Search Results (3,407)

Rapid global urbanization is increasing the need for accurate, large-scale traffic monitoring to support sustainable transportation and city governance. Satellite video remote sensing offers a unique way to continuously observe urban road networks over large areas. It provides high-resolution spatio-temporal data that is essential for traffic flow analysis, infrastructure assessment, and dynamic urban planning. Moving vehicle detection in satellite video sequences is a basic task that turns raw imagery into useful traffic-state information, supporting these applications. Despite the advantages of satellite video data, detecting moving vehicles in practice remains a tough problem. Objects are extremely small and lack clear appearance details, while low local contrast makes them hard to separate from complex backgrounds. Satellite platform motion also introduces background misalignment and intensity fluctuations, resulting in missed detections and false alarms that hurt monitoring reliability. Furthermore, current methods do not fully exploit temporal motion cues or transform-domain priors, creating a performance bottleneck that restricts their practical use. To solve these problems, this paper proposes a Channel-Attentive Spatio-Temporal-Frequency Alignment (CASTFA) framework to effectively use and combine multi-dimensional features for moving vehicle detection in satellite videos, with the goal of providing high-quality traffic monitoring data to help smart city planning. Specifically, a State Space-Guided Temporal Compression (SSGTC) module first collects information along the time dimension with linear computational complexity, greatly reducing overhead while keeping motion cues that are critical for traffic-state estimation. The compressed temporal features are then processed with a multi-scale Haar wavelet transform to get hierarchical time-frequency representations that capture subtle motion dynamics across different frequency bands. At the same time, a pre-trained backbone network extracts multi-scale spatial features. To allow these different domains to work together, a Cross-Domain Feature Alignment (CDFA) mechanism aligns and combines spatial and time-frequency features through channel-attentive operations. Experimental results on the publicly available satellite video moving vehicle detection dataset show that the proposed CASTFA method consistently outperforms existing approaches, with better precision, recall, and F1-scores across diverse urban scenarios. These results show that CASTFA can provide reliable moving vehicle detection performance under difficult real-world conditions, supporting accurate traffic-flow monitoring and providing valuable geospatial intelligence for smart urban planning, transportation management, and sustainable city development. Full article

Background/Objectives: Handgrip strength is a widely used indicator of physical function that is associated with various health outcomes of older adults. However, the relationship between lifestyle factors and handgrip strength, as well as the age-associated relationship between them, remains insufficiently understood. This study examined age-adjusted associations between multiple lifestyle factors and handgrip strength among older women. Methods: During this cross-sectional study of 2206 older women, handgrip strength was categorized into low, middle, and high tertiles. Lifestyle factors such as meal enjoyment, exercise frequency, sleep quality, social interaction, and outing frequency were assessed using a questionnaire. Group differences were evaluated using an analysis of variance and chi-square tests. A general linear model with age as a covariate was used to compare age-adjusted proportions of lifestyle behaviors across handgrip strength tertiles. Results: Participants in the high handgrip strength tertile were younger and more likely to report favorable lifestyle behaviors. After adjusting for age, meal enjoyment (p = 0.024), social interaction (p = 0.001), and outing frequency (p = 0.017) remained significantly associated with handgrip strength. In contrast, sleep quality (p = 0.073) and exercise frequency (p = 0.060) were not significantly associated with handgrip strength after age adjustment. Higher lifestyle scores were significantly associated with higher handgrip strength. Conclusions: Among older women, meal enjoyment, social interaction, and outing frequency were associated with handgrip strength after adjustment for age. These findings highlight the potential relevance of meal enjoyment and social engagement as contextual lifestyle characteristics associated with handgrip strength. However, causal relationships cannot be inferred because of the cross-sectional study design. Full article

