Search Results (525)

Recipes available on the web often lack nutritional transparency and clear indicators of dietary suitability. While searching by title is straightforward, exploring recipes that meet combined dietary needs, nutritional goals, and ingredient-level preferences remains challenging. Most existing recipe search systems do not effectively support flexible multi-dietary reasoning in combination with user preferences and restrictions. For example, users may seek gluten-free and dairy-free dinners with suitable substitutions, or compound goals such as vegan and low-fat desserts. Recent systematic reviews report that most food recommender systems are content-based and often non-personalized, with limited support for dietary restrictions, ingredient-level exclusions, and multi-criteria nutrition goals. This paper introduces DietQA, an end-to-end, language-adaptable chatbot system that integrates a Knowledge Graph (KG), Retrieval-Augmented Generation (RAG), and a Large Language Model (LLM) to support personalized, dietary-aware recipe search and question answering. DietQA crawls Greek-language recipe websites to extract structured information such as titles, ingredients, and quantities. Nutritional values are calculated using validated food composition databases, and dietary tags are inferred automatically based on ingredient composition. All information is stored in a Neo4j-based knowledge graph, enabling flexible querying via Cypher. Users interact with the system through a natural language chatbot friendly interface, where they can express preferences for ingredients, nutrients, dishes, and diets, and filter recipes based on multiple factors such as ingredient availability, exclusions, and nutritional goals. DietQA supports multi-diet recipe search by retrieving both compliant recipes and those adaptable via ingredient substitutions, explaining how each result aligns with user preferences and constraints. An LLM extracts intents and entities from user queries to support rule-based Cypher retrieval, while the RAG pipeline generates contextualized responses using the user query and preferences, retrieved recipes, statistical summaries, and substitution logic. The system integrates real-time updates of recipe and nutritional data, supporting up-to-date, relevant, and personalized recommendations. It is designed for language-adaptable deployment and has been developed and evaluated using Greek-language content. DietQA provides a scalable framework for transparent and adaptive dietary recommendation systems powered by conversational AI. Full article

Multi-view data, captured from various perspectives, is crucial for training view-invariant human action recognition models, yet its acquisition is hindered by spatio-temporal constraints and high costs. This study aims to develop the Pose Scene EveryWhere (PSEW) framework, which automatically generates temporally consistent, multi-view 3D human action data from a single monocular video. The proposed framework first predicts 3D human parameters from each video frame using a deep learning-based Human Mesh Recovery (HMR) model. Subsequently, it applies tracking, linear interpolation, and Kalman filtering to refine temporal consistency and produce naturalistic motion. The refined human meshes are then reconstructed into a virtual 3D scene by estimating a stable floor plane for alignment, and finally, novel-view videos are rendered using user-defined virtual cameras. As a result, the framework successfully generated multi-view data with realistic, jitter-free motion from a single video input. To assess fidelity to the original motion, we used Root Mean Square Error (RMSE) and Mean Per Joint Position Error (MPJPE) as metrics, achieving low average errors in both 2D (RMSE: 0.172; MPJPE: 0.202) and 3D (RMSE: 0.145; MPJPE: 0.206) space. PSEW provides an efficient, scalable, and low-cost solution that overcomes the limitations of traditional data collection methods, offering a remedy for the scarcity of training data for action recognition models. Full article

Electronic quick response (e-QR) codes provide access to real-time sensor data using smartphone readers and internet connectivity. Printed electronics and hybrid integration on flexible substrates is a promising solution for wide-scale and low-cost deployment of sensor systems. This paper presents a 21 × 21-pixel e-QR display implemented on black Kapton using hybrid additive and subtractive microfabrication techniques. The process flow for the double-sided circuit allows for layer alignment using multiple fiducial markers. The steps include inkjet printing of tracks on both sides of the substrate, laser-cut via holes, stencil-aided via filling, solder paste dispensing, and final integration of discrete surface-mount components by semi-automatic pick-and-place. Full article

