Showing papers on "Class (philosophy) published in 2023"

HiGCIN: Hierarchical Graph-based Cross Inference Network for Group Activity Recognition

Abstract: Group activity recognition (GAR) is a challenging task aimed at recognizing the behavior of a group of people. It is a complex inference process in which visual cues collected from individuals are integrated into the final prediction, being aware of the interaction between them. This paper goes one step further beyond the existing approaches by designing a Hierarchical Graph-based Cross Inference Network (HiGCIN), in which three levels of information, i.e., the body-region level, person level, and group-activity level, are constructed, learned, and inferred in an end-to-end manner. Primarily, we present a generic Cross Inference Block (CIB), which is able to concurrently capture the latent spatiotemporal dependencies among body regions and persons. Based on the CIB, two modules are designed to extract and refine features for group activities at each level. Experiments on two popular benchmarks verify the effectiveness of our approach, particularly in the ability to infer with multilevel visual cues. In addition, training our approach does not require individual action labels to be provided, which greatly reduces the amount of labor required in data annotation.

Fair Matching under Constraints: Theory and Applications

Abstract: This paper studies a general model of matching with constraints. Observing that a stable matching typically does not exist, we focus on feasible, individually rational, and fair matchings. We characterize such matchings by fixed points of a certain function. Building on this result, we characterize the class of constraints on individual schools under which there exists a student-optimal fair matching (SOFM), the matching that is the most preferred by every student among those satisfying the three desirable properties. We study the numerical relevance of our theory using data on government-organized daycare allocation.

A model with deep analysis on a large drug network for drug classification.

Abstract: Drugs are an important means to treat various diseases. They are classified into several classes to indicate their properties and effects. Those in the same class always share some important features. The Kyoto Encyclopedia of Genes and Genomes (KEGG) DRUG recently reported a new drug classification system that classifies drugs into 14 classes. Correct identification of the class for any possible drug-like compound is helpful to roughly determine its effects for a particular type of disease. Experiments could be conducted to confirm such latent effects, thus accelerating the procedures for discovering novel drugs. In this study, this classification system was investigated. A classification model was proposed to assign one of the classes in the system to any given drug for the first time. Different from traditional fingerprint features, which indicated essential drug properties alone and were very popular in investigating drug-related problems, drugs were represented by novel features derived from a large drug network via a well-known network embedding algorithm called Node2vec. These features abstracted the drug associations generated from their essential properties, and they could overview each drug with all drugs as background. As class sizes were of great differences, synthetic minority over-sampling technique (SMOTE) was employed to tackle the imbalance problem. A balanced dataset was fed into the support vector machine to build the model. The 10-fold cross-validation results suggested the excellent performance of the model. This model was also superior to models using other drug features, including those generated by another network embedding algorithm and fingerprint features. Furthermore, this model provided more balanced performance across all classes than that without SMOTE.

Rethinking Maximum Mean Discrepancy for Visual Domain Adaptation

Abstract: Existing domain adaptation approaches often try to reduce distribution difference between source and target domains and respect domain-specific discriminative structures by some distribution [e.g., maximum mean discrepancy (MMD)] and discriminative distances (e.g., intra-class and inter-class distances). However, they usually consider these losses together and trade off their relative importance by estimating parameters empirically. It is still under insufficient exploration so far to deeply study their relationships to each other so that we cannot manipulate them correctly and the model’s performance degrades. To this end, this article theoretically proves two essential facts: 1) minimizing MMD equals to jointly minimizing their data variance with some implicit weights but, respectively, maximizing the source and target intra-class distances so that feature discriminability degrades and 2) the relationship between intra-class and inter-class distances is as one falls and another rises. Based on this, we propose a novel discriminative MMD with two parallel strategies to correctly restrain the degradation of feature discriminability or the expansion of intra-class distance; specifically: 1) we directly impose a tradeoff parameter on the intra-class distance that is implicit in the MMD according to 1) and 2) we reformulate the inter-class distance with special weights that are analogical to those implicit ones in the MMD and maximizing it can also lead to the intra-class distance falling according to 2). Notably, we do not consider the two strategies in one model due to 2). The experiments on several benchmark datasets not only prove the validity of our revealed theoretical results but also demonstrate that the proposed approach could perform better than some compared state-of-art methods substantially. Our preliminary MATLAB code will be available at https://github.com/WWLoveTransfer/ .

