Rongen Yan

Forest foods play a vital role in enhancing dietary diversity, human health, and the sustainable use of forest ecosystems. However, structured and machine-readable resources that systematically describe their taxonomic and nutritional attributes remain scarce. To fill this gap, we introduce ForestFoodKG, a comprehensive resource that integrates taxonomic hierarchy and nutritional composition of 1191 forest food items. The resource consists of two components—(i) the ForestFoodKG dataset, containing standardized taxonomic and nutritional records across seven biological levels, and (ii) the ForestFoodKG Knowledge Graph (ForestFoodKG-KG), which semantically links forest food entities using named entity recognition and relation extraction. The constructed graph comprises 4492 entities and 14,130 semantic relations, providing a structured foundation for intelligent querying, nutrition analytics, and ecological informatics. All data were manually verified and made publicly available in CSV format on GitHub. ForestFoodKG serves as the first structured knowledge base for forest foods, promoting data-driven research in nutrition science, sustainable forestry, and knowledge-based decision-making.

Traditional WiFi fingerprint based localization scheme relies on high-overhead signal collection, and then estimates the location for each user, respectively. Is it feasible to achieve a higher estimate accuracy using a low-overhead fingerprint approach, maximizing the utilization of collaborative information shared among users? This paper provides an affirmative answer. Specifically, we propose an emerging collaborative localization scheme named LCWF, which first uses access point (AP) rank as a feature to discretize and cluster the area of interest. Then, we propose a signal strength difference (SSD) similarity metric, to discern which clustering area a user belongs to and select users with robust signal relationships. Finally, the received signal strength (RSS) relationships between selected users are leveraged to infer their corresponding physical location relationships, for outputting the user final location. Furthermore, considering the device heterogeneity among either mobile devices or APs, we propose a device calibration algorithm to standardize the collaborative localization process among heterogeneous online devices. Real-world experiments results validate the effectiveness of our proposed LCWF system, compared to other state-of-the-art approaches (e.g. NN, OCLoc, CBWF+). Specifically, in a 40 m × 17 m real scenario with only 20 reference points (RPs) and 11 access points (APs), our algorithm achieves an average localization accuracy of 3.42 m for a heterogeneous dataset.

Document-level relation extraction (RE) aims to determine the relations between entities scattered across different sentences through reading and reasoning. Existing methods use semantic segmentation to obtain global information among triples by analyzing entity-level matrices. However, complete document input may introduce certain interference, making it challenging to express the underlying relationships. To address this, we propose a novel approach introducing a low-entity redundancy feature map, achieved by removing certain entities. The proposed optimal path filtering (OPF) selects entity-related sentences using heuristic rules and formulates sentence selection as a set cover problem, solved via backtracking pruning. U-Net is then applied to obtain global features. Our experiment achieves state-of-the-art results on two common document-level RE datasets, Re-DocRED and CDR, outperforming previous methods. The code is available at https://github.com/dadadaray/document-RE-feature-map.

A standardized representation and sharing of crop disease and pest data is crucial for enhancing crop yields, especially in China, which features vast cultivation areas and complex agricultural ecosystems. A knowledge graph for crop diseases and pests, acting as a repository of entities and relationships, is crucial conceptually for achieving unified data management. However, there is currently a lack of knowledge graphs specifically designed for this field. In this paper, we propose CropDP-KG, a knowledge graph for crop diseases and pests in China, which leverages natural language processing techniques to analyze data from the Chinese crop diseases and pests image-text database. CropDP-KG covers relevant information on crop diseases and pests in China, featuring 8 primary entities such as diseases, symptoms, and crops, and is organized into 7 relationships such as primary occurrence locations, affected parts and suitable temperature. In total, it includes 13,840 entities and 21,961 relationships. In the case studies presented in this research, we also show a versatile application of CropDP, namely a knowledge service system, and have released its codebase under an open-source license. The content of this paper provides a guide for users to build their own knowledge graphs, aiming to help them effectively reuse and extend the knowledge graphs they create.

Relation extraction, a crucial task in natural language processing (NLP) for constructing knowledge graphs, entails extracting relational semantics between pairs of entities within a sentence. Given the intricacy of language, a single sentence often encompasses multiple entities that mutually influence one another. Recently, various iterations of recurrent neural networks (RNNs) have been introduced into relation extraction tasks, where the efficacy of neural network structures directly influences task performance. However, many neural networks necessitate manual determination of optimal parameters and network architectures, resulting in limited generalization capabilities for specific tasks. In this paper, we formally define the context-based relation extraction problem and propose a solution utilizing neural architecture search (NAS) to optimize RNN. Specifically, NAS employs an RNN controller to delineate an RNN cell, yielding an optimal structure to represent all relationships, thereby aiding in extracting relationships between target entities. Additionally, to enhance relation extraction performance, we leverage the XLNet pretrained model to comprehensively capture the semantic features of the sentence. Extensive experiments conducted on a real-world dataset containing words with multiple relationships demonstrate that our proposed method significantly enhances micro-F1 scores compared to state-of-the-art baselines.