This study developed and evaluated transformer-based models enhanced with inter-sentence attention (iAttention) mechanisms to improve the automatic grading of student responses to open-ended questions. Traditional transformer models emphasize intra-sentence relationships and often fail to capture complex semantic alignments needed for accurate assessment. To overcome this limitation, three iAttention mechanisms, including ${iAttention}_{TF-IDF}$, ${iAttention}_{word}$ and ${iAttention}_{HW}$ were proposed to enhance the model’s capacity to align key ideas between students and reference answers. This helps improve the model’s ability to capture important semantic relationships between words in two sentences. Unlike previous approaches that rely solely on aggregated sentence embeddings, the proposed method introduces inter-sentence attention layers that explicitly model semantic correspondence between individual sentences. This enables finer-grained matching of key concepts, reasoning, and logical structure which are crucial for fair and reliable assessment. The models were evaluated on multiple benchmark datasets, including Semantic Textual Similarity (STS), SemEval-2013 Beetle, SciEntsBank, Mohler, and a composite of university-level educational datasets (U-datasets). Experimental results demonstrated that integrating iAttention consistently outperforms baseline models, achieving higher Pearson and Spearman Correlation scores on STS, Mohler, and U-datasets, as well as superior Macro-F1, Weighted-F1, and Accuracy on the Beetle and SciEntsBank datasets. This approach contributes to the development of scalable, consistent, and fair automated grading systems by narrowing the gap between machine evaluation and human judgment, ultimately leading to more accurate and efficient assessment practices. Full article

We introduce a code-only approach for modeling web page layouts directly from their source code (HTML and CSS only), bypassing rendering. Our method employs a neural architecture with specialized encoders for style rules, CSS selectors, and HTML attributes. These encodings are then aggregated in another neural network that integrates hierarchical context (sibling and ancestor information) to form rich representational vectors for each web page’s element. Using these vectors, our model predicts eight spatial relationships between pairs of elements, focusing on edge-based proximity in a multilabel classification setup. For scalable training, labels are automatically derived from the Document Object Model (DOM) data for each web page, but the model operates independently of the DOM during inference. During inference, the model does not use bounding boxes or any information found in the DOM; instead, it relies solely on the source code as input. This approach facilitates structure-aware visual analysis in a lightweight and fully code-based way. Our model demonstrates alignment with human judgment in the evaluation of web page similarity, suggesting that code-only layout modeling offers a promising direction for scalable, interpretable, and efficient web interface analysis. The evaluation metrics show our method yields similar performance despite relying on less information. Full article

Cantonese automatic speech recognition (ASR) faces persistent challenges due to its nine lexical tones, extensive phonological variation, and the scarcity of professionally transcribed corpora. To address these issues, we propose a lightweight and data-efficient framework that leverages weak phonetic supervision (WPS) in conjunction with two pho-neme-aware augmentation strategies. (1) Dynamic Boundary-Aligned Phoneme Dropout progressively removes entire IPA segments according to a curriculum schedule, simulating real-world phenomena such as elision, lenition, and tonal drift while ensuring training stability. (2) Phoneme-Aware SpecAugment confines all time- and frequency-masking operations within phoneme boundaries and prioritizes high-attention regions, thereby preserving intra-phonemic contours and formant integrity. Built on the Whistle encoder—which integrates a Conformer backbone, Connectionist Temporal Classification–Conditional Random Field (CTC-CRF) alignment, and a multi-lingual phonetic space—the approach requires only a grapheme-to-phoneme lexicon and Montreal Forced Aligner outputs, without any additional manual labeling. Experiments on the Cantonese subset of Common Voice demonstrate consistent gains: Dynamic Dropout alone reduces phoneme error rate (PER) from 17.8% to 16.7% with 50 h of speech and 16.4% to 15.1% with 100 h, while the combination of the two augmentations further lowers PER to 15.9%/14.4%. These results confirm that structure-aware phoneme-level perturbations provide an effective and low-cost solution for building robust Cantonese ASR systems under low-resource conditions. Full article

