MEASegNet: 3D U-Net with Multiple Efficient Attention for Segmentation of Brain Tumor Images by Ruihao Zhang, Peng Yang, Can Hu, Bin Guo

“…In pursuit of improved segmentation precision for brain tumor MRI images, we propose the MEASegNet, which incorporates multiple efficient attention mechanisms into the 3D U-Net architecture. …”
Get full text

High-performance parallel acceleration method for domestic public key cryptographic algorithm SM2 based on domestic GPU by WU Wen, DONG Jiankuo, LIU Pengbo, DONG Zhenjiang, HU Xin, ZHANG Pinchang, XIAO Fu

“…Then, point addition and point doubling were implemented using Jacobian coordinates, leveraging register and global memory features, and offline/online precomputation tables were introduced to enhance scalar multiplication efficiency. Finally, experimental design was carried out based on the characteristics of the Hygon deep compute unit (DCU) platforms, achieving high-performance SM2 signature and verification with throughput of 6 816 kops/s and 1 385 kops/s, respectively. …”
Get full text

Effect of Sodium Nitroprusside with Plant Growth Regulators on in vitro Propagation and Genetic Stability of ‘Barhee’ Date Palm (Phoenix dactylifera L.) by Al-Mayahi Ahmed Madi Waheed

“…Date palm micropropagation still faces many limitations in practical applications due to tissue browning, reduced callus growth and development, low organogenesis and multiplication efficiency, and low rooting rate. This study investigated the effects of sodium nitroprusside (SNP), a source of nitric oxide and plant growth regulators, on the growth attributes and some biochemical constituents of in vitro cultured ‘Barhee’ date palm. …”
Get full text

An End-to-End Relearning Framework for Building Energy Optimization by Avisek Naug, Marcos Quinones-Grueiro, Gautam Biswas

“…Building HVAC systems face significant challenges in energy optimization due to changing building characteristics and the need to balance multiple efficiency objectives. Current approaches are limited: physics-based models are expensive and inflexible, while data-driven methods require extensive data collection and ongoing maintenance. …”
Get full text

A full-stack memristor-based computation-in-memory system with software-hardware co-development by Ruihua Yu, Ze Wang, Qi Liu, Bin Gao, Zhenqi Hao, Tao Guo, Sanchuan Ding, Junyang Zhang, Qi Qin, Dong Wu, Peng Yao, Qingtian Zhang, Jianshi Tang, He Qian, Huaqiang Wu

“…The software aspect enables automatic model placement and multiple efficient optimizations. The proposed optimization methods can enhance the robustness of model weights against hardware nonidealities during the training phase and automatically identify the optimal hardware parameters to suppress the impacts of analogue computing noise during the inference phase. …”
Get full text

Ensemble EfficientNet: a novel technique for identification, classification and prediction of diabetic retinopathy by Nilesh Shelke, Rachna Somkunwar, Amit Pimpalkar, Sudhanshu Maurya, Sharda Chhabria

“…Utilizing the publicly available Kaggle DR Dataset, we pre-processed the images and divided them into training and validation sets. Multiple EfficientNet models were trained with various hyperparameters, and their predictions were combined through an ensemble learning approach. …”
Get full text

Advanced Multi-Level Ensemble Learning Approaches for Comprehensive Sperm Morphology Assessment by Abdulsamet Aktas, Taha Cap, Gorkem Serbes, Hamza Osman Ilhan, Hakkı Uzun

“…Features extracted from multiple EfficientNetV2 variants are fused and classified using Support Vector Machines (SVM), Random Forest (RF), and Multi-Layer Perceptron with Attention (MLP-Attention). …”
Get full text