Search Results (101)

We present HGC-Net, a hybrid pipeline for assessing geometric consistency between stereo image pairs. Our method integrates classical epipolar geometry with deep learning components to compute an interpretable scalar score A, reflecting the degree of alignment. Unlike traditional techniques, which may overlook subtle miscalibrations, HGC-Net reliably detects both severe and mild geometric distortions, such as sub-degree tilts and pixel-level shifts. We evaluate the method on the Middlebury 2014 stereo dataset, using synthetically distorted variants to simulate misalignments. Experimental results show that our score degrades smoothly with increasing geometric error and achieves high detection rates even at minimal distortion levels, outperforming baseline approaches based on disparity or calibration checks. The method operates in real time (12.5 fps on 1080p input) and does not require access to internal camera parameters, making it suitable for embedded stereo systems and quality monitoring in robotic and AR/VR applications. The approach also supports explainability via confidence maps and anomaly heatmaps, aiding human operators in identifying problematic regions. Full article

As the resolution and data volume of remote sensing imagery continue to grow, achieving efficient compression without sacrificing reconstruction quality remains a major challenge, given that traditional handcrafted codecs often fail to balance rate-distortion performance and computational complexity, while deep learning-based approaches offer superior representational capacity. However, challenges remain in achieving a balance between fine-detail adaptation and computational efficiency. Mamba, a state–space model (SSM)-based architecture, offers linear-time complexity and excels at capturing long-range dependencies in sequences. It has been adopted in remote sensing compression tasks to model long-distance dependencies between pixels. However, despite its effectiveness in global context aggregation, Mamba’s uniform bidirectional scanning is insufficient for capturing high-frequency structures such as edges and textures. Moreover, existing visual state–space (VSS) models built upon Mamba typically treat all channels equally and lack mechanisms to dynamically focus on semantically salient spatial regions. To address these issues, we present an innovative architecture for distant sensing image compression, called the Multi-scale Channel Global Mamba Network (MGMNet). MGMNet integrates a spatial–channel dynamic weighting mechanism into the Mamba architecture, enhancing global semantic modeling while selectively emphasizing informative features. It comprises two key modules. The Wavelet Transform-guided Local Structure Decoupling (WTLS) module applies multi-scale wavelet decomposition to disentangle and separately encode low- and high-frequency components, enabling efficient parallel modeling of global contours and local textures. The Channel–Global Information Modeling (CGIM) module enhances conventional VSS by introducing a dual-path attention strategy that reweights spatial and channel information, improving the modeling of long-range dependencies and edge structures. We conducted extensive evaluations on three distinct remote sensing datasets to assess the MGMNet. The results of the investigations revealed that MGMNet outperforms the current SOTA models across various performance metrics. Full article

This study presents numerical analyses of the thermal, metallurgical, and mechanical processes involved in welding. The temperature fields were computed by solving the transient heat transfer equation using the ABAQUS/Standard 2024 finite element solver. Two types of moving heat sources were applied: a surface Gaussian distribution and a volumetric model, both implemented via DFLUX subroutines to simulate welding on butt-jointed plates. The simulation accounted for key welding parameters, including current, voltage, welding speed, and plate dimensions. The thermophysical properties of the INC 738 LC nickel superalloy were used in the model. Solidification characteristics, such as dendritic arm spacing, were estimated based on cooling rates around the weld pool. The model also calculated transverse residual stresses and applied a hot cracking criterion to identify regions vulnerable to cracking. The peak transverse stress, recorded in the heat-affected zone (HAZ), reached 1.1 GPa under Goldak’s heat input model. Additionally, distortions in the welded plates were evaluated for both heat source configurations. Full article

