Entropy-Guided Distributional Reinforcement Learning with Controlling Uncertainty in Robotic Tasks by Hyunjin Cho, Hyunseok Kim

“…This enables the existing algorithm to learn stably even in scenarios with limited training data, ensuring more robust adaptation. …”
Get full text

Cost-Effective Autonomous Drone Navigation Using Reinforcement Learning: Simulation and Real-World Validation by Tomasz Czarnecki, Marek Stawowy, Adam Kadłubowski

“…A vital component of this approach is creating a multi-stage training environment that accurately replicates actual flight conditions and progressively increases the complexity of scenarios, ensuring a robust evaluation of algorithm performance. …”
Get full text

Enhanced Gold Ore Classification: A Comparative Analysis of Machine Learning Techniques with Textural and Chemical Data by Fabrizzio Rodrigues Costa, Cleyton de Carvalho Carneiro, Carina Ulsen

“…The evaluation was randomly divided into training (60%) and testing (40%) with 10-fold cross-validation. …”
Get full text

Substation Inspection Safety Risk Identification Based on Synthetic Data and Spatiotemporal Action Detection by Chengcheng Liu, Weihua Zhang, Weijin Xu, Bo Lu, Weijie Li, Xuefeng Zhao

“…Finally, using the model trained on the real dataset as a baseline, the evaluation results on the test set shows that the use of synthetic datasets in training improves the model’s average precision by up to 10.7%, with a maximum average precision of 73.61%. …”
Get full text

Two-stage object detection in low-light environments using deep learning image enhancement by Ghaith Al-refai, Hisham Elmoaqet, Abdullah Al-Refai, Ahmad Alzu’bi, Tawfik Al-Hadhrami, Abedalrhman Alkhateeb

“…The ExDark dataset, recognized for its extensive collection of low-light images, served as the basis for training and evaluation. No-reference image quality evaluators were applied to measure improvements in image quality, while object detection performance was assessed using metrics such as recall and mean average precision (mAP). …”
Get full text

Simultaneous OPEX and carbon footprint reduction with hydrogen enhancement in autothermal reforming: a machine learning–based surrogate modeling and optimization framework by Sahar Shahriari, Davood Iranshahi

“…The approach integrates tabular Q-learning with a random forest-based surrogate model to accelerate objective evaluations during policy training, significantly improving sample efficiency and reducing dependence on computationally expensive reactor simulations. …”
Get full text

Development and validation of a machine-learning model for the risk of potentially inappropriate medications in elderly stroke patients by Xiaodan Yang, Qianqian Ye, Mengxiang Zhang, Yuewei Xu, Manqin Yang

“…The dataset was randomly split into training and internal validations sets in a 7:3 ratio. …”
Get full text

The Impact of AI-Generated Instructional Videos on Problem-Based Learning in Science Teacher Education by Nikolaos Pellas

“…The limited impact of the preview feature highlights the need for careful design and evaluation of instructional elements, such as interactivity and adaptive learning algorithms, to fully realize their potential.…”
Get full text

Machine learning of whole-brain resting-state fMRI signatures for individualized grading of frontal gliomas by Yue Hu, Xin Cao, Hongyi Chen, Daoying Geng, Kun Lv

“…The patients were stratified and randomized into the training and testing datasets with a 7:3 ratio. The logical regression, random forest, support vector machine (SVM) and adaptive boosting algorithms were used to establish models. …”
Get full text

Transcriptomic analysis and machine learning modeling identifies novel biomarkers and genetic characteristics of hypertrophic cardiomyopathy by Feng Zhang, Chunrui Li, Lulu Zhang

“…A predictive model for HCM was developed through systematic evaluation of 113 combinations of 12 machine-learning algorithms, employing 10-fold cross-validation on training datasets and external validation using an independent cohort (GSE180313).ResultsA total of 271 DEGs were identified, primarily enriched in multiple biological pathways. …”
Get full text

Adaptive neuro-fuzzy inference systems for improved mastitis classification and diagnosis by Javad Shirani Shamsabadi, Saeid Ansari Mahyari, Mostafa Ghaderi-Zefrehei

