Artificial intelligence (AI) and big data are increasingly applied in drug regulation and have demonstrated significant potential worldwide. The U.S. Food and Drug Administration (FDA) has developed a relatively comprehensive approach through strategic frameworks, regulatory guidelines, and pilot programs. The European Medicines Agency (EMA) has promoted AI adoption via the Big Data Task Force, DARWIN EU®, and a multi-annual work plan, while Japan, Canada, and other countries have also advanced relevant initiatives and strengthened international cooperation. In China, smart regulation has been incorporated into the "14th Five-Year Plan" and subsequent strategies, with progress in establishing national regulatory data platforms, pharmaceutical traceability systems, and pilot AI applications. Nevertheless, AI in drug regulation remains at an exploratory stage, facing challenges such as limited model reliability and interpretability, insufficient data standards and interoperability, regulatory gaps, and ethical as well as public trust concerns. Future progress will depend on strengthening regulatory standards, enhancing data governance, improving regulatory capacity, and deepening international collaboration to achieve more scientific, intelligent, and efficient drug regulation.

• We use PQk-means to convert AIS trajectories into sequences of code documents. • We apply TF-IDF to extract code distribution-based representation of trajectories. • We compute cosine similarity to find similar trajectories and vessels. • We apply K-means to cluster voyages and vessels from the proposed representation. • We use SVM to recognize vessels based on the proposed representation. Automatic Identification System (AIS) data received from vessels in a maritime area of interest is a valuable resource for understanding vessel behavior and gaining insights into maritime activities. This paper presents a novel approach for representing vessel trajectories using code distribution and analyzing AIS trajectory big data through machine learning techniques. By introducing PQk-means vector quantization algorithms, AIS trajectory data records are transformed into a series of code documents. Applying the TF-IDF (Term Frequency-Inverse Document Frequency) technique from text mining to these code documents produces a code distribution-based representation of vessel trajectories. This preliminary process enables the application of machine learning algorithms to AIS trajectory big data. Using this representation, three types of applications have been developed: detecting similar trajectories and vessels using vector space models and cosine similarity, clustering voyages and vessels with the K-means algorithm, and recognizing vessels with support vector machine algorithms. The potential of the proposed approach is demonstrated through a series of experiments using practical AIS datasets from a region in northwest France. Overall, the experimental results show that the proposed approach is highly effective for mining AIS big data, outperforms other methods, and confirms its ability to handle high-dimensional trajectories and massive amounts of AIS data within a reasonable computational cost. Moreover, this work provides an opportunity to develop an AIS-oriented version of a large language model based on our code distribution representation of trajectories, and to extend trajectory representation to any type of moving object or numerical vector from diverse sensors.

Artificial intelligence and automated monitoring for Marine Protected Area Management: A case of Chaojing marine protected area in Taiwan

Urbanisation, climate change, and natural hazards pose significant threats to urban development and environmental health, particularly in developing countries (DCs) across Asia, South America, and Africa. Urban resilience (UR) is critical for managing these challenges, especially in urban historic areas (UHAs). Despite its importance, there has been no systematic review of UR in DCs, specifically addressing the unique problems of historical sectors and potential solutions to enhance UR. This study aims to address this gap by examining the UR of DCs in response to urbanisation and risks impacting urban historic areas (UHAs). The research focuses on key UR indicators, including infrastructure, social systems, economic diversity, environmental sustainability, and cultural heritage (CH). A comprehensive literature review was conducted using reliable scientific databases, employing a thematic analysis approach to categorise and synthesise key findings. Key themes explored include the definition and components of UR, associated challenges, strategies for improvement, and the roles of Geographic Information Systems (GIS), Remote Sensing (RS), big data, Artificial Intelligence (AI) and multi-criteria decision-making (MCDM) tools. A comparative analysis of UR experiences in DCs was undertaken, featuring case studies from ten cities in each of the three continents (Asia, Latin America & Africa). The findings indicate the multifaceted nature of UR, underscoring its importance in maintaining critical functions and fostering positive development amid diverse challenges. Although some studies included a combination of different UR challenges, there were natural hazards in Asia (50%) and Africa (70%), and human-urbanization hazards (70%) in Latin America, compared to other aspects. The study contributes to a deeper understanding of UR in DCs, offering valuable insights from multiple perspectives and laying the groundwork for enhanced UR strategies in UHAs.

