Original Class Research Articles

A semi-supervised resampling method for class-imbalanced learning

Clustering analysis is widely used as a pre-process to discover the data distribution for resampling. Existing clustering-based resampling methods mostly run unsupervised clustering on labeled data without taking advantage of the class information to guide the clustering. When there are not enough labeled data, the clustering can hardly capture the underlying data distribution. In this paper, we propose a semi-supervised hybrid resampling (SSHR) method which runs semi-supervised clustering to capture the data distribution for both over-sampling and under-sampling. Firstly, we design a semi-supervised hierarchical clustering algorithm (SSHC) which uses labeled data to guide the clustering procedure on the whole dataset. Specifically, labeled data are used to initialize a clustering model and then guide its updating via an iterative cluster-splitting process. In this way, original classes are divided into multiple disjunct clusters, which contributes o disclosing not only the inter-class imbalance but also the intra-class imbalance. Subsequently, a hybrid resampling is performed according to the result of SSHC Labeled data of the majority class are under-sampled according to the distances to their cluster centroids and the adjacency to minority cluster centroids. Furthermore, we propose a novel over-sampling approach which selects some confident unlabeled data in minority clusters as pseudo-labeled data to enlarge the training set Compared with traditional over-sampling methods, our approach contributes to discovering more about the distribution of the minority class. In order to validate the effectiveness of SSHR, we conduct extensive experiments on 44 benchmark datasets. Our method achieves the best performances in terms of both F-measure and AUC. The Friedman test demonstrates that SSHR significantly outperforms the compared state-of-the-art resampling algorithms.

Privacy protection for 3D point cloud classification based on an optical chaotic encryption scheme.

In allusion to the privacy and security problems in 3D point cloud classification, a novel privacy protection method for 3D point cloud classification based on optical chaotic encryption scheme is proposed and implemented in this paper for the first time. The mutually coupled spin-polarized vertical-cavity surface-emitting lasers (MC-SPVCSELs) subject to double optical feedback (DOF) are studied to generate optical chaos for permutation and diffusion encryption process of 3D point cloud. The nonlinear dynamics and complexity results demonstrate that the MC-SPVCSELs with DOF have high chaotic complexity and can provide tremendously large key space. All the test-sets of ModelNet40 dataset containing 40 object categories are encrypted and decrypted by the proposed scheme, and then the classification results of 40 object categories for original, encrypted, and decrypted 3D point cloud are entirely enumerated through the PointNet++. Intriguingly, the class accuracies of the encrypted point cloud are nearly all equal to 0.0000% except for the plant class with 100.0000%, indicating the encrypted point cloud cannot be classified and identified. The decryption class accuracies are very close to the original class accuracies. Therefore, the classification results verify that the proposed privacy protection scheme is practically feasible and remarkably effective. Additionally, the encryption and decryption results show that the encrypted point cloud images are ambiguous and unrecognizable, while the decrypted point cloud images are identical to original images. Moreover, this paper improves the security analysis via analyzing 3D point cloud geometric features. Eventually, various security analysis results validate that the proposed privacy protection scheme has high security level and good privacy protection effect for 3D point cloud classification.

Lipopolysaccharide biosynthesis and traffic in the envelope of the pathogen Brucella abortus

Lipopolysaccharide is essential for most Gram-negative bacteria as it is a main component of the outer membrane. In the pathogen Brucella abortus, smooth lipopolysaccharide containing the O-antigen is required for virulence. Being part of the Rhizobiales, Brucella spp. display unipolar growth and lipopolysaccharide was shown to be incorporated at the active growth sites, i.e. the new pole and the division site. By localizing proteins involved in the lipopolysaccharide transport across the cell envelope, from the inner to the outer membrane, we show that the lipopolysaccharide incorporation sites are determined by the inner membrane complex of the lipopolysaccharide transport system. Moreover, we identify the main O-antigen ligase of Brucella spp. involved in smooth lipopolysaccharide synthesis. Altogether, our data highlight a layer of spatiotemporal organization of the lipopolysaccharide biosynthesis pathway and identify an original class of bifunctional O-antigen ligases.

Explaining the black-box smoothly-A counterfactual approach.

