Search Results (117)

GNSS array receivers suffer tracking degradation under array nonidealities such as element-position perturbations, channel amplitude/phase errors, and slowly varying manifold mismatch. Conventional blind anti-jamming suppresses interference, but adaptive weight fluctuations can propagate into the correlator domain, increasing cross-branch correlation, causing Early/Late metric imbalance, and reducing Prompt phase consistency. Existing noncoherent combining methods mainly convert multi-branch correlator outputs into scalar energy metrics for code tracking, leaving the carrier loop’s complex Prompt input insufficiently constrained. To address this problem, we propose a blind adaptive joint code–carrier channel-combining method for nonideal arrays. After first-stage anti-jamming, the method estimates an Early/Late correlator-domain covariance matrix and reuses it as a shared statistical constraint. In the code loop, this matrix drives whitened noncoherent energy combining with closed-loop gain normalization to stabilize the DLL discriminator scale. In the carrier loop, it is combined with a Prompt-derived coherent direction to form a covariance-constrained PLL complex input. Simulations under wideband interference, static array errors, and dynamic mismatch show that the proposed J-WNCC reduces both code-phase error and carrier-phase jitter, improving joint tracking robustness in nonideal array environments. Ablation results further reveal a dominant-effect separation: DLL gain normalization mainly calibrates the whitened code-discriminator scale, whereas coherent Prompt combining mainly reconstructs the complex PLL input. Full article

Aligning information technology (IT) workforce demands with educational assessments is essential for bridging skills gaps; yet, no prior corpus maps IT task reasoning to Programme for International Student Assessment (PISA) proficiency levels. This paper introduces a large language model (LLM)-powered framework aligning IT competencies with PISA 2022 and the OECD (Organisation for Economic Co-operation and Development) Learning Compass 2030, drawing on O*NET v30.2 (Occupational Information Network), ESCO (European Skills, Competences, Qualifications, and Occupations) v1.2.1, PISA descriptors and OECD definitions. The framework operates in two stages: Stage 1 aligns 562 IT task statements with minimum PISA 2022 proficiency levels via LLM annotation and cross-model validation; and Stage 2 extends this mapping to the OECD Learning Compass 2030 through the semantic clustering of task embeddings and a bidirectional gap analysis of 95 ESCO transversal skills. Using Gemini 2.5 Flash, 562 tasks are annotated with minimum PISA levels across Mathematical, Reading, and Science literacy (first stage). Annotation reliability is assessed through a five-model cross-validation against a blind human domain expert (treated as a reference benchmark, not a gold standard) on a stratified 100-task sample (17.8% of the corpus), with agreement ranging from fair (Gemini 2.5 Flash, κ = 0.29) to moderate (Claude Haiku 4.5, κ = 0.50; LLaMA 3.3 70B, κ = 0.44). A bias-correction sensitivity analysis confirms that distributional findings remain stable after accounting for the primary annotator’s systematic overestimation, and OLS-calibrated alignment against O*NET ability ratings provides directional plausibility support. Validated tasks are embedded and clustered into 25 technical profiles via K-Means, each classified against OECD dimensions. The framework is extended to 95 ESCO transversal skills in 24 clusters. Bidirectional analysis reveals that, while every PISA proficiency level is engaged by at least one transversal cluster, 33% of these clusters, covering creative, ethical, social–emotional, and dispositional competencies, fall entirely outside PISA’s cognitive scope. This boundary mapping identifies where the PISA-based alignment is valid and where complementary tools are required for a full readiness assessment. Full article