Users upload their own WiFi localization request signals to match against the received signal strengths (RSS) in an offline constructed fingerprint database, thereby obtaining their own geographic location estimates. However, the relationships between the measured signals of users are seldom explored for enhancing the localization accuracy. Furthermore, the tedious site surveys required for building an offline fingerprint database hinder the wider application of this technology. To address the above issues, this paper proposes a collaboratively enhanced lightweight WiFi localization algorithm named CBWF+, capable of providing an accurate indoor position with low-overhead fingerprints and collaborative localization. Specifically, we first discretize the area of interest to produce virtual points (VPs), and leverage the concept of circular-boundary-based localization to select a few VPs that share similar signal characteristics with the request signals. Then, important users for collaborative localization are chosen by two new proposed indicators. Next, based on the selection results and the RSS relationships among users, the spatiotemporal characteristics of WiFi signals are used to further filter out VPs that contradict the relationship between RSS and physical location. Finally, the credible VPs are used to obtain a high-accuracy estimate, by a proposed weighting method. The results of the real-world experiments validate the effectiveness of our proposed CBWF+ algorithm, compared to other state-of-the-art approaches (e.g. NN, OCLoc, CBWF, etc.). Specifically, in a 40 m × 17 m real scenario with only 20 reference points (RPs) and 11 access point (APs), our algorithm achieves an average localization accuracy of 2.49 m. Our codes are available at: https://github.com/dadadaray/CBWF2.0.

As a promising indoor localization technology, WiFi fingerprint-based localization encounters many issues that need to be addressed urgently, such as high-overhead fingerprint map construction, device heterogeneity among either mobile devices or access points (APs), etc. In this article, we present CBWF: a lightweight circular boundary -based WiFi fingerprinting localization system that is able to provide low-overhead, device calibration-free accurate indoor localization. CBWF achieves this by dividing a localization area into multiple subregions, and then leveraging the relation between the received signal strength (RSS) vectors from two different APs as fingerprints for localization. The key idea behind CBWF is that a superior division mechanism is attained to divide the localization area. Specifically, we propose the circle boundary mechanism to better approximate the real boundary of subregions, compared with the widely used linear boundary mechanism, and then sufficiently exploit the theoretical characteristics behind this novel mechanism. Extensive simulation and real-world experiments show that our lightweight system outperforms state-of-the-art approaches. Specifically, in a 40 m $\times 17$ m real scenario with only 20 reference points (RPs) and 11 APs, CBWF achieves an average localization accuracy of 2.95 and 4.15 m for two different mobile devices, respectively. Our codes are available at: https://github.com/dadadaray/circular-boundary .

Purpose: Question answering (QA) answers the questions asked by people in the form of natural language. In the QA, due to the subjectivity of users, the questions they query have different expressions, which increases the difficulty of text retrieval. Therefore, the purpose of this paper is to explore new query rewriting method for QA that integrates multiple related questions (RQs) to form an optimal question. Moreover, it is important to generate a new dataset of the original query (OQ) with multiple RQs.Design/methodology/approach: This study collects a new dataset SQuAD_extend by crawling the QA community and uses word-graph to model the collected OQs. Next, Beam search finds the best path to get the best question. To deeply represent the features of the question, pretrained model BERT is used to model sentences.Findings: The experimental results show three outstanding findings. (1) The quality of the answers is better after adding the RQs of the OQs. (2) The word-graph that is used to model the problem and choose the optimal path is conducive to finding the best question. (3) Finally, BERT can deeply characterize the semantics of the exact problem.Originality/value: The proposed method can use word-graph to construct multiple questions and select the optimal path for rewriting the question, and the quality of answers is better than the baseline. In practice, the research results can help guide users to clarify their query intentions and finally achieve the best answer.

Information Extraction (IE) in Natural Language Processing (NLP) aims to extract structured information from unstructured text to assist a computer in understanding natural language. Machine learning-based IE methods bring more intelligence and possibilities but require an extensive and accurate labeled corpus. In the materials science domain, giving reliable labels is a laborious task that requires the efforts of many professionals. To reduce manual intervention and automatically generate materials corpus during IE, in this work, we propose a semi-supervised IE framework for materials via automatically generated corpus. Taking the superalloy data extraction in our previous work as an example, the proposed framework using Snorkel automatically labels the corpus containing property values. Then Ordered Neurons-Long Short-Term Memory (ON-LSTM) network is adopted to train an information extraction model on the generated corpus. The experimental results show that the F1-score of γ’ solvus temperature, density and solidus temperature of superalloys are 83.90%, 94.02%, 89.27%, respectively. Furthermore, we conduct similar experiments on other materials, the experimental results show that the proposed framework is universal in the field of materials.