Search Results (1,664)

Tomato is one of the most important vegetable crops worldwide, with about one quarter of the yearly production of fresh fruits dispatched to the processing industry. Paste, canned tomatoes, and sauces represent the three leading categories. Background/Objectives: The metabolic profile of processed tomatoes can be modified by several production steps, affecting the nutritional and sensory profile of the finished product. Despite this, a detailed metabolomic profiling of transformed tomatoes is currently missing. The goal of this investigation is to provide qualitative metabolomic profiling of tomato purees with two main advances: first, the use of a more sustainable analytical approach based on a single extraction protocol and one-shot analysis for multiple information retrieval on different compound classes; second, the achievement of a curated database consolidated over a wide collection of commercial samples representative of the Italian market. Methods: A non-selective ethanol extraction was applied to collect the main polar metabolites followed by untargeted high-resolution MS/MS analysis and software-based compound identification. Results: A list of more than five hundred features was collected and assigned to specific compounds or compound groups with different confidence levels. The results confirmed the persistence in processed tomatoes of the main primary and secondary metabolites already reported in fresh fruits, such as essential amino acids, sugar, organic acids, vitamins, fatty acyls, and phytohormones. Moreover, new insight on specific components never traced before in similar finished samples is provided. Bioactive compounds were detected in all samples, such as oligopeptides with ACE-inhibitor activity, ɣ-aminobutyric acid, alkaloids, and polyphenols (flavonoids, coumarins, and cinnamic acids). Many of these compounds have antioxidant activities, proving the relevance of transformed tomatoes as a source of health-promoting compounds for the human diet. Conclusions: A detailed metabolic profile of commercial tomato puree samples was obtained, and a curated database of metabolites was compiled, which can be useful for multiple purposes, for example, authentication, quality, or nutritional assessments. Full article

Medical image segmentation, driven by the intrinsic fractal characteristics of biological patterns, plays a crucial role in medical image analysis. Recently, universal image segmentation, which aims to build models that generalize robustly to unseen anatomical structures and imaging modalities, has emerged as a promising research direction. To achieve this, previous solutions typically follow the in-context learning (ICL) framework, leveraging segmentation priors from a few labeled in-context references to improve prediction performance on out-of-distribution samples. However, these ICL-based methods often overlook the quality of the in-context set and struggle with capturing intricate anatomical details, thus limiting their segmentation accuracy. To address these issues, we propose VG-SAM, which employs a multi-scale in-context retrieval phase and a visual in-context guided segmentation phase. Specifically, inspired by the hierarchical and self-similar properties in fractal structures, we introduce a multi-level feature similarity strategy to select in-context samples that closely match the query image, thereby ensuring the quality of the in-context samples. In the segmentation phase, we propose to generate multi-granularity visual prompts based on the high-quality priors from the selected in-context set. Following this, these visual prompts, along with the semantic guidance signal derived from the in-context set, are seamlessly integrated into an adaptive fusion module, which effectively guides the Segment Anything Model (SAM) with powerful segmentation capabilities to achieve accurate predictions on out-of-distribution query images. Extensive experiments across multiple datasets demonstrate the effectiveness and superiority of our VG-SAM over the state-of-the-art (SOTA) methods. Notably, under the challenging one-shot reference setting, our VG-SAM surpasses SOTA methods by an average of $6.61\%$ in DSC across all datasets. Full article

This article presents a case study showing the development of a chatbot, named Selene, in a Software-as-a-Service platform for behavioral analysis using Retrieval-Augmented Generation (RAG) integrating domain-specific knowledge and enforcing adherence to organizational rules to improve response quality. Selene is designed to provide deep analyses and practical recommendations that help users optimize organizational behavioral development. To ensure that the RAG pipeline had updated information, we implemented an Extract, Transform, and Load process that updated the knowledge base of the pipeline daily and applied prompt engineering to ensure compliance with organizational rules and directives, using GPT-4 as the underlying language model of the chatbot, which was the state-of-the-art model at the time of deployment. We followed the Generative AI Project Life Cycle Frameworkas the basic methodology to develop this system. To evaluate Selene, we used the DeepEval library, showing that it provides appropriate responses and aligning with organizational rules. Our results show that the system achieves high answer relevancy in 78% of the test cases achieved and a complete absence of bias and toxicity issues. This work provides practical insights for organizations deploying similar knowledge-based chatbot systems. Full article