We propose a BlackBox Counterfactual Explainer, designed to explain image classification models for medical applications. Classical approaches (e.g.,, saliency maps) that assess feature importance do not explain how imaging features in important anatomical regions are relevant to the classification decision. Such reasoning is crucial for transparent decision-making in healthcare applications. Our framework explains the decision for a target class by gradually exaggerating the semantic effect of the class in a query image. We adopted a Generative Adversarial Network (GAN) to generate a progressive set of perturbations to a query image, such that the classification decision changes from its original class to its negation. Our proposed loss function preserves essential details (e.g.,support devices) in the generated images. We used counterfactual explanations from our framework to audit a classifier trained on a chest X-ray dataset with multiple labels. Clinical evaluation of model explanations is a challenging task. We proposed clinically-relevant quantitative metrics such as cardiothoracic ratio and the score of a healthy costophrenic recess to evaluate our explanations. We used these metrics to quantify the counterfactual changes between the populations with negative and positive decisions for a diagnosis by the given classifier. We conducted a human-grounded experiment with diagnostic radiology residents to compare different styles of explanations (no explanation, saliency map, cycleGAN explanation, and our counterfactual explanation) by evaluating different aspects of explanations: (1) understandability, (2) classifier's decision justification, (3) visual quality, (d) identity preservation, and (5) overall helpfulness of an explanation to the users. Our results show that our counterfactual explanation was the only explanation method that significantly improved the users' understanding of the classifier's decision compared to the no-explanation baseline. Our metrics established a benchmark for evaluating model explanation methods in medical images. Our explanations revealed that the classifier relied on clinically relevant radiographic features for its diagnostic decisions, thus making its decision-making process more transparent to the end-user.

Classes of trivial ring extensions and amalgamations subject to pseudo-almost valuation condition

Abstract This paper studies the transfer of pseudo-almost valuation property (PAVR property for short) to various context of commutative ring extensions such as power series ring, trivial ring extension and amalgamation. Our work is motivated by an attempt to generate new original classes of rings satisfying this property. The obtained results are backed with new and illustrative examples arising as trivial ring extensions, amalgamations and pullback constructions.

A theoretical distribution analysis of synthetic minority oversampling technique (SMOTE) for imbalanced learning

Class imbalance occurs when the class distribution is not equal. Namely, one class is under-represented (minority class), and the other class has significantly more samples in the data (majority class). The class imbalance problem is prevalent in many real world applications. Generally, the under-represented minority class is the class of interest. The synthetic minority over-sampling technique (SMOTE) method is considered the most prominent method for handling unbalanced data. The SMOTE method generates new synthetic data patterns by performing linear interpolation between minority class samples and their K nearest neighbors. However, the SMOTE generated patterns do not necessarily conform to the original minority class distribution. This paper develops a novel theoretical analysis of the SMOTE method by deriving the probability distribution of the SMOTE generated samples. To the best of our knowledge, this is the first work deriving a mathematical formulation for the SMOTE patterns’ probability distribution. This allows us to compare the density of the generated samples with the true underlying class-conditional density, in order to assess how representative the generated samples are. The derived formula is verified by computing it on a number of densities versus densities computed and estimated empirically.

Encrypting Hashing Against Localization

Hashing for localization (HfL) is an effective method for fast localizing specific scenes in a large-scale remote sensing image. Key to its efficiency arises from a comprehensive deep hashing network that generates representational binary hash codes for image patches cropped from the remote sensing image. On the other hand, this paper will investigate the problem of encrypting the remote sensing image against the HfL task. We refer to the new task as encrypting hashing against localization (EHaL). We characterize the EHaL task in term of two cues: (I) An encrypted image patch is supposed to appear as visually similar to its original image patch as possible; (II) The hash code generated by the deep hashing network for the encrypted image patch is supposed to be not close to its original class but close to a different class. Following the two cues, we develop an encrypted patch generator, which is trained in an adversarial fashion. Based on the encrypted patch generator, we propose two remote sensing image encryption frameworks that can cause non-localization and mis-localization to the HfL task separately. Experiments validates the effectiveness of our method. Reproducible executions are given at https://github.com/JingpengHan/EHaL.