Ginger (Zingiber officinale) fields in northern China are often covered by plastic mulch film and shade netting, so Sentinel-2 records management materials as well as the crop canopy. Because these materials and their deployment differ among production systems, models calibrated locally may transfer poorly. We defined three observation windows for the main study counties: spring film mulching, summer shade-net coverage, and autumn exposed-canopy greening. Within each window, spectral bands, vegetation indices, and gray-level co-occurrence matrix (GLCM) textures were extracted from single Sentinel-2 scenes across three northern Chinese counties with contrasting practices. A cross-regional Random Forest Gini ranking, weighted by the similar county model-sample totals, retained four variables per feature family per stage (36 of 120 variables across the three-stage stack). The spectral-index-texture scheme achieved within-county F1 scores of 95.00% in Changyi, 94.83% in Qingzhou, and 95.58% in Fengrun. Leave-one-county-out (LOCO) model fitting returned a mean F1 of 94.73% compared with 95.14% for the within-county splits. Because the fixed-feature protocol was selected using all three counties, this LOCO test evaluates county-held-out classifier fitting rather than a fully nested feature-selection pipeline. Independent field verification with Global Positioning System (GPS) points ranged from 85.80% to 89.95%, and village-level area estimates agreed with remote-sensing totals (R² = 0.869). The 36-variable protocol performed similarly to the full 120-variable input (95.14% vs. 95.24% mean F1), and the selected features were stable across the three tested weighting rules. In Funing County, where shade nets are absent, omitting the shading stage on the basis of local agronomic practice yielded 93.75% accuracy against 96 independent GPS points. The results support management timing as a practical guide for ginger mapping within the tested northern production systems; wider climatic validation and fully nested transfer tests are still needed. Full article

With the rapid development of intelligent sensing systems, digital monitoring platforms, and multisource data acquisition technologies, accurate identification of operational states and potential risks from heterogeneous sensing signals has become an important research issue in artificial intelligence-driven sensing. Existing studies have primarily focused on either textual information understanding or behavioral data analysis, with limited attention paid to jointly modeling the consistency between textual declarations and executed behaviors. As a result, many potential risks that have not yet manifested as significant anomalies but already involve execution deviations are difficult to detect in a timely manner. To address this issue, a language–behavior consistency sensing framework for multisource sensing signals is proposed. Textual sensing signals and behavioral sensing signals are mapped into a shared state logic space, and intelligent perception and quantitative analysis of deviations between textual states and executed states are achieved through a textual state logic extraction module, an observed behavioral state modeling module, and a language–behavior consistency measurement module. Systematic experiments were conducted on a multisource sensing dataset containing public declaration texts, operation reports, behavioral logs, resource allocation records, and state-response information. The results show that the proposed method achieved the best performance in the baseline comparison experiment, with a language–behavior consistency score ($LCS$) of $0.742$, an $AUC$ of $0.846$, an $F1$-score of $0.811$, a Precision of $0.802$, and an explanation consistency score ($ECS$) of $0.821$, clearly outperforming advanced methods such as FinBERT, LSTM, Multimodal Transformer, and the Contrastive Multimodal Model. These results demonstrate that language–behavior consistency sensing can effectively fuse multisource sensing information and improve complex system state identification, anomaly early warning, and risk perception, providing an interpretable artificial intelligence-driven sensing framework with the potential to support industrial operation and maintenance, intelligent manufacturing, digital infrastructure management, and other intelligent monitoring scenarios. Full article

Capacitive and resistive electric transfer (TECAR) therapy is increasingly used in equine physiotherapy; however, objective evidence regarding its immediate effects on equine back muscles remains limited. This pilot study aimed to evaluate the effects of TECAR therapy on body surface temperature and muscle tone of the longissimus dorsi muscle in Thoroughbred racehorses. A randomized, single-blinded experimental study was conducted in 20 clinically healthy Thoroughbred racehorses aged 2–3 years. Horses were randomly assigned to either a TECAR treatment group (n = 10) or a sham-treatment control group (n = 10). Thermographic imaging and palpation-based muscle tone assessment were performed before treatment, immediately after treatment, and 10 min post-treatment in the thoracolumbar region (Th15–L6). Differences between groups and changes over time were analyzed using repeated-measures ANOVA for temperature data and Friedman’s test with post hoc Wilcoxon signed-rank tests for palpation scores. TECAR therapy was associated with a significant increase in body surface temperature, with mean values rising from 25.3 ± 1.5 °C before treatment to 28.9 ± 1.3 °C immediately after treatment (p < 0.001) and remaining elevated after 10 min (27.6 ± 1.3 °C; p = 0.002). In contrast, only minor temperature changes were observed in the sham group. Palpation assessment demonstrated a significant reduction in muscle tone following TECAR therapy, with median scores decreasing from 3 [2–3] before treatment to 0 [0–1] immediately afterward (p < 0.001). These findings indicate that TECAR therapy induces an immediate thermal response, which persists for at least 10 min, and is associated with reduced longissimus dorsi muscle tone in racing horses. Further studies are warranted to investigate its clinical applications and long-term effects in equine rehabilitation. Full article