This article analyses the role of the Spanish university system in promoting fair Trade (FT) and the sustainable development goals (SDGs), with a particular focus on the Universities for Fair Trade (UxFT) programme. A mixed methodology combining qualitative and quantitative approaches was used to review and analyse the websites of 90 Spanish universities (both public and private) to assess their commitment to FT and the SDGs. This was based on four variables: (1) reference to the SDGs; (2) a structured programme to promote the SDGs; (3) specific actions to promote or raise awareness of the SDGs; and (4) working on FT. The results show that, while most universities include the SDGs in their institutional strategies, only some have structured programmes. Regarding FT, several universities carry out activities linked to this movement, with some actively participating in the UxFT. Public universities demonstrate greater commitment. The SDGs that are most frequently addressed are 12 (Responsible consumption and production), 4 (Quality education) and 13 (Climate action), highlighting the close relationship between FT and sustainability. The study reveals a gap between discursive commitments to sustainability and the actual implementation of FT practices, suggesting that the integration of FT is not automatic even when SDG strategies are present. This has important implications: promoting FT within universities requires not only structured SDG strategies, but also explicit institutional policies, dedicated resources, and greater awareness of FT transformative potential. The findings underscore the need for stronger institutional commitment to move beyond isolated actions and toward a university model grounded in social justice and sustainability. Integrating the UxFT programme more broadly could help foster critical thinking, participatory governance, and more coherent practices aligned with the 2030 Agenda. Full article

Wilderness Search and Rescue (WSAR) missions are time-critical emergency response operations that require locating a lost person within a short timeframe. Large forested terrains must be explored in challenging environments and adverse conditions. Unmanned Aerial Vehicles (UAVs) equipped with thermal cameras enable the efficient exploration of vast areas. However, manual analysis of the huge amount of collected data is difficult, time-consuming, and prone to errors, increasing the risk of missing a person. This work proposes an object detection and tracking pipeline that automatically analyzes UAV thermal videos in real-time to identify lost people in forest environments. The tracking module combines information from multiple viewpoints to suppress false alarms and focus responders’ efforts. In this moving camera scenario, tracking performance is enhanced by introducing a motion compensation module based on known camera poses. Experimental results on the collected thermal video dataset demonstrate the effectiveness of the proposed tracking-based approach by achieving a Precision of 90.3% and a Recall of 73.4%. On a dataset of UAV thermal images, the introduced camera alignment technique increases the Recall by 6.1%, with negligible computational overhead, reaching 35.2 FPS. The proposed approach, optimized for real-time video processing, has direct application in real-world WSAR missions to improve operational efficiency. Full article

Phytoplankton plays a pivotal role in marine ecosystems and global biogeochemical cycles. Accurate identification and monitoring of phytoplankton are essential for understanding environmental dynamics and climate variations. Despite the significant progress made in automatic phytoplankton identification, current datasets predominantly consist of idealized laboratory images, leading to models that demonstrate persistent limitations in the fine-grained differentiation of phytoplankton species. To achieve high accuracy and transferability for morphologically similar species and diverse ecosystems, we introduce a hybrid dataset by integrating laboratory-based observations with in situ marine environmental data. We evaluate the performance of our dataset on contemporary deep learning models, revealing that CNN-based architectures offer superior stability (85.27% mAcc., 93.76% oAcc.). Multimodal learning facilitates refined phytoplankton recognition through the integration of visual and textual representations, thereby enhancing the model’s semantic comprehension capabilities. We present a fine-tuned visual language model leveraging enhanced textual prompts augmented with expert-annotated morphological descriptions, significantly enhancing visual-semantic alignment and allowing for more accurate and interpretable recognition of closely related species (84.11% mAcc., 94.48% oAcc.). Our research establishes a benchmark dataset that facilitates real-time ecological monitoring and aquatic biodiversity research. Furthermore, it also contributes to the field by enhancing model robustness and transferability to diverse environmental contexts and taxonomically similar species. Full article