“…ANFIS models were evaluated using training and test datasets, and performance metrics derived from confusion matrix (accuracy, precision, recall, F1-score). …”
Get full text

In Vitro Oral Cavity Permeability Assessment to Enable Simulation of Drug Absorption by Pankaj Dwivedi, Priyata Kalra, Haiying Zhou, Khondoker Alam, Eleftheria Tsakalozou, Manar Al-Ghabeish, Megan Kelchen, Giovanni M. Pauletti

Get full text

CLINICAL CONFERENCE AS A FORM OF INDEPENDENT WORK OF INTERNS by T.P. Skripnikova, M.V. Khrebor, Yu.I. Silenko

“…Meeting this challenge requires the focus on active methods of acquiring knowledge, creativity, transition from the current to the individualized training tailored to the needs and abilities of the individual. …”
Get full text

Accurate modeling and simulation of the effect of bacterial growth on the pH of culture media using artificial intelligence approaches by Suleiman Ibrahim Mohammad, Hamza Abu Owida, Asokan Vasudevan, Suhas Ballal, Shaker Al-Hasnaawei, Subhashree Ray, Naveen Chandra Talniya, Aashna Sinha, Vatsal Jain, Ahmad Abumalek

“…Evaluation of model performance demonstrated that the 1D-CNN model exhibited enhanced predictive precision, attaining the minimal RMSE and the maximum R² values and MAPE percentages in both training and testing phases. …”
Get full text

Invisible Manipulation: Deep Reinforcement Learning-Enhanced Stealthy Attacks on Battery Energy Management Systems by Qi Xiao, Lidong Song, Jong Ha Woo, Rongxing Hu, Bei Xu, Kai Ye, Ning Lu

“…Testing on the same testbed allows real-time evaluation of microgrid responses, where the BEMS, EKF-based SoC estimation algorithms interact dynamically with the injected false measurements. …”
Get full text

3D spectral CT-based fusion model predicts prognosis and postoperative adjuvant chemotherapy benefit in locally advanced rectal cancer by Shuxuan Fan, Jiaxin Liu, Xiaomeng Yang, Lisha Qi, Xiaomei Lu, Haiwei Liu, Xiaonan Cui

Get full text

Use of Machine Learning to Predict California Bearing Ratio of Soils by Semachew Molla Kassa, Betelhem Zewdu Wubineh

“…From these evaluation metrics, the random forest algorithm gets a smaller error and larger relative error (R2) value to compare with other algorithms. …”
Get full text

A METHOD FOR INVESTIGATING MACHINE LEARNING ATTACKS ON ARBITER-TYPE PHYSICALLY UNCLONABLE FUNCTIONS by Yuri A. Korotaev

“…A method is proposed to enhance the efficiency of attacks on APUFs by preliminarily selecting an appropriate machine learning algorithm using PUF models. This approach allows for a preliminary evaluation of the effectiveness of different algorithms for attacking APUFs without access to challenge-response datasets from real instances of physically unclonable functions. …”
Get full text

Faster R-CNN-based Detection and Tracking of Hydrogen and Oxygen Bubbles in Alkaline Water Electrolysis by Kohei TOYAMA, Ryo KANEMOTO, Ryuta MISUMI, Takuto ARAKI, Shigenori MITSUSHIMA

“…The images required for CNN training were automatically generated by a pseudo-bubble image generation algorithm specifically developed for the purpose of this study. …”
Get full text

Construction of an oligometastatic prediction model for nasopharyngeal carcinoma patients based on pathomics features and dynamic multi-swarm particle swarm optimization support ve... by Yunfei Li, Dongni Zhang, Yiren Wang, Yiren Wang, Yiheng Hu, Zhongjian Wen, Zhongjian Wen, Cheng Yang, Ping Zhou, Wen-Hui Cheng

“…Based on these screened features, three models were built: Dynamic Multi-Swarm Particle Swarm Optimization SVM (DMS-PSO-SVM), Particle Swarm Optimization SVM (PSO-SVM), and a standard SVM. Model training and hyperparameter tuning were conducted on the training set (n=369), followed by evaluation on a validation set (n=93).Results6 pathomics features were screened as important features. …”
Get full text