Experimental validation of machine learning for contamination classification of polluted high voltage insulators using leakage current by Umer Amir Khan, Mansoor Asif, Muhammad Hamza Zafar, Luai Alhems

“…The Bayesian optimization technique was used to optimize the parameters of Machine Learning Models. The models demonstrated exceptional performance, with accuracies consistently exceeding 98 %. …”
Get full text

MRI-based differentiation of Parkinson's disease by cerebellar gray matter volume by Dacong Zhao, Jiang Guo, Guanghua Lu, Rui Jiang, Chao Tian, Xu Liang

“…These independent components were then utilized for correlation analysis with clinical scales and trained as input features for the SVM model. PD patients (n = 20) and HC (n = 20) from the TaoWu dataset were used as test data to validate our SVM model. …”
Get full text

In silico assessment of biocompatibility and toxicity: molecular docking and dynamics simulation of PMMA-based dental materials for interim prosthetic restorations by Ravinder S. Saini, Rayan Ibrahim H. Binduhayyim, Vishwanath Gurumurthy, Abdulkhaliq Ali F. Alshadidi, Shashit Shetty Bavabeedu, Rajesh Vyas, Doni Dermawan, Punnoth Poonkuzhi Naseef, Seyed Ali Mosaddad, Artak Heboyan

“…MD simulation results provided strong evidence supporting the structural stability of PMMA complexes over time. Pharmacophore modeling highlighted the significance of carbonyl and hydroxyl groups as pharmacophoric features, indicating compounds with favorable biocompatibility profiles. …”
Get full text

Primed to vocalize: Wild-derived male house mice increase vocalization rate and diversity after a previous encounter with a female. by Sarah M Zala, Doris Nicolakis, Maria Adelaide Marconi, Anton Noll, Thomas Ruf, Peter Balazs, Dustin J Penn

“…We automatically detected USVs and processed recordings using the Automatic Mouse Ultrasound Detector (A-MUD version 3.2), and we describe our improved version of this tool and tests of its performance. We measured vocalization rate and spectro-temporal features and we manually classified USVs into 15 types to investigate priming effects on vocal repertoire diversity and composition. …”
Get full text

Advancing organic photovoltaic materials by machine learning-driven design with polymer-unit fingerprints by Xiumin Liu, Xinyue Zhang, Ye Sheng, Zihe Zhang, Pan Xiong, Xuehai Ju, Junwu Zhu, Caichao Ye

“…The proposed framework demonstrates the ability to design novel materials based on PUFp-ML-established feature/substructure-property relationships, providing rational design guidelines for developing high-performance OPV acceptors. …”
Get full text

MTMU: Multi-domain Transformation based Mamba-UNet designed for unruptured intracranial aneurysm segmentation by Bing Li, Nian Liu, Jianbin Bai, Jianfeng Xu, Yi Tang, Yan Liu

“…To relieve these issues, this article proposes a multi-domain transformation-based Mamba-UNet (MTMU) for UIA segmentation. The model employs a U-shaped segmentation architecture, equipped with the feature encoder consisting of a set of Mamba and Flip (MF) blocks. …”
Get full text

Artificial intelligence and radiomics applications in adrenal lesions: a systematic review by Matteo Ferro, Octavian Sabin Tataru, Giuseppe Carrieri, Gian Maria Busetto, Ugo Giovanni Falagario, Martina Maggi, Felice Crocetto, Biagio Barone, Francesco Del Giudice, Michele Marchioni, Daniela Terracciano, Giuseppe Lucarelli, Pasquale Ditonno, Raul Gherasim, Ciprian Todea-Moga, Giuseppe Fallara, Marco Tozzi, Antonio Cioffi, Roberto Bianchi, Alessio Digiacomo, Alessandro Veccia, Alessandro Antonelli, Maria Chiara Sighinolfi, Luigi Schips, Bernardo Rocco

“…Nuclear medicine (four studies) demonstrated that hybrid 18F-FDG PET/CT models (SUVmax + texture features) achieved an AUC of 0.97 for metastatic versus benign lesions. …”
Get full text

Explainable hybrid transformer for multi-classification of lung disease using chest X-rays by Xiaoyang Fu, Rongbin Lin, Wei Du, Adriano Tavares, Yanchun Liang

“…Several enhancement techniques, such as CLAHE, flipping and denoising, are employed to improve the classification performance of our study. The Grad-CAM visual technique is leveraged to represent the heat map of disease detection, explaining the consistency among clinical doctors and neural network models in the treatment of lung disease from Chest X-ray. …”
Get full text

