A Novel Machine Learning Model for the Automated Diagnosis of Nasal Pathology in Canine Patients by Andreea Istrate, Radu Constantinescu, Lithicka Anandavel, Shraddha Rajeshkumar Tandel, Simon Dye, Charlotte Dye

“…The machine learning algorithm showed reasonable accuracy (86%) in classifying the diagnosis from an isolated scan slice but high accuracy (99%) when aggregating over slices taken from a full scan. …”
Get full text

Design and validation of a CFD model for energy-efficient Ni-Co-Mn cathode calcination process by Jaeseop Jo, Minyoung Hwang, Jungeui Lee, Joo Hyun Park

“…The primary objective is to quantitatively predict and optimize energy consumption in high-temperature solid-state synthesis processes. …”
Get full text

Data-Driven Approach for Passenger Mobility Pattern Recognition Using Spatiotemporal Embedding by Chao Yu, Haiying Li, Xinyue Xu, Jun Liu, Jianrui Miao, Yitang Wang, Qi Sun

“…Third, a density-based clustering algorithm is introduced to identify passenger mobility patterns based on the embedded dense trip vectors. …”
Get full text

Determining IFI44 as a key lupus nephritis’s biomarker through bioinformatics and immunohistochemistry by Yue Tan, Xueyao Wang, Deyou Zhang, Jiahui Wang, Shuxian Wang, Jinyu Yu, Hao Wu

“…Additionally, the study characterizes the immune profiles of LN patients through the CIBERSORT algorithm, focusing on the role of interferon-inducible protein 44 (IFI44) as a key biomarker.Results IFI44 shows elevated expression in LN-affected kidneys, compared to healthy controls. …”
Get full text

EEG-Driven Arm Movement Decoding: Combining Connectivity and Amplitude Features for Enhanced Brain–Computer Interface Performance by Hamidreza Darvishi, Ahmadreza Mohammadi, Mohammad Hossein Maghami, Meysam Sadeghi, Mohamad Sawan

“…After preprocessing (resampling, normalization, bandpass filtering), FBCSP and multi-lag PLV features were fused, and the ReliefF algorithm selected the most informative subset. A feedforward neural network achieved average metrics of: Pearson correlation 0.829 ± 0.077, R-squared value 0.675 ± 0.126, and root mean square error (RMSE) 0.579 ± 0.098 in predicting EMG amplitudes indicative of arm movement angles. …”
Get full text

Maglev Derived Systems: An Interoperable Freight Vehicle Application Focused on Minimal Modifications to the Rail Infrastructure and Vehicles by Jesus Felez, Miguel A. Vaquero-Serrano, William Z. Liu, Carlos Casanueva, Michael Schultz-Wildelau, Gerard Coquery, Pietro Proietti

“…Target speed profiles were precomputed using dynamic programming, while a model predictive control algorithm determined the optimal train state and control trajectories. …”
Get full text

Mapping the landscape of AI and ML in vaccine innovation: A bibliometric study by Jirui Niu, Ruotian Deng, Zipu Dong, Xue Yang, Zhaohui Xing, Yin Yu, Jian Kang

“…However, despite the substantial benefits of AI and ML in vaccine innovation, challenges remain regarding data quality, algorithm reliability, and ethical considerations. …”
Get full text

Develoment of The Computer Simulation of Oscillation in Physics Learning by Y Sumardi, A F Amalia, U N Prabowo

“…The research method used was Research and Development (RD) developed by Borg Gall (1983) for developing educational products. They are the pre-product form was developed by creating computer programs based on algorithms, validation through forum group discussion carried out by several lecturers to provide validation of the pre-product, major product revision, the pre-trial by 10 students, operational product revision, the operational product trial carried out by a class of students at the computer laboratory, final product revision, and dissemination.The steps were research and information collection, planning, develop a preliminary form of product, preliminary testing, main product revision, main field testing, and operational product revision. …”
Get full text

Enhanced variable step sizes perturb and observe MPPT control to reduce energy loss in photovoltaic systems by Abdelkadir Belhadj Djilali, Elhadj Bounadja, Adil Yahdou, Habib Benbouhenni, Z. M. S. Elbarbary, Ilhami Colak, Saad F. Al-Gahtani

“…Compared to traditional algorithms, the proposed approach reduces response time and undershoots by 30%, demonstrating superior reliability and performance. …”
Get full text

Advancing smart aquaculture: Cost-efficient strategies for climbing perch cultivation using AI-based models by Kosit Sriputhorn, Achara Jutagate, Surasak Matitopanum, Rungwasun Kraiklang, Rapeepan Pitakaso, Chakat Chueadee, Sarayut Gonwirat

“…By integrating Taguchi experimental design with reinforcement learning and metaheuristic algorithms, the model identifies critical environmental and operational parameters that influence fish growth and economic outcomes. …”
Get full text

