AML-Based Multi-Dimensional Co-Evolution Approach Supported by Blockchain: Architecture Design and Case Study on Intelligent Production Lines for Industry 4.0 by Kai Ding, Detlef Gerhard, Liuqun Fan

“…Its innovations are, firstly, developing a comprehensive two-layer management model, combining blockchain with the Interplanetary File System (IPFS) to build an integrated solution for private and public hybrid containers based on a collaborative model; secondly, designing a version co-evolution management method by combining smart contract workflows and AML multi-dimensional modeling processes; meanwhile, introducing a specially designed conflict resolution mechanism based on the graph model to maintain consistency in version multi-batch management and; finally, using the test cases established in the lab’s I5Blocks for verification.…”
Get full text

AER U-Net: attention-enhanced multi-scale residual U-Net structure for water body segmentation using Sentinel-2 satellite images by Naga Surekha Jonnala, Shaik Siraaj, Y. Prastuti, P. Chinnababu, B. Praveen babu, Shonak Bansal, Prashant Upadhyaya, Krishna Prakash, Mohammad Rashed Iqbal Faruque, K. S. Al-mugren

“…The architecture employs a contracting path consisting of convolutional layers, batch normalization, and activation layers to extract multi-scale features. …”
Get full text

Quality evaluation of Polygonatum sibiricum slices from different regions based on appearance traits and multi-index metabolites combined with TOPSIS and gray relation analysis by Cheng Wang, Cheng Wang, Ju Ye, Sisi Jiang, Sisi Jiang, Xuguang He, Xuguang He, Min Ma, Min Ma, Li Yin

“…PCA showed that the first three principal components contributed over 80% of the cumulative variance, and 16 batches of slices were clustered into three categories by origin. …”
Get full text

Enhancing Recognition and Categorization of Skin Lesions with Tailored Deep Convolutional Networks and Robust Data Augmentation Techniques by Syed Ibrar Hussain, Elena Toscano

“…Multiple networks, including XceptionNet, DenseNet, MobileNet, NASNet Mobile, and EfficientNet, were evaluated to test deep learning’s potential in complex, multi-class classification tasks. Training these models on pre-processed datasets with optimized hyper-parameters (e.g., batch size, learning rate, and dropout) improved classification precision for early-stage skin cancers. …”
Get full text

Modulation recognition method based on multiscale convolutional fusion coding networks by LI Guojun, ZHU Siyuan, ZHENG Jianzhong, WANG Jie, YE Changrong

“…A multi-head self-attention mechanism was utilized to enable parallel processing for capturing diverse signal characteristics. …”
Get full text

Integrated Metabolomics and Lipidomics Analysis Reveals the Mechanism Behind the Action of Chiglitazar on the Protection Against Sepsis-Induced Acute Lung Injury by Liu-Liu Lu, Yu-Li Cao, Zhen-Chen Lu, Han Wu, Shan-Song Hu, Bing-Qing Ye, Jin-Zhi He, Lei Di, Xu-Lin Chen, Zhi-Cheng Liu

Get full text

Physics-based and data-driven hybrid modelling and optimisation of stirred-slurry reactors for CO2 capture via enhanced weathering of dolomite mineral by Yalun Zhao, Mingliang Wang, Jin Xuan, Dengao Chang, Ziming Li, Shiyu Wang, Yun Ou, Xu Wang, Lei Xing

“…The energy consumption for gas enrichment in the batch system is expected to be less than 50% of that in continuous systems. …”
Get full text

Engineering a controlled cardiac multilineage co-differentiation process using statistical design of experiments by Hirokazu Akiyama, Yosuke Katayama, Kazunori Shimizu, Hiroyuki Honda

“…Given that the performance of progenitor cell induction may critically influence the overall process performance, we carefully optimized activin A and CHIR-99021 using the sequential design of experiments to achieve approximately 95% induction efficiency of KDR+/PDGFR-α+ cardiogenic mesoderm cells from iPSCs with minimal batch-to-batch variability. In the trilineage co-differentiation stage, we developed unique multi-response models to delineate trilineage co-differentiation ratios within a defined parameter space of WNT signal inhibitor and vascular endothelial growth factor. …”
Get full text

A Feature Engineering Framework for Smart Meter Group Failure Rate Prediction by Yihong Li, Xia Xiao, Zhengbo Zhang, Wenao Liu