Metabolomics, the comprehensive analysis of low-molecular-weight metabolites, is central to biomarker discovery, drug development, and precision medicine. While large-scale metabolomics from biobanks could greatly advance individualized healthcare, conventional GC–MS and LC-MS approaches remain limited by time-consuming preparation and separation, restricting sample throughput. Matrix-assisted laser desorption/ionization mass spectrometry (MALDI-MS) offers a high-throughput alternative, being robust to contaminants and compatible with automated formats. Moreover, coupling MALDI with ion mobility (IM) expands molecular coverage by combining m/z and collision cross section measurements, positioning MALDI-IM-MS as a scalable platform for next-generation metabolomics and clinical big-data applications. The MALDI-IM-MS workflow, combined with acetonitrile extraction, enabled reproducible detection of >2000 features spanning hydrophilic and lipid metabolites across a broad m/z range. Ion mobility separation enhanced coverage beyond 700 features and resolved isomeric species by collision cross section (CCS) values. Averaging signals from multiple raster positions kept coefficients of variation below 20%, while adduct correlations (R 2 > 0.90) indicated strong quantitative potential. UMAP analysis of 34 specimens reliably clustered replicates and separated healthy volunteers from cancer patients, revealing both shared and disease-specific metabolic alterations. Notably, plasma LPC levels, known to decrease in malignancies, were consistently reduced across patient groups, confirming clinical observations. Despite the relatively small cohort, these results demonstrate that MALDI-IM-MS can sensitively capture disease-related metabolic alterations and provides a scalable platform for large-scale cancer metabolomics and precision medicine applications. The approach presented in this study offers a promising solution for conducting large-scale clinical trials with minimal effort, and is expected to serve as a big data generation platform that contributing to “precision medicine” by utilizing existing biobanks. Furthermore, we believe that this technology can be used not only in clinical research, but also to large-scale chemical and biochemical screening in a wide range of research fields, including pharmaceuticals, food, fisheries, livestock, and agriculture. • MALDI-IM-MS detects over 2000 metabolites within seconds per sample • Quantitative reproducibility achieved with CV values below 20% • Ion mobility with m/z enhances coverage and accuracy of detection • Quantitative reproducibility achieved with CV values below 20% • Plasma profiling visualizes metabolic differences among cancer types

Three-dimensional mapping of key soil properties with multi-stage validation and big data

Balancing transportation needs of national parks and local communities: an interdisciplinary approach

How digital intelligence technologies reshape emergency collaboration: An agent-based model of multi-actor governance

Retraction notice to “Integrated Development of Industrial and Regional Economy using Big Data Technology” [Computers and Electrical Engineering 109 (2023) 108764

Possible adverse effects of mining activity on the neurocognitive development of children in the area of Cerro de Pasco (Perú).

An efficient big data framework for validating the random walk hypothesis in high-frequency markets via neural networks and large language models

Integrating machine learning algorithms and game theory for optimized shipyard site selection in Istanbul

Big data energy systems: A survey of practices and associated challenges

A hybrid metaheuristics-Bayesian optimization framework with safe transfer learning for continuous spark tuning

Retraction notice to “Mobile internet big data technology-based echo loss measurement method of optical communication system” [Computers and Electrical Engineering 101 (2022) 108097

Urban villages and the new dual structure: Integrating multi-source big data to understand informality and socio-spatial dynamics

Dynamically cross-linked PVA hydrogel reinforced with poly(γ-glutamic acid) for highly Stretchable and rapidly self-healing wearable sensors.

