TIBW: Task-Independent Backdoor Watermarking with Fine-Tuning Resilience for Pre-Trained Language Models by Weichuan Mo, Kongyang Chen, Yatie Xiao

“…Pre-trained language models such as BERT, GPT-3, and T5 have made significant advancements in natural language processing (NLP). …”
Get full text

KANDiff: Kolmogorov–Arnold Network and Diffusion Model-Based Network for Hyperspectral and Multispectral Image Fusion by Wei Li, Lu Li, Man Peng, Ran Tao

“…Diffusion models, known for their stable training process and exceptional image generation capabilities, have shown good application potential in this field. …”
Get full text

An optimal operation method for hydrogen refueling stations considering the electric energy-reserve-hydrogen coupling market environment by ZHOU Xin, CHEN Shun, TAN Hong, CHEN Daicai, RAN Menghong

Get full text

Construction and application of two intrinsic models for Ti-Al composite plates considering current parameters by Tao Huang, Yihan Zhai, Binghui Xing, Chaomin Zhang, Nan Xiang, Kexing Song, Wenjing Zhang, Lei Shi

“…By employing ABAQUS finite element software, we conducted a finite element analysis of the EA forming process. A modified heterogeneous layer ontology model for Ti-Al composite plates was used in this process. …”
Get full text

Decoding Human Facial Emotions: A Ranking Approach Using Explainable AI by Sudheer Babu Punuri, Sanjay Kumar Kuanar, Tusar Kanti Mishra, Veeranki Venkata Rama Maheswara Rao, Shiva Shankar Reddy

Get full text

Collaborative planning of distribution-grid and micro-grid considering bilateral transactions under wind-solar uncertain conditions by Shuzheng WANG, Shouhao WU, Zhi WU, Yuzhu SUN

Get full text

Decomposition-Aware Framework for Probabilistic and Flexible Time Series Forecasting in Aerospace Electronic Systems by Yuanhong Mao, Xin Hu, Yulang Xu, Yilin Zhang, Yunan Li, Zixiang Lu, Qiguang Miao

“…This design enables the model to process multiple distinct sequences independently while maintaining the flexibility to learn shared patterns across channels. …”
Get full text

Insights into structure and activity of a UDP-GlcNAc 2-epimerase involved in secondary cell wall polymer biosynthesis in Paenibacillus alvei by Cordula Stefanović, Max S. G. Legg, Nick Mateyko, Jakob J. Ender, Tea Kuvek, Chris Oostenbrink, Christina Schäffer, Stephen V. Evans, Fiona F. Hager-Mair

Get full text

Ultra-Reliable and Low-Latency Wireless Hierarchical Federated Learning: Performance Analysis by Haonan Zhang, Peng Xu, Bin Dai

“…However, due to the broadcast nature of wireless communication, the WHFL is susceptible to eavesdropping during the training process. Apart from this, recently ultra-reliable and low-latency communication (URLLC) has received much attention since it serves as a critical communication service in current 5G and upcoming 6G, and this motivates us to study the URLLC-WHFL in the presence of physical layer security (PLS) issue. …”
Get full text

Research and application of innovative models for public data integration based on secure multi-party computation by Jiahe JIN, Chengyao ZHAO, Haoze QIU, Peng LIU

“…Secure multi-party computation is widely used in finance, the Internet, and other fields to solve the problem of ＆quot;data silos＆quot;, but its application in the field of public data is not yet mature.An innovative model for public data integration based on secure multi-party computation was proposed, and a technical architecture for joint computing using public data from different parties while protecting their private information was presented.The model breaks through institutional constraints through technological innovation, achieving a balance between improving data value and ensuring data security.Three sub-layers of the core system of secure multi-party computation in the proposed model, including the joint computation substructure layer, the secure relational algebra layer, and the basic operator layer of secure multi-party computation were mainly analyzed.Additionally, a general process for implementing the innovative model was presented, and the practical application of the innovative model was also discussed.The results of this study provide a new reference for promoting digital China construction and facilitating the flow of data resources.…”
Get full text