Camera and LiDAR sensors in safety-critical autonomous systems suffer undetected distributional shifts that silently corrupt downstream perception. Out-of-distribution (OOD) detection is the established sensor-data-integrity primitive, but no single post hoc detector covers every shift type, and existing detectors lack guarantees on their false-positive rate (FPR). This paper asks when calibrated score fusion helps and provides a distribution-free finite-sample FPR certificate. Four post hoc scores—Maximum Softmax Probability (MSP), Energy, Mahalanobis distance and k-nearest-neighbour (KNN) distance—are calibrated to p-values by the empirical cumulative distribution function (ECDF) and combined by Fisher’s method or cross-backbone z-score averaging, then wrapped in a conformal predictor with Hoeffding-based Probably Approximately Correct (PAC) bounds. On the full-split PUG camera benchmark (215,040 images), uniform same-backbone p-value fusion does not beat the best single detector (Mahalanobis); the gain comes from cross-backbone diversity: a z-score average of Mahalanobis distances over ResNet-50 and frozen DINOv2 reaches a mean area-under-the-ROC-curve (AUROC) of $0.9258$ ($+0.0199$), rising to $0.9292$ ($+0.0233$) with added spectral and dropout signals (DeLong $p<{10}^{-9}$). On the nuScenes LiDAR sensor (256,873 frames), uniform fusion yields only a small, calibration-sensitive gain over the best single detector (MSP), so the substantial fusion gain is confined to cross-backbone averaging on the camera. The distribution-free PAC certificate, by contrast, transfers across both sensors with margins below $1.5\%$ ($0.96\%$ camera, $0.25\%$ LiDAR), giving evidence usable in ISO 26262 and EASA CoDANN safety cases. Full article

Machine learning techniques for network-based intrusion detection systems (NIDS) have advanced considerably over the past decade. Still, improvements are inhibited by handcrafted feature pipelines, isolated public benchmark data, and evaluation procedures that do not reflect real-life deployment. AutoML, a branch of ML automating model selection, automated architecture search, and the creation of model pipelines, may help overcome these shortcomings. While numerous NIDS applications employing automated ML techniques have been proposed, and recent surveys have mapped the AutoML framework landscape for network intrusion detection, no existing review critically audits the evaluation practice of this literature: the quality of its benchmark datasets, the reproducibility of its reported results, and the realism of its deployment assumptions. This paper critically reviews 26 research works published between January 2023 and June 2026, collected via a two-phase structured search: a documented keyword search across five databases (Scopus, IEEE Xplore, Web of Science, ACM Digital Library, and Google Scholar), followed by full-text eligibility screening, citation chaining, and expert evaluation. Findings drawn from this collection capture trends observed among the selected studies, rather than reflecting the broader state of the field. Analysis of the corpus reveals that 88% of dataset-verified studies evaluate exclusively or partly on the legacy benchmark family (KDD-derived, CICIDS, UNSW-NB15, CIDDS), 21% evaluate on a single dataset only, and among attribute-verified studies only 32% release source code, 40% report statistical significance testing, and 36% include variance analysis, findings that collectively motivate the four contributions of this study. First, a recommended evaluation framework is proposed, addressing baseline parity, transparent search-space and budget reporting, nested cross-validation for selection-bias control, and stability reporting across multiple random seeds. Second, a dataset quality scoring framework is introduced, assessing five dimensions: overlap rate, duplication rate, label correctness, attack-type representativeness, and coverage of benign, IoT, and IIoT traffic. Third, a cross-domain justification is provided for neural architecture search (NAS) and meta-learning in NIDS, grounded in advances in federated NAS, out-of-distribution robustness, edge-constrained search cost reduction, and few-shot adaptation. Fourth, a structured research roadmap is outlined, targeting real-world validation, standardized benchmarks, curated datasets, resource-aware AutoML, and privacy-preserving federated NAS. In contrast to prior surveys of AutoML for network intrusion detection, which map frameworks and computational paradigms, this review contributes a formalized evaluation checklist, an explicit and partially empirically validated dataset quality scoring scheme, and evidence-based methodological guidance grounded in a transparent, fully enumerated study corpus. Full article