Autonomous unmanned aerial vehicles (UAVs) must decide when to trust onboard perception, when to request edge support, and when to avoid acting under poor visual or communication conditions. This study develops a risk-aware edge-assisted UAV perception framework that combines calibrated visual confidence with next-window service-level agreement (SLA) feasibility. The local branch uses MobileNetV3-Small for fast onboard color recognition, while the edge branch uses ResNet-18 for stronger remote inference. Low-confidence samples are offloaded only when the SLA predictor estimates that the wireless link is feasible; otherwise, the system enters fallback, meaning that the current prediction is not treated as immediately actionable. The evaluation follows a hard cross-illumination split: indoor and fluorescent light samples are used for training and validation, and indoor night and sunlight samples are reserved for testing. Under this setting, the local model achieves 76.89% accuracy and 73.25% macro-F1, while the edge model achieves 81.26% accuracy and 77.58% macro-F1. The SLA predictor, trained on enhanced telemetry features while preserving the original target label, achieves 85.74% accuracy, 85.57% macro-F1, 0.9420 ROC-AUC, and 0.9585 PR-AUC on temporally held-out records. The joint policy achieves 93.23% coverage and 79.90% success over active decisions, using local inference for 82.76% of the samples, edge offloading for 10.47%, and fallback for 6.77%. These results indicate that the framework is best understood as a tunable risk management layer for UAV perception rather than a pure accuracy maximization classifier. It avoids blind offloading and reduces forced decisions when both visual confidence and communication feasibility are weak. Full article

Background/Objectives: Maggot debridement therapy (MDT) is an established biodebridement modality in chronic wound management; however, quantitative evidence regarding its effects on wound-healing dynamics remains limited. This study aimed to evaluate morphometric healing changes in chronic wounds treated with MDT using quantitative image-based analysis. Methods: This retrospective observational study analyzed archival records of patients who underwent MDT between 1 January 2024, and 1 January 2025. Wound images acquired according to a standardized clinical photography protocol were analyzed in ImageJ software (version 1.53k) after scale calibration. Lesion areas were measured in a blinded manner by two independent anatomy specialists. Morphometric data were analyzed using R, and healing trajectories were evaluated using the Kaplan–Meier method. Results: A total of 95 chronic wound cases were included. The mean age was 65 ± 11 years, and 73% of patients were male. Most lesions were localized to the foot (91%), and 40% were classified as stage 3 wounds. A total of 294 MDT sessions were performed. The mean wound-area reduction per session was 9.7% (median 6.6%). Wound-area reduction differed significantly across treatment sessions (H = 14; p = 0.008), with the greatest improvement during the first three sessions; pairwise analysis showed a significant difference between sessions 1 and 3 (p = 0.029). Approximately 18% of cases achieved ≥50% wound-area reduction, with a median of eight sessions required to reach this threshold. Age and sex were not significantly associated with healing outcomes. Conclusions: MDT facilitates measurable reductions in wound area and contributes to the healing process in chronic wounds. The findings suggest that the therapeutic effect of MDT may be more pronounced during the early treatment sessions and may help optimize treatment planning in chronic wound management. Full article

Structural planes widely developed in slope rock masses are key geological elements governing deformation, failure modes and engineering stability. Traditional manual logging suffers from low efficiency, high safety risks and inadequate data integrity, failing to meet large-scale and refined survey needs. This paper proposes a cross-modal collaborative recognition system for slope discontinuities. The principal methodological contribution is the cross-modal ROI-guidance mechanism itself: 2D detection bounding boxes are back-projected through pixel-to-point-cloud registration to construct region-of-interest constraints in 3D space, transforming intractable global blind-search segmentation into localized oriented analysis within bounded volumes—to the best of the authors’ knowledge, the first systematic establishment of such a “visual detection → ROI-guided 3D analysis” framework for slope discontinuity characterization. Within this paradigm, established modules are adapted to the discontinuity recognition task rather than newly invented: channel attention, bidirectional multi-scale fusion and angle-aware regression are integrated into the detection backbone to address the weak texture contrast, large-scale span and extreme aspect-ratio morphology of discontinuity targets, while a PCA–DBSCAN–RANSAC cascade operating within the ROI volumes extracts dip direction, dip angle, spacing and trace length. Validated on two typical slopes in Hunan Province, the improved network achieves a mAP@0.5 of 89.4%, the average IoU of point cloud segmentation is 82.6–86.3%, the dip angle RMSE is 2.46° and the spacing average relative error is 6.8%. The full workflow takes about 86 min, a 19.5-fold efficiency gain over manual methods, and provides an automated pipeline from heterogeneous remote sensing data to engineering-usable structural parameters. The resulting outputs are organized in a tabular schema compatible with mainstream discrete-element software such as 3DEC and UDEC, where they serve as geometric inputs to downstream stability modelling once site-specific mechanical calibration is performed. The two-site validation reported here should accordingly be read as a proof of operational feasibility within the limestone and sandstone–mudstone envelope examined, with broader deployment to other lithologies identified as the natural next phase of evaluation. Full article

