Search Results (138)

Against the dual backdrop of the rural revitalization strategy and the pursuit of high-quality, balanced urban–rural education, optimizing rural campus spaces has emerged as an important lever for addressing educational resource disparities and improving pedagogical quality. However, conventional evaluation of campus space optimization faces two systemic dilemmas. First, top-down decision-making often neglects the authentic needs of diverse stakeholders and place-based knowledge, resulting in spatial interventions that lose regional distinctiveness. Second, routine public participation is constrained by geographical barriers, time costs, and sample-size limitations, which can amplify professional cognitive bias and impede comprehensive feedback formation. The compounded effect of these challenges contributes to a disconnect between spatial optimization outcomes and perceived needs, thereby constraining the distinctive development of rural educational spaces. To address these constraints, this study proposes a novel method that integrates regional spatial feature recognition with digital media-based public perception assessment. At the data collection and ethical governance level, the study strictly adheres to platform compliance and academic ethics. A total of 12,800 preliminary comments were scraped from major social media platforms (e.g., Douyin, Dianping, and Xiaohongshu) and processed through a three-stage screening workflow—keyword screening–rule-based filtering–manual verification—to yield 8616 valid records covering diverse public groups across China. All user-identifying information was fully anonymized to ensure lawful use and privacy protection. At the analytical modeling level, we develop a Transformer-based deep learning system that leverages multi-head attention mechanisms to capture implicit spatial-sentiment features and metaphorical expressions embedded in review texts. Evaluation on an independent test set indicates a classification accuracy of 89.2%, aligning with balanced and stable scoring performance. Robustness is further strengthened by introducing an equal-weight alternative strategy and conducting stability checks to indicate the consistency of model outputs across weighting assumptions. At the scenario interpretation level, we combine grounded-theory coding with semantic network analysis to establish a three-tier spatial analysis framework—macro (landscape pattern/hydro-topological patterns), meso (architectural interface), and micro (teaching scenes/pedagogical scenarios)—and incorporate an interpretive stakeholder typology (tourists, residents, parents, and professional groups) to systematically identify and quantify key features shaping public spatial perception. Findings show that, at the macro level, naturally integrated scenarios—such as “campus–farmland integration” and “mountain–water embeddedness”—exhibit high affective association, aligning with the “mountain-water-field-village” spatial sequence logic and suggesting broad public endorsement of ecological campus concepts, whereas vernacular settlement-pattern scenarios receive relatively low attention due to cognitive discontinuities. At the meso level, innovative corridor strategies (e.g., framed vistas and expanded corridor spaces) strengthen the building–nature interaction and suggest latent value in stimulating exploratory spatial experience. At the micro level, place-based practice-oriented teaching scenes (e.g., intangible cultural heritage handcraft and creative workshops) achieve higher scores, aligning with the compatibility of vernacular education’s “differential esthetics,” while urban convergence-oriented interdisciplinary curriculum scenes suggest an interpretive gap relative to public expectations. These results indicate an embedded relationship between public perception and regional spatial features, which is further shaped by a multi-actor governance process—characterized by “Government + Influencers + Field Study”—that mediates how rural educational spaces are produced, communicated, and interpreted in digital environments. The study’s innovative value lies in integrating sociological theories (e.g., embeddedness) with deep learning techniques to fill the regional and multi-actor perspective gap in rural campus POE and to promote a methodological shift from “experience-based induction” toward a “data-theory” dual-drive model. The findings provide inferential evidence for rural campus renewal and optimization; the methodological pipeline is transferable to small-scale rural primary schools with media exposure and salient regional ecological characteristics, and it offers a new pathway for incorporating digital media-driven public perception feedback into planning and design practice. The research methodology of this study consists of four sequential stages, which are implemented in a systematic and progressive manner: First, data collection was conducted: Python and the Octopus Collector were used to crawl online comment data related to Fuwen Township Central Primary School, strictly complying with the user agreements of the Douyin, Dianping, and Xiaohongshu platforms. Second, semantic preprocessing was performed: The evaluation content was segmented to generate word frequency statistics and semantic networks; qualitative analysis was conducted using Origin software, and quantitative translation was realized via Sankey diagrams. Third, spatial scene coding was carried out: Combined with a spatial characteristic identification system, a macro–meso–micro three-tier classification system for spatial scene characteristics was constructed to encode and quantitatively express the textual content. Finally, sentiment quantification and correlation analysis was implemented: A deep learning model based on the Transformer framework was employed to perform sentiment quantification scoring for each comment; Sankey diagrams were used to quantitatively correlate spatial scenes with sentiment tendencies, thereby exploring the public’s perceptual associations with the architectural spatial environment of rural campuses. Full article