Toward Fine-grained Image Retrieval with Adaptive Deep Learning for Cultural Heritage Image

Fine-grained image classification is a challenging research topic because of the high degree of similarity among categories and the high degree of dissimilarity for a specific category caused by different poses and scales. A cultural heritage image is one of the fine-grained images because each image has the same similarity in most cases. Using the classification technique, distinguishing cultural heritage architecture may be difficult. This study proposes a cultural heritage content retrieval method using adaptive deep learning for fine-grained image retrieval. The key contribution of this research was the creation of a retrieval model that could handle incremental streams of new categories while maintaining its past performance in old categories and not losing the old categorization of a cultural heritage image. The goal of the proposed method is to perform a retrieval task for classes. Incremental learning for new classes was conducted to reduce the re-training process. In this step, the original class is not necessary for re-training which we call an adaptive deep learning technique. Cultural heritage in the case of Thai archaeological site architecture was retrieved through machine learning and image processing. We analyze the experimental results of incremental learning for fine-grained images with images of Thai archaeological site architecture from world heritage provinces in Thailand, which have a similar architecture. Using a fine-grained image retrieval technique for this group of cultural heritage images in a database can solve the problem of a high degree of similarity among categories and a high degree of dissimilarity for a specific category. The proposed method for retrieving the correct image from a database can deliver an average accuracy of 85 percent. Adaptive deep learning for fine-grained image retrieval was used to retrieve cultural heritage content, and it outperformed state-of-the-art methods in fine-grained image retrieval.

Supporting change management of UML class diagrams

Class diagram is an important model in object-oriented software development. A class diagram specifies the structure of a system with the system's classes, classes’ attributes and methods, and relations among classes. Sometimes class diagrams should be modified in accordance with requirements changes or correction of errors. In such a modification, careless mistakes may lead to include another error in the diagram. In this paper, we propose a method of visualization of the difference between original class diagram and modified one by emphasizing the difference in order to avoid newly produced errors. We illustrate our method with examples.

건강장애아동의 기본권 보호를 위한 대안연구

Traditionally, expanding the infrastructure to guarantee children’s health right has been under the national responsibility. In addition, how to protect the learning right of children hospitalized for a long time, like paediatric cancer patients, has been recognized as a national project in the educational continuity dimension where the education of children should not stop due to external environments, in order for children’s growth ad development. Hospital school is an educational institution in hospital for the children with health impairments(the students who need to be hospitalized for more than three months due to their chronic diseases, or continue to need medical support like outpatient treatment, and thereby have difficulty with school life and learning). In accordance with ｢Act on Special Education for Persons with Disabilities｣, it is defined as a special school under Office of Education, or a dispatch class of general school(special class). In order to guarantee the learning right of children with health impairments, who should have compulsory education, it is required to recognize the operation of hospital school as an essential national project. Nevertheless, whether to open a hospital school depends on a hospital’s policy, and dispatching a special education teacher to a hospital school relies on the educational finance of a local government. There is a possibility that the children are able to set the required number of school days through distance education in hospital and to complete their curriculum. However, face-to-face class in hospital school makes it possible to provide the individual guidance through interaction with children, which is impossible in distance education, and to serve as the preparation process to return to their original classes after discharge. From the standpoint of child students, it is a very important way to guarantee their learning right. Opening and closing a hospital school should not be determined according to the current hospital policy. Instead, it is required to legislate on hospital school as an essential institution secured for treatment and education at the time when a hospital with a certain wards is open or when a medical institution for children is designated. In accordance with ｢Act on Special Education for Persons with Disabilities｣, an educational institution is classified into a special educational institution(special school and special class) and a special education support center. In the current system, such institutions like hospital school where education is provided in a separate space of medical institution have no classification. From the standpoint of school institutions, hospital school is the class of itinerant education, but is an institution in hospital. For this reason, it is necessary to consider the safety and operation criteria of both hospital and educational institution. To do that, there are limitations in following the system in accordance with ｢Act on Special Education for Persons with Disabilities｣. Hospital school is highly likely to be the subject of co-management in association with the Ministry of Health and Welfare and the Ministry of Education. Given the speciality of practical control, it is effective to enact separate legislation. In Germany, a law related to county schools lays the foundation for hospital schools, and detailed standards are separately set forth in legal orders. Given that, maintaining the provision about itinerant education in ｢Act on Special Education for Persons with Disabilities｣ and enacting a law about the operation of hospital school, etc. will become a long-term alternative from the perspective of management and supervision.