Employee onboarding is a key process in workforce integration but is manual, time-consuming, and departmental. This paper presents OnboardGPT v1.0, an intelligent, scalable conversational AI platform to meet this task with automated and personalized onboarding experience through lightweight neural components. The platform uses a feedforward intent classification model, dense semantic retrieval through cosine similarity, and personalization aware of user profiles to deliver context-sensitive and relevant output. A 500-question proprietary dataset about onboarding and annotated answers was constructed to simulate real enterprise conversations from various roles and departments. The platform was launched with a Flask-based web interface that was not third-party API-dependent and enabled multi-turn dialogue, knowledge base searching, and role-aware task instruction. Experimental evaluation on performance indicators such as task success rate, intent classification accuracy, BLEU score, and user satisfaction in simulation demonstrates the system to be effective in offering coherent and actionable onboarding support. The contribution of this work includes a modular, explainable, and deployable AI pipeline suitable for onboarding automation at the enterprise level and lays the foundation for future extensions that include multilingual support, inclusion of long-term memory, and backend system interoperability. Full article

Innovative reasoning frameworks have been proposed to enhance the reasoning capabilities of AI agents, improving their performance in various tasks. However, most existing research has focused on enhancing designing frameworks for LLMs, with limited attention on leveraging in-context learning to boost their reasoning power. This paper proposes a novel approach, Demo-ToT, which enhances the Tree-of-Thought (ToT) reasoning framework by dynamically retrieving relevant demonstrations to improve reasoning accuracy. Various demonstration retrieval strategies, including vector similarity, sparse retrieval, and string similarity, were explored to identify the most effective methods for optimizing LLM performance. Experiments conducted across multiple benchmarks and language models of varying sizes demonstrated that Demo-ToT substantially enhanced the reasoning ability of smaller LLMs, achieving performance comparable to or even surpassing that of much larger models such as GPT-4. Full article

Spaceborne Synthetic Aperture Radar (SAR) can be applied for monitoring tropical cyclones (TCs), but co-polarized C-band SAR suffers from signal saturation such that it is improper for high wind-speed conditions. In contrast, cross-polarized SAR data does not suffer from this issue, but the retrieval algorithm needs more deliberation. Previously, many geophysical model functions (GMFs) have been developed using cross-polarized data, which obtain wind speeds using the complex relationships described by radar backscatter, incidence angle, wind direction, and radar look direction. In this regard, the rapid development of artificial intelligence technology has provided versatile machine learning methods for such a nonlinear inversion problem. In this study, we comprehensively compare the wind-speed retrieval performance of several models including Back Propagation Neural Network (BPNN), Support Vector Machine (SVM), Random Forest (RF), and Deep Neural Network (DNN), which were developed based on spatio-temporal matching and correlation analysis of stepped frequency microwave radiometer (SFMR) and dual-polarized Sentinel-1 SAR data after noise removal. A data set with ~2800 samples is generated during TCs for training and validating the inversion model. The generalization ability of different models is tested by the reserved independent data. When using similar parameters with GMFs, RF inversion has the highest accuracy with a Root Mean Square Error (RMSE) of 3.40 m/s and correlation coefficient of 0.94. Furthermore, considering that the sea surface temperature is a crucial factor for generating TCs and influencing ocean backscattering, its effects on the proposed RF model are also explored, the results of which show improved wind-speed retrieval performances. Full article

Monitoring PM2.5 in mining areas is essential for air quality management; however, most studies focus on single-step forecasts, limiting timely decision making. This work addresses the need for accurate multi-step PM2.5 prediction to support proactive pollution control in mining regions. So, a new model for multi-step PM2.5 time series forecasting is proposed, which is based on historical data such as the last day observed (LDO), retrieved data by correlation levels, and linear interpolation. As case studies, data from three environmental monitoring stations in mining areas of Peru were considered: Tala station near the Cuajone mine, Uchumayo near the Cerro Verde mine, and Espinar near the Tintaya mine. The proposed model was compared with benchmark models, including Long Short-Term Memory (LSTM), Bidirectional LSTM (BiLSTM), Gated Recurrent Unit (GRU), and Bidirectional GRU (BiGRU). The results show that the proposed model achieves results similar to those obtained by the benchmark models. The main advantages of the proposed model over the benchmark models lie in the amount of data required for predictions and the training time, which represents less than 0.2% of that required by deep learning-based models. Full article