Time-reversed Young (TRY) interferometry reconstructs interference from a fixed detector by reading out a programmable source-label distribution. This work formulates the architecture as a source-coded Bayesian response sensor. For a perturbation parameter $\theta$, the detected source-label histogram is a posterior distribution determined by a programmed source prior, an optical likelihood for a fixed-detector click, and an evidence factor equal to the click probability. The key point is not the Bayesian identity itself, but its physical implementation: in TRY the prior is imposed before propagation and can therefore reshape the response ensemble actually sampled by the detector. The normalized posterior is shown to respond through a centered likelihood score, and the detected-event Fisher information is the posterior variance of this score. This identifies posterior-weighted score contrast, rather than local response magnitude alone, as the relevant sensing resource. The framework separates posterior-shape information from evidence information, giving a resource-aware way to judge near-null response enhancement. It also yields practical design rules: a two-label source code converts a weak perturbation into a fixed-detector label imbalance, while the multiparameter score covariance provides a route to nuisance rejection and gives a minimal-label rank condition for sensing multiple perturbations. A passive double-slit implementation with weak one-slit phase and loss perturbations is proposed, requiring only fixed-detector source scans before and after calibrated perturbations. Practical tolerances associated with source-programming error, drift, background, imperfect coherence, and polarization mismatch are analyzed, and extensions to multi-aperture and integrated photonic systems are formulated. The results position TRY as a source-programmable Bayesian sensing architecture complementary to conventional detector-plane Young interferometry. Full article

For the task of encrypted traffic classification, existing approaches commonly rely on a single feature view, such as side-channel characteristics or raw packet bytes, often incorporating techniques inspired by natural language processing and computer vision for modeling and classification. In recent years, multi-view learning has gained increasing attention due to its ability to enhance discriminative power and generalization performance by capturing complementary information from different perspectives. However, heterogeneous feature views often exhibit distributional discrepancies, which makes direct multi-view integration difficult. To address this issue, we propose CGF-Net, a multi-view contrastive learning framework for encrypted traffic classification. The proposed model is inspired by cross-modal contrastive learning and employs lightweight adaptation to learn representations from both behavioral and content views. During pre-training, CGF-Net performs instance-level cross-view contrastive learning by treating the behavioral and content views of the same network flow as a positive pair, thereby aligning heterogeneous representations at the flow-instance level. In addition, a lightweight fine-tuning module together with a gating-based fusion mechanism is introduced to improve the collaborative modeling capability of multi-view representations. Extensive experiments on four public datasets show that CGF-Net achieves ACC scores of 95.81%, 93.38%, 96.38%, and 95.72% on CSTNET-TLS1.3, CipherSpectrum, ISCXVPN2016, and ISCXTor2016, respectively. Compared with the best-performing baseline on each dataset, CGF-Net improves the average ACC and F1-score by 0.78 and 0.69 percentage points, respectively, demonstrating the effectiveness of the proposed model. Full article

Background and Objectives: Posterior circulation ischemic stroke (PCIS) is a life-threatening disease with a poor prognosis. It has nonspecific symptoms. It is very difficult to diagnose. The aim of the study is to examine to what degree radiological methods, in addition to standard clinical indicators, can serve as a reliable and independent predictor of death in patients with PCIS. Materials and Methods: It is a retrospective study on 175 patients at the Special Hospital “Saint Sava” (2023–2025) with symptoms of acute PCIS, who did not have proven PCIS on the initial non-contrast computed tomography (NCCT). The radiology protocol included NCCT, CT perfusion (CTP) and CT angiography (CTA). The experimental group (n = 116, CTP+) and the control group (n = 59, CTP-) were monitored clinically and radiologically, with a follow-up NCCT after 24 h when all had confirmed acute PCIS. At discharge, the outcome was monitored on the National Institutes of Health Stroke Scale (NIHSS 2) and the Modified Rankin Scale (mRs). Results: Of 175 patients with acute PCIS, 24% died within 30 days. Those who died were older (p < 0.05), had a lower Posterior Circulation Alberta Stroke Program Early CT Score (pcASPECT), and more often had hyperdensity (26.2% vs. 7.5%), occlusions (69% vs. 31.6%), and symptomatic blood vessels on CTA and CTP+ (81% vs. 61.7%, p < 0.01). Multivariate regression singled out CTP+ (OR = 4.08), complications (OR = 2.96), Israeli Vertebrobasilar Stroke Scale (IVBSS) (OR = 1.22) and Trial of Org 10172 in Acute Stroke Treatment (TOAST) (OR = 1.92) as predictors of mortality, with shorter survival in CTP+ (949 vs. 1449 days, Log-rank p = 0.015), more NIHSS/mRS, lower Glasgow Coma Score, and more frequent obesity in the deceased. Conclusions: Negative CTP represents the protective factor against death in patients with acute PCIS. Complications, higher IVBSS, and TOAST classification (large vessels atherosclerosis) represent an increased risk. The importance of CTP for early detection of acute PCIS and early risk assessment is highlighted. Full article