Identifying Malignant Breast Ultrasound Images Using ViT-Patch

Abstract: Recently, the Vision Transformer (ViT) model has been used for various computer vision tasks, due to its advantages to extracting long-range features. To better integrate the long-range features useful for classification, the standard ViT adds a class token, in addition to patch tokens. Despite state-of-the-art results on some traditional vision tasks, the ViT model typically requires large datasets for supervised training, and thus, it still face challenges in areas where it is difficult to build large datasets, such as medical image analysis. In the ViT model, only the output corresponding to the class token is fed to a Multi-Layer Perceptron (MLP) head for classification, and the outputs corresponding to the patch tokens are exposed. In this paper, we propose an improved ViT architecture (called ViT-Patch), which adds a shared MLP head to the output of each patch token to balance the feature learning on the class and patch tokens. In addition to the primary task, which uses the output of the class token to discriminate whether the image is malignant, a secondary task is introduced, which uses the output of each patch token to determine whether the patch overlaps with the tumor area. More interestingly, due to the correlation between the primary and secondary tasks, the supervisory information added to the patch tokens help with improving the performance of the primary task on the class token. The introduction of secondary supervision information also improves the attention interaction among the class and patch tokens. And by this way, ViT reduces the demand on dataset size. The proposed ViT-Patch is validated on a publicly available dataset, and the experimental results show its effectiveness for both malignant identification and tumor localization.

A Multi-Source Weighted Deep Transfer Network for Open-Set Fault Diagnosis of Rotary Machinery

Abstract: In real industries, there often exist application scenarios where the target domain holds fault categories never observed in the source domain, which is an open-set domain adaptation (DA) diagnosis issue. Existing DA diagnosis methods under the assumption of sharing identical label space across domains fail to work. What is more, labeled samples can be collected from different sources, where multisource information fusion is rarely considered. To handle this issue, a multisource open-set DA diagnosis approach is developed. Specifically, multisource domain data of different operation conditions sharing partial classes are adopted to take advantage of fault information. Then, an open-set DA network is constructed to mitigate the domain gap across domains. Finally, a weighting learning strategy is introduced to adaptively weigh the importance on feature distribution alignment between known class and unknown class samples. Extensive experiments suggest that the proposed approach can substantially boost the performance of open-set diagnosis issues and outperform existing diagnosis approaches.

Pengembangan modul ajar berbasis kurikulum merdeka pada materi bentuk aljabar di kelas vii smp negeri 13 medan

Abstract: This study aims to obtain teaching modules based on the independent curriculum on algebraic material in class VII SMP Negeri 13 Medan that are vali, practical, and effective. The type is research used in this study is Research and Development (R&D). The teaching module development process is oriented based on the ADDIE model. The subjects in this study were all students of class VII SMP Negeri 13 Medan (chosen one class out of five classes randomly). While the object of this study is teaching material in the form of teaching modules based on the independent curriculum on algebraic material. The research instruments used in this study were validation sheets, interview, questionnaires with validation data analysis techniques, practicality and effectiveness. Based on the results of expert validation, student response questionnaries, and student assessment results, it is known that independent curriculum-based teaching modules in algebraic form material meet the very valid criteria with a percentage of 85,93%, very practical with a percentage of 86,03%, and very effective based on the results of the completeness assessment of students with a percentage of 83,33%.

