Sparse Attention-Based Residual Joint Network for Aspect-Category-Based Sentiment Analysis by Jooan Kim, Hyunyoung Kil

“…Recent studies on sparse attention transformation functions have demonstrated their effectiveness over the conventional softmax function. …”
Get full text

Noisier2Inverse: Self-Supervised Learning for Image Reconstruction With Correlated Noise by Nadja Gruber, Johannes Schwab, Markus Haltmeier, Ander Biguri, Clemens Dlaska, Gyeongha Hwang

“…We propose Noisier2Inverse, a correction-free, self-supervised deep learning method for general inverse problems. …”
Get full text

TARGE: large language model-powered explainable hate speech detection by Muhammad Haseeb Hashir, Memoona, Sung Won Kim

“…Traditional manual moderation methods are impractical due to the sheer volume and complexity of online discourse, necessitating automated solutions. However, existing deep learning models for hate speech detection typically function as black-box systems, providing binary classifications without interpretable insights into their decision-making processes. …”
Get full text

Node Classification Based on Kolmogorov-Arnold Networks by YUAN Lining, FENG Wengang, LIU Zhao

“…Most graph deep learning methods extract feature information from graph data by using learnable weights and specific activation functions. …”
Get full text

Adaptive Dynamic Programming-Based Intelligent Finite-Time Flexible SMC for Stabilizing Fractional-Order Four-Wing Chaotic Systems by Mai The Vu, Seong Han Kim, Duc Hung Pham, Ha Le Nhu Ngoc Thanh, Van Huy Pham, Majid Roohi

“…The control strategy eliminates the need for explicit system models by exploiting the norm-bounded characteristics of chaotic system states. …”
Get full text

Automated Dead Chicken Detection in Poultry Farms Using Knowledge Distillation and Vision Transformers by Ridip Khanal, Wenqin Wu, Joonwhoan Lee

“…EfficientNet-B0 is employed as the teacher model, while DeiT-Tiny functions as the student model, balancing high accuracy and computational efficiency. …”
Get full text

A Lightweight Transformer-Based Spatiotemporal Analysis Prediction Algorithm for High-Dimensional Meteorological Data by Yinghao Tan, Junfeng Wu, Yihang Liu, Shiyu Shen, Xia Xu, Bin Pan

“…Furthermore, SA-Fit introduces explicit functions with a lasso penalty to fit variations in high-dimensional meteorological data, achieving the prediction of a large amount of data with minimal prediction values. …”
Get full text

Reflection of Irony in O. Henry's The Gift of Magi and Firat Cewerî's Bîsîklêt Stories by Sami Çeliktaş

“…Following a thorough analysis, it was determined that both writers employed the literary device of irony to shed light on the social and personal challenges faced by their characters. Irony functioned as both a narrative tool and a key plot element, allowing for the expression of deep human emotions and experiences. …”
Get full text

False vacuum decay rate from thin to thick walls by Marco Matteini, Miha Nemevšek, Yutaro Shoji, Lorenzo Ubaldi

“…We find that truncating such an expansion at second order we obtain a remarkably accurate bounce action also deep into thick wall regimes. We calculate the functional determinant numerically in 3 and 4 dimensions and fit the results with simple polynomials of the same thin wall parameter. …”
Get full text

Tafsir on the Qur’an’s Discourse Against Hypocrisy by Fereshteh Motamed Langrody, Fathiyeh Fattahizadeh

“…This study examines the ideological structures at the descriptive level to reveal the central meanings in the deep structures of these ayahs and to understand the Qur’an’s discoursebuilding methods against hypocrisy. …”
Get full text

System Reliability Analysis of Slope Stability of Earth Rock Dams Based on Finite Element Strength Reduction Method by Huibao Huang, Junchi Zhu, Zhenyu Wu, Jiankang Chen, Jichen Tian

“…Each pathway, treated as a parallel system of shear-failed elements, is analyzed via the response surface method to derive explicit limit state functions. Reliability indices are computed using an improved first-order second-moment method, while interdependencies are assessed through stepwise equivalent linearization. …”
Get full text

