International Journal of System Control and Information Processing (4 papers in press)

Regular Issues

• Controlled quantum dialogue based on Brown states  
  by Tianyu Miao, Min Jiang 
  Abstract: In this paper, a controlled quantum dialogue protocol based on Brown states is proposed. In the beginning, the controller Cindy creates a five-qubit Brown state as the channel and distributes it to the other two communication participants, Alice and Bob. Then, Alice and Bob can encode the secret key by performing unitary operation onto the entangled particles that Cindy sends to them. Finally, The messages can be exchanged by entanglement swapping and the results of Bell state measurement. The security analysis shows that our protocol can not only solves the problem of information leakage, but also can effectively prevent a variety of well-known attacks. Under the control of Cindy, there are two possible decoding methods for participants to obtain each other's information, improving communication security. In addition, this protocol does not involve complex quantum operations and demonstrates a good physical operational feasibility.
  Keywords: Quantum dialogue; Brown states; Information leakage problem; Entanglement Swapping.
  DOI: 10.1504/IJSCIP.2026.10075050
   
  
• UVSC-MT: an Uncertain-guided Mean Teacher Model with Virtual Adversarial and Sample Relation Consistency for Semi-supervised Medical Image Classification  
  by Kai Wu, Yubin Wei, Jinting Guan 
  Abstract: Semi-supervised deep learning models have been developed for medical image classification, enabling the utilization of both labeled and unlabeled data. Among these, the Teacher-Student model has gained significant recognition. Despite its success, this model faces two critical limitations, the unreliability of target knowledge generated by the teacher model and the model's limited robustness and generalization capabilities. We propose a semi-supervised medical image classification framework, termed UVSC-MT. Drawing inspiration from Monte Carlo uncertainty, we leverage uncertainty information to guide the student model toward more reliable and meaningful target learning. Furthermore, we incorporate sample relation consistency to enable the extraction of additional semantic insights from unlabeled data and thereby enhance utilization. Additionally, we integrate virtual adversarial training as a regularization strategy to bolster the model's classification performance and robustness. Experiments conducted on diverse datasets demonstrate that UVSC-MT surpasses existing methods, offering advancements and insights for semi-supervised learning in medical image classification.
  Keywords: medical image classification; semi-supervised learning; uncertainty; sample relation consistency; virtual adversarial.
  
  
• Coal Mine Artificial Intelligence Technology and Scenario Applications  
  by Wen Cui, Yuting Zhou, Zhou Zheng, Hao Gu, Mujtaba Asad, Xiaolin Huang, He Jiang 
  Abstract: Addressing coal mine safety requirements, we systematically analyze the efficacy of artificial intelligence (AI) technologies in underground operations. By integrating audio-visual technology, an intelligent solution covering core scenarios including safety monitoring, mining optimization, and equipment maintenance is established. The results confirm that video technology dynamically monitors gas concentrations, detects roadway deformations, and intelligently controls mining equipment, while audio technology identifies equipment fault signatures and geological acoustic patterns, significantly improving real-time early warning capabilities. This integrated system significantly improves operational safety, production efficiency, and intelligentization levels, providing an effective pathway for smart coal mine construction.
  Keywords: Scenario applications; Coal mine; Artificial intelligence; Audio-visual technology; Intelligentization levels.
  DOI: 10.1504/IJSCIP.2026.10077006
   
  
• Intelligent Prediction of Internet of Vehicles (IoV) Data Security Performance based on GF-Net  
  by Tiancheng Li, Liliang Zhang, Lingwei Xu, T. Aaron Gulliver 
  Abstract: The Internet of Vehicles (IoV) enables seamless communication. However, its complex environment creates significant data security challenges. This paper proposes a novel method to predict IoV data security performance based on GF-Net. First, an IoV secure communication model is developed over N-Nakagami channels. This model analyses security performance and generates a communication dataset. The proposed GF-Net features a dual-branch structure. The upper branch uses a GLSTM network to capture spatio-temporal features. The lower branch applies a Fusion Module to improve feature robustness. Next, a Multilayer Perceptron integrates the branch outputs for accurate prediction. Experimental results show that GF-Net outperforms the WNN, GAT, and Transformer algorithms. Notably, its Mean Squared Error is 69% lower than that of the Transformer.
  Keywords: Internet of Vehicles; Secure Communication; Security Performance; Intelligent Prediction; GF-Net.
  DOI: 10.1504/IJSCIP.2026.10077333