Enhancing corn industry sustainability through deep learning hybrid models for price volatility forecasting. by Chengjin Yang, Yanzhong Zhai, Zehua Liu

“…The model integrates a three-layer decomposition combined dual-filter time-series denoising method (TLDCF-TSD), a bidirectional time-convolutional enhancement network (BiTCEN), a bidirectional long- and short-term memory network (BiLSTM), and a frequency-enhanced channel attention mechanism (FECAM) to improve prediction accuracy and robustness. …”
Get full text

Training Language Models for Estimating Priority Levels in Ultrasound Examination Waitlists: Algorithm Development and Validation by Kanato Masayoshi, Masahiro Hashimoto, Naoki Toda, Hirozumi Mori, Goh Kobayashi, Hasnine Haque, Mizuki So, Masahiro Jinzaki

“…ObjectiveThis study aimed to investigate potential challenges associated with using language models for estimating the priority of medical examination requests and to evaluate the performance of language models in processing Japanese medical texts. …”
Get full text

The shallowest transparent and interpretable deep neural network for image recognition by Gurmail Singh, Stefano Frizzo Stefenon, Kin-Choong Yow

“…Abstract Trusting the decisions of deep learning models requires transparency of their reasoning process, especially for high-risk decisions. …”
Get full text

Investigation of process parameter influence on the mechanical properties of FDM-printed PEEK-carbon fiber composites using RSM and Taguchi methods by Muhammad Nasir Bashir, Joon Sang Lee, Mohammed A. Bou-Rabee, Heba G. Mohamed, Ding Zhou, Irfan Anjum Badruddin, M.A. Fazal, Zafar Masood

“…The models can improve the mechanical performance of FDM printed parts by optimising process parameters across multiple objectives. …”
Get full text

Adaptation of Concrete Model to 3D Printing Technology by Oleg Kabantsev

“…This study presents the results of adapting an existing mathematical model of concrete, originally based on the isotropic properties of traditional cast concrete, to the conditions of 3D printing technology using layer-by-layer horizontal extrusion. …”
Get full text

Effect of Fused Filament Fabrication Parameters on Selected Indicators for Assessing Technological Quality of Shaped Models by Marek Łoś, Wojciech Zawadka, Krzysztof Nadolny

“…The conducted tests showed that samples with a layer height of 0.12 mm have the most advantageous surface roughness parameters compared to the other layer heights of 0.16 mm and 0.20 mm tested. …”
Get full text

DermaTransNet: Where Transformer Attention Meets U-Net for Skin Image Segmentation by Anum Abdul Salam, Muhammad Usman Akram, Muhammad Haroon Yousaf, Babar Rao

“…To enhance the efficacy of analysis and assist pathologists, computer-aided diagnostic systems have been proposed to automate the process of disease detection and classification. A crucial initial step in skin disease diagnosis is the accurate segmentation of skin layers, as it facilitates the identification of regions of interest for subsequent processing. …”
Get full text

Deformation and Evolution of Akata Formation Mudstone in the Niger Delta Basin: Insights from Analogue Models by Shuaiyu Shi, Wenlong Ding, Yixin Yu, Jixin Zhang

“…The simulation of the evolutionary process and evolutionary model established in this study improves the understanding of mudstone tectonics and provides a reference for analyzing the genetic mechanism and hydrocarbon exploration in the basin.…”
Get full text

Exploring the aerosol activation properties in coastal shallow convection using cloud- and particle-resolving models by G. Yu, Y. Wang, Z. Wang, X. Shi, X. Shi

“…The differences between the aerosol populations in the boundary layer and at cloud altitudes highlight the necessity of vertical observations and numerical modeling. …”
Get full text

Modelling of elastoviscoplastic properties of the subgrade. Problem statement 1 by V. M. Bel’Kov

Get full text