Discrete Features Research Articles

Holstein Polarons, Rashba-Like Spin Splitting, and Ising Superconductivity in Electron-Doped MoSe2.

Interaction between electrons and phonons in solids is a key effect defining the physical properties of materials, such as electrical and thermal conductivity. In transition metal dichalcogenides (TMDCs), the electron-phonon coupling results in the formation of polarons, quasiparticles that manifest themselves as discrete features in the electronic spectral function. In this study, we report the formation of polarons at the alkali-dosed MoSe2 surface, where Rashba-like spin splitting of the conduction band states is caused by an inversion-symmetry breaking electric field. In addition, we observed a crossover from phonon-like to plasmon-like polaronic spectral features at the MoSe2 surface with increasing doping. Our findings support the concept of electron-phonon coupling-mediated superconductivity in electron-doped layered TMDC materials, as observed using ionic liquid gating technology. Furthermore, the discovered spin-splitting at the Fermi level could offer crucial experimental validation for theoretical models of Ising-type superconductivity in these materials.

Space-time shape optimization of rotating electric machines

This paper is devoted to the shape optimization of the internal structure of an electric motor, and more precisely of the arrangement of air and ferromagnetic material inside the rotor part with the aim to increase the torque of the machine. The governing physical problem is the time-dependent, nonlinear magneto-quasi-static version of Maxwell’s equations. This multiphase problem can be reformulated on a 2D section of the real cylindrical 3D configuration; however, due to the rotation of the machine, the geometry of the various material phases at play (the ferromagnetic material, the permanent magnets, air, etc.) undergoes a prescribed motion over the considered time period. This original setting raises a number of issues. From the theoretical viewpoint, we prove the well-posedness of this unusual nonlinear evolution problem featuring a moving geometry. We then calculate the shape derivative of a performance criterion depending on the shape of the ferromagnetic phase via the corresponding magneto-quasi-static potential. Our numerical framework to address this problem is based on a shape gradient algorithm. The nonlinear time periodic evolution problems for the magneto-quasi-static potential is solved in the time domain, with a Newton–Raphson method. The discretization features a space-time finite element method, applied on a precise, meshed representation of the space-time region of interest, which encloses a body-fitted representation of the various material phases of the motor at all the considered stages of the time period. After appraising the efficiency of our numerical framework on an academic problem, we present a quite realistic example of optimal design of the ferromagnetic phase of the rotor of an electric machine.

Boosting Point Set-Based Network with Optimal Transport Optimization for Oriented Object Detection

When handling complex remote sensing scenarios, rotational angle information can improve detection accuracy and enhance algorithm robustness, providing support for fine-grained detection. Point set representation is one of the most commonly used methods in arbitrary-oriented object detection tasks, leveraging discrete feature points to represent oriented targets and achieve high accuracy in angle prediction. However, due to the inherent discreteness of point set representation, it is prone to significant impact from isolated points and representational ambiguity in harsh application scenarios, leading to inaccurate detection. To address this issue, an efficient aerial object detector named BE-Det is proposed, which uses the optimal transport (OT) strategy to constrain the positions of isolated points. Additionally, a candidate point set quality evaluation scheme is designed to effectively assess the quality of candidate point sets. Experimental results on two challenging aerial datasets demonstrate that the proposed method outperforms several advanced detection methods.

Second Language Sentence Stress Assignment: Self‐ and Other‐Assessment

AbstractResearch on second language (L2) pronunciation self‐assessment reports a general misalignment between self‐ and other‐assessment. This has been attributed to the object of self‐assessment, the self‐assessment task, the measures to which self‐assessment is compared, and speakers’ characteristics. Here, we examined self‐assessment of a discrete phonological feature—sentence stress—by L2 English speakers as compared to the assessment of first language English listeners through a timed, forced‐choice judgment task with low‐pass filtered stimuli, which contained only suprasegmental cues. Additionally, we explored how individual differences among speakers predict self‐assessment. Speakers generally overestimated their accuracy in sentence stress assignment in a pattern resembling the Dunning‐Kruger effect despite the controlled nature of the task. Speakers with larger vocabulary size judged their sentence stress assignment as correct more often and showed greater overconfidence and miscalibration. Finally, the assessments of speakers with a background in applied linguistics and/or language teaching were more aligned with listeners’ assessments.

