Large-scale Vision-Language Models (VLMs) like Contrastive Language-Image Pre-training (CLIP) have demonstrated their impressive zero-shot capabilities. However, adapting them to downstream tasks remains challenging, especially under domain shifts where visual features become unreliable. Existing training-free methods, such as Tip-Adapter, rely heavily on visual similarity, which often fails in out-of-distribution (OOD) scenarios. To address this, Decoupled Correction Adapter (DeCo-Adapter), a robust adaptation framework that integrates a Decoupled Knowledge Stream into the visual baseline, is proposed. Specifically, a novel Negative Semantic Suppression mechanism is introduced, leveraging Large Language Models (LLMs) to generate and penalize distractor descriptions. This mechanism effectively corrects visual ambiguities without requiring any training. Extensive experiments on ImageNet-Sketch, ImageNet-V2, and ImageNet-A demonstrate that DeCo-Adapter consistently outperforms state-of-the-art methods. Notably, it achieves a top-1 accuracy of 54.11% on ImageNet-Sketch, surpassing the strong Tip-Adapter baseline by leveraging negative knowledge for error correction.
Accelerated urbanization, sustained rural labor migration, and increasing inefficiencies in land management have contributed to the widespread abandonment of cultivated land in China, thereby posing significant challenges to national food security, agricultural sustainability, and rural revitalization. Although intelligent supervision technologies have been increasingly introduced into agricultural governance systems, the heterogeneous requirements of multiple stakeholders have not been systematically incorporated into existing platform design frameworks. To address this gap, a Kano model–based requirements analysis framework was developed and applied to the governance of farmland abandonment in a major agricultural county in Jiangxi Province, China. A mixed-methods approach integrating literature analysis, semi-structured interviews, and questionnaire surveys was adopted to identify, classify, and prioritize the requirements for an intelligent supervision platform. The identified requirements were categorized into four dimensions: must-be requirements (e.g., policy subsidy information and data stability), one-dimensional requirements (e.g., historical data comparison and land transfer information), attractive requirements (e.g., high-precision monitoring and fallow warning), and indifferent requirements (e.g., user operation training and feedback channels). The findings demonstrated that must-be requirements should be prioritized to ensure the operational reliability of the platform, whereas one-dimensional requirements should be continuously strengthened to improve core capabilities. Attractive requirements were found to significantly enhance user experience and should therefore be gradually integrated. In contrast, indifferent requirements should be strategically managed to avoid unnecessary allocation of resources. Empirical evidence for the optimization of intelligent supervision platforms in farmland abandonment governance was provided by this study, while the applicability of the Kano model in public governance technology requirement analysis was further validated. The findings are expected to contribute to the advancement of intelligent, data-driven, and precision-oriented farmland governance systems in China and other developing agricultural regions.
Effective tourism planning, scenic-area evaluation, and regulatory supervision depend on the accurate interpretation of extensive collections of tourism-related laws, administrative regulations, technical standards, and local normative documents. However, these documents are characterized by heterogeneous structures, frequent revisions, and complex cross-document dependencies, which limit the effectiveness of conventional keyword-based retrieval approaches and increase the risk of unsupported or unverifiable outputs generated by large language models. To address these challenges, a retrieval-augmented generation framework, termed ReguTourRAG, was proposed for intelligent question answering and knowledge access within tourism regulatory and standards corpora. A two-stage retrieval architecture was adopted. In the first stage, broad hybrid recall was performed through the collaborative integration of Best Matching 25 (BM25) lexical retrieval, Elastic Learned Sparse EncodeR (ELSER)-based sparse semantic retrieval, and Hierarchical Navigable Small World (HNSW)-based dense vector retrieval. In the second stage, candidate documents were refined through a cross-encoder reranking model, whereby high-value evidence was prioritized before response generation. Through the explicit separation of coverage-oriented recall and precision-oriented reranking, the traceability, completeness, and reliability of generated responses were enhanced for regulation-driven tourism management tasks. The proposed framework was evaluated using a corpus comprising 970 tourism regulatory and standards documents. Experimental results demonstrated consistent improvements over representative single-strategy retrieval-augmented generation baselines across multiple retrieval and generation metrics, including mean reciprocal rank, normalized discounted cumulative gain, accuracy, Recall-Oriented Understudy for Gisting Evaluation-Longest Common Subsequence (ROUGE-L), and BERTScore. The observed gains indicate that the collaborative utilization of lexical, sparse semantic, and dense retrieval signals, together with cross-encoder evidence refinement, provides substantial advantages for regulation-intensive domains in which precise legal terminology, semantic paraphrasing, and cross-document reasoning must be simultaneously accommodated. These findings suggest that ReguTourRAG offers a robust and scalable foundation for regulatory decision support, policy interpretation, compliance assessment, and intelligent knowledge services in tourism governance environments.