Background/Objectives: Otitis media (OM), including acute otitis media (AOM) and chronic otitis media (COM), is a common middle ear disease that can lead to significant morbidity if not accurately diagnosed. Otoscopic interpretation remains subjective and operator-dependent, underscoring the need for objective and reproducible diagnostic support. Recent advances in artificial intelligence (AI) offer promising solutions for automated otoscopic image analysis. Methods: We developed an AI-based diagnostic framework consisting of three sequential steps: (1) semi-supervised learning for automatic recognition and semantic segmentation of tympanic membrane structures, (2) region-based feature extraction, and (3) disease classification. A total of 607 clinical otoscopic images were retrospectively collected, including normal ears (n = 220), AOM (n = 157), and COM with tympanic membrane perforation (n = 230). Among these, 485 images were used for training and 122 for independent testing. Semantic segmentation of five anatomically relevant regions was performed using multiple convolutional neural network architectures, including U-Net, PSPNet, HRNet, and DeepLabV3+. Following segmentation, color and texture features were extracted from each region and used to train a neural network-based classifier to differentiate disease states. Results: Among the evaluated segmentation models, U-Net demonstrated superior performance, achieving an overall pixel accuracy of 96.76% and a mean Dice similarity coefficient of 71.68%. The segmented regions enabled reliable extraction of discriminative chromatic and texture features. In the final classification stage, the proposed framework achieved diagnostic accuracies of 100% for normal ears, 100% for AOM, and 91.3% for COM on the independent test set, with an overall accuracy of 96.72%. Conclusions: This study demonstrates that a semi-supervised, segmentation-driven AI pipeline integrating feature extraction and classification can achieve high diagnostic accuracy for otitis media. The proposed framework offers a clinically interpretable and fully automated approach that may enhance diagnostic consistency, support clinical decision-making, and facilitate scalable otoscopic assessment in diverse healthcare screening settings for disease prevention and health education. Full article

This study proposes an approach for detecting alcohol intoxication from speech based on a combination of audio segmentation and a hybrid neural network architecture that integrates convolution neural network (CNN) and long-short term memory (LSTM) layers. The proposed design enables effective modeling of both local spectral patterns and long-term temporal dependencies in speech signals. By operating on relatively long audio segments, the approach allows the simultaneous analysis of complex speech constructions and pause patterns, which are known to be sensitive to alcohol-induced speech impairments. Each audio signal was divided into two equal-duration segments that are processed sequentially by the model, which helps reduce the impact of asymmetrical distribution of intoxication-related speech artifacts. The approach was evaluated using the GradusSpeech-v1 corpus, which contains more than 1300 recordings of Russian tongue twisters collected from 31 speakers under controlled conditions in both sober and intoxicated states. Experimental results demonstrate that the proposed method achieves high performance. When full recordings are analyzed using median aggregation of segment-level predictions, the model reaches Accuracy, Recall, and F1-score values close to 0.93, indicating the effectiveness of the approach for alcohol intoxication detection in speech. Full article

