Experimental study on purification of low concentration coalbed methane by hydrate method under amino acid system by Tian ZHAO, Yongliang XU, Lanyun WANG, Zecheng LYU, Xingwang HUO

“…However, their effects on coalbed methane separation by hydrate method in synergy with 1,3−dioxolane are not known. Amino acids are efficient green kinetic promoters for hydrate generation and can be used in gas storage and transportation technologies. …”
Get full text

MDEU-Net: Medical Image Segmentation Network Based on Multi-Head Multi-Scale Cross-Axis by Shengxian Yan, Yuyang Lei, Jing Zhang, Xiao Gao, Xiang Li, Penghui Wang, Hui Cao

“…Additionally, a gated attention mechanism facilitates efficient feature fusion by selectively emphasizing key features rather than relying on simple concatenation and improves the model’s ability to capture critical details at multiple scales. …”
Get full text

A Multi-Branch Convolution and Dynamic Weighting Method for Bearing Fault Diagnosis Based on Acoustic–Vibration Information Fusion by Xianming Sun, Yuhang Yang, Changzheng Chen, Miao Tian, Shengnan Du, Zhengqi Wang

“…Although existing methods have achieved certain success in processing acoustic and vibration signals, they still face challenges such as insufficient feature fusion, inflexible weight allocation, lack of effective feature selection mechanisms, and low computational efficiency. …”
Get full text

Inhibition of Semliki Forest virus replication with long double-stranded RNA in Aedes albopictus cells by Alejandra Centurión, Bodunrin Omokungbe, Sabrina Stiehler, Andreas Vilcinskas, Kornelia Hardes

“…Our results highlight the importance of efficient dsRNA delivery and selection of critical viral targets, such as nsP4, for successful RNAi-mediated viral suppression. …”
Get full text

The Role of Hydroxyl Modification of Peptidoglycan to Reduce the TTX Toxicity via Superior Absorption by Chang’e Wang, Yi Guo, Lili Zhang, Junjian Miao, Ying Lu

“…Peptidoglycan (PG) of lactic acid bacteria could adsorb TTX; however, its complex structure and poor solubility limited adsorption efficiency. …”
Get full text

ACU-Net: Attention-based convolutional U-Net model for segmenting brain tumors in fMRI images by Md Alamin Talukder, Md Abu Layek, Md Aslam Hossain, Md Aminul Islam, Mohammad Nur-e-Alam, Mohsin Kazi

“…This study introduces the attention-based convolutional U-Net (ACU-Net) model, designed to improve segmentation accuracy and efficiency in fMRI images by incorporating attention mechanisms that selectively highlight critical features while preserving spatial context. …”
Get full text

Downlink wireless resource allocation method of V2X based on wireless sensing assistance by Zhimin HE, Yuzhe LIN, Yujie CHENG, Shi YAN

“…In vehicle-to-everything, the high-speed distribution and sharing of perception and safety data is crucial to road safety.However, the instability of communication links caused by high-speed vehicle movement will make the existing communication resource allocation methods based on vehicle location information reporting no longer efficient.Therefore, a downlink wireless resource allocation method based on wireless sensing assistance of communication nodes was proposed.Firstly, a joint optimization problem of communication mode selection and wireless resource allocation under the orthogonality of communication and sensing resources was constructed.Then, a communication mode selection based on clustering by Delaunay triangulation and a resource allocation strategy based on improved graph coloring to improve the downlink throughput was proposed to solve the problem of construction.Finally, the impact of wireless sensing estimation error and the number of vehicles on the performance of the algorithm was simulated and analyzed.Simulation results show that compared with traditional methods, the proposed algorithm can obtain better downlink communication performance gain under the same proportion of sensing bandwidth resources, and can withstand the impact of larger sensing errors on performance.At the same time, the computational complexity of the proposed algorithm is lower and the network computing resources can be saved.…”
Get full text

Balancing Depth for Robustness: A Study on Reincarnating Reinforcement Learning Models by Gang Li, Zhuxiao Wang, Shaowei He, Xiyuan Chen, Yunlei Xie, Jiajun Hu, Kehe Wu, Jingping Jia

“…While deeper networks risk overfitting, shallower architectures struggle to cope with complex task dynamics. Our results highlight the key role of adaptive depth in enhancing the generalization, stability, and efficiency of RRL models.…”
Get full text

Harnessing the Power of Improved Deep Learning for Precise Building Material Price Predictions by Zhilong Guo, Yayong Luo, Tongqiang Yi, Xiangnan Jing, Jing Ma

“…This approach offers new insights for short-term price prediction of building materials and contributes to enhancing the economic benefits and management efficiency of construction projects.…”
Get full text

Matrix Theory for Neutrosophic Hypersoft Set and Applications in Multiattributive Multicriteria Decision-Making Problems by Muhammad Naveed Jafar, Muhammad Saeed