Wireless sensor networks operate in highly dynamic environments, where channel conditions are continuously influenced by several factors. Accurate characterization of channel state dynamics is therefore essential for evaluating network reliability, communication efficiency, and overall system performance. An entropy-based stochastic framework was proposed for the statistical analysis of channel state information derived from wireless sensor networks. The link quality of an individual sensor node was modeled as a discrete random variable with four mutually exclusive channel states representing outage (deep fade), marginal connection, stable communication, and line-of-sight operation, corresponding respectively to complete packet loss, elevated retransmission rates, nominal communication performance, and maximum achievable data throughput. The information of each communication channel state was quantified through link information, whereas the uncertainty associated with the link quality was measured using link entropy. Because wireless communication environments exhibit inherent temporal variability, repeated observations of sensor states were collected to construct empirical probability distributions. Based on these empirical distributions, the maximum uncertainty point, expected channel state, entropy, information elasticity coefficient, and unpredictability coefficient were systematically derived to quantify the statistical characteristics of channel-state variability. Consequently, different channel-state samples were objectively classified according to their statistical properties, thereby facilitating quantitative assessment of network stability, communication quality, and operational robustness under dynamic environmental conditions. The proposed framework provides a rigorous and computationally efficient methodology for entropy-based characterization of wireless sensor network behavior and establishes a general analytical foundation for reliability assessment, adaptive network management, and information-driven optimization of wireless sensing systems.
Brand perception has increasingly been recognized as a critical source of competitive intelligence in digital markets, yet existing studies have largely examined consumer sentiment, discussion topics, or product attributes independently, thereby limiting their ability to support strategic brand positioning. A competitive brand perception framework was proposed to address this limitation by integrating sentiment analysis, latent Dirichlet allocation-based topic modeling, and aspect-based sentiment analysis into a unified analytical framework capable of transforming consumer-generated social media data into competitive intelligence. The framework was validated using 12,603 posts collected from X (formerly Twitter) concerning four leading beauty and personal care brands—Dove, Nivea, Estée Lauder, and L’Oréal. Overall consumer attitudes were quantified through sentiment analysis, dominant perception themes were identified using latent Dirichlet allocation-based topic modeling, and evaluations of brand- and product-related attributes were examined through aspect-based sentiment analysis. Three complementary competitive positioning indicators—topic salience, aspect sentiment, and brand distinctiveness—were introduced. The findings demonstrate that overall sentiment alone is insufficient for explaining competitive positioning. Although Nivea generated the greatest volume of consumer discussion, the highest sentiment score and strongest topic distinctiveness were observed for Estée Lauder. Dove was primarily associated with cleansing and body care, whereas L’Oréal demonstrated a distinctive perceptual position centered on facial skincare and makeup-related discussions. These findings further indicate that competitive differentiation is shaped not only by the polarity of consumer evaluations but also by the thematic structure and attribute-specific associations embedded within online conversations. Consequently, brand perception should be conceptualized as a multidimensional and competitive construct rather than as a single sentiment-based metric. The proposed competitive brand perception framework extends the methodological foundation of social media analytics by integrating complementary analytical perspectives into a unified competitive intelligence framework and provides a practical decision-support tool for identifying perceptual advantages, uncovering differentiation opportunities, and prioritizing strategic brand positioning using large-scale consumer-generated data.
Open Access
Journal Metrics
Journal Overview
Associated Journals