Background/Objectives: Fixed orthodontic appliances interfere with oral hygiene and contribute to plaque retention, gingival inflammation and demineralization of enamel. Standard techniques for keeping oral hygiene (tooth brushing, mouthwashes, dental floss, interdental brush, etc.) are not sufficiently effective. The aim of this study was to investigate the effectiveness, safety, tolerability, and influence on quality of life of an electrolysis device being added to standard techniques of oral hygiene in orthodontic patients, compared to standard methods only. Methods: This 6-month study was designed as an observational prospective-cohort investigation. Primary outcomes of the study were indices of gingival inflammation and bleeding, dental plaque indices, the number of white spots on enamel, and safety (incidence of adverse events). Secondary outcomes were quality of life and overall costs of keeping oral hygiene. Results: The addition of the Neo Pill device to standard oral hygiene maintenance measures was associated with improvements in oral health indices after 6 months; however, given the non-randomized, preference-driven design, these findings reflect an association and should not be interpreted as evidence of causal efficacy. After 6 months, the primary outcomes of the study were significantly reduced compared to the application of only standard oral hygiene methods (from 21 to 55% reduction); the quality of life related to oral health was higher (for 14%), the tolerability of maintaining oral hygiene was the same as with standard measures and the costs of maintaining oral hygiene consumables were lower in the Neo Pill group (median difference 30%); however, this figure excludes the acquisition cost of the device itself, which was donated to all participants by the manufacturer, and the 95% confidence interval for this difference includes zero. Conclusions: The addition of an electrolysis device to standard oral hygiene maintenance measures in people wearing fixed orthodontic appliances was associated with improvements in gingival inflammation, papillary bleeding, and dental plaque indices—outcomes measured with established clinical instruments. Apparent reductions in white-spot lesion counts were also observed but should be considered exploratory given the absence of calibrated or blinded lesion assessment. These findings are preliminary and do not establish causal efficacy. Full article

Speech-based non-invasive screening offers a cost-effective and scalable approach for the early detection of Alzheimer’s disease (AD). However, the clinical utility of deep learning models remains severely constrained by the scarcity of labeled speech data in low-resource languages, necessitating cross-lingual transfer learning. Conventional domain adaptation paradigms typically assume semantically consistent feature domains and focus heavily on aligning marginal distributions; however, they suffer catastrophic performance degradation when applied to cross-lingual pathologic speech. By analyzing disease-associated representation vectors within a self-supervised HuBERT space, we uncover a systematic mechanism driving this failure, a phenomenon we term cross-lingual polarity flip, where the direction of disease-relative-to-control feature offsets fundamentally reverses between languages. While prior multilingual studies have largely discarded such dimensional inconsistencies as ungeneralizable noise, a 500-round Monte Carlo stability analysis demonstrates that these flips occur in a highly stable, structural manner across 18.3% of top discriminative dimensions. Leveraging this insight, we introduce Monte Carlo Polarity Flip Calibration (MC-PFC), a few-shot framework designed to explicitly rectify flip orientations. Requiring only five labeled support samples per class from the target domain, MC-PFC robustly estimates direction flips via a separability-weighted ensemble voting mechanism. Evaluated on a strictly held-out Chinese blind test set, MC-PFC achieves an area under the receiver operating characteristic curve (AUC) of 0.871, recovering 99.5% of the performance achieved by a full in-domain trained upper bound (AUC = 0.875). Ablation experiments confirm that direction calibration yields a substantial +0.361 AUC gain, vastly outperforming standard distribution alignment (+0.081). This work establishes a data-efficient paradigm for cross-lingual medical analysis, shifting the clinical AI focus from discarding cross-lingual discrepancies to actively modeling and calibrating them. Full article

