Benchmarking Diffusion Annealing-Based Bayesian Inverse Problem Solvers by Evan Scope Crafts, Umberto Villa

“…The results provide insight into the strengths and limitations of existing diffusion-model based posterior samplers, while the benchmark problems provide a testing ground for future algorithmic developments.…”
Get full text

Improving Surgical Site Infection Prediction Using Machine Learning: Addressing Challenges of Highly Imbalanced Data by Salha Al-Ahmari, Farrukh Nadeem

“…Grid search five-fold cross-validation was employed for comprehensive hyperparameter optimization, in conjunction with balanced sampling techniques. …”
Get full text

Skewed Multifractal Cross-Correlations Between Green Bond Index and Energy Futures Markets: A New Perspective Based on Change Point by Yun Tian, Zhihui Li, Jue Wang, Xu Wu, Huan Huang

“…This study is the first to use the Bayesian Estimator of Abrupt Change, Seasonality, and Trend (BEAST) algorithm to detect trend change points in the nexuses between the green bond index (Green Bond) and WTI of crude oil, gasoline, as well as natural gas futures. …”
Get full text

An Innovative Priority-Aware Mission Planning Framework for an Agile Earth Observation Satellite by Guangtong Zhu, Zixuan Zheng, Chenhao Ouyang, Yufei Guo, Pengyu Sun

“…The proposed approach effectively maintains satellite maneuver constraints while achieving significant improvements in priority-based target acquisition and computational efficiency. …”
Get full text

Robust Adaptive Fractional-Order PID Controller Design for High-Power DC-DC Dual Active Bridge Converter Enhanced Using Multi-Agent Deep Deterministic Policy Gradient Algorithm for... by Seyyed Morteza Ghamari, Daryoush Habibi, Asma Aziz

“…To overcome this issue, Grey Wolf Optimization (GWO) algorithm is proposed to identify the most suitable initial gains for each agent, providing faster adaptation and consistent performance during the training process. …”
Get full text

Frame Theory and Fractional Programming for Sparse Recovery-Based mmWave Channel Estimation by Razvan-Andrei Stoica, Hiroki Iimori, Giuseppe Thadeu Freitas de Abreu, Koji Ishibashi

“…The two algorithms differ from each other in that in the first (slightly more accurate), the resulting convex problem is solved via interior point methods, while the second (stand-alone) makes use of the alternating direction method of multipliers (ADMM). …”
Get full text

Container Liner Shipping System Design Considering Methanol-Powered Vessels by Zhaokun Li, Xinke Yu, Jianning Shang, Kang Chen, Xu Xin, Wei Zhang, Shaoqiang Yu

“…Moreover, we propose an adaptive piecewise linearization approach combined with a genetic algorithm, which can efficiently solve large-scale instances. …”
Get full text

Protecting digital assets using an ontology based cyber situational awareness system by Tariq Ammar Almoabady, Yasser Mohammad Alblawi, Ahmad Emad Albalawi, Majed M. Aborokbah, S. Manimurugan, Ahmed Aljuhani, Hussain Aldawood, P. Karthikeyan

“…The Isolation Forest algorithm excels in anomaly detection in high-dimensional datasets, while autoencoders provide nonlinear detection capabilities and adaptive feature learning. …”
Get full text

AI-Driven Innovation in Skin Kinetics for Transdermal Drug Delivery: Overcoming Barriers and Enhancing Precision by Nubul Albayati, Sesha Rajeswari Talluri, Nirali Dholaria, Bozena Michniak-Kohn

“…Machine learning models trained on extensive molecular datasets predict skin permeability and accelerate the selection of suitable drug candidates. AI-driven algorithms optimize formulations, including penetration enhancers and advanced delivery technologies like microneedles and liposomes, while ensuring safety and efficacy. …”
Get full text

Streaming LiDAR Scene Flow Estimation by Mazen Abdelfattah, Z. Jane Wang, Rabab Ward

“…Furthermore, to enhance test-time optimization within our streaming framework, our novel initialization scheme ’warm-starts' the current optimization using optimized parameters from the preceding slice. …”
Get full text