Benzo[c][1,2]thiazine‐Based Analogs in the Inverse Electron Demand [4+2] Hetero Diels‐Alder Reaction with Glycals: Access to Tetracyclic Fused Galactose and Fucose Derivatives

AbstractThe synthesis and reactivity in an [4+2] inverse electron demand hetero Diels‐Alder reaction (ihDA) of an original class of electron‐poor heterodienes, the N‐substituted‐1H‐benzo[c][1,2]thiazin‐4‐one‐2,2‐dioxides, are described. These are highly reactive electrophiles that allow easy access to unprecedented benzo‐thiazine glyco‐fused derivatives in a remarkably selective way, even when using acetylated glycals, previously unexplored within this version of ihDA. DFT calculations support the experimental data, and moreover show that acetylated dienophiles can easily react making cycloadditions feasible.

2N labeling defense method against adversarial attacks by filtering and extended class label set

The fast improvement of deep learning methods resulted in breakthroughs in image classification, however, these models are sensitive to adversarial perturbations, which can cause serious problems. Adversarial attacks try to change the model output by adding noise to the input, in our research we propose a combined defense method against it. Two defense approaches have been evolved in the literature, one robustizes the attacked model for higher accuracy, and the other approach detects the adversarial examples. Only very few papers discuss both approaches, thus our aim was to combine them to obtain a more robust model and to examine the combination, in particular the filtering capability of the detector. Our contribution was that the filtering based on the decision of the detector is able to enhance the accuracy, which was theoretically proved. Besides that, we developed a novel defense method called 2N labeling, where we extended the idea of the NULL labeling method. While the NULL labeling suggests only one new class for the adversarial examples, the 2N labeling method suggests twice as much. The novelty of our idea is that a new extended class is assigned to each original class, as the adversarial version of it, thus it assists the detector and robust classifier as well. The 2N labeling method was compared to competitor methods on two test datasets. The results presented that our method surpassed the others, and it can operate with a constant classification performance regardless of the presence or amplitude of adversarial attacks.

Fault Detection for Wind Turbine Blade Bolts Based on GSG Combined with CS-LightGBM.

Aiming at the problem of class imbalance in the wind turbine blade bolts operation-monitoring dataset, a fault detection method for wind turbine blade bolts based on Gaussian Mixture Model–Synthetic Minority Oversampling Technique–Gaussian Mixture Model (GSG) combined with Cost-Sensitive LightGBM (CS-LightGBM) was proposed. Since it is difficult to obtain the fault samples of blade bolts, the GSG oversampling method was constructed to increase the fault samples in the blade bolt dataset. The method obtains the optimal number of clusters through the BIC criterion, and uses the GMM based on the optimal number of clusters to optimally cluster the fault samples in the blade bolt dataset. According to the density distribution of fault samples in inter-clusters, we synthesized new fault samples using SMOTE in an intra-cluster. This retains the distribution characteristics of the original fault class samples. Then, we used the GMM with the same initial cluster center to cluster the fault class samples that were added to new samples, and removed the synthetic fault class samples that were not clustered into the corresponding clusters. Finally, the synthetic data training set was used to train the CS-LightGBM fault detection model. Additionally, the hyperparameters of CS-LightGBM were optimized by the Bayesian optimization algorithm to obtain the optimal CS-LightGBM fault detection model. The experimental results show that compared with six models including SMOTE-LightGBM, CS-LightGBM, K-means-SMOTE-LightGBM, etc., the proposed fault detection model is superior to the other comparison methods in the false alarm rate, missing alarm rate and F1-score index. The method can well realize the fault detection of large wind turbine blade bolts.

Positive-gradient-weighted object activation mapping: visual explanation of object detector towards precise colorectal-polyp localisation.