Cross-Domain Contrastive Learning for Unsupervised Domain Adaptation

Abstract: Unsupervised domain adaptation (UDA) aims to transfer knowledge learned from a fully-labeled source domain to a different unlabeled target domain. Most existing UDA methods learn domain-invariant feature representations by minimizing feature distances across domains. In this work, we build upon contrastive self-supervised learning to align features so as to reduce the domain discrepancy between training and testing sets. Exploring the same set of categories shared by both domains, we introduce a simple yet effective framework CDCL, for domain alignment. In particular, given an anchor image from one domain, we minimize its distances to cross-domain samples from the same class relative to those from different categories. Since target labels are unavailable, we use a clustering-based approach with carefully initialized centers to produce pseudo labels. In addition, we demonstrate that CDCL is a general framework and can be adapted to the data-free setting, where the source data are unavailable during training, with minimal modification. We conduct experiments on two widely used domain adaptation benchmarks, i.e., Office-31 and VisDA-2017, for image classification tasks, and demonstrate that CDCL achieves state-of-the-art performance on both datasets.

Feature and Subfeature Selection for Classification Using Correlation Coefficient and Fuzzy Model

Abstract: This article presents an analysis of data extraction for classification using correlation coefficient and fuzzy model. Several traditional methods of data extraction are used for classification that could not provide sufficient information for further step of data analysis on class. It needs refinement of features data to distinguish a class that differs from a traditional class. Thus, it proposes the feature tiny data (subfeature data) to find distinguish class from a traditional class using two methods such as correlation coefficient and fuzzy model to select features as well as subfeature for distinguishing class. In the first approach, the correlation coefficient methods with gradient descent technique are used to select features from the dataset and in the second approach, the fuzzy model with supreme of minimum value is considered to get subfeature data. As per the proposed model, some features (i.e., three features from the acoustic dataset, two features from the QCM dataset, and eight features from the audit dataset, etc.) and subfeatures (as per threshold value like 20 for acoustic; 10 for QCM, and 20 for audit, etc.) are selected based on correlation coefficient as well as fuzzy methods, respectively. Further, the probability approach is used to find the association and availability of subfeature data from the dimensional reduced database. The experimental results show the proposed framework identifies and selects both feature and subfeature data with the effectiveness of the new class. The comparison results of several classifiers on several datasets are explained in the experimental section.

Sampled-Data Consensus Protocols for a Class of Second-Order Switched Nonlinear Multiagent Systems

Abstract: In this study, the sampled-data consensus problem is investigated for a class of heterogeneous multiagent systems (MASs) in which each agent is described by a second-order switched nonlinear system. Owing to the heterogeneity and the occurrence of dynamic switching in the MASs, the sampled-data consensus protocol design problem is challenging. In this study, two periodic sampled-data consensus protocols and an event-triggered consensus protocol are developed. Here, we first propose a new periodic sampled-data consensus protocol that involves the local objective trajectory interaction among agents. The protocol is then improved by applying the finite-time control and sliding-mode control techniques. Notably, the improved protocol can be implemented without the transmission of constructed auxiliary dynamical variables, which is a major feature of the present study. It is shown that complete consensus of the underlying MASs can be achieved by the two proposed protocols with only sampled-data measurements. To further reduce the communication load, we introduce an event-triggered mechanism to obtain a new protocol. Finally, the effectiveness of the given schemes is demonstrated by considering a numerical example.

Hyers–Ulam stability for a class of Hadamard fractional Itô–Doob stochastic integral equations

Abstract: Our goal in this work is to demonstrate the existence and uniqueness of the solution to a class of Hadamard Fractional Itô–Doob Stochastic integral equations (HFIDSIE) of order φ∈(0,1) via the fixed point technique (FPT). Hyers–Ulam stability (HUS) is investigated for HFIDSIE according to the Gronwall inequality. Two theoretical examples are provided to illustrate our results.

Saliency Guided Inter- and Intra-Class Relation Constraints for Weakly Supervised Semantic Segmentation

Abstract: Weakly supervised semantic segmentation with only image-level labels aims to reduce annotation costs for the segmentation task. Existing approaches generally leverage class activation maps (CAMs) to locate the object regions for pseudo label generation. However, CAMs can only discover the most discriminative parts of objects, thus leading to inferior pixel-level pseudo labels. To address this issue, we propose a saliency guided Inter- and Intra-Class Relation Constrained (I²CRC) framework to assist the expansion of the activated object regions in CAMs. Specifically, we propose a saliency guided class-agnostic distance module to pull the intra-category features closer by aligning features to their class prototypes. Further, we propose a class-specific distance module to push the inter-class features apart and encourage the object region to have a higher activation than the background. Besides strengthening the capability of the classification network to activate more integral object regions in CAMs, we also introduce an object guided label refinement module to take a full use of both the segmentation prediction and the initial labels for obtaining superior pseudo-labels. Extensive experiments on PASCAL VOC 2012 and COCO datasets demonstrate well the effectiveness of I²CRC over other state-of-the-art counterparts.