Triticale (×Triticosecale Wittmack), a synthetic hybrid of wheat (Triticum spp.) and rye (Secale cereale), is a valuable dual-purpose crop for its high yield and stress tolerance. Introducing beneficial alien chromatin is crucial for expanding genetic diversity and improving cultivars. This study aimed to introduce Thinopyrum intermedium St genome chromatin into hexaploid triticale via trigeneric hybridization to develop novel germplasm. Six stable lines were selected from crosses between an octoploid wheat-Th. intermedium partial amphiploid line Maicao 8 and a hexaploid triticale cultivar Hashi 209. Agronomic traits were evaluated over two cropping seasons, revealing that the translocation lines exhibited superior agronomic performance compared to the parental triticales. These lines showed longer spikes, higher tiller numbers, and increased grain protein content, without compromising thousand-kernel weight. Cytogenetic analysis using sequential multicolor genomic in situ hybridization (smGISH), fluorescence in situ hybridization (FISH), and oligonucleotide probes, alongside validation with species-specific molecular markers, identified all six lines as St-R terminal translocation lines containing 14 rye chromosomes. Three lines carried a small terminal St segment on chromosome 1R, while the other three carried St segments on both 1RL and 4RS chromosomes. This work demonstrates that trigeneric hybridization is an effective strategy for inducing intergeneric recombination between Thinopyrum intermedium and rye chromosomes, leading to stable, small-segment terminal translocations. The developed St-R translocation lines represent a novel and valuable germplasm resource for enriching genetic diversity and breeding improved triticale cultivars with enhanced yield and quality traits. Full article

Background: Accurate staging of bladder cancer is critical for guiding clinical management, particularly the distinction between non–muscle-invasive (T1) and muscle-invasive (T2–T4) disease. Although MRI offers superior soft-tissue contrast, image interpretation remains opera-tor-dependent and subject to inter-observer variability. This study proposes an automated deep learning framework for MRI-based bladder cancer staging to support standardized radio-logical interpretation. Methods: A sequential AI-based pipeline was developed, integrating hybrid tumor segmentation using YOLOv11 for lesion detection and DeepLabV3 for boundary refinement, followed by three deep learning classifiers (VGG19, ResNet50, and Vision Transformer) for MRI-based stage prediction. A total of 416 T2-weighted MRI images with radiology-derived stage labels (T1–T4) were included, with data augmentation applied during training. Model performance was evaluated using accuracy, precision, recall, F1-score, and multi-class AUC. Performance un-certainty was characterized using patient-level bootstrap confidence intervals under a fixed training and evaluation pipeline. Results: All evaluated models demonstrated high and broadly comparable discriminative performance for MRI-based bladder cancer staging within the present dataset, with high point estimates of accuracy and AUC, particularly for differentiating non–muscle-invasive from muscle-invasive disease. Calibration analysis characterized the probabilistic behavior of predicted stage probabilities under the current experimental setting. Conclusions: The proposed framework demonstrates the feasibility of automated MRI-based bladder cancer staging derived from radiological reference labels and supports the potential of deep learning for stand-ardizing and reproducing MRI-based staging procedures. Rather than serving as an independent clinical decision-support system, the framework is intended as a methodological and work-flow-oriented tool for automated staging consistency. Further validation using multi-center datasets, patient-level data splitting prior to augmentation, pathology-confirmed reference stand-ards, and explainable AI techniques is required to establish generalizability and clinical relevance. Full article

Background: Rehabilitation of the severely atrophic posterior mandible remains surgically challenging, and inferior alveolar nerve (IAN) repositioning is a well-established technique that enables implant placement in anatomically compromised cases. Although neurosensory outcomes following nerve relocation have been extensively investigated, the regenerative capacity of the mandibular canal itself has not been previously evaluated. This study presents the first computer-assisted, cone-beam computed tomography (CBCT)-based assessment of bony canal regeneration after IAN transposition. Methods: Twenty-two patients who underwent unilateral IAN transposition were evaluated using standardized CBCT one year postoperatively. A semi-manual segmentation workflow was performed using Mimics Core Medical software version 27.0 (Materialise), and regenerated canal walls were identified according to four strict criteria: (1) canal continuity across sequential CBCT sections, (2) defined canal walls demonstrating high-density bone (>800 HU, or >400 HU), (3) ≥270° circumferential bony enclosure, and (4) morphology consistent with the native mandibular canal. Regeneration was quantified as the proportion of the surgically disrupted canal segment exhibiting a fully, or near fully, reconstructed canal. Results: Mandibular canal regeneration was observed in all patients. The mean regeneration at one year was 72.7% ± 13% when applying strict >800 HU criteria, with 20 patients demonstrating substantial (>70%) reformation and 2 patients showing partial regeneration (<40%). When a lower density threshold (>400 HU) was applied to include early or less mineralized bone, the mean regeneration increased to 78.1% ± 11%, indicating the presence of maturing bone structures that did not yet meet full-density criteria. Conclusions: Computer-assisted CBCT analysis demonstrates that partial to extensive regeneration of the mandibular canal occurs within one year following IAN transposition. This study provides the first quantitative evidence of this phenomenon, highlighting the intrinsic regenerative potential of the mandibular canal and suggesting a possible association with postoperative neurosensory recovery. Full article