Accurate and stable indoor occupancy information is essential for occupant-based intelligent ventilation control. Under a single-camera setting, existing indoor occupancy detection methods commonly suffer from missed detections caused by occlusion and blind zones, false detections caused by people outside the room, and cumulative entry–exit errors that are difficult to correct. These problems lead to false fluctuations in detected occupancy, affect control performance, and may further reduce indoor comfort or cause unnecessary energy use. To address the practical situation in which indoor spaces are commonly equipped with a single security camera, this study proposes an indoor occupancy detection method by fusing field-of-view information and entry–exit events with a single camera. The study covers method development, multi-scenario validation, parameter analysis, and a ventilation control application. The proposed method uses YOLOv8x and DeepSORT as front-end models and performs post-processing on their outputs to extract field-of-view occupancy information, entry–exit events, and blind-zone events. An occupancy confirmation and correction module is then constructed. The blind-zone event mechanism reduces the influence of missed entry–exit events and camera blind zones on occupancy judgment. The correction module integrates frame-by-frame ID counts, historical outputs, and multiple event signals to verify and suppress false occupancy changes caused by false detections, missed detections, and blind zones, thereby producing more stable indoor occupancy results. Experimental results show that the proposed method outperforms the baseline methods based on front-end object detection and tracking in terms of score, RMSE, and F1 score in three typical scenarios: an office, a home, and a classroom. In the office scenario, the proposed method achieved a score of 99.36%, an RMSE of 0.081, and an F1 score of 0.781. The detection stability was also improved in the home and classroom scenarios. In the high-density and strongly occluded classroom scenario, the absolute detection performance of the fusion-based detection method was limited by the front-end models, indicating that the method still has certain applicability boundaries in complex high-density scenes. Parameter sensitivity analysis shows that key parameters, including the entry–exit area depth, confidence threshold, and time threshold, affect the detection results of the fusion-based detection method. Under the test conditions of this study, the method performs well when the entry–exit area depth is approximately 1.5d, the YOLOv8x confidence threshold is 40%, and the time threshold is 5 × FPS. These results can provide a reference for initial parameter setting and on-site calibration in similar scenarios. Using the office scenario as a case study, the method was further applied to occupant-based ventilation control. The average CO₂ concentration during occupied periods under the proposed method was 622.43 ppm, which was closest to the result under ground-truth occupancy control, with a deviation of only 0.9 ppm. This indicates that the method can help improve indoor air quality. Compared with conventional schedule-based control, occupant-based ventilation control driven by the proposed fusion method reduced cumulative fan energy consumption by approximately 65.2%, showing good energy-saving potential at the ventilation-control level. In summary, the proposed method can effectively improve the accuracy and stability of indoor occupancy detection under a single-camera setting and provide more reliable input for occupant-based ventilation control. The framework is modular, and the front-end object detection and tracking models can be replaced according to actual deployment needs. However, the validation in this study is still mainly based on scenarios where existing security cameras can cover the main activity areas and all entry–exit passages. The applicability of the method under more complex camera arrangements, lighting variations, and automatic region configuration requires further investigation. Full article

Recyclers worldwide face a common bottleneck: incoming mixed plastic bales are chemically opaque, yet the choice between mechanical recycling, chemical recycling, and energy recovery hinges on contaminant levels that cannot be judged by visual inspection alone. This study develops and validates a tiered analytical decision-support framework that translates standard laboratory measurements into explicit, actionable go/no-go routing criteria for any mixed polyolefin waste stream. The framework is organized into three successive analytical tiers of increasing specificity: Tier 1 uses FTIR and DSC for rapid polymer identification and thermal subclass confirmation; Tier 2 applies TGA/DTG for thermal stability assessment and filler quantification; and Tier 3 deploys ICP-OES, WD-XRF, CIC, and TG–MS for targeted heavy metal, halogen, and evolved gas profiling, triggered only when Tier 1/2 flags are raised. This staged logic minimizes unnecessary testing while ensuring that contaminant-relevant information is captured where it matters. The framework is demonstrated on nine blind mixed plastic waste streams (P1–P9) supplied by an industrial recycling facility without prior disclosure of polymer identity, filler content, or additive history—conditions that replicate the uncertainty encountered at any sorting plant globally. Application of the tiered protocol identified dominant polymers (HDPE, LDPE, PP), quantified inorganic fillers (CaCO₃ up to ~38 wt%), and detected hazardous contaminants, including chlorine (up to ~1900 ppm), lead, chromium, and titanium, enabling each stream to be assigned to a specific recycling route with defined contaminant thresholds. Because the method relies exclusively on commercially available, vendor-independent instrumentation and follows a reproducible, rule-based decision logic, it is directly transferable to recycling facilities in any geographic context without site-specific calibration. The proposed framework thus provides a practical, scalable decision-support tool for feedstock-level quality control under emerging regulations such as the UNEP Global Plastics Treaty. Full article