Multi-angular remote sensing plays a critical role in the study domains of ecological monitoring, climate change, and energy balance. The successful retrieval of the surface Bidirectional Reflectance Distribution Function (BRDF) and albedo from multi-angular remote sensing observations for various applications relies on the sensitivity of an appropriate BRDF model to both the number and the sampling distribution of multi-angular observations. In this study, based on selected high-quality multi-angular datasets, we designed three representative angular sampling schemes to systematically analyze different illuminating–viewing configurations of the retrieval results in a kernel-driven BRDF model framework. We first proposed an angular information index (AII) by incorporating a weighting mechanism and information effectiveness to quantify the angular information content for the angular sampling distribution schemes. In accordance with the principle that observations on the principal plane (PP) provide the most representative anisotropic scattering features, the assigned weight gradually decreases from the PP towards the cross-principal plane (CPP). The information effectiveness is determined based on the cosine similarity between the observations, effectively reducing the information redundancy. With such a method, we assess the AII of the different sampling schemes and further analyze the impact of angular distribution on both BRDF inversion and the estimation of snow surface albedo, including White-Sky Albedo (WSA) and Black-Sky Albedo (BSA) based on the RossThick-LiSparseReciprocal-Snow (RTLSRS) BRDF model. The main conclusions are as follows: (1) The AII approach can serve as a robust indicator of the efficiency of different sampling schemes in BRDF retrieval, which indicates that the RTLSRS model can provide a robust inversion when the AII value exceeds a threshold of −2. (2) When the AII value reaches such a reliable level, different sampling schemes can reproduce the BRDF shapes of snow across different bands to somehow varying degrees. Specifically, observations with smaller view zenith angle (VZA) ranges can reconstruct a BRDF shape that amplifies the anisotropic effect of snow; in addition, the forward scattering tends to be more pronounced at larger solar zenith angles (SZAs), while the variations in BRDF shape reconstructed from off-PP observations depend on both wavelength and SZAs. (3) The relative differences in both BSA and WSA grow with increasing wavelength for all these sampling schemes, mostly within 5% for short bands but up to 30% for longer wavelengths. With this novel AII method to quantify the information contribution of multi-angular sampling distributions, this study offers valuable insights into several main multi-angular BRDF sampling strategies in satellite sensor missions, which relate to most of the fields of multi-angular remote sensing applications in engineering. Full article

The Retrieval-Augmented Generation (RAG) framework shows great potential in terms of improving the reasoning and knowledge utilization capabilities of language models. However, most existing RAG systems heavily rely on large language models (LLMs) and suffer severe performance degradation when using small language models (SLMs), which limits their efficiency and deployment in resource-constrained environments. To address this challenge, we propose Retrieval-Adaptive-Planning RAG (RAP-RAG), a lightweight and high-efficiency RAG framework with adaptive retrieval task planning that is compatible with both SLMs and LLMs simultaneously. RAP-RAG is built on three key components: (1) a heterogeneous weighted graph index that integrates semantic similarity and structural connectivity; (2) a set of retrieval methods that balance efficiency and reasoning power; and (3) an adaptive planner that dynamically selects appropriate strategies based on query features. Experiments on the LiHua-World, MultiHop-RAG, and Hybrid-SQuAD datasets show that RAP-RAG consistently outperforms representative baseline models such as GraphRAG, LightRAG, and MiniRAG. Compared to lightweight baselines, RAP-RAG achieves 3–5% accuracy improvement while maintaining high efficiency and maintains comparable efficiency in both small and large model settings. In addition, our proposed framework reduces storage size by 15% compared to mainstream frameworks. Component analysis further confirms the necessity of weighted graphs and adaptive programming for robust retrieval under multi-hop reasoning and heterogeneous query conditions. These results demonstrate that RAP-RAG is a practical and efficient framework for retrieval-enhanced generation, suitable for large-scale and resource-constrained scenarios. Full article