Simplifying the calibration of ecological models by using the parameter estimation tool (PEST): The Curonian Lagoon case by Burak Kaynaroglu, Mindaugas Zilius, Rasa Idzelytė, Artūras Razinkovas-Baziukas, Georg Umgiesser

“…However, we challenged this assumption by initiating the inverse problem at different locations in the parameter space using a robust variant of a gradient-based method, which ultimately resulted in a better fit than global methods.We tested four different optimization algorithms available in the PEST and PEST++ suites. …”
Get full text

Machine learning-based prediction method for open-pit mining truck speed distribution in manned operation by Changyou XU, Gang CHEN, Qiuxia ZHANG, Bo WANG, Hongwang ZHANG, Hongrui LI, Weiwei QIN, Muyang LI

“…Finally, machine learning algorithms such as random forest and XGBoost are used to predict vehicle speed based on onboard data and weather sensor data. …”
Get full text

A data-driven approach utilizing machine learning (ML) and geographical information system (GIS)-based time series analysis with data augmentation for water quality assessment in M... by Abhijeet Das

“…From the results, it produces two metrics, TKN and coliform, that are higher than WHO guidelines while maintaining the optimal level of DO throughout the duration of the study. …”
Get full text

Evaluating Customer Segmentation Techniques in the Retail Sector by Nur Diyabi, Duygu Çakır, Ömer Melih Gül, Tevfik Aytekin, Seifedine Kadry

“…DBSCAN showed strengths in identifying non-spherical clusters, while GMM and SOM provided more granular segmentation. …”
Get full text

Designing an Adaptive Velocity Obstacle Avoidance System for Autonomous Mars Rover Navigation in Dynamic Terrains by Karim Ahmadi Dastgerdi, SeyedehMarziyeh SalehiGhahfarokhi, Sadegh Ahmadi Dastgerdi

Get full text

Calibrating multiplex serology for Helicobacter pylori by Emmanuelle A. Dankwa, Martyn Plummer, Daniel Chapman, Rima Jeske, Julia Butt, Michael Hill, Tim Waterboer, Iona Y. Millwood, Ling Yang, Christiana Kartsonaki

“…We discuss these challenges and propose a novel solution to optimize the translation of the continuous measurements from multiplex serology into probabilities of H. pylori infection, using classification algorithms (Bayesian additive regressive trees (BART), multidimensional monotone BART, logistic regression, random forest and elastic net). …”
Get full text

Integrated energy microgrid bi-level game scheduling optimization taking into account electricity-heat-hydrogen enriched compressed natural gas coupling and shared energy storage by Changgang Wang, Xiaoning Sun

“…Additionally, tiered carbon trading mechanisms, integrated demand response strategies, and shared energy storage are introduced to optimize carbon reduction on both the demand and storage sides while effectively constraining energy emissions. …”
Get full text

Deep Learning-Based Detection of Aflatoxin B1 Contamination in Almonds Using Hyperspectral Imaging: A Focus on Optimized 3D Inception–ResNet Model by Md. Ahasan Kabir, Ivan Lee, Sang-Heon Lee

Get full text

Construction and Application Analysis of an Intelligent Distribution Network Identification System Based on Deep Neural Networks by Yu Ma

“…In addition, the Cross-Validation Grid Search Algorithm (GSA) was used to optimize the hyperparameters to ensure that the model can achieve the optimal performance on different data sets. …”
Get full text

HypE-GA based study on optimal design of standard floor facade windowing of high-rise office buildings facing energy saving in heating, cooling and lighting. by Weixiang Zhang, Jieli Sui

“…Therefore, this paper takes the standard floor of a high-rise office building as the research object in cold region-Yantai, facing façade windowing design, the three building performance objectives of each office unit-Annual Cooling Energy Consumption (AC), Annual Heating Energy Consumption (AH) and Annual Lighting Energy Consumption (AL)-are simulated and single/multi-objective optimized by relying on Ladybug and Honeybee (LB + HB) platform and Hypervolume Estimation Genetic Algorithm (HypE-GA) to obtain the genome of Pareto-Window-to-Wall Ratio (WWR), Window Height (WH) and Sill Height (SH)-at the lowest of each performance objective in order to determine the most energy-efficient façade windowing expression. …”
Get full text