A new construction of weightwise perfectly balanced Boolean functions

Abstract: In this paper, we first introduce a class of quartic Boolean functions. And then, the construction of weightwise perfectly balanced Boolean functions on $ 2^m $ variables are given by modifying the support of the quartic functions, where $ m $ is a positive integer. The algebraic degree, the weightwise nonlinearity, and the algebraic immunity of the newly constructed weightwise perfectly balanced functions are discussed at the end of this paper.

Semi-supervised bidirectional alignment for Remote Sensing cross-domain scene classification

Abstract: Remote sensing (RS) image scene classification has obtained increasing attention for its broad application prospects. Conventional fully-supervised approaches usually require a large amount of manually-labeled data. As more and more RS images becoming available, how to make full use of these unlabeled data is becoming an urgent topic. Semi-supervised learning, which uses a few labeled data to guide the self-training of numerous unlabeled data, is an intuitive strategy. However, it is hard to apply it to cross-dataset (i.e., cross-domain) scene classification due to the significant domain shift among different datasets. To this end, semi-supervised domain adaptation (SSDA), which can reduce the domain shift and further transfer knowledge from a fully-labeled RS scene dataset (source domain) to a limited-labeled RS scene dataset (target domain), would be a feasible solution. In this paper, we propose an SSDA method termed bidirectional sample-class alignment (BSCA) for RS cross-domain scene classification. BSCA consists of two alignment strategies, unsupervised alignment (UA) and supervised alignment (SA), both of which can contribute to decreasing domain shift. UA concentrates on reducing the distance of maximum mean discrepancy across domains, with no demand for class labels. In contrast, SA aims to achieve the distribution alignment both from source samples to the associate target class centers and from target samples to the associate source class centers, with awareness of their classes. To validate the effectiveness of the proposed method, extensive ablation, comparison, and visualization experiments are conducted on an RS-SSDA benchmark built upon four widely-used RS scene classification datasets. Experimental results indicate that in comparison with some state-of-the-art methods, our BSCA achieves the superior cross-domain classification performance with compact feature representation and low-entropy classification boundary. Our code will be available at https://github.com/hw2hwei/BSCA.

Why there is no need to use a big-M in linear bilevel optimization: a computational study of two ready-to-use approaches

Abstract: Abstract Linear bilevel optimization problems have gained increasing attention both in theory as well as in practical applications of Operations Research (OR) during the last years and decades. The latter is mainly due to the ability of this class of problems to model hierarchical decision processes. However, this ability makes bilevel problems also very hard to solve. Since no general-purpose solvers are available, a “best-practice” has developed in the applied OR community, in which not all people want to develop tailored algorithms but “just use” bilevel optimization as a modeling tool for practice. This best-practice is the big- M reformulation of the Karush–Kuhn–Tucker (KKT) conditions of the lower-level problem—an approach that has been shown to be highly problematic by Pineda and Morales (2019). Choosing invalid values for M yields solutions that may be arbitrarily bad. Checking the validity of the big- M s is however shown to be as hard as solving the original bilevel problem in Kleinert et al. (2019). Nevertheless, due to its appealing simplicity, especially w.r.t. the required implementation effort, this ready-to-use approach still is the most popular method. Until now, there has been a lack of approaches that are competitive both in terms of implementation effort and computational cost. In this note we demonstrate that there is indeed another competitive ready-to-use approach: If the SOS-1 technique is applied to the KKT complementarity conditions, adding the simple additional root-node inequality developed by Kleinert et al. (2020) leads to a competitive performance—without having all the possible theoretical disadvantages of the big- M approach.