Online education has become an important channel for extensive, inclusive and flexible learning experiences. However, significant gaps persist in providing truly accessible, personalized and adaptable e-learning environments, especially for students with disabilities, varied language backgrounds, or limited bandwidth. This paper presents AccessiLearnAI, an AI-driven platform, which converges accessibility-first design, multi-format content delivery, advanced personalization, and Progressive Web App (PWA) offline capabilities. Our solution is compliant with semantic HTML5 and ARIA standards, and incorporates features such as automatic alt-text generation for images using Large Language Models (LLMs), real-time functionality for summarization, translation, and text-to-speech capabilities. The platform, built on top of a modular MVC and microservices-based architecture, also integrates robust security, GDPR-aligned data protection, and a human-in-the-loop to ensure the accuracy and reliability of AI-generated outputs. Early evaluations indicate that AccessiLearnAI improves engagement and learning outcomes across multiple ranges of users, suggesting that responsible AI and universal design can successfully coexist to bring equity through digital education. Full article

This paper presents a modular framework for character-coherent, emotion-aware role-playing dialogue with large language models (LLMs), centered on a novel Verifiable Emotion Reward (VER) objective. We introduce VER as a reinforcement-style signal derived from frozen emotion classifiers to provide both turn-level and dialogue-level alignment, effectively mitigating emotional drift across long interactions. To amplify VER’s benefits, we construct Character-Coherent Dialogues (CHARCO), a large-scale multi-turn dataset of over 230,000 dialogues, richly annotated with persona profiles, semantic contexts, and ten emotion labels. Our experiments show that fine-tuning LLMs on CHARCO significantly enhances VER’s impact, driving marked improvements in emotional consistency, role fidelity, and dialogue coherence. Through the evaluation that integrates lexical diversity metrics, automatic scoring with GPT-4, and human assessments, we demonstrate that the collaboration between a purpose-built multi-turn dataset and the VER objective leads to significant advancements in the field of persona-aligned conversational agents. Full article

In the manufacturing supply chain, management reports often begin with concise messages that summarize key inventory insights. Traditionally, human analysts manually crafted these summary messages by sifting through complex data—a process that is both time-consuming and prone to inconsistency. In this research study, we present an AI-based system that automatically generates high-quality inventory insight summaries, referred to as “headline messages,” using real-world inventory data. The proposed system leverages lightweight natural language processing (NLP) and machine learning models to achieve accurate and efficient performance. Historical messages are first clustered using a sentence-translation MiniLM model that provides fast semantic embedding. This is used to derive key message categories and define structured input features for this purpose. Then, an explainable and low-complexity classifier trained to predict appropriate headline messages based on current inventory metrics using minimal computational resources. Through empirical experiments with real enterprise data, we demonstrate that this approach can reproduce expert-written headline messages with high accuracy while reducing report generation time from hours to minutes. This study makes three contributions. First, it introduces a lightweight approach that transforms inventory data into concise messages. Second, the proposed approach mitigates confusion by maintaining interpretability and fact-based control, and aligns wording with domain-specific terminology. Furthermore, it reports an industrial validation and deployment case study, demonstrating that the system can be integrated with enterprise data pipelines to generate large-scale weekly reports. These results demonstrate the application and technological innovation of combining small-scale language models with interpretable machine learning to provide insights. Full article

Improving the operational speed of cabbage transplanters is essential for precision seed-ling placement and labor efficiency. In South Korea, manual cabbage transplanting can demand up to 184 person-hours per hectare, often leading to delays during peak periods due to labor shortages. Moreover, the environmental urgency to reduce plastic waste has accelerated the adoption of biodegradable pots in mechanized systems, supporting global sustainable development goals. This study aimed to determine optimal working conditions for a 1.54 kW semi-automatic single-row cabbage transplanter designed for biodegradable pots. The cam-follower-based planting mechanism was analyzed to identify ideal forward and rotational speeds, while evaluating power consumption and seedling placement quality. The mechanism includes a crank-driven four-bar linkage, with an added restoring spring for enhanced motion stability. A total of nine simulation trials were conducted across forward speeds of 250, 300, and 350 mm/s and planting unit speeds of 40, 50, and 60 rpm. Simulation and experimental results confirmed that a forward velocity of 300 mm/s and crank speed of 60 rpm produced optimal outcomes, achieving a vertical hopper displacement of 280 mm, minimal soil disturbance (2186.95 ± 2.27 mm²), upright seedling alignment, and the lowest power usage (17.42 ± 1.21 W). Comparative analysis showed that under the optimal condition, the characteristic coefficient λ = 1 minimized misalignment and power loss. These results support scalable and energy-efficient transplanting systems suitable for smallholder and mid-sized farms, offering an environmentally sustainable solution. Full article