“…Smart meters are grouped by batch and distribution area. Next, 25 condition features are constructed based on failure mechanisms and technical specifications. …”
Get full text

Synthesis and characterization of polyurethane based on hydroxyl terminated polybutadiene and reinforced by carbon nanotubes by S.A. Shokry, A.K. El Morsi, M.S. Sabaa, R.R. Mohamed, H.E. El Sorogy

“…Nanocomposites consisting of multi wall carbon wall carbon nano tubes MWCNT/polyurethane (PU) had been successfully prepared based on hydroxy terminated polybutadiene HTPB and the prepared MWCNT. …”
Get full text

Investment Decision Model of Rural Power Grid Projects Considering Contribution of Rural Revitalization by Huiru ZHAO, Manyu YAO, Bingkang LI, Guanglong XIE, Zhihua DING, Zhenda HU

Get full text

Implementation of MF block in CNN for advanced REB fault diagnosis by M. Pandiyan, Narendiranath Babu T.

“…By incorporating techniques such as batch normalization and dropout, the model has improved stability and prevented overfitting. …”
Get full text

Cost-Effective Multitask Active Learning in Wearable Sensor Systems by Asiful Arefeen, Hassan Ghasemzadeh

Get full text

Simultaneous determination of five nitroimidazole antimicrobials in pharmaceuticals using HPLC-ESM and QAMS methods by Baoxia Fang, Dan Jiang, Sicen Wang, Fuchao Chen

“…The methods were validated in terms of linearity, intra- and inter-batch precision, accuracy, stability, and recovery. …”
Get full text

Research on the Lossless Data Compression System of the Argo Buoy Based on BiLSTM-MHSA-MLP by Sumin Guo, Wenqi Zhang, Yuhong Zheng, Hongyu Li, Yilin Yang, Jiayi Xu

“…This study addresses the issues of the limited data storage capacity of Argo buoys and satellite communication charges on the basis of data volume by proposing a block lossless data compression method that combines bidirectional long short-term memory networks and multi-head self-attention with a multilayer perceptron (BiLSTM-MHSA-MLP). …”
Get full text

Lightweight pose estimation spatial-temporal enhanced graph convolutional model for miner behavior recognition by WANG Jianfang, DUAN Siyuan, PAN Hongguang, JING Ningbo

“…The generated skeleton sequences were processed by the BN layer for batch normalization, and the miner behavior features were extracted through the multi-dimensional feature-enhanced graph convolution module. …”
Get full text

Partially characterized topology guides reliable anchor-free scRNA-integration by Chuan He, Paraskevas Filippidis, Steven H. Kleinstein, Leying Guan

“…To address this, we propose scCRAFT, an autoencoder model that separates cell-type-related signals from batch effects for reliable multi-batch integration. scCRAFT integrates three key loss components: a reconstruction loss for observation reconstruction, a multi-domain adaptation loss to eliminate batch effects, and an innovative dual-resolution triplet loss to preserve intra-batch, introduced as an effective mechanism to counteract the over-correction effect of domain adaptation loss amid heterogeneous cell distributions across batches. …”
Get full text

Performance of automated machine learning in detecting fundus diseases based on ophthalmologic B-scan ultrasound images by Chen Zhao, Rui Jiang, Qian Chen, Qiaoling Wei

“…Batch prediction accuracies ranged from 86.57% to 97.65% for various fundus conditions in the multi-label AutoML model. …”
Get full text

Dose sensitivity of MAGIC-f polymer gel using different MRI sequences by Nícollas Gonçalves Cavedini, Ricardo Meurer Papaléo, Nícolas Borges Jobim, Phelipi Nunes Schuck, Fabrício Nery Garrafiel, Elisa Magno Nunes de Oliveira, Marcelo Menna Barreto Schwarcke, Alex Cristóvão Holanda de Oliveira, Paulo Rauli Rafeson Vasconcelos Caribé, Ana Maria Marques da Silva

“…In the first batch, doses of 0, 2, 4, 6, 8, 10, 20, and 40 Gy were planned. …”
Get full text

Sub-Pilot-Scale and Bench-Scale Reactor Tests and Thermodynamic Integrated Process Analysis of Production of H₂ from Woody Biomass via Chemical Looping by Ranjani Siriwardane, Jarrett Riley, Chris Atallah, Michael Bobek

“…Multi-reactor approaches were experimentally simulated by switching the gas atmosphere around the batch charge of the OC. …”
Get full text