and relatively economic costs to prepare training datasets by directly annotating real seismic data. Seismic convolution method is an efficient way to synthesize seismic data, which can easily and quickly generate large amount of training datasets. However, there are large differences in feature space between synthetic seismic data and real seismic data. That results in the poor performance of network models trained using synthetic training datasets on real seismic data. In this paper, we propose to use Fourier domain adaptation (FDA) to achieve domain transfer. First, amplitude spectrum of synthetic seismic data is replaced with those of real seismic data to make feature space mapping. Then synthetic seismic data is used for transfer training of network models to improve its performance on real seismic data. The experimental results demonstrate that the FDA performs the domain transfer of synthetic seismic data to real seismic data, which improves the generalization of network models trained based on synthetic seismic data. Meanwhile, the FDA is a promising method for deep learning model transfer training in seismic structure interpretation.

A Gait Energy Image-Based System for Brazilian Sign Language Recognition

Sign language is the main type of communication of the deaf community. However, most people do not know this language, which causes communication problems for many people. Many technological solutions have been proposed to overcome this issue. Some use the concept of wearable devices, but gesture recognition in a video sequence is a cheaper and less intrusive solution. In this work, we address the problem of gesture recognition in video. To do so, we employ a two-step method with feature space mapping and classification. First, the body parts of each subject in a video are segmented through a deep neural network architecture. Then, we use Gait Energy Image to encode the motion of the body parts in a compact feature space. Small datasets are usually a problem in this type of application, leading to sparse representation in the feature space. To contour this problem, we evaluate SMOTE as a data augmentation technique in the feature space and classical dimensionality reduction techniques. We evaluate our method on three challenging Brazilian sign language (Libras) datasets, CEFET/RJ-Libras, MINDS-Libras, and LIBRAS-UFOP, achieving global accuracies of 85.40±3.13%, 84.66±1.78%, and 64.91±3.79%, respectively, with <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">singular value decomposition</i> and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">support vector machine</i> .

Glaucoma Assessment from Fundus Images with Fundus to OCT Feature Space Mapping

Early detection and treatment of glaucoma is of interest as it is a chronic eye disease leading to an irreversible loss of vision. Existing automated systems rely largely on fundus images for assessment of glaucoma due to their fast acquisition and cost-effectiveness. Optical Coherence Tomographic ( OCT ) images provide vital and unambiguous information about nerve fiber loss and optic cup morphology, which are essential for disease assessment. However, the high cost of OCT is a deterrent for deployment in screening at large scale. In this article, we present a novel CAD solution wherein both OCT and fundus modality images are leveraged to learn a model that can perform a mapping of fundus to OCT feature space. We show how this model can be subsequently used to detect glaucoma given an image from only one modality (fundus). The proposed model has been validated extensively on four public andtwo private datasets. It attained an AUC/Sensitivity value of 0.9429/0.9044 on a diverse set of 568 images, which is superior to the figures obtained by a model that is trained only on fundus features. Cross-validation was also done on nearly 1,600 images drawn from a private (OD-centric) and a public (macula-centric) dataset and the proposed model was found to outperform the state-of-the-art method by 8% (public) to 18% (private). Thus, we conclude that fundus to OCT feature space mapping is an attractive option for glaucoma detection.

Multi-label text classification via joint learning from label embedding and label correlation

For the multi-label text classification problems with many classes, many existing multi-label classification algorithms become infeasible or suffer an unaffordable cost. Some researches hence perform the Label Space Dimension Reduction(LSDR) to solve this problem, but a number of methods ignore the sequence information of texts and the label correlation in the original label space, and treat the label as a meaningless multi-hot vector. In this paper, we put forward a multi-label text classification algorithm LELC(joint learning from Label Embedding and Label Correlation) based on the multi-layer attention and label correlation to solve the issue of multi-label text classification with a large number of class labels. Specifically, we firstly extract features through Bidirectional Gated Recurrent Unit Network(Bi-GRU), multi-layer attention and linear layers. Bi-GRU will capture the content information and sequence information of the text at the same time, and the attention mechanism can help us select the valid features related to labels. Then, we use matrix factorization to perform LSDR, and consider label correlation of the original label space in this process, which allows us to implicitly encode the latent space and simplify the model learning. Finally, Deep Canonical Correlation Analysis(CCA) technology is exploited to couple features and the latent space in an end-to-end pattern, so that these two can influence each other to learn the mapping of feature space to latent space. Experiments on 11 real-world datasets show the comparability between our proposed model and the state-of-the-art methods.