Ventricular arrhythmias such as ventricular fibrillation (VF) and ventricular tachycardia (VT) are among the leading causes of sudden cardiac death worldwide, making their timely and accurate detection a critical task in modern cardiology. This study presents an advanced framework for the automatic detection of critical cardiac arrhythmias—specifically ventricular fibrillation (VF) and ventricular tachycardia (VT)—by integrating deep learning techniques with neuro-fuzzy systems. Electrocardiogram (ECG) signals from the MIT-BIH and AHA databases were preprocessed through denoising, alignment, and segmentation. Convolutional neural networks (CNNs) were employed for deep feature extraction, and the resulting features were used as input for various fuzzy classifiers, including Fuzzy ARTMAP and the Adaptive Neuro-Fuzzy Inference System (ANFIS). Among these classifiers, ANFIS demonstrated the best overall performance. The combination of CNN-based feature extraction with ANFIS yielded the highest classification accuracy across multiple cardiac rhythm types. The classification performance metrics for each rhythm type were as follows: for Normal Sinus Rhythm, precision was 99.09%, sensitivity 98.70%, specificity 98.89%, and F1-score 98.89%. For VF, precision was 95.49%, sensitivity 96.69%, specificity 99.10%, and F1-score 96.09%. For VT, precision was 94.03%, sensitivity 94.26%, specificity 99.54%, and F1-score 94.14%. Finally, for Other Rhythms, precision was 97.74%, sensitivity 97.74%, specificity 99.40%, and F1-score 97.74%. These results demonstrate the strong generalization capability and precision of the proposed architecture, suggesting its potential applicability in real-time biomedical systems such as Automated External Defibrillators (AEDs), Implantable Cardioverter Defibrillators (ICDs), and advanced cardiac monitoring technologies. Full article

Background/Objectives: Human epidermal growth factor 2 (HER2) scoring is critical for modern breast cancer therapies, especially with emerging indications of antibody–drug conjugates for HER2-low tumors. However, inter-observer agreement remains limited in borderline cases. Automatic artificial intelligence-based scoring has the potential to improve diagnostic consistency and scalability. This study aimed to develop two transformer-based models for HER2 scoring of breast cancer whole-slide images (WSIs) and compare their performance. Methods: We adapted a large-scale foundation model (Virchow) and a lightweight model (TinyViT). Both were trained using patch-level annotations and integrated into a WSI scoring pipeline. Performance was evaluated on a clinical test set (n = 66), including clinical decision tasks and inference efficiency. Results: Both models achieved substantial agreement with pathologist reports (linear weighted kappa: 0.860 for Virchow, 0.825 for TinyViT). Virchow showed slightly higher WSI-level accuracy than TinyViT, whereas TinyViT reduced inference times by 60%. In three binary clinical tasks, both models demonstrated a diagnostic performance comparable to pathologists, particularly in identifying HER2-low tumors for antibody–drug conjugate (ADC) therapy. A continuous scoring framework demonstrated a strong correlation between the two models (Pearson’s r = 0.995) and aligned with human assessments. Conclusions: Both transformer-based artificial intelligence models achieved human-level accuracy for automated HER2 scoring with interpretable outputs. While the foundation model offers marginally higher accuracy, the lightweight model provides practical advantages for clinical deployment. In addition, continuous scoring may provide a more granular HER2 quantification, especially in borderline cases. This could support a new interpretive paradigm for HER2 assessment aligned with the evolving indications of ADC. Full article