Parallel boosting neural network with mutual information for day-ahead solar irradiance forecasting by Ubaid Ahmed, Anzar Mahmood, Ahsan Raza Khan, Levin Kuhlmann, Khurram Saleem Alimgeer, Sohail Razzaq, Imran Aziz, Amin Hammad

“…Traditional deep learning (DL) models and decision tree (DT)-based algorithms have been widely employed for this purpose. …”
Get full text

Deep learning-based identification of patients at increased risk of cancer using routine laboratory markers by Vivek Singh, Shikha Chaganti, Matthias Siebert, Sowmya Rajesh, Andrei Puiu, Raj Gopalan, Jamie Gramz, Dorin Comaniciu, Ali Kamen

“…For most screening programs, age and clinical risk factors such as family history are part of the initial risk stratification algorithm. …”
Get full text

Target Detection in Low Grazing Angle with Adaptive OFDM Radar by Yang Xia, Zhiyong Song, Zaiqi Lu, Hao Wu, Qiang Fu

“…Then, we propose an algorithm to optimally design the transmitted subcarrier weights to improve the detection performance. …”
Get full text

Design and Experiment of a Single-Disk Silage Corn Harvester by Wenxuan Wang, Wei Sun, Hui Li, Xiaokang Li, Yongwei Yuan

“…In addition, the main program was optimized by writing the program of the SMPSO algorithm. …”
Get full text

Research and application of flexible starting method for metro trains with permanent magnet motors based on PI control by LIU Zhicheng, CHEN Xijun, HE Ye, HU Hui

“…To address train rollback protection and control, an incremental proportional-integral (PI) algorithm was introduced, by establishing an active rollback prevention and control system model specifically for the train starting process, this approach enhanced the robustness of train starting on inclined track sections. …”
Get full text

Joint Resource Scheduling of the Time Slot, Power, and Main Lobe Direction in Directional UAV Ad Hoc Networks: A Multi-Agent Deep Reinforcement Learning Approach by Shijie Liang, Haitao Zhao, Li Zhou, Zhe Wang, Kuo Cao, Junfang Wang

“…The algorithm with the main lobe direction scheduling improves performance by 67.06% compared to the algorithm without the main lobe direction scheduling.…”
Get full text

Federated learning for digital twin applications: a privacy-preserving and low-latency approach by Jie Li, Dong Wang

“…Our approach introduces an improved Paillier encryption method with a new hyperparameter and pre-calculates multiple random intermediate values during the key generation stage, significantly reducing encryption time and thereby expediting model training. …”
Get full text

A novel double machine learning approach for detecting early breast cancer using advanced feature selection and dimensionality reduction techniques by Suganya Athisayamani, Tamilazhagan S, A. Robert Singh, Jae-Yong Hwang, Gyanendra Prasad Joshi

“…This approach effectively captures both structured features and non-linear patterns, making it suitable for datasets with complex dependencies. The second model pairs eXtreme Gradient Boosting (XGBoost), a highly efficient boosting algorithm for tabular data, with an Artificial Neural Network (ANN). …”
Get full text

GDnet-IP: Grouped Dropout-Based Convolutional Neural Network for Insect Pest Recognition by Dongcheng Li, Yongqi Xu, Zheming Yuan, Zhijun Dai

“…Specifically, we optimized the base model by selecting appropriate optimizers, fine-tuning the dropout probability, and adjusting the learning rate decay strategy. …”
Get full text

Machine learning to predict virological failure among HIV patients on antiretroviral therapy in the University of Gondar Comprehensive and Specialized Hospital, in Amhara Region, E... by Daniel Niguse Mamo, Tesfahun Melese Yilma, Makda Fekadie Tewelgne, Yakub Sebastian, Tilahun Bizuayehu, Mequannent Sharew Melaku, Agmasie Damtew Walle

“…Thus, Machine learning predictive algorithms have the potential to improve the quality of care and predict the needs of HIV patients by analyzing huge amounts of data, and enhancing prediction capabilities. …”
Get full text