In the last several years, reading comprehension has declined during elementary school in the U.S. Are cell phones to blame? There is a dearth of evidence concerning the cell phone impact on reading comprehension at the elementary school level. Our primary question was whether acquisition of a phone would be negatively related to the reading comprehension performance of third- and sixth-grade children. More specifically, would notifications or the mere presence of a phone reduce the concentration required for an optimal reading comprehension performance? Among 106 children, we studied 55 children in a sixth-grade group and 51 children in a third-grade group. The sample was linguistically diverse: English was the home language for 42%, Arabic for 30%, and Spanish for 28%. The experimental procedure used a repeated-measures design: Participants who brought phones to school the day of the study took a grade-appropriate reading comprehension test from the DIBELS 8th edition with their phone next to them and a different test from the same battery without their phone nearby or in sight. Participants who did not have a phone with them also took two reading comprehension tests from the DIBELS 8th edition; they were the same tests taken by participants in the experimental portion of the study who had phones with them. All participants completed a short survey about phone ownership and use, along with demographic questions. There was no effect of the experimental conditions on reading comprehension: Whether or not a child had their phone in sight made no difference to their reading comprehension performance. Nor did reading comprehension differ for students with or without phones at school the day of the study. This absence of short-term effects contrasted with the presence of long-term relationships: Possessing a personal cell phone was significantly associated with lower reading comprehension scores across the whole sample. However, for participants from non-English-speaking homes who had their own phones, reading comprehension was significantly better the earlier a child began texting and had access to games on their phone. For children from English-speaking homes who had their own phones, neither early mobile game access nor earlier initiation of texting was associated with better reading comprehension. Full article

Robotic percutaneous coronary intervention (PCI) remains predominantly teleoperated, while the most demanding part of the procedure, guidewire navigation through a moving coronary tree under fluoroscopy, still depends on the continuous human interpretation of vessel anatomy, cardiac phase, guidewire position, and target location. We present a preclinical perception-to-action framework for AI-driven robotic PCI that integrates fluoroscopic perception, dynamic coronary vessel memory, vessel-coordinate state estimation, and robot-executable guidewire command generation on a robotic PCI platform. During contrast angiography, phase-indexed vessel–catheter templates and a dynamic vessel-coordinate coronary map are generated. During guidewire manipulation without contrast injection, live fluoroscopy is segmented into catheter and guidewire structures, cardiac phase is estimated by overlap between the live catheter–guidewire skeleton and stored vessel–catheter templates, the guidewire is assigned to the most likely vessel branch, and the distal tip is projected to a vessel-coordinate target representation for robotic action generation. The segmentation dataset contained 6269/1567/957 vessel images, 3857/964/537 guidewire images, and 4796/1199/667 catheter images for training/validation/test splits, respectively. Test-set Dice scores were 90.7% for vessels, 92.6% for catheters, and 89.0% for guidewires. In 623 real-time fluoroscopy frames from physician-supervised animal experiments, phase selection accuracy was 589/623 (94.6%; 95% CI, 92.5–96.1%) and vessel assignment accuracy was 575/623 (92.3%; 95% CI, 89.9–94.1%). Across 34 scenario-level episodes and their associated command-level decisions, correct-command rates ranged from 83.6% to 95.6% across target navigation and safety scenarios. These results provide preclinical evidence that live fluoroscopic perception can be converted into robot-executable coronary guidewire actions within an integrated AI-robotic PCI workflow. The study was designed to establish early system feasibility rather than to prove clinical superiority, large-scale generalization, or comparative advantages over manual or teleoperated robotic PCI. Full article

