Real-time pedestrian localization is essential for effective emergency evacuation in large indoor public spaces. This study presents an intelligent digital twin system for evacuation monitoring, integrating deep learning and computer vision. The system includes four components: (1) Internet of Things sensor network, (2) cloud computing server, (3) Artificial Intelligence processing engine, and (4) interactive user interface. The Artificial Intelligence engine introduces three innovations: automated detection and tracking of pedestrian coordinates using You Only Look Once-Pose (YOLO-Pose) and Deep Simple Online and Realtime Tracking (DeepSORT); transformation of multi-camera data into a unified world coordinate system; and the Multi-Object Matching Operation (MOMO) algorithm for identity association. These enable accurate detection, localization, and counting while minimizing identifiability. The system was validated in controlled experiments and a high-speed rail station waiting hall with dense, dynamic pedestrian flow. It achieves high localization precision, with a root mean square error of 5.3 cm, a mean absolute error of 4.8 cm, and a people counting accuracy of 92.34% while processing 30 frames per second video at 27.8 ms per frame. These results demonstrate the potential of the digital twin framework in intelligent evacuation management. The main contribution in Artificial Intelligence is the Multi-Object Matching Operation algorithm, and the engineering contribution is the realization of a real-time digital twin system in a large public facility. • Proposes a digital twin system integrating YOLO-Pose and DeepSORT for real-time pedestrian tracking. • Introduces a novel multi-camera calibration method for global coordinate unification. • Achieves 92.34% people counting accuracy in complex public infrastructure environments.

202501 bcrc

Xiangkun Hu, Dongyu Ru, Lin Qiu, Qipeng Guo, Tianhang Zhang, Yang Xu, Yun Luo, Pengfei Liu, Yue Zhang, Zheng Zhang. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.

Cheng Jiayang, Chunkit Chan, Qianqian Zhuang, Lin Qiu, Tianhang Zhang, Tengxiao Liu, Yangqiu Song, Yue Zhang, Pengfei Liu, Zheng Zhang. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.

Shuqian Sheng, Yi Xu, Tianhang Zhang, Zanwei Shen, Luoyi Fu, Jiaxin Ding, Lei Zhou, Xiaoying Gan, Xinbing Wang, Chenghu Zhou. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.

Despite Retrieval-Augmented Generation (RAG) has shown promising capability in leveraging external knowledge, a comprehensive evaluation of RAG systems is still challenging due to the modular nature of RAG, evaluation of long-form responses and reliability of measurements. In this paper, we propose a fine-grained evaluation framework, RAGChecker, that incorporates a suite of diagnostic metrics for both the retrieval and generation modules. Meta evaluation verifies that RAGChecker has significantly better correlations with human judgments than other evaluation metrics. Using RAGChecker, we evaluate 8 RAG systems and conduct an in-depth analysis of their performance, revealing insightful patterns and trade-offs in the design choices of RAG architectures. The metrics of RAGChecker can guide researchers and practitioners in developing more effective RAG systems.

Large language models (LLMs) have achieved great success in general domains of natural language processing. In this paper, we bring LLMs to the realm of geoscience with the objective of advancing research and applications in this field. To this end, we present the first-ever LLM in geoscience, K2, alongside a suite of resources developed to further promote LLM research within geoscience. For instance, we have curated the first geoscience instruction tuning dataset, GeoSignal, which aims to align LLM responses to geoscience-related user queries. Additionally, we have established the first geoscience benchmark, GeoBench, to evaluate LLMs in the context of geoscience. In this work, we experiment with a complete recipe to adapt a pre-trained general-domain LLM to the geoscience domain. Specifically, we further train the LLaMA-7B model on 5.5B tokens of geoscience text corpus, including over 1 million pieces of geoscience literature, and utilize GeoSignal's supervised data to fine-tune the model. Moreover, we share a protocol that can efficiently gather domain-specific data and construct domain-supervised data, even in situations where manpower is scarce. Meanwhile, we equip K2 with the abilities of using tools to be a naive geoscience aide. Experiments conducted on the GeoBench demonstrate the effectiveness of our approach and datasets on geoscience knowledge understanding and utilization.We open-source all the training data and K2 model checkpoints at https://github.com/davendw49/k2

Tianhang Zhang, Lin Qiu, Qipeng Guo, Cheng Deng, Yue Zhang, Zheng Zhang, Chenghu Zhou, Xinbing Wang, Luoyi Fu. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 2023.

Software defect prediction (SDP) utilizes a trained prediction model to predict the defect proneness of code modules in a software system by mining the inherent characteristics of historical defect data. An effective model can optimize the allocation of testing resources, thus improving the quality of software products. Most previous studies use handcrafted features to represent code snippets, but the main problem is that it is difficult to capture the semantic and structural information of the code context, which is often crucial for software defect prediction. Meanwhile, most of the existing software defect prediction models cannot make predictions at the code line level, which makes it extremely arduous to provide developers with more detailed reference information. To address these issues, in this paper, we propose a model based on ensemble learning techniques and attention mechanisms to offer more comprehensive prediction information to developers by locating suspect lines of code when making method-level defect predictions. This model leverages abstract syntax trees (ASTs) as the intermediate representation of code snippets. Since the historical defect data has a striking characteristic of class-imbalance, an approach based on Self-organizing Map (SOM) clustering is employed to handle noisy data. Experimental results show that, on average, the proposed model improves the F-measure by 17.7% and AUC by 37.8%, compared with the other four machine learning algorithms.

In linear cooperative spectrum sensing, the weights of secondary users and detection threshold should be optimally chosen to minimize missed detection probability and to maximize secondary network throughput. Since these two objectives are not completely compatible, we study this problem from the viewpoint of multiple-objective optimization. We aim to obtain a set of evenly distributed Pareto solutions. To this end, here, we introduce the normal constraint (NC) method to transform the problem into a set of single-objective optimization (SOO) problems. Each SOO problem usually results in a Pareto solution. However, NC does not provide any solution method to these SOO problems, nor any indication on the optimal number of Pareto solutions. Furthermore, NC has no preference over all Pareto solutions, while a designer may be only interested in some of them. In this paper, we employ a stochastic global optimization algorithm to solve the SOO problems, and then propose a simple method to determine the optimal number of Pareto solutions under a computational complexity constraint. In addition, we extend NC to refine the Pareto solutions and select the ones of interest. Finally, we verify the effectiveness and efficiency of the proposed methods through computer simulations.