Images used in real-world applications such as image or video retrieval, outdoor surveillance, and autonomous driving suffer from poor weather conditions. When designing robust computer vision systems, removing adverse weather such as haze, rain, and snow is a significant problem. Recently, deep-learning methods offered a solution for a single type of degradation. Current state-of-the-art universal methods struggle with combinations of degradations, such as haze and rain streaks. Few algorithms have been developed that perform well when presented with images containing multiple adverse weather conditions. This work focuses on developing an efficient solution for multiple adverse weather removal, using a unified quaternion neural architecture called CMAWRNet. It is based on a novel texture–structure decomposition block, a novel lightweight encoder–decoder quaternion transformer architecture, and an attentive fusion block with low-light correction. We also introduce a quaternion similarity loss function to better preserve color information. The quantitative and qualitative evaluation of the current state-of-the-art benchmarking datasets and real-world images shows the performance advantages of the proposed CMAWRNet, compared to other state-of-the-art weather removal approaches dealing with multiple weather artifacts. Extensive computer simulations validate that CMAWRNet improves the performance of downstream applications, such as object detection. This is the first time the decomposition approach has been applied to the universal weather removal task. Full article

The Directional Polarimetric Camera (DPC) onboard the Gaofen-5 (02) satellite includes gas absorption bands that are crucial for the quantitative retrieval of clouds, atmospheric aerosols, and surface parameters. However, in-flight radiometric calibration of these bands remains challenging due to strong absorption features and the lack of onboard calibration devices. In this study, a calibration method that exploits functional relationships between the reflectance ratios of gas absorption and adjacent reference bands and key surface–atmosphere parameters over sunglint were presented. Radiative transfer simulations were combined with polynomial fitting to establish these relationships, and prior knowledge of surface pressure and water vapor column concentration was incorporated to achieve high-precision calibration. Results show that the calibration uncertainty of the oxygen absorption band is mainly driven by surface pressure, with a total uncertainty of 3.01%. For the water vapor absorption band, uncertainties are primarily associated with water vapor column concentration and surface reflectance, yielding total uncertainties of 3.45%. Validation demonstrates the robustness of the proposed method: (1) cross-calibration using desert samples confirms the stability of the results, and (2) the retrieved surface pressure agrees with the DEM-derived estimates, and the retrieved total column water vapor agrees with the MODIS products, confirming the calibration. Overall, the method provides reliable in-flight calibration of DPC gas absorption bands on Gaofen-5 (02) and can be adapted to similar sensors with comparable spectral configurations. Full article

The increased reliance on thermal satellite images for urban climatic analysis requires robust temperature retrievals for urban surfaces. As the emissivity of any surface type determines the amount of thermal radiation received by a sensor, accurate emissivity values of reflecting surfaces are important in Land Surface Temperature (LST) computations. It is known that the commonly used Temperature Emissivity Separation (TES) algorithm is inaccurate over low-emissivity surfaces such as desert sand and metallic surfaces. However, in indigenous cities, much of the satellite ‘seen’ surface consists of metallic roofing materials like corrugated iron or aluminum. This study uses 853 ECOSTRESS images to examine the diurnal and seasonal pattern of LST for five indigenous cities in sub-Saharan Africa. Surface Urban Cool Islands (SUCIs) were observed in all five cities during both summer and winter, which were more pronounced during daytime than at night. This conflicts with air temperature data and published reports, as well as the dominant low-rise urban morphology, which would suggest the occurrence of Surface Urban Heat Islands (SUHIs). The influence of emissivity on urban LST was examined by allocating more realistic emissivity values to metallic surfaces. For a Landsat image, LST values for the urban area increased from 41 °C to 44, 46, and 49 °C when metallic surfaces were allocated emissivity values of 0.96, 0.83, 0.74, and 0.63, respectively, and SUHIs, rather than SUCIs, were observed. Similar results were obtained for an ECOSTRESS image. As increasing summer temperatures cause significant morbidity and mortality in the populations of these cities, accurate urban climatic data are essential. Full article

