A chemical language model for molecular taste prediction by Yoel Zimmermann, Leif Sieben, Henrik Seng, Philipp Pestlin, Franz Görlich

“…Its transformer architecture allows for interpretability through gradient-based visualization of molecular features. The model identifies key structural elements driving taste properties and demonstrates utility in analyzing known tastants as well as novel compounds. …”
Get full text

Automated scan quality evaluation for DDH using transfer learning: Development of a novel ensemble system. by Yeon-Kyoung Ko, Seung-Bo Lee, Si-Wook Lee

“…<h4>Results</h4>All the selected models achieved kappa values of 0.6 or higher, indicating substantial agreement, and the AUC score for classifying standard images based on the total score was 0.89. The activation map of the trained models properly reflected the structural features of the image. …”
Get full text

Improved Word Segmentation System for Chinese Criminal Judgment Documents by Chi Zhang

“…BERT uses a deep bidirectional Transformer encoder to pre-train general language representations from large-scale unlabeled text corpora. …”
Get full text

Context-aware data augmentation for enhanced speech command recognition in industrial environments by Giuseppe De Simone, Antonio Greco, Francesco Rosa, Alessia Saggese, Mario Vento

“…To address this, we propose a modular framework designed to optimize recognition accuracy and rejection robustness while minimizing the need for extensive industrial dataset collection. The framework features an efficient Command Recognition module trained on laboratory-collected data augmented with synthetic samples. …”
Get full text

Using deep learning artificial intelligence for sex identification and taxonomy of sand fly species. by Mohammad Fraiwan, Rami Mukbel, Dania Kanaan

“…Using locally field-caught and prepared samples over a period of two years, and based on convolutional neural networks, transfer learning, and early fusion of genital and pharynx images, we achieved exceptional classification accuracy (greater than 95%) across multiple performance metrics and using a wide range of pre-trained convolutional neural network models. …”
Get full text

Analysis of guideway dynamic response induced by accelerations in medium- and low-speed maglev systems by WEI Gaoheng

“…Dynamic simulations were performed based on the model. Furthermore, field experiments were conducted on the selected line. …”
Get full text

CMAB: A Multi-Attribute Building Dataset of China by Yecheng Zhang, Huimin Zhao, Ying Long

“…We trained bootstrap aggregated XGBoost models with city administrative classifications, incorporating morphology, location, and function features. …”
Get full text

Validation of an AI-enabled exome/transcriptome liquid biopsy platform for early detection, MRD, disease monitoring, and therapy selection for solid tumors by J. Abraham, V. Domenyuk, N. Perdigones, S. Klimov, S. Antani, T. Yoshino, E. I. Heath, E. Lou, S. V. Liu, J. L. Marshall, W. S. El-Deiry, A. F. Shields, M. F. Dietrich, Y. Nakamura, T. Fujisawa, G. D. Demetri, A. Barker, J. Xiu, D. A. Sacchetti, S. Stahl, R. Hahn-Lowry, A. Stark, J. Swensen, G. Poste, D. D. Halbert, M. Oberley, M. Radovich, G. W. Sledge, David B. Spetzler

“…Caris Assure for therapy selection was CLIA validated using 1,910 samples. 376,197 tissue profiles along with 7,061 paired blood and tissue profiles were used to engineer features for three machine learning models. The MCED model was trained on 1,013 patients and validated on an independent set of 2,675 patients. …”
Get full text

A Data-Driven Framework for Accelerated Modeling of Stacking Fault Energy from Density of States Spectra by Md Tohidul Islam, Scott R. Broderick

“…The second part of this work focuses on the predictive modeling of SFE, where a machine learning model trained on UMAP-reduced features achieved high accuracy (R² = 0.86, MAE = 15.46 mJ/m²). …”
Get full text

Improved IEC performance via emotional stimuli-aware captioning by Zibo Zhou, Zhengjun Zhai, Xin Gao, Jiaqi Zhu

“…An affective captioning dataset, based on emotional attributes, is also developed to generate emotion-related captions and pre-train the image captioning model. …”
Get full text