Precise polyp detection and localisation are essential for colonoscopy diagnosis. Statistical machine learning with a large-scale data set can contribute to the construction of a computer-aided diagnosis system for the prevention of overlooking and miss-localisation of a polyp in colonoscopy. We propose new visual explaining methods for a well-trained object detector, which achieves fast and accurate polyp detection with a bounding box towards a precise automated polyp localisation. We refine gradient-weighted class activation mapping for more accurate highlighting of important patterns in processing a convolutional neural network. Extending the refined mapping into multiscaled processing, we define object activation mapping that highlights important object patterns in an image for a detection task. Finally, we define polyp activation mapping to achieve precise polyp localisation by integrating adaptive local thresholding into object activation mapping. We experimentally evaluate the proposed visual explaining methods with four publicly available databases. The refined mapping visualises important patterns in each convolutional layer more accurately than the original gradient-weighted class activation mapping. The object activation mapping clearly visualises important patterns in colonoscopic images for polyp detection. The polyp activation mapping localises the detected polyps in ETIS-Larib, CVC-Clinic and Kvasir-SEG database with mean Dice scores of 0.76, 0.72 and 0.72, respectively. We developed new visual explaining methods for a convolutional neural network by refining and extending gradient-weighted class activation mapping. Experimental results demonstrated the validity of the proposed methods by showing that accurate visualisation of important patterns and localisation of polyps in a colonoscopic image. The proposed visual explaining methods are useful for the interpreting and applying a trained polyp detector.

Improving EEG Decoding via Clustering-Based Multitask Feature Learning.

Accurate electroencephalogram (EEG) pattern decoding for specific mental tasks is one of the key steps for the development of brain-computer interface (BCI), which is quite challenging due to the considerably low signal-to-noise ratio of EEG collected at the brain scalp. Machine learning provides a promising technique to optimize EEG patterns toward better decoding accuracy. However, existing algorithms do not effectively explore the underlying data structure capturing the true EEG sample distribution and, hence, can only yield a suboptimal decoding accuracy. To uncover the intrinsic distribution structure of EEG data, we propose a clustering-based multitask feature learning algorithm for improved EEG pattern decoding. Specifically, we perform affinity propagation-based clustering to explore the subclasses (i.e., clusters) in each of the original classes and then assign each subclass a unique label based on a one-versus-all encoding strategy. With the encoded label matrix, we devise a novel multitask learning algorithm by exploiting the subclass relationship to jointly optimize the EEG pattern features from the uncovered subclasses. We then train a linear support vector machine with the optimized features for EEG pattern decoding. Extensive experimental studies are conducted on three EEG data sets to validate the effectiveness of our algorithm in comparison with other state-of-the-art approaches. The improved experimental results demonstrate the outstanding superiority of our algorithm, suggesting its prominent performance for EEG pattern decoding in BCI applications.

A GAN-based hybrid sampling method for imbalanced customer classification

Class imbalance is a critical issue in customer classification, for which a plethora of techniques have been proposed in the current body of literature. In particular, generative adversarial network (GAN)-based oversampling can capture the true data distribution of minority class samples and generate new samples, and this approach has demonstrated an outstanding ability to address class imbalance. However, GAN-based oversampling suffers from the issue of class overlap. As a result, in this work, we propose a novel a novel GAN-based hybrid sampling method. The new approach first uses GAN-based oversampling to generate the initial balanced dataset and then applies a novel adaptive neighborhood-based weighted undersampling method to remove generated instances and original majority class instances. This approach not only produces instances that fit the actual data distribution but also significantly reduces the influence of class overlap. Experimental results on artificial data and real-world customer datasets show that the proposed GAN-based hybrid sampling method has better performance than other benchmark methods with both accuracy-based and profit-based evaluation metrics.

Clustered Bayesian classification for within-class separation

The Bayesian classification is one of the frequently used approaches in machine learning. This approach obtains probabilities based on attributes of classes using Bayes' theorem and makes predictions according to these probabilities. Bayesian classifiers employ densities such as Gaussian, kernel, multivariate Gaussian, and Copula densities when attributes consist of continuous variables. These densities partially produce rough density values. When the attributes of any of the classes are concentrated on more than one region, above mentioned densities are not inherently suitable. In order to overcome this problem, this study introduces a novel approach called Clustered Bayesian classification. The proposed method creates a new class variable by detecting the different concentrations within the class using the Gaussian Mixture Clustering method. It makes predictions by setting a model over the new class variable. Then, the probabilities of the original classes are calculated over the probabilities of the new classes. The proposed method is compared with 5 different Bayesian classifiers on 27 different data sets. As a result, it has been seen that Clustered Bayesian classification outperformed all Bayesian classifiers for different performance metrics.