Quantifying the Visuo-Perceptual Segregation Between Ortabayır and Levent District in Istanbul through Semantic Segmentation

Urban segregation has always been a critical problem affecting citizens’ socio-cultural equality. Although the issue has been widely investigated, recent methodological perspectives based on machine learning techniques can provide alternative viewpoints while contributing to precise findings. This study highlights the urban segregation problem in the context of Levent and Ortabayir districts in Istanbul while reviewing the existing literature on the relevant issue of segregation. The study aims to elaborate on the visual and perceptual segregation between Levent and Ortabayir while providing quantitative evidence. This study applies semantic segmentation of street view images and scene ratings to quantify visuo-perceptual segregation. The dataset for semantic segmentation contains 150 street view images for both Levent and Ortabayır regions. Seven semantic label criteria are decided, such as nature, pavement, road, sky, buildings, people, and cars, to outline the basic visual qualities of the urban environment. The street view scenes are evaluated on a 7-Likert scale by fifty raters who are asked to focus on the scenes’ safety and beauty perceptual qualities. We applied comparison analysis to detect the statistical similarities and variations and correlation analyses to investigate the associative trends between virtual and perceptual variables. This study distinguishes itself from the existing literature by adopting the machine learning method to asses the segregation problem between Levent and Ortabayir through semantic labels. Our approach contributes to the literature with its methodology and the quantitative, precise segregation findings. This study confirms the segregation between Levent and Ortabayir with their visual and perceptual qualities and illustrates the discrete visuo-perceptual features of both regions. This study shows that segregation appears in the selected regions on both inter-regional and intra-regional scales.

Identification of distinct subtypes of post-stroke and neurotypical gait behaviors using neural network analysis of kinematic time series data.

Heterogeneous types of gait impairment are common post-stroke. Studies used supervised and unsupervised machine learning on discrete biomechanical features to summarize the gait cycle and identify common patterns of gait behaviors. However, discrete features cannot account for temporal variations that occur during gait. Here, we propose a novel machine-learning pipeline to identify subgroups of gait behaviors post-stroke using kinematic time series data. We analyzed ankle and knee kinematic data during treadmill walking data in 39 individuals post- stroke and 28 neurotypical controls. The data were first input into a supervised dual-stage Convolutional Neural Network-Temporal Convolutional Network, trained to extract temporal and spatial gait features. Then, we used these features to find clusters of different gait behaviors using unsupervised time series k-means. We repeated the clustering process using 10,000 bootstrap training data samples and a Gaussian Mixture Model to identify stable clusters representative of our dataset. Finally, we assessed the kinematic differences between the identified clusters using 1D statistical parametric mapping ANOVA. We then compared gait spatiotemporal and clinical characteristics between clusters using one-way ANOVA. We obtained five clusters: two clusters of neurotypical individuals (C1 and C2) and three clusters of individuals post-stroke (S1, S2, S3). C1 had kinematics that resembled the normative gait pattern. Individuals in C2 had a shorter stride time than C1. Individuals in S1 had mild impairment and walked with increased bilateral knee flexion during the loading response. Individuals in S2 had moderate impairment, were the slowest among the clusters, took shorter steps, had increased knee flexion during stance bilaterally and reduced paretic knee flexion during swing. Individuals in S3 had mild impairment, asymmetric swing time, had increased ankle abduction during the gait cycle and reduced dorsiflexion bilaterally during loading response and stance. Every individual was assigned to a cluster with a cluster membership likelihood above 93%. Our results indicate that joint kinematics in individuals post-stroke are distinct from controls, even in those individuals with mild impairment. The three subgroups post-stroke showed distinct kinematic impairments during specific phases in the gait cycle, providing additional information to clinicians for gait retraining interventions.

Retraction Note: ICM-BTD: improved classification model for brain tumor diagnosis using discrete wavelet transform-based feature extraction and SVM classifier

Retraction Note: ICM-BTD: improved classification model for brain tumor diagnosis using discrete wavelet transform-based feature extraction and SVM classifier

Discrete Variational Feature Transfer Learning for Skeleton-based Abnormal Behavior Detection

Discrete Variational Feature Transfer Learning for Skeleton-based Abnormal Behavior Detection

A virtual scene reconstruction algorithm for 3D digital images based on machine learning

In order to obtain a better quality image of virtual scene reconstruction of three-dimensional digital image, a virtual scene reconstruction algorithm of three-dimensional digital image based on machine learning is proposed. Firstly, the state information and presentation instructions of the scene are analyzed to obtain the distribution position of the vertices of the mesh model of the image reconstruction. The global image is approximately calculated by the local coordinate method, and the local details are corrected to complete the rendering of the three-dimensional digital image. Then, the space and scale are used as feature points to build a window detection template on the image, and the classifier is applied to suppress discrete feature points and remove redundant features. Finally, the smoothed three-dimensional coordinates are obtained according to the fitting function method to reconstruct the three-dimensional surface, and the local two-dimensional triangle is segmented and mapped to the three-dimensional space to realize the reconstruction of the virtual scene of the three-dimensional digital image. The experimental results show that the algorithm has a fast convergence speed, the reconstructed image details and edge contours are complete, and the overall effect is good.