An adequate food supply is a core issue for sustainable development worldwide. Amid greater instability in the food supply triggered by more armed conflicts, trade disputes, and climate change, a decline in grain cultivation area still plagues many regions. China, a major food producer globally, is a case in point. The truth is that at the moment, the formulation and implementation of policies as well as academic discussions regarding this issue are predominantly based on the sown area of grains, overlooking the fundamental role co-played by population, yield efficiency, and sown area in determining food supply. Furthermore, the commonly used indicator, the non-grain cultivation rate, fails to directly reflect the impact of the phenomenon on the grain supply. To address these gaps, this study introduces trend-change detection and factor-contribution analysis, uses long-term grain sown area data to identify regions with significant grain retreat, and quantifies the relative influence of population shifts, crop yield improvements, and sown area changes on food supply. Key findings include the following: China’s total grain production maintained steady growth from 2003 to 2023, far exceeding conventional food security thresholds. Temporary reductions in grain sown area (2015–2019, 2021–2022) were offset by rising yields, with no substantial decline in supply. Twelve provinces/municipalities, Beijing, Shanghai, Zhejiang, Fujian, Guangdong, Guangxi, Guizhou, Shaanxi, Ningxia, Sichuan, Chongqing, and Hainan, exhibited substantial declines in grain plantation. However, Sichuan and Shaanxi achieved counter-trend growth in food supply, while Ningxia and Guizhou experienced frequent fluctuations. The sown area was not always the dominant factor in per capita grain availability. Yield increases neutralized cropland reduction in Sichuan, Shaanxi, Guizhou, and Ningxia, whereas population inflows outweighed the sown area effect in the other eight provinces. The study concludes that China’s grain cropland reduction has not yet posed a threat to national food security. That said, the spatial concentration of these affected regions and their ongoing output reductions may raise domestic grain redistribution costs and intensify inter-regional conflicts over cropland protection. Meanwhile, population influx plays a similarly important role to that of grain plantation decline in the grain supply. Considering that, we believe that more moderate measures should be adopted to address the shrinkage of grain planting areas, with pre-set food self-sufficiency standards. These measures include, but are not limited to, improving productivity and adopting integrated farming. Methodologically, this work lowers distortions from normal annual cropland fluctuations, enabling more precise identification of non-grain production zones. By quantifying the separate impacts of population, crop yield, and sown area changes, it supplements existing observations on grain cropland decline and provides better targeted suggestions on policy formulation and coordination. Full article

Many researchers focus on improving reproductive health in sows and ensuring successful breeding by accurately identifying the optimal time of ovulation through estrus detection. One promising non-contact technique involves using computer vision to analyze temperature variations in thermal images of the sow’s vulva. However, variations in camera distance during dataset collection can significantly affect the accuracy of this method, as different distances alter the resolution of the region of interest, causing pixel intensity values to represent varying areas and temperatures. This inconsistency hinders the detection of the subtle temperature differences required to distinguish between estrus and non-estrus states. Moreover, failure to maintain a consistent camera distance, along with external factors such as atmospheric conditions and improper calibration, can distort temperature readings, further compromising data accuracy and reliability. Furthermore, without addressing distance variations, the model’s generalizability diminishes, increasing the likelihood of false positives and negatives and ultimately reducing the effectiveness of estrus detection. In our previously proposed methodology for estrus detection in sows, we utilized YOLOv8 for segmentation and keypoint detection, while monocular depth estimation was used for camera calibration. This calibration helps establish a functional relationship between the measurements in the image (such as distances between labia, the clitoris-to-perineum distance, and vulva perimeter) and the depth distance to the camera, enabling accurate adjustments and calibration for our analysis. Estrus classification is performed by comparing new data points with reference datasets using a three-nearest-neighbor voting system. In this paper, we aim to enhance our previous method by incorporating the mean pixel intensity of the region of interest as an additional factor. We propose a detailed four-step methodology coupled with two stages of evaluation. First, we carefully annotate masks around the vulva to calculate its perimeter precisely. Leveraging the advantages of deep learning, we train a model on these annotated images, enabling segmentation using the cutting-edge YOLOv9 algorithm. This segmentation enables the detection of the sow’s vulva, allowing for analysis of its shape and facilitating the calculation of the mean pixel intensity in the region. Crucially, we use monocular depth estimation from the previous method, establishing a functional link between pixel intensity and the distance to the camera, ensuring accuracy in our analysis. We then introduce a classification approach that differentiates between estrus and non-estrus regions based on the mean pixel intensity of the vulva. This classification method involves calculating Euclidean distances between new data points and reference points from two datasets: one for “estrus” and the other for “non-estrus”. The classification process identifies the five closest neighbors from the datasets and applies a majority voting system to determine the label. A new point is classified as “estrus” if the majority of its nearest neighbors are labeled as estrus; otherwise, it is classified as “non-estrus”. This automated approach offers a robust solution for accurate estrus detection. To validate our method, we propose two evaluation stages: first, a quantitative analysis comparing the performance of our new YOLOv9 segmentation model with the older U-Net and YOLOv8 models. Secondly, we assess the classification process by defining a confusion matrix and comparing the results of our previous method, which used the three nearest points, with those of our new model that utilizes five nearest points. This comparison allows us to evaluate the improvements in accuracy and performance achieved with the updated model. The automation of this vital process holds the potential to revolutionize reproductive health management in agriculture, boosting breeding success rates. Through thorough evaluation and experimentation, our research highlights the transformative power of computer vision, pushing forward more advanced practices in the field. Full article

