Tiantian Tang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Tiantian Tang has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Haipeng Wang
School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China
1 shared publication - Hongdong Wan
Institute of Information Fusion, Naval Aviation University, Yantai 264001, China
1 shared publication Hongfeng Zhu
Institute of Information Fusion Naval Aviation University Yantai Shandong China
1 shared publication- Liqiang Ren
Institute of Information Fusion, Naval Aviation University, Yantai 264001, China
1 shared publication - Xinlong Pan
Institute of Information Fusion, Naval Aviation University, Yantai 264001, China
1 shared publication Yaqi Cui
Institute of Information Fusion Naval Aviation University Yantai Shandong China
1 shared publication
Latest Publications
- Open Access
Explainable Recognition of Complex Flight Maneuvers via Retrieval-Augmented Large Language Models
Complex flight maneuver recognition (FMR) underpins intelligent flight training, including training assessment, pilot skill profiling, and flight safety monitoring. Existing FMR methods typically require large labeled datasets, generalize poorly across aircraft, and provide limited decision transparency. We propose TableManeuver, an explainable LLM-based FMR method that reformulates multivariate flight parameter time series as table-understanding inputs. The method updates no base LLM parameters and uses a small labeled training set only as a retrieval library; it is therefore not a zero-shot setting. TableManeuver first converts flight parameter sequences into tabular text that preserves temporal indices and channel semantics, reducing the mismatch between numerical time series and the textual semantic space of LLMs. It then combines domain knowledge, neighborhood sample references, and task decomposition prompts in a retrieval-augmented reasoning architecture that guides explicit step-by-step inference. We evaluate the method on a flight dataset collected from human pilots on a high-fidelity flight simulation platform. Without base LLM parameter updates, TableManeuver achieves 96.2% precision, 96.8% recall, and a 96.5% F1 score, exceeding the strongest supervised baseline by 3.5 percentage points in F1. In cross-aircraft evaluation, the F1 score decreases by only 1.4 percentage points, which is substantially smaller than the degradation observed for deep learning baselines. Retrieval-only baselines that transfer neighbor labels without LLM inference perform markedly worse, indicating that the performance gains are not explained by neighbor label transfer alone. TableManeuver combines recognition accuracy, cross-aircraft robustness, and readable step-by-step reasoning evidence, offering a practical route for applying LLMs to aviation time series analysis.
Open AccessExplainable Recognition of Complex Flight Maneuvers via Retrieval-Augmented Large Language Models
Complex flight maneuver recognition (FMR) underpins intelligent flight training, including training assessment, pilot skill profiling, and flight safety monitoring. Existing FMR methods typically require large labeled datasets, generalize poorly across aircraft, and provide limited decision transparency. We propose TableManeuver, an explainable LLM-based FMR method that reformulates multivariate flight parameter time series as table-understanding inputs. The method updates no base LLM parameters and uses a small labeled training set only as a retrieval library; it is therefore not a zero-shot setting. TableManeuver first converts flight parameter sequences into tabular text that preserves temporal indices and channel semantics, reducing the mismatch between numerical time series and the textual semantic space of LLMs. It then combines domain knowledge, neighborhood sample references, and task decomposition prompts in a retrieval-augmented reasoning architecture that guides explicit step-by-step inference. We evaluate the method on a flight dataset collected from human pilots on a high-fidelity flight simulation platform. Without base LLM parameter updates, TableManeuver achieves 96.2% precision, 96.8% recall, and a 96.5% F1 score, exceeding the strongest supervised baseline by 3.5 percentage points in F1. In cross-aircraft evaluation, the F1 score decreases by only 1.4 percentage points, which is substantially smaller than the degradation observed for deep learning baselines. Retrieval-only baselines that transfer neighbor labels without LLM inference perform markedly worse, indicating that the performance gains are not explained by neighbor label transfer alone. TableManeuver combines recognition accuracy, cross-aircraft robustness, and readable step-by-step reasoning evidence, offering a practical route for applying LLMs to aviation time series analysis.
- Open Access
- 21 May 2021
- Published by Institution of Engineering and Technology (IET) in IET Radar, Sonar & Navigation
- Vol. 15 (9) , 1112-1124
A new adaptive track correlation method for multiple scenarios
The traditional track correlation methods have problems such as limitation of the application scenarios, unstable performances and poor practicalities. To solve those problems, a new adaptive track correlation method for multiple scenarios was proposed in this paper using the theories and methods from machine learning. Through interpreting and translating the track correlation problem in the field of information fusion into the classification recognition problem in the field of machine learning, the new method was derived based on deep convolutional neural networks. The association performance and adaptation capabilities of the proposed method had been validated by simulation experiments. The results show that the proposed method is better than the traditional methods with respect to association performance and adaptation capabilities, and can solve the track association problems for multiple scenarios, for example sensors have systematic errors and targets are dense or in formation. Thus, it can be predicted that the proposed method would have a well‐applied foreground.
- 21 May 2021
- Published by Institution of Engineering and Technology (IET) in IET Radar, Sonar & Navigation
- Vol. 15 (9) , 1112-1124
Open AccessA new adaptive track correlation method for multiple scenarios
The traditional track correlation methods have problems such as limitation of the application scenarios, unstable performances and poor practicalities. To solve those problems, a new adaptive track correlation method for multiple scenarios was proposed in this paper using the theories and methods from machine learning. Through interpreting and translating the track correlation problem in the field of information fusion into the classification recognition problem in the field of machine learning, the new method was derived based on deep convolutional neural networks. The association performance and adaptation capabilities of the proposed method had been validated by simulation experiments. The results show that the proposed method is better than the traditional methods with respect to association performance and adaptation capabilities, and can solve the track association problems for multiple scenarios, for example sensors have systematic errors and targets are dense or in formation. Thus, it can be predicted that the proposed method would have a well‐applied foreground.
- Open Access
- 1 March 2017
- Published by Universitas Ahmad Dahlan in TELKOMNIKA (Telecommunication Computing Electronics and Control)
- Vol. 15 (1) , 457-463
Design of LDPC Decoder Based On FPGA in Digital Image Watermarking Technology
In this paper, a digital image watermarking system compiled by the LDPC code is introduced to embed and extract the image watermark. The system software is realized by the mixed programming with Matlab and Qt at first. It could get real-time input data for the LDPC decoder. Then the hardware of the LDPC decoder is primarily implemented by FPGA in the digital image watermarking system. And the serial port is used to make the output data of the decoder back to computer for verification. Through the simulation results, the Models time simulation diagram is given, and the watermark image compared with the original image is got. The results show that the resource usage of our system is few, and the decoding rate is fast. It has a certain practical value.
- 1 March 2017
- Published by Universitas Ahmad Dahlan in TELKOMNIKA (Telecommunication Computing Electronics and Control)
- Vol. 15 (1) , 457-463
Open AccessDesign of LDPC Decoder Based On FPGA in Digital Image Watermarking Technology
In this paper, a digital image watermarking system compiled by the LDPC code is introduced to embed and extract the image watermark. The system software is realized by the mixed programming with Matlab and Qt at first. It could get real-time input data for the LDPC decoder. Then the hardware of the LDPC decoder is primarily implemented by FPGA in the digital image watermarking system. And the serial port is used to make the output data of the decoder back to computer for verification. Through the simulation results, the Models time simulation diagram is given, and the watermark image compared with the original image is got. The results show that the resource usage of our system is few, and the decoding rate is fast. It has a certain practical value.