Artificial intelligence (AI) coding systems now range from inline completion to repository-level agents and platform-supported application builders; yet, software engineering still lacks a code-generation-centered operational taxonomy for describing how much work is delegated, under what conditions, and with what responsibility structure. This study proposes Levels of Automated Code Generation (LACG), a six-level taxonomy (L0–L5) for classifying automation in AI-augmented software construction. LACG is organized around four responsibility-aware concepts—The Software Development Task (SDT), Operational Capability Domain (OCD), fallback responsibility, and minimal risk condition—and is assigned to a declared configuration–SDT–OCD tuple rather than to a vendor brand or model family in the abstract. To reduce the risk that public vendor documentation reproduces marketing bias, the method separates declared affordance evidence from routine capability evidence and adopts an evidence-triangulation design. Public documentation is used only to identify configuration boundaries and declared affordances; independent software engineering benchmarks, agent studies, productivity studies, and taxonomy-evaluation literature are used to calibrate the level boundaries and constrain the claims. LACG is then applied to 30 representative current AI coding tool configurations using time-stamped public-documentation records, with boundary logic cross-checked against independent evidence on repository-level issue solving, agent tool use, and context-dependent productivity outcomes. Three anonymized human raters, selected for software engineering or AI-coding-tool expertise and independent of the authors and evaluated vendors, then classified the same prepared, blinded public-documentation records using the LACG coding manual. Exact three-rater agreement was 28/30 (93.3%); adjacent-level and majority agreement were both 30/30 (100.0%); mean pairwise quadratic-weighted Cohen’s kappa was 0.963; and Krippendorff’s alpha for ordinal ratings was 0.963. These agreement statistics test classification consistency over a structured documentary evidence base; they do not test actual tool behavior, direct execution, product performance, safety, productivity, or deployment outcomes. After adjudication, the final sample contains six L1 configurations, nine L2 configurations, and fifteen L3 configurations; no public configuration is classified as L4 or L5 under the fallback-responsibility criterion. The study supports preliminary, documentation-bound classification applicability, boundary calibration, and discriminative vocabulary development, not predictive validation or product-level performance claims. LACG provides an operational vocabulary for future empirical work on AI-augmented software construction, benchmark design, tool comparison, and responsibility allocation, while leaving outcome validation for governance, security, productivity, and procurement to subsequent empirical studies. Full article

