Lung cancer is one of the major causes of death worldwide, and Vietnam is not an exception. This disease is the second most common type of cancer globally and the second most common cause of death in Vietnam, just after liver cancer, with 23,797 fatal cases and 26,262 new cases, or 14.4% of the disease in 2020. Recently, with rising disease rates in Vietnam causing a huge public health burden, lung cancer continues to hold the top position in attention and care. Especially together with climate change, under a variety of types of pollution, deforestation, and modern lifestyles, lung cancer risks are on red alert, particularly in Vietnam. To understand more about the severe disease sources in Vietnam from a diversity of key factors, including environmental features and the current health state, with a particular emphasis on Vietnam's distinct socioeconomic and ecological context, we utilize large datasets such as patient health records and environmental indicators containing necessary information, such as deforestation rate, green cover rate, air pollution, and lung cancer risks, that is collected from well-known governmental sharing websites. Then, we process and connect them and apply analytical methods (heatmap, information gain, p-value, spearman correlation) to determine causal correlations influencing lung cancer risks. Moreover, we deploy machine learning (ML) models (Decision Tree, Random Forest, Support Vector Machine, K-mean clustering) to discover cancer risk patterns. Our experimental results, leveraged by the aforementioned ML models to identify the disease patterns, are promising, particularly, the models as Random Forest, SVM, and PCA are working well on the datasets and give high accuracy (99%), however, the K means clustering has very low accuracy (10%) and does not fit the datasets.

Continual generalized category discovery has been introduced and studied in the literature as a method that aims to continuously discover and learn novel categories in incoming data batches while avoiding catastrophic forgetting of previously learned categories. A key component in addressing this challenge is the model's ability to separate novel samples, where Extreme Value Theory (EVT) has been effectively employed. In this work, we propose a novel method that integrates EVT with proxy anchors to define boundaries around proxies using a probability of inclusion function, enabling the rejection of unknown samples. Additionally, we introduce a novel EVT-based loss function to enhance the learned representation, achieving superior performance compared to other deep-metric learning methods in similar settings. Using the derived probability functions, novel samples are effectively separated from previously known categories. However, category discovery within these novel samples can sometimes overestimate the number of new categories. To mitigate this issue, we propose a novel EVT-based approach to reduce the model size and discard redundant proxies. We also incorporate experience replay and knowledge distillation mechanisms during the continual learning stage to prevent catastrophic forgetting. Experimental results demonstrate that our proposed approach outperforms state-of-the-art methods in continual generalized category discovery scenarios.

Automated scoring (AS) systems are increasingly used for evaluating L2 writing, but require ongoing refinement for construct validity. While prior work suggested lexical bundles (LBs) - recurrent multi-word sequences satisfying certain frequency criteria - could inform assessment, their empirical integration into AS models needs further investigation. This study tested the impact of incorporating LB frequency features into an AS model for TOEFL independent writing tasks. Analyzing a sampled subcorpus (N=1,225 essays, 9 L1s) from the TOEFL11 corpus, scored by ETS-trained raters (Low, Medium, High), 3- to 9-word LBs were extracted, distinguishing prompt-specific from non-prompt types. A baseline Support Vector Machine (SVM) scoring model using established linguistic features (e.g., mechanics, cohesion, sophistication) was compared against an extended model including three aggregate LB frequency features (total prompt, total non-prompt, overall total). Results revealed significant, though generally small-effect, relationships between LB frequency (especially non-prompt bundles) and proficiency (p < .05). Mean frequencies suggested lower proficiency essays used more LBs overall. Critically, the LB-enhanced model improved agreement with human raters (Quadratic Cohen's Kappa +2.05%, overall Cohen's Kappa +5.63%), with notable gains for low (+10.1% exact agreement) and medium (+14.3% Cohen's Kappa) proficiency essays. These findings demonstrate that integrating aggregate LB frequency offers potential for developing more linguistically informed and accurate AS systems, particularly for differentiating developing L2 writers.

Hierarchical graph pooling(HGP) are designed to consider the fact that conventional graph neural networks(GNN) are inherently flat and are also not multiscale. However, most HGP methods suffer not only from lack of considering global topology of the graph and focusing on the feature learning aspect, but also they do not align local and global features since graphs should inherently be analyzed in a multiscale way. LGRPool is proposed in the present paper as a HGP in the framework of expectation maximization in machine learning that aligns local and global aspects of message passing with each other using a reg-ularizer to force the global topological information to be inline with the local message passing at different scales through the representations at different layers of HGP . Experimental results on some graph classification benchmarks show that it slightly outperforms some baselines.