Coarse-to-Fine: Progressive Knowledge Transfer-Based Multitask Convolutional Neural Network for Intelligent Large-Scale Fault Diagnosis

Abstract: In modern industry, large-scale fault diagnosis of complex systems is emerging and becoming increasingly important. Most deep learning-based methods perform well on small number of fault diagnosis, but cannot converge to satisfactory results when handling large-scale fault diagnosis because the huge number of fault types will lead to the problems of intra/inter-class distance unbalance and poor local minima in neural networks. To address the above problems, a progressive knowledge transfer-based multitask convolutional neural network (PKT-MCNN) is proposed. First, to construct the coarse-to-fine knowledge structure intelligently, a structure learning algorithm is proposed via clustering fault types in different coarse-grained nodes. Thus, the intra/inter-class distance unbalance problem can be mitigated by spreading similar tasks into different nodes. Then, an MCNN architecture is designed to learn the coarse and fine-grained task simultaneously and extract more general fault information, thereby pushing the algorithm away from poor local minima. Last but not least, a PKT algorithm is proposed, which can not only transfer the coarse-grained knowledge to the fine-grained task and further alleviate the intra/inter-class distance unbalance in feature space, but also regulate different learning stages by adjusting the attention weight to each task progressively. To verify the effectiveness of the proposed method, a dataset of a nuclear power system with 66 fault types was collected and analyzed. The results demonstrate that the proposed method can be a promising tool for large-scale fault diagnosis.

Getting Dynamic Implementation to Work

Abstract: We develop a new class of two-stage mechanisms, which fully implement any social choice function under initial rationalizability in complete information environments. We show theoretically that our simultaneous report (SR) mechanisms are robust to small amounts of incomplete information about the state of nature. We also highlight the robustness of the mechanisms to a wide variety of reasoning processes and behavioral assumptions. We show experimentally that an SR mechanism performs well in inducing truth telling in both complete and incomplete information environments and that it can induce efficient investment in a two-sided holdup problem with ex ante investment.

What I know, what I want to know, what I learned: Activating EFL college students' cognitive, behavioral, and emotional engagement through structured feedback in an online environment

Abstract: Given the spread of the COVID-19 pandemic, online classes have received special attention worldwide. Since teachers have a lasting effect on the students, the teacher–student relationship is a pivotal factor in language learning classes. Students will not be engaged in class activities if they are not sufficiently challenged by them or if they do not find them interesting, especially in online classes. From this point of view, motivating, engaging, and testing techniques in online classes are highly important. The present study attempts to demonstrate a correlation between structured feedback and three types of engagement in an online class: cognitive, behavioral, and emotional engagement. The structured feedback, which is used at the end of each lesson lets the students express what they know, what they want to know, and what they learned. The sample of the study consists of 114 EFL third-year college students. The study's findings reveal positive and significant correlations between the three types of engagement; cognitive, behavioral, and emotional, and the use of structured feedback in online classes. In a nutshell, some academic implications and recommendations are provided.

Applying game-based learning to a primary school class in computer science terminology learning

Abstract: Introduction Game-based learning is an innovative technique that utilizes the educational potential of videogames in general, and serious games in particular, to enhance training processes and make it simpler for users to attain motivated learning. Methods In this study, we propose game based learning for primary school students in computer science terminology learning. Primary school students often engage in game-based learning. Academic accomplishment motivation consequences have been researched extensively. The purpose of this research was to see how successful Game-Based Learnings are in motivating primary school kids to attain academic success. Fifty primary school students in two focus groups participated in the experiment during 10 weeks to test the involvement of game based learning to pupils. Results There are two kind of measurements were applied in identifying benefits of game based learning. First, one is the questionnaire that students answered to questions in three categories as Impression, Usability, and User Interface. Second part of measurement is downloading and uploading of hometasks, and their academic performance. Approximately 90% of the students found the game based learning to be beneficial in their studies and remembering computer science terminologies. The children were satisfied with its functionality and ease of use. Discussion The results can be useful for educators, instructional and game designers, and researchers from implementation, design and research perspectives.