A Proposal of Quantum-Inspired Machine Learning for Medical Purposes: An Application Case

Learning tasks are implemented via mappings of the sampled data set, including both the classical and the quantum framework. Biomedical data characterizing complex diseases such as cancer typically require an algorithmic support for clinical decisions, especially for early stage tumors that typify breast cancer patients, which are still controllable in a therapeutic and surgical way. Our case study consists of the prediction during the pre-operative stage of lymph node metastasis in breast cancer patients resulting in a negative diagnosis after clinical and radiological exams. The classifier adopted to establish a baseline is characterized by the result invariance for the order permutation of the input features, and it exploits stratifications in the training procedure. The quantum one mimics support vector machine mapping in a high-dimensional feature space, yielded by encoding into qubits, while being characterized by complexity. Feature selection is exploited to study the performances associated with a low number of features, thus implemented in a feasible time. Wide variations in sensitivity and specificity are observed in the selected optimal classifiers during cross-validations for both classification system types, with an easier detection of negative or positive cases depending on the choice between the two training schemes. Clinical practice is still far from being reached, even if the flexible structure of quantum-inspired classifier circuits guarantees further developments to rule interactions among features: this preliminary study is solely intended to provide an overview of the particular tree tensor network scheme in a simplified version adopting just product states, as well as to introduce typical machine learning procedures consisting of feature selection and classifier performance evaluation.

An end-to-end graph convolutional kernel support vector machine

A novel kernel-based support vector machine (SVM) for graph classification is proposed. The SVM feature space mapping consists of a sequence of graph convolutional layers, which generates a vector space representation for each vertex, followed by a pooling layer which generates a reproducing kernel Hilbert space (RKHS) representation for the graph. The use of a RKHS offers the ability to implicitly operate in this space using a kernel function without the computational complexity of explicitly mapping into it. The proposed model is trained in a supervised end-to-end manner whereby the convolutional layers, the kernel function and SVM parameters are jointly optimized with respect to a regularized classification loss. This approach is distinct from existing kernel-based graph classification models which instead either use feature engineering or unsupervised learning to define the kernel function. Experimental results demonstrate that the proposed model outperforms existing deep learning baseline models on a number of datasets.

MaDeNet: Disentangling Individuality of EEG Signals through Feature Space Mapping and Detachment.

The cross-subject variability, or individuality, of electroencephalography (EEG) signals often has been an obstacle to extracting target-related information from EEG signals for classification of subjects' perceptual states. In this paper, we propose a deep learning-based EEG classification approach, which learns feature space mapping and performs individuality detachment to reduce subject-related information from EEG signals and maximize classification performance. Our experiment on EEG-based video classification shows that our method significantly improves the classification accuracy.

Extractive Document Summarization Based on Dynamic Feature Space Mapping

The exponential growth of the Web documents has constituted the need for automatic document summarization. In this context, extractive document summarization, i.e., that task of extracting the most relevant information, removing redundancy and presenting the remained data in a coherent and cohesive structure, is a challenging task. In this article, we propose a novel intelligent approach, namely ExDoS, that harvests benefits of both supervised and unsupervised algorithms simultaneously. To the best of our knowledge, ExDoS is the first approach to combine both supervised and unsupervised algorithms in a single framework and an interpretable manner for document summarization purpose. ExDoS iteratively minimizes the error rate of the classifier in each cluster with the help of dynamic local feature weighting. Moreover, this approach specifies the contribution of features to discriminate each class, which is a challenging issue in the summarization task. Therefore, in addition to summarizing text, ExDoS is also able to measure the importance of each feature in the summarization process. We evaluate our model both automatically (in terms of ROUGE factor) and empirically (human analysis) on the benchmark datasets: the DUC2002 and CNN/DailyMail. Results show that our model obtains higher ROUGE scores comparing to most state-of-the-art models. The human evaluation also demonstrates that our model is capable of generating informative and readable summaries.

A parallel computing-based Deep Attention model for named entity recognition

Named entity recognition (NER) is an important task in natural language processing and has been widely studied. In recent years, end-to-end NER with bidirectional long short-term memory (BiLSTM) has received more and more attention. However, it remains a major challenge for BiLSTM to parallel computing, long-range dependencies and single feature space mapping. We propose a deep neural network model which is based on parallel computing self-attention mechanism to address these problems. We only use a small number of BiLSTMs to capture the time series of texts and then make use of self-attention mechanism that allows parallel computing to capture long-range dependencies. Experiments on two NER datasets show that our model is superior in quality and takes less training time. Our model achieves an F1 score of 92.63% on the SIGHAN bakeoff 2006 MSRA portion for Chinese NER, improving over the existing best results by over 1.4%. On the CoNLL2003 shared task portion for English NER, our model achieves an F1 score of 92.17%, which outperforms the previous state-of-the-art results by 0.91%.