The long-term success of dental implants is significantly influenced by primary stability, which is commonly assessed through insertion torque (IT) and removal torque (RT) measurements in vitro. While polyurethane (PU) blocks are accepted by the American Society for Testing and Materials (ASTM) as the standard bone analog material for biomechanical testing, the use of polyethylene (PE) as a bone model material for dental implant research remains limited and not well established. This operator-blinded, in vitro study compared the IT and RT values of dental implants placed in PE and PU blocks of identical density (60 pounds per cubic foot [pcf]; 0.96 g/cm³). A total of 60 tapered dental implants (4.2 × 12 mm, RBM surface, platform switching) were placed into PE (n = 30) and PU (n = 30) blocks by a calibrated operator blinded to the material type. Implant sockets were prepared by an independent surgeon following the manufacturer’s drilling protocol. IT and RT values were recorded using a physiodispenser with torque measurement capability (5–80 N·cm). Statistical analysis was performed using Student’s t-test (α = 0.05), with Mann–Whitney U tests reported as a sensitivity analysis for non-normally distributed variables. No statistically significant difference was observed in IT between PE and PU groups (58.50 ± 8.42 vs. 58.17 ± 9.60 N·cm; p = 0.887; Cohen’s d = 0.04; 95% CI of mean difference: −4.33 to 5.00 N·cm). However, RT was significantly higher in the PU group compared to the PE group (71.17 ± 7.15 vs. 64.33 ± 9.17 N·cm; p = 0.002; Cohen’s d = 0.83; 95% CI: −11.08 to −2.58 N·cm; Mann–Whitney U sensitivity analysis p = 0.004). Under the specific high-density (60 pcf) conditions tested, the absence of a statistically significant IT difference does not constitute formal evidence of equivalence or non-inferiority, and the significantly higher RT in PU indicates that PE and PU are not interchangeable bone analogs. Further studies across a range of densities, implant macrogeometries, and using formal equivalence testing are required before PE can be considered for in vitro dental implant stability research. Full article

Background/Objectives: Uroflowmetry is done in the surveillance period after End-to-end Anastomotic Urethroplasty for pelvic fracture urethral injury. But is maximum flow rate a reliable surrogate for urethral calibre in these cases? The above question laid the foundation of the study. The aim of the study was: “Is uroflowmetry alone sufficient to predict a successful outcome following urethroplasty after pelvic fracture urethral injury (PFUI)?” Methods: We conducted a prospective masked study of all patients undergoing end-to-end anastomosis (EEA) urethroplasty for PFUI from January 2017 to September 2022. The first follow-up was 4 weeks after surgery, micturating cystourethrogram (MCU) was done after urethral catheter removal and at the same time, uroflowmetry was also done. The second follow-up was 6 months after surgery, when uroflowmetry was repeated, and urethroscopy was performed. The urologist performing urethroscopy was blinded to the uroflowmetry results. Results: In total, 26 patients were included in the study. After 6 months, 1 patient had poor flow (maximum flow rate [Q max] < 10 mL/s), 7 patients had flow with Q max 10–15 mL/s, and 18 patients had normal flow (Q max > 15 mL/s). On urethroscopy, all patients had a normal and easily passable urethra. The International Prostate Symptom Score (IPSS) and quality of life (QoL) scores showed a positive correlation. The urologist performing urethroscopy and the investigator recording uroflowmetry reached different conclusions. Conclusions: A reduced peak on uroflowmetry after EEA urethroplasty in PFUI does not always indicate surgical failure. Urethroscopy enables direct visualisation of the anastomotic site and provides more detailed information than uroflowmetry. The IPSS score and quality of life are more important than Q max alone. Full article

Background: Emergency triage systems using machine learning traditionally rely on structured tabular data (vital signs), creating a “contextual blind spot” that ignores diagnostic information embedded in unstructured clinical narratives. Hybrid AI models that fuse tabular and text data may improve predictive discrimination, but the magnitude and conditions under which fusion adds value remain unclear. Methods: Five databases (PubMed, Scopus, Web of Science, IEEE Xplore, ACM Digital Library) were searched from 1 January 2015 to 15 December 2025. Eligible studies employed Hybrid AI models integrating structured and unstructured emergency department data with quantitative baseline comparisons. Twenty-five studies (N ≈ 4.8 million encounters) met inclusion criteria. We extracted marginal performance gains (ΔAUC), calibration metrics, and demographic reporting. Synthesis followed SWiM principles with subgroup meta-regression testing our novel “Complexity Gradient” hypothesis. Results: Hybrid models demonstrated superior discrimination compared to tabular baselines, with effect magnitude dependent on clinical task complexity. Low-complexity tasks (tachycardia prediction) showed minimal gains (median ΔAUC + 0.036, IQR: 0.02–0.05), while high-complexity tasks (hypoxia, sepsis) demonstrated substantial improvement (median ΔAUC + 0.111, IQR: 0.09–0.13). Meta-regression confirmed complexity significantly moderated effect size (R² = 0.42, p = 0.003). Only 12% (3/25) of studies reported calibration metrics (Brier scores: 0.089–0.142). Zero studies stratified performance by race/ethnicity; 88% (22/25) failed to report training data demographics. Discussion: The complexity gradient framework explains when multimodal fusion adds predictive value: tasks where diagnostic signal resides in narrative features (temporality, negation) rather than physiological measurements. However, systematic absence of calibration reporting and fairness auditing prevents clinical deployment. Seventy-two percent of studies had high risk of bias in the analysis domain due to retrospective designs without temporal validation. Conclusions: Hybrid triage models show promise for complex diagnostic tasks but require mandatory calibration reporting and demographic performance stratification before clinical implementation. We propose minimum reporting standards including Brier scores, race-stratified metrics, and temporal validation protocols. Full article