Explainable machine learning for neoplasms diagnosis via electrocardiograms: an externally validated study by Juan Miguel Lopez Alcaraz, Wilhelm Haverkamp, Nils Strodthoff

“…Key ECG features contributing to predictions were identified and analyzed. …”
Get full text

FibroRegNet: A Regression Framework for the Pulmonary Fibrosis Prognosis Prediction Using a Convolutional Spatial Transformer Network by Pardhasaradhi Mittapalli, V. Thanikaiselvan

“…FibroRegNet estimates the lung volume from a fraction of CT slices, encodes the demographic information, and combines these features with the convolutional features, from selected CT slices, that are learned through convolutional spatial transformer modules in three identical parallel streams. …”
Get full text

Predicting bone metastasis risk of colorectal tumors using radiomics and deep learning ViT model by Guanfeng Chen, Wenxi Liu, Yingmin Lin, Jie Zhang, Risheng Huang, Deqiu Ye, Jing Huang, Jieyun Chen

“…Additionally, a dual-modality ViT model was trained on the same CT images, with a late fusion strategy employed to combine outputs from the different modalities. …”
Get full text

ChatGPT for the Standardized Operative Notes in Plastic Surgery by Fizzah Arif

“…It is a conversational AI model developed by OpenAI. It is based on the GPT (Generative Pretrained Transformer) architecture that responds conversationally to all human text inputs [1]. …”
Get full text

Detection and Localization of Stationary Waves on Venus Using a Self‐Supervised Anomaly Detection Model by Husnu Baris Baydargil, Jose Eduardo Oliveira Silva, Yeon Joo Lee, Meeyoung Cha

“…Our model is developed over Akatsuki images of Venus and is trained on smaller cropped images containing features other than stationary waves, allowing it to learn the underlying patterns of normal cloud features. …”
Get full text

Physics consistent machine learning framework for inverse modeling with applications to ICF capsule implosions by Daniel A. Serino, Evan Bell, Marc Klasky, Ben S. Southworth, Balasubramanya Nadiga, Trevor Wilcox, Oleg Korobkin

“…Our machine learning (ML)-based methodology involves a pipeline of two architectures, a radiograph-to-features network (R2FNet) and a features-to-parameters network (F2PNet), that are trained independently and later combined to approximate a posterior distribution for the parameters from radiographs. …”
Get full text

Steiner eccentricity: Predictions and applications by Xingfu Li, Zongbo Yang, Siyi Lin, Jialu Wang

“…To circumvent this challenge, we propose a supervised regression model based on linear Support Vector Machines (SVMs), leveraging graph energy and average eccentricity as pivotal features. …”
Get full text

A Machine Learning Approach for Predicting Particle Spatial, Velocity, and Temperature Distributions in Cold Spray Additive Manufacturing by Lurui Wang, Mehdi Jadidi, Ali Dolatabadi

“…Masked cold spray additive manufacturing (CSAM) is investigated for fabricating nickel-based electrodes with pyramidal pin-fins that enlarge the active area for the hydrogen-evolution reaction (HER). …”
Get full text

Detection of tuberculosis using cough audio analysis: a deep learning approach with capsule networks by Sakthi Jaya Sundar Rajasekar, Anu Rithiga Balaraman, Deepa Varnika Balaraman, Saleem Mohamed Ali, Kannan Narasimhan, Narayanasamy Krishnasamy, Varalakshmi Perumal

“…These recordings were processed into spectral images, and HOG features were extracted. Various models, including Capsule Networks + FCNN, CNN, VGG16, and ResNet50 were trained and evaluated. …”
Get full text

AI-Powered Structural Health Monitoring: Predicting Fatigue Damage in Aircraft Composites with Ultrasonic Guided Wave Inspections by Panagiotis Kolozis, Dimitrios Karasavvas, José Manuel Royo, Javier Hernandez-Olivan, Vanessa Thalassinou-Lislevand, Andrea Calvo-Echenique, Elias Koumoulos

“…The signals captured by the piezoelectric sensors are utilized to engineer key features sensitive to composite structural damage, which are then used to train a deep neural network (DNN) for accurate structural damage prediction. …”
Get full text