Review of Research on Artificial Intelligence-driven Joint Radar Communication by Xianmei WANG, Xiangbo LIU, Yuzheng REN, Yang LU, Haijun ZHANG

“…Artificial Intelligence (AI), with its powerful learning ability, automatically learns features from large amounts of data without the need for explicit modeling, thereby promoting the deep fusion of radar communication. …”
Get full text

Psycholinguistic Specifics of Understanding by Ukrainian Students the Principles of Nomination of Linguocultural Models “clothing” in English and Ukrainian by Наталія Михальчук, Павло Левчук, Ернест Івашкевич, Людмила Ясногурська, Олена Чернякова

“…Productivity of students’ understanding of linguocultural units of the thematic group “clothing” in the Ukrainian language is determined by (a) the deep meaning of lexical units; (b) semantics and spatio-temporal meanings of linguocultural units; (c) syntactics of lexical units; (d) verb and noun basis of clothing nomination; (e) various connections between explicit concepts (metaphorical and metonymic transference); (f) assertive content of the nominative unit denoting “clothing”; (g) understanding of inferences, implications, intentions of the expressionж (h) explication of usualized (a priori) communicative meanings.…”
Get full text

Application of physics-informed neural networks for two-phase flow model with variable diffusion and experimental validation by Daulet Kalesh, Timur Merembayev, Sagyn Omirbekov, Yerlan Amanbek

“…This paper presents Physics-Informed Neural Networks (PINNs) with a spatially-dependent diffusion function to model two-phase flow in porous media, explicitly addressing the Buckley-Leverett problem. …”
Get full text

COGNITIVE SEMANTICS OF NOUNS IN DENUMERATIVE WORD FORMATION (BASED ON UKRAINIAN LANGUAGE) by Olha V. Kostryba

“…Revival of interest in the linguistic-cognitive interpretation of the deep level of language, as a means of facilitating the computerization of the semantic continuum of derived words, is driven by the schemati- zation of both implicit and explicit data concerning these words. …”
Get full text

Anisotropic jet broadening and jet shape by Weiyao Ke, John Terry, Ivan Vitev

“…Using Soft-Collinear Effective Theory, we explicitly calculate the jet functions associated with these observables with a standard jet axis and with a Winner-Take-All jet axis in both the resummed and fixed order limits. …”
Get full text

A brain-inspired memory transformation based differentiable neural computer for reasoning-based question answering by Yao Liang, Yao Liang, Yuwei Wang, Yuwei Wang, Hongjian Fang, Hongjian Fang, Feifei Zhao, Yi Zeng, Yi Zeng, Yi Zeng, Yi Zeng, Yi Zeng

“…Reasoning and question answering, as fundamental cognitive functions in humans, remain significant hurdles for artificial intelligence. …”
Get full text

Time-Series Interval Forecasting with Dual-Output Monte Carlo Dropout: A Case Study on Durian Exports by Unyamanee Kummaraka, Patchanok Srisuradetchai

“…Deep neural networks (DNNs) are prominent in predictive analytics for accurately forecasting target variables. …”
Get full text

Time series AQI forecasting using Kalman-integrated Bi-GRU and Chi-square divergence optimization by Narmeen Fatima, Samia Nawaz Yousafzai, Nadhem Nemri, Hadeel Alsolai, Shouki A. Ebad, Shaymaa Sorour, Yeonghyeon Gu, Muhammad Syafrudin, Norma Latif Fitriyani

“…Additionally, we incorporate a Chi-square Divergence-based regularization term into the loss function to explicitly minimize the distributional mismatch between predicted and actual pollutant levels–a contribution not explored in prior AQI models. …”
Get full text

MTCDNet: Multimodal Feature Fusion-Based Tree Crown Detection Network Using UAV-Acquired Optical Imagery and LiDAR Data by Heng Zhang, Can Yang, Xijian Fan

“…In addition, a learnable positional encoding scheme is introduced to facilitate the fused features in capturing the complex, densely distributed tree crown structures by explicitly incorporating spatial information. A hybrid loss function is further designed to enhance the model’s capability in handling occluded crowns and crowns of varying sizes. …”
Get full text