An evolutionary algorithm‐based classification method for high‐dimensional imbalanced mixed data with missing information

AbstractThe data scale keeps growing by leaps and the majority of it is high‐dimensional imbalanced data, which is hard to classify. Data missing often happens in software which further aggravates the difficulty of classifying the data. In order to resolve high‐dimensional imbalanced mixed‐variables missing data classification problem, a novel method based on particle swarm optimization is developed. It has three original components including multiple feature selection, mixed attribute imputation, and quantum oversampling. Multiple feature selection uses a two‐stage strategy to obtain stable relevant features. Mixed attribute imputation separates features into continuous and discrete features and fills missing values with different models. Quantum oversampling chooses instances to balance data based on the quantum operator. Furthermore, particle swarm optimization is employed to optimize the parameters of the components to obtain preferable classification results. Six representative classification datasets, six typical algorithms, and four measures are taken to conduct exhaust experiments, and results indicate that the proposed method is superior to the comparison algorithms.

Random subspace ensemble-based detection of false data injection attacks in automatic generation control systems

Automatic Generation Control (AGC) systems in smart grids are increasingly vulnerable to cyber-attacks, particularly False Data Injection (FDI) attacks, due to their reliance on information and communication technologies. These vulnerabilities pose significant threats to the reliable operation of power systems. To address this challenge, this research paper introduces the machine learning (ML) based cyberattack detection technique designed to identify FDI attacks with the highest accuracy proficiently. The study involves a comprehensive analysis of three features: the original discrete signal feature, the cycle-to-cycle-based feature, and the sample-to-sample-based feature. These features are utilized for detecting FDI attacks and distinguishing them from normal load variations. The research meticulously collects data by simulating diverse FDI attacks, including step attacks, pulse attacks, random attacks, and normal load variation cases on an AGC power system. Four ML classifiers are selected and compared for the classification task. The simulation results reveal that the sample-to-sample-based feature proves highly effective in distinguishing FDI attacks compared to the original signal and cycle-to-cycle-based features. Notably, the results indicate that the random subspace ensemble (RaSE) classifier, utilizing sample-to-sample-based features, effectively identifies and classifies all normal and FDI attacks. This research provides valuable insights into the potential of ML techniques for enhancing FDI attack detection in the AGC of power systems. It provides a potential pathway for overcoming the limitations associated with traditional model-based FDI detection methods.

Salient event detection via hypergraph convolutional network with cross-view self-supervised learning

Identifying the most dominant and central events in a document is critical for holistically understanding its important information. To measure the importance of an event, it is critical to understand its context: who is involved, where it happened, which other events it is related to, and what kind of relationship it has, among other factors. Although existing studies have achieved some accomplishments, they are still not fully effective for two main reasons: (1) They incorporate only the discrete global features of the document, which is insufficient for effectively capturing the contextual information of events; (2) They inadequately model the dependency relationships between events. According to previous research findings, it has been shown that hypergraphs effectively capture the global context (i.e., the document-level context) of long text. However, their potential for salient event detection has remained unexplored. To address this, we propose a novel framework called Salient Event Detection via Hypergraph Convolutional Network with Graph Self-supervised Learning (SEDGS). More specifically, we first construct two hypergraphs: one in the event argument view and another in the event view. We then propose a hypergraph convolutional network to model the event context and discourse relations between events. Moreover, to enhance hypergraph modeling and ensure consistency between argument-view and event-view event representations, we employ contrastive self-supervised learning (SSL) in our model training. Experimental results on a standard event salience dataset verify the superiority of SEDGS, advancing state-of-the-art models.