Pan-Homophonic events denote fluctuations in stock prices that are triggered by phonetic similarities between event keywords and stock tickers. As a relatively novel and under-researched phenomenon, they mirror a subtle yet influential behavioral deviation within financial markets. Centering on the case of Chuandazhisheng, this study delves into how such events produce dynamic and time-varying impacts on stock prices. A linguistic amplitude segmentation method is devised to discriminate between high- and low-intensity events based on information entropy. To separate pan-homophonic-driven price movements from broader market trends, the Relational Stock Ranking (RSR) model is integrated with a Dynamic Conditional Correlation-Generalized Autoregressive Conditional Heteroskedasticity (DCC-GARCH) framework to establish an adjusted price benchmark. The empirical analysis reveals a sequential price response: initial moderate fluctuations in the low-amplitude phase often yield to more prominent volatility in the high-amplitude phase. While price surges typically occur within one or two days of the event, they generally revert within approximately three weeks. Moreover, repeated exposures to homo- phonic stimuli seem to attenuate the response, indicating a decaying spillover pattern. These findings contribute to a more profound understanding of the intersection between linguistic cues and market behavior and provide practical insights for investor education, information filtering, and regulatory supervision. Full article

Sporadic-E (Es) layers can strongly perturb HF/VHF propagation and create intermittent interference, motivating higher-revisit monitoring at the frequencies most affected. EsTRACE (Es-layer TRAnsient Cloud Explorer) is a PlanarSat mission concept that transmits sequential beacons in the 28/50 MHz amateur bands using FT4 (weak-signal digital) and CW (continuous wave) waveforms and leverages distributed amateur receiver networks for near-real-time SNR mapping. This paper documents the early-phase spacecraft design from the Bid/proposal phase (Bid), through the Conceptual Design Review (CoDR), to the Preliminary Design Review (PDR), using a power-first sizing loop that couples link-budget closure to duty cycle and solar-array area under a free-tumbling, batteryless constraint. The analysis supports conceptual feasibility of the architecture under stated antenna and ground-segment assumptions; on-orbit demonstration and measured RF/antenna characterization are identified as required future validation steps. Full article

To reduce the computational cost associated with traditional moving heat source methods, a segmented approach is proposed for simulating the welding process of T-joints in large-scale infrastructure steel modules. Firstly, the hole-drilling method was employed to measure the welding residual stresses in a 2400 mm T-joint. Subsequently, a three-dimensional finite element model was established in ABAQUS, and a user-defined subroutine for the segmented moving heat source was developed in Fortran to calculate the welding residual stresses. The numerical simulation results were compared with experimental data, showing high consistency and further validating the accuracy of the finite element model. Furthermore, the distribution patterns of residual stresses along the thickness direction and the effects of different welding sequences on temperature, stress, and deformation were investigated to optimize the welding sequence. The results indicated that the residual stresses along the weld seam exhibited a compressive–tensile–compressive distribution, with the maximum tensile stress reaching approximately 347 MPa. Additionally, the simulation results demonstrated that the double-ellipsoidal heat source method was computationally intensive and failed to provide accurate results for long weld seams, whereas the segmented moving heat source approach reduced the computation time to only 38 h. Moreover, different welding sequences had a significant impact on residual stresses and deformation. Through comprehensive analysis, it was found that Case 1 (sequential welding in the forward direction) achieved the best performance in minimizing welding residual stresses and deformation. Full article

