Latest Publications on OSINT
This is our latest selection of worldwide publications on OSINT, between many scientific online journals, classified and focused on OSINT, data mining, social media analysis, web scraping, geolocation, metadata analysis, threat intelligence and open data.
Tip: Further to this selection on OSINT, you can search and filter our > publication database < by author, topic, keywords, date or journal.
Data Value-Added Service Comprehensive Evaluation Method on the Performance of Power System Big Data
On 2025-02-03 by Hao Zhang, Ye Liang, Jing Wang, Yuanzhuo Li, Xiaorui Rong, Hongda Gao @MDPI
Keywords: data mining, value-added services, comprehensive evaluation method, power system big data, digital transformation
AI summary: Development of energy big data integration and sharing, exploration of power data applications, determination of key factors for value-added services, identification of key technologies for digital transformation.
Abstract: With the development of digital economy, the integration and secure sharing of energy big data have become pivotal in driving innovation across the energy production, distribution, and consumption sectors. For power enterprises, leveraging data to enhance operational efficiency and drive business development will play a crucial role in value added. Firstly, based on the value-added service framework system of grid enterprises, this paper explores the basic technologies for power data application[...]
Publication
A Scalable Sorting Network Based on Hybrid Algorithms for Accelerating Data Sorting
On 2025-02-01 by Xufeng Li, Li Zhou, Yan Zhu @MDPI
Keywords: hybrid algorithms, scalable sorting network, hardware acceleration, sequential data mining, data sorting
AI summary: Improved sorting network using hybrid algorithms for hardware acceleration. Scalable design reduces computational load and hardware requirements. Pre-comparison layer and pipelined architecture enhance performance. Experimental results demonstrate significant improvements in throughput and operating frequency.
Abstract: Sorting in sequential data mining is significantly improved through hardware acceleration, which becomes essential as data volume and complexity increase. This paper presents a scalable hybrid sorting network that maintains or improves performance while reducing computational load and hardware requirements. The network is composed of the pre-comparison odd&ndash;even sorting network (P-OESN) and the bidirectional insertion sorting network (BISN). A pre-comparison layer is introduced to t[...]
Publication
Wazuh Security Event Response with Retrieval-Augmented-Generation-Driven Copilot
On 2025-01-31 by Ismail, Rahmat Kurnia, Farid Widyatama, Ilham Mirwansyah Wibawa, Zilmas Arjuna Brata, Ukasyah, Ghitha Afina Nelistiani, Howon Kim @MDPI
Keywords: Wazuh, Security Event Response, Retrieval-Augmented-Generation-Driven, Copilot, SIEM
AI summary: Cyberthreat sophistication requires efficient tools. SERC assists analysts in responding to breaches. Wazuh integrates RAG methods for data extraction. Combining threat intelligence frameworks with AI-driven models is essential.
Abstract: The sophistication of cyberthreats demands more efficient and intelligent tools to support Security Operations Centers (SOCs) in managing and mitigating incidents. To address this, we developed the Security Event Response Copilot (SERC), a system designed to assist analysts in responding to and mitigating security breaches more effectively. SERC integrates two core components: (1) security event data extraction using Retrieval-Augmented Generation (RAG) methods, and (2) LLM-based incident respon[...]
Publication
Ship Anomalous Behavior Detection Based on BPEF Mining and Text Similarity
On 2025-01-29 by Yongfeng Suo, Yan Wang, Lei Cui @MDPI
Keywords: anomalous behavior detection, BPEF mining, text similarity, maritime surveillance, ship navigation
AI summary: Novel framework integrates BPEF mining and text similarity for ship anomaly detection. Achieves over 90% accuracy in detecting abnormal trajectories. Enhances maritime safety and advances intelligent supervision. Valuable insights for detecting anomalous vessel behavior through maritime big data mining.
Abstract: Maritime behavior detection is vital for maritime surveillance and management, ensuring safe ship navigation, normal port operations, marine environmental protection, and the prevention of illegal activities on water. Current methods for detecting anomalous vessel behaviors primarily rely on single time series data or feature point analysis, which struggle to capture the relationships between vessel behaviors, limiting anomaly identification accuracy. To address this challenge, we proposed a nov[...]
Publication
A Multi-Level Location-Aware Approach for Session-Based News Recommendation
On 2025-01-28 by Xu Yu, Shuang Cui, Xiaohan Wang, Jiale Zhang, Zihan Cheng, Xiaofei Mu, Bin Tang @MDPI
Keywords: session-based news recommendation, location-aware approach, news recommendation systems, geolocation information, personalized news recommendations
AI summary: Utilizing geolocation information for personalized session-based news recommendations, proposing a multi-level approach, improving model recommendation performance, outperforming baselines.
Abstract: Recently, personalized news recommendation systems have been widely used, which can achieve personalized news recommendations based on people&rsquo;s different preferences, optimize the reading experience, and alleviate the problem of information overload. Among them, session-based news recommendation has gradually become a research hotspot as it can recommend news without requiring users to log in or when their reading history is difficult to obtain. The key to session-based news recomm[...]
Publication
A Novel Benchmark and View-Optimized Framework for Pedestrian Detection from UAV Perspectives
On 2025-01-27 by Chenglizhao Chen, Shengran Gao, Hongjuan Pei, Ning Chen, Lei Shi, Peiying Zhang @MDPI
Keywords: pedestrian detection, UAV perspectives, benchmark dataset, data mining, perspective features
AI summary: Novel benchmark dataset NSV enhances UAV pedestrian detection. Data mining approach improves efficiency and annotation quality. Improved method overcomes performance degradation from perspective changes. Modules enhance model generalization and adaptability to geometric deformations.
Abstract: To address the issues of insufficient samples, limited scene diversity, missing perspectives, and low resolution in existing UAV-based pedestrian detection datasets, this paper proposes a novel UAV-based pedestrian detection benchmark dataset named the Novel Surveillance View (NSV). This dataset encompasses diverse scenes and pedestrian information captured from multiple perspectives, and introduces an innovative data mining approach that leverages tracking and optical flow information. This app[...]
Publication