This paper presents MS-MTSA, a multi-scale multi-type self-attention network designed to enhance AV1-compressed video through targeted post-filtering. The objective is to address two persistent artifact issues observed in our previous MTSA model: visible seams at patch boundaries and grid-like distortions from upsampling. To this end, MS-MTSA introduces two key architectural enhancements. First, multi-scale block-wise self-attention applies sequential attention over 16 × 16 and 12 × 12 blocks to better capture local context and improve spatial continuity. Second, refined patch-wise self-attention includes a lightweight convolutional refinement layer after upsampling to suppress structured artifacts in flat regions. These targeted modifications significantly improve both perceptual and quantitative quality. The proposed network achieves BD-rate reductions of 12.44% for Y, 21.70% for Cb, and 19.90% for Cr compared to the AV1 anchor. Visual evaluations confirm improved texture fidelity and reduced seam artifacts, demonstrating the effectiveness of combining multi-scale attention and structural refinement for artifact suppression in compressed video. Full article

This study explores the design and performance of an underwater magnetic sensor network (UMSN) tailored for intrusion detection in complex environments such as riverbeds and areas with dense vegetation. The system utilizes wireless sensor network (WSN) principles and integrates AMR-based magnetic sensors (e.g., LSM303AGR) with MEMS-based accelerometers to provide accurate and high-resolution magnetic field measurements. Extensive calibration techniques were employed to correct hard-iron and soft-iron distortions, ensuring reliable performance in fluctuating environmental conditions. Field tests included both controlled setups and real-world scenarios, such as detecting intrusions across river sections, shorelines, and coordinated land-water activities. The results showed detection rates consistently above 90%, with response times averaging 2.5 s and a maximum detection range of 5 m. The system also performed well under adverse weather conditions, including fog and rain, demonstrating its adaptability. The findings underline the potential of UMSN as a scalable and cost-efficient solution for monitoring sensitive areas. By addressing the limitations of traditional surveillance systems, this research offers a practical framework for enhancing security in critical regions, laying the groundwork for future developments in magnetic sensor technology. Full article

Background/Objectives: Helicobacter pylori (H. pylori) is a significant global health issue causing chronic gastritis, peptic ulcers, and gastric malignancies. Unfortunately, many, particularly in the Middle East, continue to exhibit alarming rates of prevalence. This study aimed to elucidate local epidemiological patterns of H. pylori and examine its histopathological impact on the gastric mucosa. Methods: This retrospective-cross-sectional study included 805 symptomatic adults (329 males, 476 females) who underwent endoscopic evaluation at King Salman Hospital, Ha’il, Saudi Arabia. Biopsies from the antrum and body were processed using routine formalin fixation and paraffin embedding. Staining with hematoxylin–eosin (H&E) and Giemsa permitted assessment of chronic gastritis and detection of H. pylori. Data were evaluated by IBM SPSS (version 23, IBM Corp., Armonk, NY) for associations among infection, histopathology, and patient characteristics. Results: A total of 727 (90.3%) were H. pylori-positive with marginally higher rates in females (91.2%) than males (89.0%). Infection spanned all age groups, reaching 100% in males aged 60–80 years. Overall chronic GI complications were identified in 726 (99.9%), with chronic gastritis being the most profound histopathologically (19.3%). Lymphoid aggregates in 93.0% biopsies reflected a pronounced immune response. Advanced lesions, including metaplasia (0.8%), atrophy (0.3%), and lymphoma (0.1%), were uncommon, though indicative of potential malignant progression. Despite both sexes exhibiting universal symptoms of gastritis, dyspepsia, and heartburn, there were no statistically significant gender-based differences (p > 0.05); specifically, post-H. pylori signs such as vomiting, nausea, weight loss, bleeding or hematemesis occurred equally in all. Histopathology consistently revealed chronic active gastritis with glandular distortion, lymphoplasmacytic infiltration, and occasional mucosal erosions. Giemsa staining further confirmed abundant spiral shapes underscoring a high bacterial load. Conclusion: These findings highlight the age-specific persistently elevating rates of H. pylori significantly associated with chronic gastric inflammatory complications. Although advanced gastric lesions remain rare, reflecting regional epidemiology, early screening, and sleeve treatment efforts, the potential for malignant transformation makes it imperative for continued vigorous eradication, therapy, and vigilant follow-up to avert severe disease outcomes. Full article