Background/Objectives: Histopathological images are fundamental for the morphological diagnosis and subtyping of lung cancer. However, their high resolution, color diversity, and structural complexity make automated segmentation highly challenging. This study aims to address these challenges by developing a novel hybrid metaheuristic approach for multilevel image thresholding to enhance segmentation accuracy and computational efficiency. Methods: An adaptive hybrid metaheuristic algorithm, termed SCSOWOA, is proposed by integrating the Sand Cat Swarm Optimization (SCSO) algorithm with the Whale Optimization Algorithm (WOA). The algorithm combines the exploration capacity of SCSO with the exploitation strength of WOA in a sequential and adaptive manner. The model was evaluated on histopathological images of lung cancer from the LC25000 dataset with threshold levels ranging from 2 to 12, using PSNR, SSIM, and FSIM as performance metrics. Results: The proposed algorithm achieved stable and high-quality segmentation results, with average values of 27.9453 dB in PSNR, 0.8048 in SSIM, and 0.8361 in FSIM. At the threshold level of T = 12, SCSOWOA obtained the highest performance, with SSIM and FSIM scores of 0.9340 and 0.9542, respectively. Furthermore, it demonstrated the lowest average execution time of 1.3221 s, offering up to a 40% improvement in computational efficiency compared with other metaheuristic methods. Conclusions: The SCSOWOA algorithm effectively balances exploration and exploitation processes, providing high-accuracy, low-variance, and computationally efficient segmentation. These findings highlight its potential as a robust and practical solution for AI-assisted histopathological image analysis and lung cancer diagnosis systems. Full article

Biomass production in organisms is closely linked to their growth rate, necessitating rapid, in situ, nondestructive, and accurate growth measurement. Existing imaging platforms are often limited by high cost, lack of scalability, wired connections, or insufficient automation, restricting their applicability for high-throughput growth monitoring. Here, we present SIPEREA, a scalable imaging platform built on cost-effective ESP32-CAM modules. SIPEREA comprises three graphical user interface (GUI) based applications: (1) an embedded program for the ESP32-CAM responsible for imaging, (2) an image acquisition program for automatic wireless image transmission from multiple ESP32-CAMs, and (3) an image analysis program that automatically segments organisms in the images using a deep neural network (DNN) and calculates their area. The implementation of asynchronous, sequential wireless image acquisition enables the efficient management of multiple ESP32-CAM modules. To demonstrate the usefulness of this platform, we analyzed images captured over a two-week period using four ESP32-CAM units during Lemna sp. (duckweed) cultivation to compute doubling time. Full article

The real-time deployment of cascaded generative AI pipelines for applications like video translation is constrained by significant system-level challenges. These include the cumulative latency of sequential model inference and the quadratic ($\mathcal{O}\left(N^2\right)$) computational complexity that renders multi-user video conferencing applications unscalable. This paper proposes and evaluates a practical system-level framework designed to mitigate these critical bottlenecks. The proposed architecture incorporates a turn-taking mechanism to reduce computational complexity from quadratic to linear in multi-user scenarios, and a segmented processing protocol to manage inference latency for a perceptually real-time experience. We implement a proof-of-concept pipeline and conduct a rigorous performance analysis across a multi-tiered hardware setup, including commodity (NVIDIA RTX 4060), cloud (NVIDIA T4), and enterprise (NVIDIA A100) GPUs. Our objective evaluation demonstrates that the system achieves real-time throughput ($\tau <1.0$) on modern hardware. A subjective user study further validates the approach, showing that a predictable, initial processing delay is highly acceptable to users in exchange for a smooth, uninterrupted playback experience. The work presents a validated, end-to-end system design that offers a practical roadmap for deploying scalable, real-time generative AI applications in multilingual communication platforms. Full article