S3C: Self-Supervised Stochastic Classifiers for Few-Shot Class-Incremental Learning

Abstract: Few-shot class-incremental learning (FSCIL) aims to learn progressively about new classes with very few labeled samples, without forgetting the knowledge of already learnt classes. FSCIL suffers from two major challenges: (i) over-fitting on the new classes due to limited amount of data, (ii) catastrophically forgetting about the old classes due to unavailability of data from these classes in the incremental stages. In this work, we propose a self-supervised stochastic classifier (S3C) (code: https://github.com/JAYATEJAK/S3C ) to counter both these challenges in FSCIL. The stochasticity of the classifier weights (or class prototypes) not only mitigates the adverse effect of absence of large number of samples of the new classes, but also the absence of samples from previously learnt classes during the incremental steps. This is complemented by the self-supervision component, which helps to learn features from the base classes which generalize well to unseen classes that are encountered in future, thus reducing catastrophic forgetting. Extensive evaluation on three benchmark datasets using multiple evaluation metrics show the effectiveness of the proposed framework. We also experiment on two additional realistic scenarios of FSCIL, namely where the number of annotated data available for each of the new classes can be different, and also where the number of base classes is much lesser, and show that the proposed S3C performs significantly better than the state-of-the-art for all these challenging scenarios .

Active Learning With Complementary Sampling for Instructing Class-Biased Multi-Label Text Emotion Classification

Abstract: High-quality corpora have been very scarce for the text emotion research. Existing corpora with multi-label emotion annotations have been either too small or too class-biased to properly support a supervised emotion learning. In this article, we propose a novel active learning method for efficiently instructing the human annotations for a less-biased and high-quality multi-label emotion corpus. Specifically, to compensate annotation for the minority-class examples, we propose a complementary sampling strategy based on unlabeled resources by measuring a probabilistic distance between the expected emotion label distribution in a temporary corpus and an uniform distribution. Qualitative evaluations are also given to the unlabeled examples, in which we evaluate the model uncertainties for multi-label emotion predictions, their syntactic representativeness for the other unlabeled examples, and their diverseness to the labeled examples, for a high-quality sampling. Through active learning, a supervised emotion classifier gets progressively improved by learning from these new examples. Experiment results suggest that by following these sampling strategies we can develop a corpus of high-quality examples with significantly relieved bias for emotion classes. Compared to the learning procedures based on traditional active learning algorithms, our learning procedure indicates the most efficient learning curve and estimates the best multi-label emotion predictions.

A Novel Framework for Generalizations of Soft Open Sets and Its Applications via Soft Topologies

Abstract: Soft topological spaces (STSs) have received a lot of attention recently, and numerous soft topological ideas have been created from differing viewpoints. Herein, we put forth a new class of generalizations of soft open sets called “weakly soft semi-open subsets” following an approach inspired by the components of a soft set. This approach opens the door to reformulating the existing soft topological concepts and examining their behaviors. First, we deliberate the main structural properties of this class and detect its relationships with the previous generalizations with the assistance of suitable counterexamples. In addition, we probe some features that are obtained under some specific stipulations and elucidate the properties of the forgoing generalizations that are missing in this class. Next, we initiate the interior and closure operators with respect to the classes of weakly soft semi-open and weakly soft semi-closed subsets and look at some of their fundamental characteristics. Ultimately, we pursue the concept of weakly soft semi-continuity and furnish some of its descriptions. By a counterexample, we elaborate that some characterizations of soft continuous functions are invalid for weakly soft semi-continuous functions.

Multi-Label Sentiment Analysis on 100 Languages With Dynamic Weighting for Label Imbalance

Abstract: We investigate cross-lingual sentiment analysis, which has attracted significant attention due to its applications in various areas including market research, politics and social sciences. In particular, we introduce a sentiment analysis framework in multi-label setting as it obeys Plutchik wheel of emotions. We introduce a novel dynamic weighting method that balances the contribution from each class during training, unlike previous static weighting methods that assign non-changing weights based on their class frequency. Moreover, we adapt the focal loss that favors harder instances from single-label object recognition literature to our multi-label setting. Furthermore, we derive a method to choose optimal class-specific thresholds that maximize the macro-f1 score in linear time complexity. Through an extensive set of experiments, we show that our method obtains the state-of-the-art performance in 7 of 9 metrics in 3 different languages using a single model compared to the common baselines and the best-performing methods in the SemEval competition. We publicly share our code for our model, which can perform sentiment analysis in 100 languages, to facilitate further research.