Background/Objectives: Postural control depends on the integration and reweighting of visual, somatosensory, vestibular, and contextual sensory information. Stable auditory cues may support balance, whereas complex musical stimulation may impose additional sensory-cognitive demand during multisensory conflict. This study examined the acute effects of relative device-output music intensity on virtual-reality-based postural control in trained athletes and explored whether responses differed by sport background. Methods: Forty-eight athletes from tennis, combat sports, swimming, football, and volleyball completed the Clinical Test of Sensory Interaction in Balance delivered through virtual reality (CTSIB-VR) and Limits of Stability (LOS) assessments under four auditory conditions: routine/no sound and low (+10 dB), moderate (+20 dB), and high (+30 dB) relative device-output increments. Linear mixed-effects models included sport, auditory condition, and their interaction as fixed effects and participant-specific random intercepts and random linear condition slopes. Model-based estimated marginal means, Bonferroni-adjusted contrasts, 1.5×IQR sensitivity analyses, and robust generalized estimating equations were calculated. Results: Auditory condition affected all five CTSIB-VR outcomes (Wald χ²(3) = 16.773–94.404, all p < 0.001). The routine condition exceeded the high-intensity condition for composite score (adjusted mean difference = 6.05, 95% CI 3.99–8.10; Bonferroni-adjusted p < 0.001) and somatosensory score (8.62, 95% CI 6.78–10.46; adjusted p < 0.001). Sport × condition interactions were significant for all CTSIB-VR outcomes (χ²(12) = 54.869–98.953, all p < 0.001), but sport-stratified findings were exploratory. For LOS, auditory-condition effects were detected for endpoint excursion (p = 0.004), maximum excursion (p < 0.001), and directional control (p = 0.002), whereas reaction time (p = 0.648) and movement velocity (p = 0.056) did not show clear main effects. Sensitivity analyses supported the endpoint-excursion, maximum-excursion, and directional-control findings; movement-velocity inference was method-sensitive. Conclusions: Relative device-output music intensity was associated with consistent changes in CTSIB-VR sensory-organization measures and outcome-specific changes in LOS performance. Sport-related patterns require confirmation in adequately powered, balanced samples. Full article

Chronic ankle instability (CAI) is associated with impaired sensorimotor function and dynamic postural control; however, reach distance alone may not fully capture task-specific neuromuscular strategies during functional balance tasks. This preliminary cross-sectional case–control study examined modified Star Excursion Balance Test (mSEBT) performance and thigh muscle activation during the mSEBT in novice recreational runners with CAI. Thirty-two novice recreational runners were classified into a CAI group (n = 16) or a healthy control group (n = 16). Normalized mSEBT reach distances, composite score, weight-bearing lunge test performance, and surface electromyography (sEMG) activity of the rectus femoris, vastus lateralis, vastus medialis, and biceps femoris were analyzed. The anterior reach direction was designated as the primary functional and sEMG task before the formal analyses. No significant between-group differences were observed in functional performance or anterior-task thigh muscle activation. Within the CAI group, anterior reach distance was shorter in the involved limb before adjustment (p = 0.014), but the difference did not remain significant after false discovery rate (FDR) correction (q = 0.120). In contrast, rectus femoris (RF) activation during anterior reaching was significantly lower in the involved limb than in the uninvolved limb (p = 0.002, q = 0.035) and remained significant after FDR correction. In this preliminary sample, sEMG provided complementary information to mSEBT reach distance by identifying a side-specific difference in RF activation within novice recreational runners with CAI. Full article

The accuracy of spectro-temporal features for Makhaarij al-Huroof and Sifaat distinguishes between the ten canonical Qiraát recitation styles of the Holy Quran. However, real-world room reverberations blur formant contours and corrupt inter-word energies, thus making Qiraat discrimination difficult. The current dereverberation methods were designed to work under ordinary speech conditions and are not capable of preserving phonetic qualities for domain-specific purposes. This paper introduces a four-step, phase-consistent signal-processing approach prioritizing phonetic preservation over direct reverberation suppression. The four steps are: (1) adaptive noise-floor attenuation; (2) soft-voice activity detection using power-law boundary decay; (3) application-specific spectral contour adjustment from clean Quranic reference audio; and (4) Griffin–Lim algorithm-based phase correction. A total of 48 real-world room recordings were utilized for the evaluation of this approach based on Energy Ratio (ER), Spectral Contrast (SC), and Spectral Contour Stability (SCS)—measures specific to the Quran audio domain—alongside conventional speech-quality metrics. The proposed approach yielded the highest scores in three of seven metrics, namely SC (+40.11), SCS (+822.94), and PESQ (+1.251), alongside the second-highest Energy Ratio (+19.58 dB), while being superior to Spectral Subtraction, Wiener Filtering, and WPE Dereverberation approaches. Moreover, the perceptual enhancement was verified in a synthetic controlled experiment where the proposed approach scored an improved PESQ metric (+2.495; SNR −1.874 dB). The results illustrate the fact that an optimization for general-purpose metrics does not necessarily ensure phonetic preservation required for specific classification. Full article