“…Lastly, decision-making issues have been presented by establishing a new algorithm based on a score function, and it has been interpreted with the help of numerical example for the selection of teachers at the college level. In this study, NHSM algorithm is elaborated efficiently and conveniently for optimal choice selection to solve decision-making problems.…”
Get full text

PIV-inspired triboelectric nanogenerator for airflow velocity sensing by Sijie Li, Hongyang Ning, Rui Lei, Fujian Zhang, Zhen Liu, Zhongqiang Zhang

“…Fluid diagnostic technologies play a central role in elucidating flow mechanisms, optimizing the performance of aerospace systems, supporting energy transition, and enhancing the operational efficiency of underwater equipment. However, conventional flow field measurement techniques are often limited by high costs, poor adaptability to complex environments, and demanding system requirements. …”
Get full text

Focal Mechanism and Moment Tensor Determination for Tsunami Early Warning Systems: A Literature Study (2018–2024) by Titi Handayani, Wijayanto, Adhi Harmoko Saputro, Mohd Asyraf Zulkifley, Dede Djuhana

“…AI methods could offer novel opportunities in seismology considering the potential to enhance analysis efficiency and accuracy of focal mechanism and moment tensor, providing additional insights into earthquake characteristics quickly, accurately, and automatically. …”
Get full text

A Multivariable Probability Density-Based Auto-Reconstruction Bi-LSTM Soft Sensor for Predicting Effluent BOD in Wastewater Treatment Plants by Wenting Li, Yonggang Li, Dong Li, Jiayi Zhou

“…To address this issue, this paper proposed a multivariable probability density-based auto-reconstruction bidirectional long short-term memory (MPDAR-Bi-LSTM) soft sensor for predicting effluent BOD, enhancing the prediction accuracy and efficiency. Firstly, the selection of appropriate auxiliary variables for soft-sensor modeling is determined through the calculation of k-nearest-neighbor mutual information (KNN-MI) values between the global process variables and effluent BOD. …”
Get full text

Structured Summarization of League of Legends Match Data Optimized for Large Language Model Input by Jooyoung Kim, Wonkyung Lee, Jungwoon Park

“…Large-scale match data from esports games like League of Legends are stored in complex JSON files that often exceed the input token limitations of large language models (LLMs), restricting advanced analysis and applications such as automated commentary and strategic insight generation. …”
Get full text

Enhancing Autonomous Truck Navigation in Underground Mines: A Review of 3D Object Detection Systems, Challenges, and Future Trends by Ellen Essien, Samuel Frimpong

“…Integrating autonomous haulage systems into underground mining has revolutionized safety and operational efficiency. However, deploying 3D detection systems for autonomous truck navigation in such an environment faces persistent challenges due to dust, occlusion, complex terrains, and low visibility. …”
Get full text

Enhanced Software Testing Model Under Software Warranty Policy Considering Debugger Learning and Time Postponement Factors by Wang Li, Chih-Chiang Fang

“…This allows for the selection of the most effective option. The model takes into account the learning curve, which can significantly impact the efficiency of the software testing process. …”
Get full text

HASSDE-NAS: Heuristic–Adaptive Spectral–Spatial Neural Architecture Search with Dynamic Cell Evolution for Hyperspectral Water Body Identification by Feng Chen, Baishun Su, Zongpu Jia

“…This approach outperforms existing methods in delineating narrow river systems and resolving water bodies with weak spectral contrast under complex backgrounds, such as vegetation or cloud shadows. …”
Get full text

A comparative study of machine learning algorithms for fall detection in technology-based healthcare system: Analyzing SVM, KNN, decision tree, random forest, LSTM, and CNN by Afuan Lasmedi, Isnanto R. Rizal

“…The implications of these findings that the selection of fall detection algorithms must consider system priorities, whether focused on high accuracy or processing efficiency. …”
Get full text

Spectrum Allocation and Power Control Based on Newton’s Method for Weighted Sum Power Minimization in Overlay Spectrum Sharing by Yang Yu, Xiaoqing Tang, Guihui Xie

“…Maximizing weighted sum energy efficiency (WSEE) requires solving complex multiple-ratio fractional programming (FP) problems. …”
Get full text

A two-stage framework for enhancing crsyptocurrency portfolio performance: Integrating credibilistic CVaR criterion with a novel asset preselection approach. by Hossein Ghanbari, Sina Tavakoli, Mostafa Shabani, Emran Mohammadi, Seyed Jafar Sadjadi, Ronald Ravinesh Kumar

“…The results of this two-stage framework demonstrate its effectiveness in constructing well-diversified and efficient portfolios, addressing both the challenges of asset pre-selection and the complexities associated with uncertainty. …”
Get full text