Computer-assisted pronunciation training: A systematic review

Abstract This systematic review maps the trends of computer-assisted pronunciation training (CAPT) research based on the pedagogy of second language (L2) pronunciation instruction and assessment. The review was limited to empirical studies investigating the effects of CAPT on healthy L2 learners’ pronunciation. Thirty peer-reviewed journal articles published between 1999 and 2022 were selected based on specific inclusion and exclusion criteria. Data were collected about the studies’ contexts, participants, experimental designs, CAPT systems, pronunciation training scopes and approaches, pronunciation assessment practices, and learning measures. Using a pedagogically informed codebook, the pronunciation training and assessment practices were classified and evaluated based on established L2 pronunciation teaching guidelines. The findings indicated that most of the studies focused on the pronunciation training of adult English learners with an emphasis on the production of segmental features (i.e. vowels and consonants) rather than suprasegmental features (i.e. stress, intonation, and rhythm). Despite the innovation promised by CAPT technology, pronunciation practice in the studies reviewed was characterized by the predominant use of drilling through listen-and-repeat and read-aloud activities. As for assessment, most CAPT studies relied on human listeners to measure the accurate production of discrete pronunciation features (i.e. segmental and suprasegmental accuracy). Meanwhile, few studies employed global pronunciation learning measures such as intelligibility and comprehensibility. Recommendations for future research are provided based on the discussion of these results.

End-to-End Implicit Object Pose Estimation.

To accurately estimate the 6D pose of objects, most methods employ a two-stage algorithm. While such two-stage algorithms achieve high accuracy, they are often slow. Additionally, many approaches utilize encoding-decoding to obtain the 6D pose, with many employing bilinear sampling for decoding. However, bilinear sampling tends to sacrifice the accuracy of precise features. In our research, we propose a novel solution that utilizes implicit representation as a bridge between discrete feature maps and continuous feature maps. We represent the feature map as a coordinate field, where each coordinate pair corresponds to a feature value. These feature values are then used to estimate feature maps of arbitrary scales, replacing upsampling for decoding. We apply the proposed implicit module to a bidirectional fusion feature pyramid network. Based on this implicit module, we propose three network branches: a class estimation branch, a bounding box estimation branch, and the final pose estimation branch. For this pose estimation branch, we propose a miniature dual-stream network, which estimates object surface features and complements the relationship between 2D and 3D. We represent the rotation component using the SVD (Singular Value Decomposition) representation method, resulting in a more accurate object pose. We achieved satisfactory experimental results on the widely used 6D pose estimation benchmark dataset Linemod. This innovative approach provides a more convenient solution for 6D object pose estimation.

SRL‐ProtoNet: Self‐supervised representation learning for few‐shot remote sensing scene classification

AbstractUsing a deep learning method to classify a large amount of labelled remote sensing scene data produces good performance. However, it is challenging for deep learning based methods to generalise to classification tasks with limited data. Few‐shot learning allows neural networks to classify unseen categories when confronted with a handful of labelled data. Currently, episodic tasks based on meta‐learning can effectively complete few‐shot classification, and training an encoder that can conduct representation learning has become an important component of few‐shot learning. An end‐to‐end few‐shot remote sensing scene classification model based on ProtoNet and self‐supervised learning is proposed. The authors design the Pre‐prototype for a more discrete feature space and better integration with self‐supervised learning, and also propose the ProtoMixer for higher quality prototypes with a global receptive field. The authors’ method outperforms the existing state‐of‐the‐art self‐supervised based methods on three widely used benchmark datasets: UC‐Merced, NWPU‐RESISC45, and AID. Compare with previous state‐of‐the‐art performance. For the one‐shot setting, this method improves by 1.21%, 2.36%, and 0.84% in AID, UC‐Merced, and NWPU‐RESISC45, respectively. For the five‐shot setting, this method surpasses by 0.85%, 2.79%, and 0.74% in the AID, UC‐Merced, and NWPU‐RESISC45, respectively.

Survivals of Titanic Prediction Utilizing Tree-based Machine Learning Models

The shipwreck of Titanic is a well-known tragedy. Although it happened more than a century ago, researchers are still investigating the patterns of the survivors to gain more insight into human behaviors in catastrophes. This paper adopts machine learning techniques, including decision tree, random forest, and gradient boosting, to conduct a binary classification to predict whether a person survived. The selected models are all tree-based, making it convenient to examine the importance of features. In the preprocessing stage, all numerical features are discretized. This paper first investigates the performances of the models. Subsequently, the model with the best performance generates and studies the importance of the feature. The result demonstrates that the decision tree classifier with a max depth equal to seven achieves the highest accuracy of 0.78. The results of the three models are similar, indicating that the research is robust. The feature importance generated by the decision tree classifier shows that sex and social status significantly impact the survival result. In addition, whether the person is a child also makes a difference. The discretized features do not have enough influence on the result of survival. This paper concludes that the tunned decision tree classifier is the best model to study the features in this paper, but the created features are not effective enough.

