Assessing the performance and explainability of an avalanche danger forecast model by C. Pérez-Guillén, F. Techel, M. Volpi, A. van Herwijnen

“…SHapley Additive exPlanations (SHAP) were employed to make the model's decision process more transparent, reducing its “black-box” nature. …”
Get full text

Physics-Guided Memory Network for building energy modeling by Muhammad Umair Danish, Kashif Ali, Kamran Siddiqui, Katarina Grolinger

“…This paper introduces a Physics-Guided Memory Network (PgMN), a neural network that integrates predictions from deep learning and physics-based models to address their limitations. PgMN comprises a Parallel Projection Layers to process incomplete inputs, a Memory Unit to account for persistent biases, and a Memory Experience Module to optimally extend forecasts beyond their input range and produce output. …”
Get full text

Artificial intelligence models for determining the strength of centrally compressed pipe-concrete columns with square cross-section by Chepurnenko Anton, Yazyev Batyr, Tyurina Vasilina, Akopyan Vladimir

“…The best agreement with experimental data was obtained using the layer recurrent neural network model.…”
Get full text

Chinese Sequence Labeling Based on Stack Pre-training Model by LIU Yu-peng, LI Guo-dong

“…Sequence labeling is an important task in natural language processing. In this paper, according to the relevance of tasks, we use stacking pretraining model to extract features, segment words, and name entity recognition/chunk tagging.Through in-depth research on the internal structure of BERT, while ensuring the accuracy of the original model, the Bidirectional Encoder Representation from Transformers （BERT） is optimized, which reduces the complexity and the time cost of the model in the training and prediction process.In the upper layer structure, compared with the traditional long-short-term memory network (LSTM), this paper uses a two-layer bidirectional LSTM structure, the bottom layer uses a bidirectional long-short-term memory network (Bi-LSTM) for word segmentation, and the top layer is used for sequence labeling tasks.On the New Semi-Conditional Random Field (NSCRF), the traditional semi-Markov Conditional Random Field (Semi-CRF) and Conditional Random Field (CRF) are combined while considering the segmentation.The labeling of words improves accuracy in training and decoding. …”
Get full text

Construction exploration and application prospect of the large model in mining industry by Haijun WANG

“…This paper deeply analyzes the challenges of high R&D investment cost, difficulty in collecting high-quality data, and high difficulty in multimodal data fusion technology in the application of large model technology in the coal industry, and summarizes in detail the construction path and phased results achieved by SolStone Mine Large Model to cope with the above challenges from six aspects: infrastructure layer, data resource layer, algorithm model layer, application service layer, security and trustworthiness and testing layer, and industry ecological layer, and finally looks forward to the production and technological changes brought by the development of large model technology to the coal industry. …”
Get full text

Automatic Epilepsy Seizure Classification Using EEG Signals Based on the CNN-LSTM Model by C. Ruth Vinutha, M. S. P. Subathra, S. Thomas George, Geno Peter, Albert Alexander Stonier, N. J. Sairamya, J. Prasanna, Vivekananda Ganji

“…EEG signal features are extracted using the Inception and ResNet layers, and significant features are then trained with a deep convolutional neural network (CNN) integrated with an Adagrad-optimized LSTM layer to classify focal and nonfocal EEG signals. …”
Get full text

Multi-Node Small Radar Network Deployment Optimization in 3D Terrain by Zhiyi Wang, Min Wang, Xinghui Wu, Shuyuan Yang

Get full text

Journaling with large language models: a novel UX paradigm for AI-driven personal health management by Birger Moëll, Fredrik Sand Aronsson, Fredrik Sand Aronsson

“…We propose five design principles for patient-centric AI health tools: (1) decoupling core functionality from LLM dependencies, (2) layered transparency in AI outputs, (3) adaptive consent for data sharing, (4) clinician-facing data summarization, and (5) compliance-first architecture.DiscussionBy transforming unstructured patient narratives into structured insights through natural language processing, this approach demonstrates how journaling interfaces could serve as a critical middleware layer in healthcare ecosystems-empowering patients as active partners in care while preserving clinical oversight. …”
Get full text

