arXiv subjects

Jiajun Pan

Publications and source records attributed to Jiajun Pan.

3 recordsLinked to original sources

arXiv2026

LEO Satellite Internet of Things: Architecture, Technology, and On-Orbit Verification

Low Earth orbit (LEO) satellite constellations are poised to become a cornerstone of the sixth-generation (6G) Internet of Things (IoT), providing truly global coverage and ubiquitous connectivity. This article presents a holistic two-dimensional system architecture for 6G LEO satellite IoT that incorporates composition and functional perspectives to facilitate the seamless integration of LEO satellites and terrestrial networks. Building upon this architecture, we evaluate three pivotal enabling technologies targeting the uplink, downlink, and inter-satellite links (ISLs). Specifically, we analyze massive grant-free random access for efficient uplink connectivity, investigate deep learning-based multibeam precoding for robust downlink transmission, and examine distributed cooperative routing for resilient ISL data delivery. Furthermore, we present an on-orbit verification platform that validates the real-world feasibility and performance of the proposed solutions. Finally, we outline key open challenges and future research directions to guide the realization of future LEO satellite IoT.

cs.IT↗

arXiv2025

Magnetic-field controlled organic spintronic memristor for neural network computation

Memristors are emerging as key electronic components that retain resistance states without power. Their non-volatile nature and ability to mimic synaptic behavior make them ideal for next-generation memory technologies and neuromorphic computing systems inspired by the human brain. In this study, we present a novel organic spintronic memristor based on a La0.67Sr0.33MnO3 (LSMO)/poly(vinylidene fluoride) (PVDF)/Co heterostructure, exhibiting biologically inspired synaptic behavior. Driven by fluorine atom migration within the PVDF layer, the device demonstrates both long-term depression (LTD) and long-term potentiation (LTP) under controlled electrical polarization. Distinctively, the resistance states can also be modulated by an external magnetic field via the tunneling magnetoresistance (TMR) effect, introducing a non-electrical means of tuning synaptic plasticity. This magnetic control mechanism enables multi-state modulation without compromising device performance or endurance. Furthermore, convolutional neural network (CNN) simulations incorporating this magnetic tuning capability reveal enhanced pattern recognition accuracy and improved training stability, especially at high learning rates. These findings underscore the potential of organic spintronic memristors as high-performance, low-power neuromorphic elements, particularly suited for applications in flexible and wearable electronics.

cond-mat.mes-hall↗

arXiv2018

Relational Constraints for Metric Learning on Relational Data

Most of metric learning approaches are dedicated to be applied on data described by feature vectors, with some notable exceptions such as times series, trees or graphs. The objective of this paper is to propose a metric learning algorithm that specifically considers relational data. The proposed approach can take benefit from both the topological structure of the data and supervised labels. For selecting relative constraints representing the relational information, we introduce a link-strength function that measures the strength of relationship links between entities by the side-information of their common parents. We show the performance of the proposed method with two different classical metric learning algorithms, which are ITML (Information Theoretic Metric Learning) and LSML (Least Squares Metric Learning), and test on several real-world datasets. Experimental results show that using relational information improves the quality of the learned metric.

cs.LG↗