Gait recognition for farm workers via multi-scale temporal feature perception

The monitoring and management of farm workers play a crucial role in agricultural production. The real-time monitoring of farm workers can effectively identify them, facilitating standardized management and operation of the farm. Gait, as a unique biometric feature that can be recognized from a distance, is more suitable for identifying individual farm workers walking on the farm at a distance compared to facial and iris features. Despite the increasing research on gait recognition techniques, existing gait recognition models are still lacking in temporal modeling. The gait of farm workers walking through farmland is greatly influenced by the environment, making it crucial to model the temporal information of gait. In this study, we captured videos of 50 farm workers from 11 different perspectives walking in real agricultural fields and formed the Farm Worker Gait Dataset (FWGD). In comparison with existing gait recognition models, we present a multi-scale temporal feature modeling method based on the GaitBase model and obtain a performance improvement on the FWGD dataset. Specifically, we propose an Adaptive Temporal Self-Attention (ATSA) mechanism to extract the most representative features based on temporal contextual temporal relations. Additionally, we utilize a dilated convolutional layer to extract discrete temporal features and employ a Multi-scale Temporal Perception Module (MSTP) with three branches to perceive and aggregate temporal features. With the assistance of MSTP and ATSA, our model significantly improves the discriminability of temporal features, thus enhancing the performance of farm worker gait recognition. Extensive experiments demonstrated that our proposed method outperformed state-of-the-art gait recognition methods on the FWGD dataset.

Neural quantile optimization for edge–cloud networking

We seek the best traffic allocation scheme for the edge–cloud networking subject to SD-WAN architecture and burstable billing. First, we formulate a family of quantile-based integer programming problems for a fixed network topology with random parameters describing the traffic demands. Then, to overcome the difficulty caused by the discrete feature, we generalize the Gumbel-softmax reparameterization method to induce an unconstrained continuous optimization problem as a regularized continuation of the discrete problem. Finally, we introduce the Gumbel-softmax sampling neural network to solve optimization problems via unsupervised learning. The neural network structure reflects the edge–cloud networking topology and is trained to minimize the expectation of the cost function for unconstrained continuous optimization problems. The trained network works as an efficient traffic allocation scheme sampler, outperforming the random strategy in feasibility and cost value. Besides testing the quality of the output allocation scheme, we examine the generalization property of the network by increasing the time steps and the number of users. We also feed the solution to existing integer optimization solvers as initial conditions and verify the warm-starts can accelerate the short-time iteration process. The framework is general, and the decoupled feature of the random neural networks is adequate for practical implementations.

Building a learnable universal coordinate system for single-cell atlas with a joint-VAE model

A universal coordinate system that can ensemble the huge number of cells and capture their heterogeneities is of vital importance for constructing large-scale cell atlases as references for molecular and cellular studies. Studies have shown that cells exhibit multifaceted heterogeneities in their transcriptomic features at multiple resolutions. This nature of complexity makes it hard to design a fixed coordinate system through a combination of known features. It is desirable to build a learnable universal coordinate model that can capture major heterogeneities and serve as a controlled generative model for data augmentation. We developed UniCoord, a specially-tuned joint-VAE model to represent single-cell transcriptomic data in a lower-dimensional latent space with high interpretability. Each latent dimension can represent either discrete or continuous feature, and either supervised by prior knowledge or unsupervised. The latent dimensions can be easily reconfigured to generate pseudo transcriptomic profiles with desired properties. UniCoord can also be used as a pre-trained model to analyze new data with unseen cell types and thus can serve as a feasible framework for cell annotation and comparison. UniCoord provides a prototype for a learnable universal coordinate framework to enable better analysis and generation of cells with highly orchestrated functions and heterogeneities.

LLM for Data Management

Machine learning techniques have been verified to be effective in optimizing data management systems and are widely researched in recent years. However, traditional small-sized ML models often struggle to generalize to new scenarios, and have limited context understanding ability (e.g., inputting discrete features only). The emergence of LLMs offers a promising solution to these challenges. LLMs have been trained over a vast number of scenarios and tasks and acquire human-competitive capabilities like context understanding and summarization, which can be highly beneficial for data management tasks (e.g., natural language based data analytics). In this tutorial, we present how to utilize LLMs to optimize data management systems and review new techniques for addressing these technical challenges, including hallucination of LLMs, high cost of interacting with LLMs, and low accuracy for processing complicated tasks. First, we discuss retrieval augmented generation (RAG) techniques to address the hallucination problem. Second, we present vector database techniques to improve the latency. Third, we present LLM agent techniques for processing complicated tasks by generating multi-round pipelines. We also showcase some real-world data management scenarios that can be well optimized by LLMs, including query rewrite, database diagnosis and data analytics. Finally, we summarize some open research challenges.