Research Progress on Sequence Recommendation Based on Deep Learning and Large Language Model by XU Fengru, LI Bohan, XU Shuai

“…Firstly, the research problem of sequential recommendation is defined, and the core objectives and challenges of recommendation sequences are clarified. Next, the main techniques in sequential recommendation are summarized in detail, including: traditional methods based on Markov chains, which model user behavior sequences by relying on state transition probabilities; deep learning-driven methods, which utilize neural network models to capture long-term dependencies and complex patterns; hybrid models, which combine multiple algorithms to enhance the accuracy and robustness of recommendation systems; and emerging methods based on large language models, which improve the understanding of user behavior and recommendation content through the integration of pre-trained large language models. …”
Get full text

On Complexities of Impact Simulation of Fiber Reinforced Polymer Composites: A Simplified Modeling Framework by M. Alemi-Ardakani, A. S. Milani, S. Yannacopoulos

“…Different numerical algorithms have been developed over the past decades for impact modeling of composites, yet a considerable gap often exists between predicted and experimental observations. …”
Get full text

Intelligent Recognition and Automated Production of Chili Peppers: A Review Addressing Varietal Diversity and Technological Requirements by Sheng Tai, Zhong Tang, Bin Li, Shiguo Wang, Xiaohu Guo

“…The main current research challenges are listed including the environmental adaptability/robustness, efficiency/real-time performance, multi-cultivar adaptability/flexibility, system integration, and cost-effectiveness. …”
Get full text

High-speed threat detection in 5G SDN with particle swarm optimizer integrated GRU-driven generative adversarial network by R. Shameli, Sujatha Rajkumar

“…The attack detection in 5G SDN involves Machine learning (ML) and Deep learning (DL) algorithms to analyze large volumes of network data and identify patterns indicative of attacks. …”
Get full text

Identifying the optimal number of topics in text mining: a case study on reindeer pastoralism literature by Barbara Contiero, Øystein Holand, Giulio Cozzi

“…Text mining and topic analysis algorithms which group textual contents in the most efficient way, are becoming increasingly useful to summarise the main information contained in large data corpus of complex scientific fields. …”
Get full text

On the Prediction and Forecasting of PMs and Air Pollution: An Application of Deep Hybrid AI-Based Models by Youness El Mghouchi, Mihaela Tinca Udristioiu

“…The methodology consists of three main phases: (i) data preprocessing, including anomaly detection and missing value handling; (ii) exploratory analysis to identify trends and correlations between PM concentrations (PMs) and predictor variables; and (iii) model development using 23 machine learning and deep learning algorithms, enhanced by 50 feature selection techniques. …”
Get full text

Experimental Study on Blockage Mechanism and Blockage Locations for Polymer-Flooded Reservoirs in the Henan Oilfield by Yu Li, Meilong Fu, Baofeng Hou, Zhiyuan Zhang, Ruiyi Sun

“…The “four properties” relationship of the formation reservoir in the Nanbaxian oil and gas field was studied in depth according to the conventional logging data and core analysis data. The neural network algorithm was used to reconstruct the resistivity curve of the water layer to eliminate the influence of lithology, shale content, and pore structure on the resistivity. …”
Get full text

Prognostic genes in colon cancer and their correlation with immune cells: an analysis based on bioinformatics by Gu Zhiwen, Wu Yinteng, Liao Cun, Ma Hui, Zhang Sen, Zhang Xiaolong

“…The prognosis-related genes were screened and their expression was verified by qPCR. Cibersort algorithm was used to analyze the correlation between prognostic genes and immune cells. …”
Get full text

Collaborative swarm robotics for sustainable environment monitoring and exploration: Emerging trends and research progress by Belkacem Khaldi, Fouzi Harrou, Ying Sun

“…Recent methods in this cluster utilize deep reinforcement learning and heuristic algorithms to enhance cooperation efficiency. Five potential directions categorized into two main groups are explored to address security and reliability challenges within swarm robot systems in environmental tasks. …”
Get full text

A new approach for diabetes risk detection using quadratic interpolation flower pollination neural network by Yulianto Triwahyuadi POLLY, Adriana FANGGIDAE, Juan Rizky Mannuel LEDOH, Clarissa Elfira AMOS PAH, Bertha S. DJAHI, Kisan Emiliano Rape TUPEN

“…The evaluation was based on three main aspects: accuracy, F1 score, and training time. …”
Get full text

Evaluating the Potential of SDGSAT-1 Glimmer Imagery for Urban Road Detection by Yu Wang, Hailan Huang, Bin Wu

“…Watershed segmentation and optimal thresholding algorithms were applied to extract the road network data of these five cities. …”
Get full text