Species Distribution Models and Ecological Suitability Analysis for Potential Tick Vectors of Lyme Disease in Mexico by Patricia Illoldi-Rangel, Chissa-Louise Rivaldi, Blake Sissel, Rebecca Trout Fryxell, Guadalupe Gordillo-Pérez, Angel Rodríguez-Moreno, Phillip Williamson, Griselda Montiel-Parra, Víctor Sánchez-Cordero, Sahotra Sarkar

“…The model was based on a maximum entropy algorithm that used environmental layers to predict the relative probability of presence for each taxon. …”
Get full text

Experimental and machine learning based analysis of pervious concrete enhanced with fly ash and silica fume by Siva Shanmukha Anjaneya Babu Padavala, Siva Avudaiappan, Venkatesh Noolu

“…Five algorithms: KNN, Support Vector Machine (SVM), Artificial Neural Networks (ANN), Decision Tree (DT), and Random Forest (RF), were trained and evaluated. …”
Get full text

Data-Driven and Mechanistic Soil Modeling for Precision Fertilization Management in Cotton by Miltiadis Iatrou, Panagiotis Tziachris, Fotis Bilias, Panagiotis Kekelis, Christos Pavlakis, Aphrodite Theofilidou, Ioannis Papadopoulos, Georgios Strouthopoulos, Georgios Giannopoulos, Dimitrios Arampatzis, Evangelos Vergos, Christos Karydas, Dimitris Beslemes, Vassilis Aschonitis

“…By comparing the Mean Absolute Error (MAE) between predicted and observed cotton yield values across three ML algorithms, i.e., Random Forest (RF), XGBoost, and LightGBM, the RF model achieved the lowest error (422.6 kg/ha), outperforming XGBoost (446 kg/ha) and LightGBM (449 kg/ha). …”
Get full text

Integrating Remote Sensing and AI for precision Monitoring of Soil and Vegetation Contamination by M. Spiralski, A. Miszczak, G. Siebielec, Ż. Piasecka, R. Trojnacki, P. Kwaśnik, J. Kotlarz, K. A. Kubiak-Siwinska, M. Kacprzak, S. Marciniak, K. A. Rotchimmel, K. P. Beben, J. Szymanski

“…The future of the study will be focused on the multi-temporal analyses, improving prediction accuracy and dataset and environmental risk mapping. …”
Get full text

Design optimization and generating characteristics of a linear arc PM vernier machine for wave energy conversion system by Urooj Jadoon, Faisal Khan, Salar Ahmad Khalil, Hatim Alwadie, Adoalateef Alzhrani

“…Additionally, M2 and M4 resulted in substantial reductions in copper and iron losses, leading to overall efficiency improvements. …”
Get full text

SPL-PlaneTR: Lightweight and Generalizable Indoor Plane Segmentation Based on Prompt Learning by Zhongchen Deng, Yuanlong Ge, Xiatian Qi, Kai Sun, Ruixi Wan, Bingxu Zhang, Shenman Zhang, Xun Zhang, Yan Meng

Get full text

From understanding to justifying: Computational reliabilism for AI-based forensic evidence evaluation by Juan M. Durán, David van der Vloed, Arnout Ruifrok, Rolf J.F. Ypma

“…However, it is generally not possible to fully understand how and why these algorithms reach their conclusions. Whether and how we should include such ‘black box’ algorithms in this crucial part of the criminal law system is an open question that has not only scientific but also ethical, legal, and philosophical angles. …”
Get full text

<i>Clostridioides difficile</i> Infections in Children: What Is the Optimal Laboratory Diagnostic Method? by Mohammed Suleiman, Patrick Tang, Omar Imam, Princess Morales, Diyna Altrmanini, Jill C. Roberts, Andrés Pérez-López

“…The results of these tests as standalone methods or in four different testing algorithms were compared to a composite reference method on the basis of turnaround time, ease of use, cost, and performance characteristics including specificity, sensitivity, negative predictive value, and positive predictive value. …”
Get full text

Efficient diagnosis of diabetes mellitus using an improved ensemble method by Blessing Oluwatobi Olorunfemi, Adewale Opeoluwa Ogunde, Ahmad Almogren, Abidemi Emmanuel Adeniyi, Sunday Adeola Ajagbe, Salil Bharany, Ayman Altameem, Ateeq Ur Rehman, Asif Mehmood, Habib Hamam

“…The second phase employed the same algorithms alongside sequential ensemble methods—XG Boost, AdaBoostM1, and Gradient Boosting—using an average voting algorithm for binary classification. …”
Get full text

Prognostic risk modeling of endometrial cancer using programmed cell death-related genes: a comprehensive machine learning approach by Tianshu Chen, Yuhan Yang, Zhizhong Huang, Feng Pan, Zhendi Xiao, Kunxue Gong, Wenguang Huang, Liu Xu, Xueqin Liu, Caiyun Fang

“…Results We identified 10 critical genes (PTGIS, TIMP3, SRPX, SNCA, HIC1, BAK1, STXBP2, TRIB3, RTKN2, E2F1) and constructed a prognostic model with superior predictive performance. The StepCox[forward] + plsRcox algorithm combination demonstrated excellent predictive accuracy (AUC > 0.8). …”
Get full text