Early Diagnosis of Alzheimer’s Disease in Human Participants Using EEGConformer and Attention-Based LSTM During the Short Question Task by Seul-Kee Kim, Jung Bin Kim, Hayom Kim, Laehyun Kim, Sang Hee Kim

“…No significant performance difference was observed between the two DL models. …”
Get full text

Characteristics of phase synchronization in electrohysterography and tocodynamometry for preterm birth prediction by Jae-Hwan Kang, Young-Ju Jeon, In-Seon Lee, Junsuk Kim

“…The models’ performance was evaluated by considering varying lengths of time windows and the use of overlapping windows. …”
Get full text

Forecasting Urban Rail Transit Vehicle Interior Noise and Its Applications in Railway Alignment Design by Yifeng Wang, Ping Wang, Zihan Li, Zhengxing Chen, Qing He

“…Parameter, error distribution, and feature importance analyses were conducted for evaluating and optimizing the performance of the RF. …”
Get full text

A Generalized Bandsplit Neural Network for Cinematic Audio Source Separation by Karn N. Watcharasupat, Chih-Wei Wu, Yiwei Ding, Iroro Orife, Aaron J. Hipple, Phillip A. Williams, Scott Kramer, Alexander Lerch, William Wolcott

“…Our best model sets the state of the art on the Divide and Remaster dataset with performance above the ideal ratio mask for the dialogue stem.…”
Get full text

CRM: a new formula for internal coordination by E. V. Berezhnaya, D. A. Duginets

“…The work used methods of theoretical analysis, modeling (in terms of constructing the necessary models of marketing strategies), the method of generalization and induction.Results and discussions. …”
Get full text

A Comprehensive Analysis of Imbalance Signal Prediction in the Japanese Electricity Market Using Machine Learning Techniques by Kaiyao Jiang, Yuji Yamada

“…Power system imbalances pose significant challenges to maintaining grid stability and ensuring efficient market performance, particularly in the context of the Japanese electricity market. …”
Get full text

Advancing Seabed Bedform Mapping in the Kuźnica Deep: Leveraging Multibeam Echosounders and Machine Learning for Enhanced Underwater Landscape Analysis by Łukasz Janowski

“…The study found that models with fewer, carefully selected features performed better, reducing overfitting and computational complexity. …”
Get full text

Data-driven multi-fault detection in pipelines utilizing frequency response function and artificial neural networks by Hussein A. M. Hussein, Sharafiz B. Abdul Rahim, Faizal B. Mustapha, Prajindra S. Krishnan, Nawal Aswan B. Abdul Jalil

“…The location-invariant performance of the ANN model across different sensor placements demonstrates the robustness of the proposed data-driven SHM methodology. …”
Get full text

An Automated Compliance Framework for Critical Infrastructure Security Through Artificial Intelligence by Sardar Muhammad Ali, Abdul Razzaque, Muhammad Yousaf, Rafi Us Shan

“…Model performance was assessed using the F1 score and ROC AUC score. …”
Get full text

Predicting ICU mortality in heart failure patients based on blood tests and vital signs by Yeao Wang, Jianke Rong, Zhili Wei, Xiaoyu Bai, YunDan Deng

“…The performance of the model was assessed through cross-validation and evaluated using the F1-score.ConclusionThrough feature selection, 15 key variables were ultimately identified. …”
Get full text

Leveraging self attention driven gated recurrent unit with crocodile optimization algorithm for cyberattack detection using federated learning framework by Manal Abdullah Alohali, Hatim Dafaalla, Mohammed Baihan, Sultan Alahmari, Achraf Ben Miled, Othman Alrusaini, Ali Alqazzaz, Hanadi Alkhudhayr

“…Initially, the Z-score normalization is utilized to scale and standardize data to improve analysis consistency and accuracy. Furthermore, the feature selection (FS) process uses the crocodile optimization algorithm (COA) model. …”
Get full text

A comparison of McGrath MAC, AIRWAY SCOPE®, and AceScope® video laryngoscopes in novice healthcare providers: a randomized crossover simulation study by Musashi Yahagi, Kyuma Omi, Yuichi Yaguchi

“…Methods Sixty novice healthcare providers, including nurses and pharmacists, were enrolled in this randomized crossover study. Participants performed tracheal intubation using the McGrath MAC, AIRWAY SCOPE, and AceScope in both normal airway and cervical spine immobilization models. …”
Get full text