We consider the problem of successive-refinement coding for lossy compression of individual sequences, namely, compression in two stages, where in the first stage, a coarse description at a relatively low rate is sent from the encoder to the decoder, and in the second stage, an additional coding rate is allocated in order to refine the description and thereby improve the reproduction. Our main result is in establishing outer bounds (converse theorems) for the rate region where we limit the encoders to be finite-state machines in the spirit of Ziv and Lempel’s 1978 model. The matching achievability scheme is conceptually straightforward. We also consider the more general multiple description coding problem on a similar footing and propose achievability schemes that are analogous to the well-known El Gamal–Cover and the Zhang–Berger achievability schemes of memoryless sources and additive distortion measures. Full article

We consider a secure integrated sensing and communication (ISAC) scenario, where a signal is transmitted through a state-dependent wiretap channel with one legitimate receiver with which the transmitter communicates and one honest-but-curious target that the transmitter wants to sense. The secure ISAC channel is modeled as two state-dependent fast-fading channels with correlated Rayleigh fading coefficients and independent additive Gaussian noise components. Delayed channel outputs are fed back to the transmitter to improve the communication performance and to estimate the channel state sequence. We establish and illustrate an achievable secrecy-distortion region for degraded secure ISAC channels under correlated Rayleigh fading, for which we show that the signal-to-interference-plus-noise is not a sufficient statistic. We also evaluate the inner bound for a large set of parameters to derive practical design insights. The presented results include parameter ranges for which the secrecy capacity of a classical wiretap channel setup is surpassed and for which the channel capacity is approached. Thus, we illustrate for correlated Rayleigh fading cases that our secure ISAC methods can (i) eliminate the need for the legitimate receiver to have a statistical advantage over the eavesdropper and (ii) provide communication security with minimal rate penalty. Full article

The inefficient allocation of resources in agricultural production not only affects the quality of agricultural development and the efficiency of resource utilization but also represents a pivotal issue that constrains the sustainable progress of agriculture. Considering the urgent societal need for the optimization and advancement of industries, investigating the issue of resource misallocation within agricultural production and its specific losses on AGTFP is profoundly important in advancing the pursuit of high-quality and sustainable agricultural development. This study employs the Cobb–Douglas function and the theory of price distortion to establish a model for quantifying losses in Agricultural Green Total Factor Productivity (AGTFP). Drawing on provincial panel data from North China spanning the years 2006 to 2022, we analyze the characteristics of resource allocation and the corresponding losses in AGTFP. The findings suggest that AGTFP in North China has been gradually rising, accompanied by notable regional disparities in both the level of AGTFP and its growth rate. Nevertheless, due to the varying effects of distorted agricultural input factors, there exists different resource misallocation across North China. Despite some improvement in resource misallocation, this improvement has not been significant. Consequently, there is a loss of AGTFP in the North China region. If resource misallocation is effectively addressed, AGTFP losses could be reduced by at least 29%. It is anticipated that over the course of the next decade, AGTFP will rise and resource misallocation and AGTFP losses will diminish slightly, and it is crucial to step up efforts to enhance resource allocation. By ensuring adequate agricultural funding, enhancing agricultural efficiency, and optimizing energy inputs, it is possible to mitigate resource misallocation, thereby effectively diminishing AGTFP losses and fostering the sustainable advancement of agriculture. Full article

An accurate and numerically efficient description of the rolling process is a challenging task since the degree of computational accuracy is directly related to the complexity of the algorithm employed. In the most general case, finite element models (FEM) are used for the simulation of deformation processes; however, these techniques require significant computational time. Analytical approaches, which are suited for one or another deformation process, seem to be a proper alternative to FEM. In this study, the well-established flowline modeling approach (FLM) is extended with the aim of better describing the flow of a rolled material in both surface and subsurface regions. A new flowline function is defined, while the velocity along the particular streamline and strain rate gradients are determined analytically, based on the roll gap geometry. The new model is validated by comparing the velocity components to the ones computed by the finite element model. The distortion of meshes predicted by both FEM and FLM follow the same evolutionary pattern. Full article