<p>Future unavoidable development of individualized brain anatomy as a part of personalized medicine requires large databases from a vast number of individual brains. The simple descriptions, important in the clinic, demonstrated the wide morphological and morphometric variability of the sulci and gyri. Today, it is no longer enough, like in traditional anatomy, to simply describe one single, several, or even "all" sulcal/gyral variations in one region of the brain. Potential problems in the comprehensive analysis of their patterns with attempts to suggest further research are briefly reviewed. The medial hemispheric surface is suitable for a morphological pilot study of complete sulcal and gyral variability. Sulcal patterns should be presented in simplified linear form rather than as detailed images, and one useful simplification for analyzing gyral patterns, the essential gyral line, is described. Simultaneous investigation of gyri and sulci is recommended, but the problem is combinations of specific patterns in different percentages. Sophisticated algorithms could recognize cortical patterns and calculate their possible combinations. Anatomical terminology is an unavoidable component of these studies. Big data about variations of sulci and gyri would be useful in personalized medicine but also in genetic studies of potential laws and inheritance of their associations.</p>

ABSTRACT There is a great health challenge caused by liver disorders in terms of the rising incidence, late diagnosis, and the high number of deaths associated with these conditions. Liver cirrhosis, fatty liver, hepatitis, and liver cancer, among other diseases, do not manifest signs early and hence cannot easily be diagnosed through standard clinical means. The standard approaches used include laboratory and radiologic tests and physicians' expertise. However, they could be too costly and unreliable as well. In recent years, new technologies based on artificial intelligence (AI) have been developed for predicting, diagnosing, and classifying advanced liver disorders. In this research, various techniques based on AI, such as machine learning (ML) and deep learning (DL), will be used for the purpose of detecting liver disorders. Algorithms like decision tree, random forest, support vector machine (SVM), k-nearest neighbor (KNN), and neural networks will be used to extract information from data obtained both clinically and biochemically. The method will be composed of four stages including preprocessing, feature extraction, model training, and performance estimation. Besides, DL models are applied to detect complicated structures in medical data sets. The AI model will aid in early risk detection, classification of diseases, and decision-making in the medical field. The system will be beneficial in helping healthcare experts make more precise and efficient diagnoses while minimizing human errors. Also, AI models will facilitate an automatic analysis of big data for effective predictions about liver disorders. From the findings, it is evident that the use of AI models improves the accuracy of diagnoses when compared to traditional methods. The inclusion of AI in healthcare systems will be advantageous in promoting early interventions, developing personalized treatments, and managing complicated cases of liver disorders. Thus, AI models have great prospects in diagnosing liver conditions. . Keywords: Artificial Intelligence ( AI), Machine Learning ( ML), Deep Learning ( DL), Liver Disorder Detection, Liver Disease Prediction, Clinical Decision Support System ( CDSS)

A significant increase in the number of patent publications in recent years has created difficulties in conducting classical manual analysis and searching for patent analogues. Automation of the search for patent analogues is a key tool for reducing time and financial costs at the stages of patent application formation and patent examination. The use of Big Data technologies and distributed systems makes it possible to build an effective architecture of a system of patent analogues and improve the quality of patent search results. The theoretical significance of the work lies in the development of the architecture and concept of a full-text patent search system based on a comparative analysis of the effectiveness of various distributed systems for searching and processing textual Russian-language information, taking into account its morphological and syntactic features. The practical significance of the work lies in the implemented software, which includes tools for parsing patent documents into a distributed file system, searching taking into account the features of the natural Russian language, as well as a web interface for visualizing search results. Modern frameworks and technologies are used in the process of work: Apache Hadoop, Spark, Hive, Elasticsearch, PostgreSQL, ClickHouse. Elasticsearch showed the best results in both response time and search quality (accuracy – 0.87, completeness – 0.82, F-measure – 0.84) for complex queries reflecting the specifics of the Russian language.