Drone-based fault recognition in power systems: a systematic review of intelligent methods by Carlos A. F. Persiani, Felipe M. Sallazar, Roberto S. Inoue, Valdir Grassi, Marco H. Terra, Mário Oleskovicz

“…In this survey, we explore the main strategies of evolving Drone-based intelligent inspection methods for fault recognition in electrical power systems. …”
Get full text

Topical Issues of Drug Safety, Possibilities of Improving of Pharmacovigilance by M. V. Zhuravleva, B. K. Romanov, G. I. Gorodetskaya, O. V. Muslimova, V. S. Krysanova, E. Yu. Demchenkova

“…The analysis of pharmacovigilance structure in the Russian Federation is carried  out, its main problems are designated. Presents methods to identify causal relationships between adverse reaction and drug, evaluation of its degree of validity (questionnaires, algorithms, and scale), as already recommended by the WHO, and the new modifi ed versions. …”
Get full text

Sieving with Streaming Memory Access by Ziyu Zhao, Jintai Ding, Bo-Yin Yang

“… We implement an optimized BGJ (Becker–Gama–Joux 2015) sieve and analyze its behavior in a study of RAM access overheads (and their minimization) in sieving algorithms for large lattice problems. Both experiment and theory points to BGJ’s inherent structure being much more memory-efficient than the BDGL (Becker–Ducas– Gama–Laahoven 2016) sieve, which uses asymptotically the fewest logical operations. …”
Get full text

A comparative study of deepfake facial manipulation technique using generative adversarial networks by Wasin Al Kishri, Jabar H. Yousif, Mahmood Al Bahri, Muhammad Zakarya, Naveed Khan, Sanad Sulaiman Al Maskari, Ahmet Gurhanli

“…In recent years, Deepfake algorithms have been designed to exchange faces or modify facial features, potentially leading to more severe problems in this context. …”
Get full text

Methodical approaches to the economic assessment of costs in the operation of cars with axial load of 27 tons at the section Kachkanar—Smychka by G. A. Granovskaya, A. I. Safonova, O. A. Suslov, N. S. Okhotnikov

“…The article describes method of calculating the coefficient reflecting the change in the impact of cars with an axial load of 27 tons on the roadbed during transportation in estimated cars compared to transportation in equivalent cars. Algorithms for calculating changes in the cost of fuel and energy costs for train traction and maintenance of the track infrastructure on the site during the operation of trains formed from cars with an axial load of 27 tons are given, as well as methods for determining the initial data for the calculation.Authors provide values of the coefficient reflecting the change in the impact of vertical and horizontal forces on the railway line when passing freight cars with an axial load of 27 tons compared to analogue cars, and the coefficient of change of the main specific resistance to motion separately for loaded and empty cars.Developed calculation algorithms and methods for obtaining baseline data allow an economic assessment of changes in infrastructure maintenance costs and fuel and energy resources for the operation of trains formed from cars with an axial load of 27 tons compared to those formed from cars with a load of 23.5 tons at the experimental section Kachkanar—Smychka.The cost change assessment carried out in 2017 shows a generally definite economic effect, while there is a reduction in costs associated with the consumption of electricity for train traction as a result of the operation of the estimated cars in the experimental section and an increase in the cost of maintaining the track superstructure and the roadbed, which is quite expected for the conditions of the organization of traffic with increased axial loads.…”
Get full text

Two-stage spline-approximation in linear structure routing by D. A. Karpov, V. I. Struchenkov

“…This circumstance fundamentally complicates the problem and does not allow using mathematical models and nonlinear programming algorithms to solve it, since the dimension of the problem is unknown. …”
Get full text

Monitoring the dynamics of coastal wetlands ecosystems in Brittany (France) using LANDSAT time series and machine learning by Adrien Le Guillou, Simona Niculescu

“…The study exploits the potential of satellite image time series (SITS), machine learning (ML), and Random Forest (RF) algorithms.These algorithms enable the software to learn autonomously from multiple datasets, including Landsat 4/5 and 8 SITS archive images. …”
Get full text

Designing Predictive Tools for Personalized Functionalities in Knitted Performance Wear by Martijn ten Bhömer, Hai-Ning Liang, Difeng Yu, Yuanjin Liu, Yifan Zhang, Eva de Laat, Carola Leegwater

“…(2) How to design interactions and interfaces that use intelligent predictive algorithms to stimulate creativity during the fashion design process? …”
Get full text

Old Drugs, New Indications (Review) by I. I. Miroshnichenko, E. A. Valdman, I. I. Kuz'min

“…Using deep learning, DNN were found to outperform other algorithms for drug development and toxicity prediction.Conclusion. …”
Get full text