Protection Boundary Development in Historical–Cultural Built Environments Using Analytical Hierarchy Process (AHP) and Geographic Information System (GIS) by Can Kara, Aminreza Iranmanesh

“…The proposed method systematically includes economic, architectural, environmental, social, and legal data layers, aiming to generate a more comprehensive model for developing protection boundaries tied to multidimensional and contextual complexities, as well as considering rapid urbanisation patterns. …”
Get full text

Risk Indices Assessment of Different Cyber-Attack Actions for an SDN-Enabled IEC 61850 Substation Using Markov Decision Process by Zhihao Wu, Sugandh Seth, Haiyu Li, Zhirun Hu, James Yu

“…The proposed approach uses 1) the Purdue Model to model attack scenarios using cyber-physical devices at different layers based on typical protection control device arrangement in a substation and 2) the Markov Decision Process (MDP) model to assess cybersecurity risk indices for the substation. …”
Get full text

CROWTH OF THE FAST ICE AND ITS INFLUENCE ON THE FREEZING OF BOTTOM SEDIMENTS IN THE BUOR-KHAYA BAY COASTAL ZONE, LAPTEV SEA by P. V. Bogorodskii, A. S. Grubiy, V. Yu. Kustov, A. P. Makshtas, L. A. Sokolova

“…These data served a basis for development of a conceptual thermodynamic model of seasonal freezing of the sea water layers and underlying bottom sediments in the sea-shore zone. …”
Get full text

Artificial noise-aided robust secure information and power transmission scheme in heterogeneous networks with simultaneous wireless information and power transfer by Bo ZHANG, Kaizhi HUANG, Zhou ZHONG, Yajun CHEN

Get full text

Artificial noise-aided robust secure information and power transmission scheme in heterogeneous networks with simultaneous wireless information and power transfer by Bo ZHANG, Kaizhi HUANG, Zhou ZHONG, Yajun CHEN

Get full text

Numerical Study of the Effects of Heat Loss and Solid Thermal Conductivity on Syngas Production for Fuel Cells by Xiaolong Wang, Mengmeng Yu, Zunmin Li, Zhen Wang, Xiuxia Zhang, Junrui Shi, Xiangjin Kong, Jinsheng Lv

“…In the current paper, the conversion efficiency of methane to synthesis gas (H₂ and CO) within a two-layer porous media reactor is investigated by a one-dimensional two-temperature model. …”
Get full text

Comprehensive Effects of Operation of Pumped-Storage Hydropower Plants on Downstream Conventional Hydropower Plants by ZHU De-kang, QIN Rui, CHENG Xiang, GUO Xu-ye

“…[Methods] To systematically and quantitatively analyze this effect, this study proposed a water consumption rate-head curve fitting method based on a multi-layer perceptron (MLP). By integrating this method with the local grid’s time-of-use electricity pricing policy, a power generation scheduling model for conventional hydropower plants was established. …”
Get full text

Scientific Publications’ Bibliometric Analysis of Application-Level TCP/IP Models’ Communication Protocols for the Internet of Things by O. Borysov

Get full text

Probabilistic regression for autonomous terrain relative navigation via multi-modal feature learning by Ickbum Kim, Sandeep Singh

Get full text

СONCEPT AND CALCULATION OF THE LIMIT TRANSVERSE SIZE OF CAPILLARIES by V. G. Zhukov, N. D. Lukin

“…The absence of formulas for calculating capillaries of the limiting sizes can introduce a significant error into the analytical calculation of the moisture content in the capillary layer of a liquid in porous media and moisture transfer processes. …”
Get full text

Real-Time Optimization of Discrete Element Models for Studying Asphalt Mixture Compaction Characteristics at the Meso-Scale by Xue Wang, Zifang Wang, Xuanye Luo

“…Researchers have employed various technologies to study the compaction process. Among these, discrete element modeling (DEM) has been widely adopted due to its effectiveness in addressing particle-scale problems. …”
Get full text

Unsupervised intrusion detection model based on temporal convolutional network by LIAO Jinju, DING Jiawei, FENG Guanghui

“…Most existing intrusion detection models rely on long short-term memory (LSTM) networks to consider time-dependencies among data. …”
Get full text