Class Incremental Learning With Few-Shots Based on Linear Programming for Hyperspectral Image Classification.

Hyperspectral imaging (HSI) classification has drawn tremendous attention in the field of Earth observation. In the big data era, explosive growth has occurred in the amount of data obtained by advanced remote sensors. Inevitably, new data classes and refined categories appear continuously, and such data are limited in terms of the timeliness of application. These characteristics motivate us to build an HSI classification model that learns new classifying capability rapidly within a few shots while maintaining good performance on the original classes. To achieve this goal, we propose a linear programming incremental learning classifier (LPILC) that can enable existing deep learning classification models to adapt to new datasets. Specifically, the LPILC learns the new ability by taking advantage of the well-trained classification model within one shot of the new class without any original class data. The entire process requires minimal new class data, computational resources, and time, thereby making LPILC a suitable tool for some time-sensitive applications. Moreover, we utilize the proposed LPILC to implement fine-grained classification via the well-trained original coarse-grained classification model. We demonstrate the success of LPILC with extensive experiments based on three widely used hyperspectral datasets, namely, PaviaU, Indian Pines, and Salinas. The experimental results reveal that the proposed LPILC outperforms state-of-the-art methods under the same data access and computational resource. The LPILC can be integrated into any sophisticated classification model, thereby bringing new insights into incremental learning applied in HSI classification.

Permanence of equilibrium points in the basin of attraction and existence of periodic solutions for autonomous measure differential equations and dynamic equations on time scales via generalized ODEs

It is well-known that generalized ODEs encompass several types of differential equations as, for instance, functional differential equations, measure differential equations, dynamic equations on time scales, impulsive differential equations and any combinations among them, not to mention integrals equations, among others. The aim of this paper is to establish a theory of autonomous equations in the setting of generalized ODEs. Thus, we introduce the notion of autonomous generalized ODEs as well as new classes of right-hand sides for nonautonomous generalized ODEs. Amongst the main results, we prove that one of these new classes coincide with the original class of right-hand sides introduced by Kurzweil in 1957. We also prove that autonomous generalized ODEs do not enlarge the class of autonomous ODEs with uniformly continuous right-hand sides. Motivated by this fact, we then enlarge the class of autonomous generalized ODEs so that discontinuities can be taken into account. We then introduce a more general class of autonomous generalized ODEs, in whose integral form, a Stieltjes-type integral appears. A correspondence between these equations and autonomous measure differential equations is established and several results are obtained. We mention local existence and uniqueness of solutions, continuous dependence of solutions on initial values, existence of periodic solutions and permanence of asymptotically stable equilibrium point in the basin of attraction. All these results are, then, specified not only for autonomous generalized ODEs, but also for autonomous measure differential equations and dynamic equations on time scales.

Bayesian network-based over-sampling method (BOSME) with application to indirect cost-sensitive learning

Traditional supervised learning algorithms do not satisfactorily solve the classification problem on imbalanced data sets, since they tend to assign the majority class, to the detriment of the minority class classification. In this paper, we introduce the Bayesian network-based over-sampling method (BOSME), which is a new over-sampling methodology based on Bayesian networks. Over-sampling methods handle imbalanced data by generating synthetic minority instances, with the benefit that classifiers learned from a more balanced data set have a better ability to predict the minority class. What makes BOSME different is that it relies on a new approach, generating artificial instances of the minority class following the probability distribution of a Bayesian network that is learned from the original minority classes by likelihood maximization. We compare BOSME with the benchmark synthetic minority over-sampling technique (SMOTE) through a series of experiments in the context of indirect cost-sensitive learning, with some state-of-the-art classifiers and various data sets, showing statistical evidence in favor of BOSME, with respect to the expected (misclassification) cost.