Nondestructive detection of sweet potato leaf curl virus using 3D laser imaging combined with deep learning by Yican Yang, Nuwan K. Wijewardane, Tyler J. Slonecki, Phillip A. Wadl, Sharon A. Andreason, Jingdao Chen, Lorin Harvey

“…Experiments were then conducted to fine-tune the hyperparameters of the PointNet++ algorithm. The results showed that the optimal hyperparameter configuration entailed the adoption of the multi-scale sampling and grouping (MSG) strategy, with the augmented point cloud down sampled to 2048 points and a batch size of 8, yielding a classification accuracy of 87.7 %. …”
Get full text

Stochastic <i>H</i>_∞ Filtering of the Attitude Quaternion by Daniel Choukroun, Lotan Cooper, Nadav Berman

“…Thanks to the bilinear structure of the quaternion state-space model, the algorithm parameters are independent of the state. …”
Get full text

Cardiac Computed Tomography Measurements in Pulmonary Embolism Associated with Clinical Deterioration by Anthony J. Weekes, Angela M. Pikus, Parker L. Hambright, Kelly L. Goonan, Nathaniel O’Connell

“…Introduction: Most pulmonary embolism response teams (PERT) use a radiologist-determined right ventricle to left ventricle ratio (RV:LV) cut-off of 1.0 to risk-stratify pulmonary embolism (PE) patients. …”
Get full text

A semantic segmentation-based automatic pterygium assessment and grading system by Qingbo Ji, Qingbo Ji, Wanyang Liu, Wanyang Liu, Qingfeng Ma, Qingfeng Ma, Lijun Qu, Lin Zhang, Hui He

“…This study aims to develop an automated grading system combining deep learning and image processing techniques for precise pterygium evaluation.MethodsThe proposed system integrates two modules: 1) A semantic segmentation module utilizing an improved TransUnet architecture for pixel-level pterygium localization, trained on annotated slit-lamp microscope images from clinical datasets. 2) A severity assessment module employing enhanced curve fitting algorithms to quantify pterygium invasion depth in critical ocular regions. …”
Get full text

PERSONALIZED APPROACH TO THYROTOXICOSIS TREATMENT: THE HISTORY OF DOSIMETRIC CONCEPTS DEVELOPMENT by P. O. Rumyantsev, A. A. Trukhin, M. V. Degtyarev

“…Historically there were developed several methods for calculating effective therapeutic activity: prescription of standard activities (fixed activities) and personalized assessment of effective activity based on evaluation of individual radiobiokinetics, followed by the mathematical modeling. Accumulated variety of approaches to dosimetric planning of radionuclide therapy demonstrates that an optimal algorithm for calculation has not been developed so far. …”
Get full text

Increment of Academic Performance Prediction of At-Risk Student by Dealing With Data Imbalance Problem by Nguyen Giap Cu, Thi Lich Nghiem, Thi Hoai Ngo, Manh Tuong Lam Nguyen, Hong Quan Phung

“…Studies on automatically predicting student learning outcomes often focus on developing and optimizing machine learning algorithms that fit the data captured from different education systems. …”
Get full text

Estimation of mangrove heights and aboveground biomass using UAV-LiDAR, Sentinel-1 and ZY-3 stereo images by Bolin Fu, Yingying Wei, Linhang Jiang, Hang Yao, Xiaomin Li, Yanli Yang, Mingming Jia, Weiwei Sun

“…The ZY-3 stereo images based on MDN obtained the optimal inversion results (R2 = 0.719), with an improvement ranging from 0.143 to 0.198 when compared to the PLSR and RF algorithms. (3) Avicennia marina was associated with the highest estimation accuracy (R2 = 0.897) compared to the other dominant mangrove species. …”
Get full text

TECHNOLOGICAL ADVANCES IN ELECTROPLATING: ARTIFICIAL INTELLIGENCE TO PREDICT ZINC COATING THICKNESS ON SAE 1008 LOW CARBON STEELS by Luciano M. L. de Oliveira, Fabiana L. da Silva, Paulo R. Janissek, Juliano C. Toniolo

“…Statistical analysis and supervised machine learning algorithms, including multivariate regression, random forest, and extreme gradient boosting (XGBoost), were employed to develop prediction models. …”
Get full text

Research on the quantification and automatic classification method of Chinese cabbage plant type based on point cloud data and PointNet++ by Chongchong Yang, Chongchong Yang, Lei Sun, Lei Sun, Jun Zhang, Jun Zhang, Xiaofei Fan, Xiaofei Fan, Dongfang Zhang, Dongfang Zhang, Tianyi Ren, Tianyi Ren, Minggeng Liu, Minggeng Liu, Zhiming Zhang, Zhiming Zhang, Wei Ma, Wei Ma

“…Finally, we combined 1024 feature vectors with 10 custom dimensionless features and used the optimized PointNet++ model for supervised learning to achieve the automatic classification of Chinese cabbage plant types. …”
Get full text