This study investigates how the learning order between segmentation and classification tasks influences performance and generalization in medical image analysis. We propose a Sequential Swin Transformer framework that reuses a shared Transformer backbone with alternating task-specific heads to compare two sequential strategies: (i) segmentation followed by classification and (ii) classification followed by segmentation. Unlike conventional multitask or preprocessing-based pipelines, the proposed framework isolates the impact of task ordering on feature transfer under an identical architecture. Evaluated on the HAM10000 skin lesion dataset, the segmentation-then-classification configuration achieves the highest multiclass accuracy (up to 86.9%) while maintaining strong segmentation performance (Jaccard index ≈ 86%). Statistical tests confirm its superiority in accuracy and macro F1 score, whereas Grad-CAM and t-distributed stochastic neighbor embedding (t-SNE) analyses reveal that segmentation-first training yields more lesion-centered attention and a more discriminative latent space. Cross-domain evaluation on gastrointestinal endoscopy images further demonstrates robust segmentation (Jaccard index ≈ 91%) and multiclass accuracy (≈94.5%), confirming the generalizability of the sequential paradigm. Overall, the proposed method provides a theoretically grounded, clinically interpretable, and reproducible alternative to joint multitask learning approaches, enhancing feature transfer and generalization in medical imaging. Full article

The proliferation of disinformation on social media platforms poses a significant challenge to the reliability of online information ecosystems and the protection of public discourse. This study investigates the role of emotional sequences in detecting intentionally misleading messages disseminated on social networks. To this end, we apply a methodological pipeline that combines semantic segmentation, automatic emotion recognition, and sequential pattern mining. Emotional sequences are extracted at the subsentence level, preserving each message’s temporal order of emotional cues. Comparative analyses reveal that disinformation messages exhibit a higher prevalence of negative emotions, particularly fear, anger, and sadness, interspersed with neutral segments. Moreover, false messages frequently employ complex emotional progressions—alternating between high-intensity negative emotions and emotionally neutral passages—designed to capture attention and maximize engagement. In contrast, messages from reliable sources tend to follow simpler, more linear emotional trajectories, with a greater prevalence of positive emotions such as joy. Our dataset encompasses multiple categories of disinformation, enabling a fine-grained analysis of how emotional sequencing varies across different types of misleading content. Furthermore, we validate our approach by comparing it against a publicly available disinformation dataset, demonstrating the generalizability of our findings. The results highlight the importance of analyzing temporal emotional patterns to distinguish disinformation from verified content, reinforcing the value of integrating emotional sequences into machine learning pipelines to enhance disinformation detection. This work contributes to the growing body of research emphasizing the relationship between emotional manipulation and the virality of misleading content online. Full article

Drone photogrammetry and per-step spatial analysis were used to re-evaluate the West Gold Hill Dinosaur Tracksite (Bluff Sandstone, Colorado), which preserves an exceptionally long sauropod pes trackway. Building on earlier segment-based descriptions, we reconstructed the entire succession at millimetre-level resolution and quantified turning and gait asymmetry within an integrated digital workflow (UAV photogrammetry, Blender-based landmarking, scripted analysis). Of 134 footprints previously reported, 131 were confidently identified along a mapped path of 95.489 m that records 340° cumulative anticlockwise reorientation. Traditional end-point tortuosity (direct distance/trackway length; DL/TL) yields a moderate ratio of 0.462, whereas our incremental analysis isolates a fully looped subsection (tracks 38–83) with tortuosity of 0.0001 (DL 0.005 m; TL 34.825 m), revealing extreme local curvature that global (end-to-end) measures dilute. Gauge varies substantially along the trackway: the traditional metric (single pes width) averages 32.2% (wide gauge) with numerous medium-gauge representatives, while footprint-specific (‘incremental’) gauge spans 23.1–71.0% (narrow/medium/wide gauges observed within the same trackway). Our tests for asymmetry quantified that left-to-right paces and steps are longer (p = 0.001 and 0.008, respectively), central trackway width is greater (p = 0.043), and pace angulation is lower (p = 0.040) than right-to-left. Behaviourally, these signals are consistent with right-side load-avoidance but remain speculative (alternative explanations may include habitual laterality, local substrate heterogeneity). The study demonstrates how UAV-enabled, fully digital, sequential analyses can recover intra-trackway variability and enhance behavioural understanding of extinct trackmakers from fossil trackways. Full article