Research on intelligent energy management strategies for connected range-extended electric vehicles based on multi-source information by Xuewen Zhai, Hanwu Liu, Wencai Sun, Zihang Su

“…The Euclidean distance between consecutive traffic scenario matrices is used as a basis for similarity to optimize speed and predict future vehicle speeds. Moreover, a multi-objective intelligent EMS based on deep reinforcement learning (DRL) is employed, utilizing the Deep Deterministic Policy Gradient (DDPG) algorithm to comprehensively consider vehicle dynamics, energy consumption economy, and the degradation of batteries. …”
Get full text

Reconstruction for Scanning LiDAR with Array GM-APD on Mobile Platform by Di Liu, Jianfeng Sun, Wei Lu, Sining Li, Xin Zhou

“…This method avoids the need for field-of-view registration, improves data utilization, and reduces the complexity of the algorithm while eliminating the effect of LiDAR motion. …”
Get full text

A Method of Locating and Measuring Train Wheel Tread Defects Based on YOLOv3-tiny by JIN Kairong, WANG Junping, CHEN Shenglan

“…In order to solve the key problems that the detection frame is too large and too small, traditional image algorithms such as Fourier transform, band-stop filter, and threshold segmentation are used to construct a defect size measurement model, contours of roughly located defects are extracted and detection frame size is optimized, and finally location and size of defect are accurately calculated. …”
Get full text

Federated Synergy: Hierarchical Multi-Agent Learning for Sustainable Edge Computing in IIoT by S. Benila, K. Devi

“…It employs multi-agent reinforcement learning to optimize resource allocation and task offloading by leveraging local Actor-Critic models on IoT edge devices. …”
Get full text

Simulation and test study of transmission characteristics of V-shaped rubber belt CVT by TIAN Zhewen, TIAN Hao, CHEN Shuoyan

“…ObjectiveThe dynamic matching problem of continuously variable transmission （CVT） with the engine and Baja racing car was subjected to research analysis.MethodsThe parameters of key components of CVT were first optimized by genetic algorithm in Matlab software, then the dynamic modeling and simulation of CVT and the whole vehicle were carried out in Matlab/Simulink and RecurDyn, and finally the vehicle test was carried out on the chassis dynamometer.ResultsThe results of modeling simulation and vehicle test show that the dynamic index of Baja racing car is significantly improved after the optimization of the parameters of key components of CVT. …”
Get full text

A geometric approach for accelerating neural networks designed for classification problems by Mohsen Saffar, Ahmad Kalhor, Ali Habibnia

Get full text

An interpretable integrated machine learning framework for genomic selection by Jinbu Wang, Jia Zhang, Wenjie Hao, Wencheng Zong, Mang Liang, Fuping Zhao, Longchao Zhang, Lixian Wang, Huijiang Gao, Ligang Wang

“…Moreover, we introduced the NuSVR model, which achieved the highest accuracy among nine compared algorithms. …”
Get full text

MRI-based intratumoral and peritumoral radiomics for assessing deep myometrial invasion in patients with early-stage endometrioid adenocarcinoma by Jing Yang, Yang Liu, Xiaolong Liu, Yaoxin Wang, Xianhong Wang, Conghui Ai, Qiu Bi, Ying Zhao

“…Integrated models were constructed by ensemble and stacking algorithms based on the above radiomics models. …”
Get full text

Uncertainty quantification with graph neural networks for efficient molecular design by Lung-Yi Chen, Yi-Pei Li

“…Using benchmarks from the Tartarus and GuacaMol platforms, our results show that UQ integration via probabilistic improvement optimization (PIO) enhances optimization success in most cases, supporting more reliable exploration of chemically diverse regions. …”
Get full text

Vehicle Reidentification via Multifeature Hypergraph Fusion by Wang Li, Zhang Yong, Yuan Wei, Shi Hongxing

“…To merge multiple feature descriptors, an efficient and appropriate representation is particularly necessary, and a hypergraph is naturally suitable for modeling high-order relationships. In addition, the spatiotemporal correlation of traffic status between cameras is the constraint beyond the image, which can greatly improve the re-ID accuracy of different vehicles with similar appearances. …”
Get full text