Intelligent collaborative management and control platform for continuous mining equipment in open-pit mines by Zhiyong LEI, Xiaolong MA, Shujun ZHAO, Shiming ZHANG, Bin YAN

“…The platform integrates advanced technologies, including dual-ring network transmission, network security protocols, multi-machine cooperative control, digital twin modeling, and big data analytics, facilitating effective coordination among coal miners, transfer machines, unloaders, and conveyors for seamless continuous mining operations.Three critical technical challenges are addressed: ① The implementation of dual-ring network transmission technology reduces data transmission latency and enhances network stability. ② A secure network transmission framework has been developed to safeguard data confidentiality and integrity. ③ The multi-machine cooperative control system incorporates data acquisition, process control, and 3D visualization modules, employing real-time monitoring and optimized control algorithms to boost mining and transportation efficiency while ensuring the continuity of multi-machine operations. …”
Get full text

Research on image generation technology based on deep learning by Li Jinchen

“…Based on the above problems, this paper analyzes the methods of improving and optimizing the mainstream image generation algorithm from the perspectives of improving and optimizing the loss function, improving the space modeling, revising the structure of both the generator and discriminator, while speeding up the training process. …”
Get full text

Integrating cyber-physical systems with embedding technology for controlling autonomous vehicle driving by Manal Abdullah Alohali, Hamed Alqahtani, Abdulbasit Darem, Monir Abdullah, Yunyoung Nam, Mohamed Abouhawwash

“…Deep reinforcement learning (DRL) has emerged as a strong tool for dealing with such uncertainty, yet current DRL models struggle to ensure safety and optimal behaviour in indeterminate settings due to the difficulties of understanding dynamic reward systems. …”
Get full text

Automated Recognition of Abnormalities in Gastrointestinal Endoscopic Images – Evaluation of an AI Tool for Identifying Polyps and Other Irregularities by Weronika Jarych, Elżbieta Tokarczyk, Patryk Iglewski, Daria Ziemińska, Karina Motolko, Rafał Burczyk, Konrad Duszyński, Michał Kociński, Jan Reinald Wendt

“…Key advantages of AI integration in endoscopy include improved sensitivity, minimized detection errors, and the potential to optimize clinical workflow efficiency. …”
Get full text

AI-Driven Robotics: Innovations in Design, Perception, and Decision-Making by Lei Li, Li Li, Mantian Li, Ke Liang

“…Artificial intelligence (AI), driven by large datasets and advanced algorithms, plays a pivotal role in addressing these challenges and advancing robotics. …”
Get full text

Recent Advances in Multi-Agent Reinforcement Learning for Intelligent Automation and Control of Water Environment Systems by Lei Jia, Yan Pei

“…Multi-agent reinforcement learning (MARL) has demonstrated significant application potential in addressing cooperative control, policy optimization, and task allocation problems in complex systems. …”
Get full text

The Alliance of BIM and Artificial Intelligence: Challenges for a Reinvented Future – The State of the Art by Ellyssa Abdelmoula, Meriem Zammel, Najla Allani

“…A literature review was conducted to examine research published on the integration of BIM and AI, identifying key challenges, gaps and proposed solutions to improve interoperability, data security and workflow optimization. …”
Get full text

CPFD Simulation of Operation Characteristics of a 10t/d Sludge and Biomass Co-incineration Fluidized Bed Reactor by REN Shaohui, YU Qiao, LIN Li, XIANG Jiatao, MA Lun, ZHANG Shihong

“…ObjectiveThis research aims to comprehensively investigate the operational dynamics of a 10t/d sludge and biomass co-incineration fluidized bed reactor through Computational Particle Fluid Dynamics (CPFD) modeling, addressing critical gaps in industrial-scale waste valorization. …”
Get full text

Convolutional neural networks and vision transformers for Plankton Classification by Loris Nanni, Alessandra Lumini, Leonardo Barcellona, Stefano Ghidoni

“…The study considers the creation of ensembles combining different Convolutional Neural Network (CNN) models and transformer architectures to understand whether different optimization algorithms can result in more robust and efficient classification across various plankton datasets. …”
Get full text

Convergence of evolving artificial intelligence and machine learning techniques in precision oncology by Elena Fountzilas, Tillman Pearce, Mehmet A. Baysal, Abhijit Chakraborty, Apostolia M. Tsimberidou

“…Currently, many operational and technical challenges exist related to data technology, engineering, and storage; algorithm development and structures; quality and quantity of the data and the analytical pipeline; data sharing and generalizability; and the incorporation of these technologies into the current clinical workflow and reimbursement models.…”
Get full text

Integrating holographic counterparts for intelligent IoT consumer devices by M. Rajesh, M. Usha, Sathishkumar Veerappampalayam Easwaramoorthy

“…Advancements in quantum algorithms for predictive learning, self-optimization through more integrated machine learning models, and the development of standardised interoperability protocols to facilitate wider industrial usage are all areas that will be investigated in future research.…”
Get full text