An SEQAIHR model to study COVID-19 transmission and optimal control strategies in Hong Kong, 2022

Abstract: During the COVID-19 pandemic, one of the major concerns was a medical emergency in human society. Therefore it was necessary to control or restrict the disease spreading among populations in any fruitful way at that time. To frame out a proper policy for controlling COVID-19 spreading with limited medical facilities, here we propose an SEQAIHR model having saturated treatment. We check biological feasibility of model solutions and compute the basic reproduction number ( $$R_0$$ ). Moreover, the model exhibits transcritical, backward bifurcation and forward bifurcation with hysteresis with respect to different parameters under some restrictions. Further to validate the model, we fit it with real COVID-19 infected data of Hong Kong from 19th December, 2021 to 3rd April, 2022 and estimate model parameters. Applying sensitivity analysis, we find out the most sensitive parameters that have an effect on $$R_0$$ . We estimate $$R_0$$ using actual initial growth data of COVID-19 and calculate effective reproduction number for same period. Finally, an optimal control problem has been proposed considering effective vaccination and saturated treatment for hospitalized class to decrease density of the infected class and to minimize implemented cost.

A Comparison of Undersampling, Oversampling, and SMOTE Methods for Dealing with Imbalanced Classification in Educational Data Mining

Abstract: Educational data mining is capable of producing useful data-driven applications (e.g., early warning systems in schools or the prediction of students’ academic achievement) based on predictive models. However, the class imbalance problem in educational datasets could hamper the accuracy of predictive models as many of these models are designed on the assumption that the predicted class is balanced. Although previous studies proposed several methods to deal with the imbalanced class problem, most of them focused on the technical details of how to improve each technique, while only a few focused on the application aspect, especially for the application of data with different imbalance ratios. In this study, we compared several sampling techniques to handle the different ratios of the class imbalance problem (i.e., moderately or extremely imbalanced classifications) using the High School Longitudinal Study of 2009 dataset. For our comparison, we used random oversampling (ROS), random undersampling (RUS), and the combination of the synthetic minority oversampling technique for nominal and continuous (SMOTE-NC) and RUS as a hybrid resampling technique. We used the Random Forest as our classification algorithm to evaluate the results of each sampling technique. Our results show that random oversampling for moderately imbalanced data and hybrid resampling for extremely imbalanced data seem to work best. The implications for educational data mining applications and suggestions for future research are discussed.

Adaptive Prototypical Networks With Label Words and Joint Representation Learning for Few-Shot Relation Classification

Abstract: Relation classification (RC) task is one of fundamental tasks of information extraction, aiming to detect the relation information between entity pairs in unstructured natural language text and generate structured data in the form of entity–relation triple. Although distant supervision methods can effectively alleviate the problem of lack of training data in supervised learning, they also introduce noise into the data and still cannot fundamentally solve the long-tail distribution problem of the training instances. In order to enable the neural network to learn new knowledge through few instances such as humans, this work focuses on few-shot relation classification (FSRC), where a classifier should generalize to new classes that have not been seen in the training set, given only a number of samples for each class. To make full use of the existing information and get a better feature representation for each instance, we propose to encode each class prototype in an adaptive way from two aspects. First, based on the prototypical networks, we propose an adaptive mixture mechanism to add label words to the representation of the class prototype, which, to the best of our knowledge, is the first attempt to integrate the label information into features of the support samples of each class so as to get more interactive class prototypes. Second, to more reasonably measure the distances between samples of each category, we introduce a loss function for joint representation learning (JRL) to encode each support instance in an adaptive manner. Extensive experiments have been conducted on FewRel under different few-shot (FS) settings, and the results show that the proposed adaptive prototypical networks with label words and JRL has not only achieved significant improvements in accuracy but also increased the generalization ability of FSRC.