The field of spoken language processing is undergoing a shift from training custom-built, task-specific models toward using and optimizing spoken language models (SLMs) which act as universal speech processing systems. This trend is similar to the progression toward universal language models that has taken place in the field of (text) natural language processing. SLMs include both "pure" language models of speech -- models of the distribution of tokenized speech sequences -- and models that combine speech encoders with text language models, often including both spoken and written input or output. Work in this area is very diverse, with a range of terminology and evaluation settings. This paper aims to contribute an improved understanding of SLMs via a unifying literature survey of recent work in the context of the evolution of the field. Our survey categorizes the work in this area by model architecture, training, and evaluation choices, and describes some key challenges and directions for future work.

Traditionally, authorship attribution (AA) tasks relied on statistical data analysis and classification based on stylistic features extracted from texts. In recent years, pre-trained language models (PLMs) have attracted significant attention in text classification tasks. However, although they demonstrate excellent performance on large-scale short-text datasets, their effectiveness remains under-explored for small samples, particularly in AA tasks. Additionally, a key challenge is how to effectively leverage PLMs in conjunction with traditional feature-based methods to advance AA research. In this study, we aimed to significantly improve performance using an integrated integrative ensemble of traditional feature-based and modern PLM-based methods on an AA task in a small sample. For the experiment, we used two corpora of literary works to classify 10 authors each. The results indicate that BERT is effective, even for small-sample AA tasks. Both BERT-based and classifier ensembles outperformed their respective stand-alone models, and the integrated ensemble approach further improved the scores significantly. For the corpus that was not included in the pre-training data, the integrated ensemble improved the F1 score by approximately 14 points, compared to the best-performing single model. Our methodology provides a viable solution for the efficient use of the ever-expanding array of data processing tools in the foreseeable future.

One of the most alarming issues in digital society is hate speech (HS) on social media. The severity is so high that researchers across the globe are captivated by this domain. A notable amount of work has been conducted to address the identification and alarm system. However, a noticeable gap exists, especially for low-resource languages. Comprehensive datasets are the main problem among the constrained resource languages, such as Bangla. Interestingly, hate speech or any particular speech has no single dimensionality. Similarly, the hate component can simultaneously have multiple abusive attributes, which seems to be missed in the existing datasets. Thus, a multi-label Bangla hate speech dataset named BOISHOMMO has been compiled and evaluated in this work. That includes categories of HS across race, gender, religion, politics, and more. With over two thousand annotated examples, BOISHOMMO provides a nuanced understanding of hate speech in Bangla and highlights the complexities of processing non-Latin scripts. Apart from evaluating with multiple algorithmic approaches, it also highlights the complexities of processing Bangla text and assesses model performance. This unique multi-label approach enriches future hate speech detection and analysis studies for low-resource languages by providing a more nuanced, diverse dataset.

Federated learning is a novel decentralized learning architecture. During the training process, the client and server must continuously upload and receive model parameters, which consumes a lot of network transmission resources. Some methods use clustering to find more representative customers, select only a part of them for training, and at the same time ensure the accuracy of training. However, in federated learning, it is not trivial to know what the number of clusters can bring the best training result. Therefore, we propose to dynamically adjust the number of clusters to find the most ideal grouping results. It may reduce the number of users participating in the training to achieve the effect of reducing communication costs without affecting the model performance. We verify its experimental results on the non-IID handwritten digit recognition dataset and reduce the cost of communication and transmission by almost 50% compared with traditional federated learning without affecting the accuracy of the model.

Accurate representation to an academic network is of great significance to academic relationship mining like predicting scientific impact. A Latent Factorization of Tensors (LFT) model is one of the most effective models for learning the representation of a target network. However, an academic network is often High-Dimensional and Incomplete (HDI) because the relationships among numerous network entities are impossible to be fully explored, making it difficult for an LFT model to learn accurate representation of the academic network. To address this issue, this paper proposes a Prediction-sampling-based Latent Factorization of Tensors (PLFT) model with two ideas: 1) constructing a cascade LFT architecture to enhance model representation learning ability via learning academic network hierarchical features, and 2) introducing a nonlinear activation-incorporated predicting-sampling strategy to more accurately learn the network representation via generating new academic network data layer by layer. Experimental results from the three real-world academic network datasets show that the PLFT model outperforms existing models when predicting the unexplored relationships among network entities.

The thermoelectric performance of materials exhibits complex nonlinear dependencies on both elemental types and their proportions, rendering traditional trial-and-error approaches inefficient and time-consuming for material discovery. In this work, we present a deep learning model capable of accurately predicting thermoelectric properties of doped materials directly from their chemical formulas, achieving state-of-the-art performance. To enhance interpretability, we further incorporate sensitivity analysis techniques to elucidate how physical descriptors affect the thermoelectric figure of merit (zT). Moreover, we establish a coupled framework that integrates a surrogate model with a multi-objective genetic algorithm to efficiently explore the vast compositional space for high-performance candidates. Experimental validation confirms the discovery of a novel thermoelectric material with superior $zT$ values in the medium-temperature regime.