This paper presents a protocol-driven hybrid architecture that integrates Retrieval-Augmented Generation (RAG) with two complementary protocols—A Model Context Protocol (MCP) and an Agent Communication Protocol (ACP)—to deliver adaptive, transparent, and interoperable intelligent tutoring for higher-education STEM courses. MCP stores, fuses, and exposes session-, task- and course-level context (learning goals, prior errors, instructor flags, and policy constraints), while ACP standardizes multipart messaging and orchestration among specialized tutor agents (retrievers, context managers, pedagogical policy agents, execution tools, and generators). A Python prototype indexes curated course materials (two course corpora: a text-focused PDF and a multimodal PDF/transcript corpus) into a vector store and applies MCP-mediated re-ranking (linear fusion of semantic similarity, MCP relevance, instructor tags, and recency) before RAG prompt assembly. In a held-out evaluation (240 annotated QA pairs) and human studies (36 students, 12 instructors), MCP-aware re-ranking improved Recall@1, increased citation fidelity, reduced unsupported numerical claims, and raised human ratings for factuality and pedagogical appropriateness. Case studies demonstrate improved context continuity, scaffolded hinting under instructor policies, and useful multimodal grounding. The paper concludes that the ACP–MCP–RAG combination enables more trustworthy, auditable, and pedagogically aligned tutoring agents and outlines directions for multimodal extensions, learned re-rankers, and large-scale institutional deployment. Full article

Schizophrenia is a complex disorder influenced by genetic, neurobiological, and environmental factors, with increasing evidence implicating immune dysregulation. This study examined potential molecular mimicry between autoantigens associated with schizophrenia and proteins from Toxoplasma gondii, a parasite previously linked to the disorder. Amino acid sequences of schizophrenia-related autoantigens were retrieved from databases (AAgAtlas, PubMed), and homologous sequences were searched within the T. gondii proteome. Sequence identity was evaluated, and conserved B-cell epitopes were predicted using three-dimensional structures from the Protein Data Bank or models generated in Swiss-Model, followed by epitope mapping with ElliPro. Five autoantigens—gamma-enolase (ENO2), thyroid peroxidase (TPO), glutamic acid decarboxylase 65 kDa isoform (GAD65), serine/threonine-protein kinase 2 (VRK2), and dihydropyrimidine dehydrogenase [NADP(+)] (DPYD)—showed similarities with T. gondii proteins. Among them, enolase exhibited the highest homology, with identities up to 65%. These findings provide preliminary evidence of shared antigenic features between the parasite and schizophrenia-related autoantigens. Such mimicry could contribute to disease mechanisms by triggering autoimmune responses in genetically susceptible individuals, supporting the hypothesis that T. gondii infection may influence schizophrenia pathogenesis. Nonetheless, the results are based exclusively on in silico analyses, and experimental validation will be required to confirm potential cross-reactivity. Full article

Taxonomies provide essential hierarchical structures for classifying information, enabling effective retrieval and knowledge organization in diverse domains such as e-commerce, academic research, and web search. Traditional taxonomy construction, heavily reliant on manual curation by domain experts, faces significant challenges in scalability, cost, and consistency when dealing with the exponential growth of digital data. Recent advancements in Large Language Models (LLMs) and Natural Language Processing (NLP) present powerful opportunities for automating this complex process. This paper explores the potential of LLMs for automated taxonomy generation, focusing on methodologies incorporating semantic embedding generation, keyword extraction, and machine learning clustering algorithms. We specifically investigate and conduct a comparative analysis of two primary LLM-based approaches using a dataset of eBay product descriptions. The first approach involves fine-tuning a pre-trained LLM using structured hierarchical data derived from chain-of-layer clustering outputs. The second employs prompt-engineering techniques to guide LLMs in generating context-aware hierarchical taxonomies based on clustered keywords without explicit model retraining. Both methodologies are evaluated for their efficacy in constructing organized multi-level hierarchical taxonomies. Evaluation using semantic similarity metrics (BERTScore and Cosine Similarity) against a ground truth reveals that the fine-tuning approach yields higher overall accuracy and consistency (BERTScore F1: 70.91%; Cosine Similarity: 66.40%) compared to the prompt-engineering approach (BERTScore F1: 61.66%; Cosine Similarity: 60.34%). We delve into the inherent trade-offs between these methods concerning semantic fidelity, computational resource requirements, result stability, and scalability. Finally, we outline potential directions for future research aimed at refining LLM-based taxonomy construction systems to handle large dynamic datasets with enhanced accuracy, robustness, and granularity. Full article