As AI-driven educational systems increasingly rely on deep neural networks, their vulnerability to adversarial perturbations raises concerns about assessment integrity, fairness, and reliability. Adversarial example purification is attractive for such deployments because it removes input perturbations without modifying the already deployed models. However, most existing purification methods are inherently goal-free: denoising-based approaches apply blind heuristic operators, while reconstruction-based methods rely on stochastic sampling guided by natural image priors. These methods typically suppress perturbations at the cost of weakening semantic details or inducing structural distortions. To address this limitation, we propose a novel goal-directed purification framework, termed adversarial energy field optimization for adversarial example purification (AEFOP). AEFOP formulates purification as a constrained optimization problem by defining a learnable adversarial energy which quantifies how far an input deviates from the benign region. This allows adversarial examples to be explicitly pushed from high-energy regions toward low-energy benign regions along an interpretable descent trajectory. Specifically, we build an adversarial energy network and optimize the energy field via a two-stage strategy: adversarial energy field shaping, which enforces distance-like energy behavior and correct gradient directions, and task-driven energy field calibration, which unrolls the descent process to calibrate the field with classification-consistency and semantic-preservation objectives. Extensive experiments across multiple attack scenarios demonstrate that AEFOP achieves superior purification accuracy and high visual quality while requiring only a few gradient steps during inference, offering a practical and efficient robustness layer for vision-based AI services in education. Full article

Background/Objectives: Delayed graft function (DGF) remains a common early complication after deceased donor kidney transplantation and is challenging to anticipate using routine pre-implant clinical variables alone. We investigated whether high-throughput Fourier transform infrared (FTIR) spectroscopy of static cold storage preservation fluid (not machine perfusion perfusate) captures biochemical information associated with DGF and warrants further evaluation alongside routine pre-implant clinical predictors. Methods: In this single-center retrospective cohort, we analyzed preservation fluid samples from 56 kidney transplants originating from 49 deceased donors (7 donors contributed two kidneys); DGF occurred in 14/56 (25.0%). Dried-film FTIR spectra were acquired using a plate-based high-throughput accessory, and analyses focused on the fingerprint region (900–1800 cm⁻¹) with prespecified preprocessing and quality control. We developed and compared clinical-only, FTIR-only, and combined predictive models and estimated performance using donor-blinded 5-fold StratifiedGroupKFold cross-validation (grouped by donor code) to prevent leakage across paired kidneys. Results: Donor-blinded discrimination (pooled out-of-fold ROC-AUC) was 0.775 for the clinical-only model, 0.814 for the FTIR-only model, and 0.796 for the combined model; probabilistic accuracy (Brier score; lower is better) was 0.162, 0.194, and 0.177, respectively. Calibration intercepts were negative and slopes were <1, indicating overly extreme risk estimates under strict donor-blinded validation and supporting recalibration prior to deployment. Decision curve analysis suggested a positive net benefit for clinically plausible thresholds. Conclusions: These findings support the feasibility of rapid, low-cost FTIR profiling of routinely available preservation fluid as a proof-of-concept approach for exploratory DGF risk stratification, rather than as a clinically deployable prediction tool. Given the small sample size and the instability of subgroup estimates, the main next steps are external validation in larger multicenter cohorts, prospective workflow studies, and model updating/recalibration. Full article