Organic molecular fluorophores have been extensively utilized for biological imaging in the visible and the first near-infrared windows. However, their applications in the second near-infrared (NIR-II) window remain constrained, primarily due to the insufficient fluorescence brightness. Herein, we employ a theoretical protocol combining the thermal vibration correlation function with the time-dependent density functional theory method to investigate the mechanism of the planar-twisted strategy for developing fluorophores with balanced NIR-II emission and fluorescence brightness. Based on a planar donor–acceptor–donor molecular skeleton, various ortho-positioned alkyl side chains with steric hindrances are tactfully incorporated into the backbone to construct a series of twisted fluorophores. Photophysical characterizations of the studied fluorophores demonstrate that the emission spectra located in the NIR-II region exhibited a hypsochromic shift with the structural distortion. Notably, conformational twisting significantly accelerated the radiative decay rate while simultaneously suppressing the nonradiative decay rate, resulting in an improved fluorescence quantum efficiency (FQE). This enhancement can be mainly attributed to both the enlarged adiabatic excitation energy and reduced nonadiabatic electronic coupling between the first excited state and the ground state. Compared with the planar fluorophore, the twisted structures possessed a more than fivefold increase in FQE. In particular, the optimal twisted fluorophore BBTD-4 demonstrated a desirable fluorescence brightness (16.59 M⁻¹ cm⁻¹) on the premise of typical NIR-II emission (980 nm), making it a promising candidate for NIR-II fluorescence imaging in biomedical applications. The findings in this study elucidate the available experimental observations on the analogues, highlighting a feasible approach to modulating the photophysical performances of NIR-II chromophores for developing more highly efficient fluorophores toward optical imaging applications. Full article

In neuroimaging, there is no equivalent alternative to magnetic resonance imaging (MRI). However, image acquisitions are generally time-consuming, which may limit utilization in some cases, e.g., in patients who cannot remain motionless for long or suffer from claustrophobia, or in the event of extensive waiting times. For multiple sclerosis (MS) patients, MRI plays a major role in drug therapy decision-making. The purpose of this study was to evaluate whether an ultrafast, T2-weighted (T2w), deep learning-enhanced (DL), echo-planar-imaging-based (EPI) fluid-attenuated inversion recovery (FLAIR) sequence (FLAIR_UF) that has targeted neurological emergencies so far might even be an option to detect MS lesions of the brain compared to conventional FLAIR sequences. Therefore, 17 MS patients were enrolled prospectively in this exploratory study. Standard MRI protocols and ultrafast acquisitions were conducted at 3 tesla (T), including three-dimensional (3D)-FLAIR, turbo/fast spin-echo (TSE)-FLAIR, and FLAIR_UF. Inflammatory lesions were grouped by size and location. Lesion conspicuity and image quality were rated on an ordinal five-point Likert scale, and lesion detection rates were calculated. Statistical analyses were performed to compare results. Altogether, 568 different lesions were found. Data indicated no significant differences in lesion detection (sensitivity and positive predictive value [PPV]) between FLAIR_UF and axially reconstructed 3D-FLAIR (lesion size ≥3 mm × ≥2 mm) and no differences in sensitivity between FLAIR_UF and TSE-FLAIR (lesion size ≥3 mm total). Lesion conspicuity in FLAIR_UF was similar in all brain regions except for superior conspicuity in the occipital lobe and inferior conspicuity in the central brain regions. Further findings include location-dependent limitations of signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) as well as artifacts such as spatial distortions in FLAIR_UF. In conclusion, FLAIR_UF could potentially be an expedient alternative to conventional methods for brain imaging in MS patients since the acquisition can be performed in a fraction of time while maintaining good image quality. Full article

The urban soundscape contributes significantly to defining human perception and experience. Several standard assessment methods for data collection refer to in situ evaluations to determine how people perceive urban acoustic qualities. These methods, which generally involve soundwalks accompanied by questionnaires, are valuable but need to be validated in different cultural contexts. To address this need, international efforts such as the Soundscape Attribute Translation Project (SATP) are underway to ensure the effectiveness of a data collection standard in non-English-speaking regions. As a part of the SATP project, this study explores potential variations in how people experience urban soundscapes in North Africa. A standardized listening experiment was used to compare how Arabic speakers and French speakers rate the perceived affective qualities (PAQ) of urban soundscapes. Using data collected in public urban spaces in London, participants from both language groups rated 27 recorded urban soundscapes using a PAQ questionnaire. Findings from the Kruskal–Wallis H-test suggest that the perception of pleasant, chaotic, and vibrant are significant, while the dimensions of eventful, monotonous, and quiet show no significant distinctions between the two PAQ groups. Furthermore, opposing Pearson correlations were observed for the attributes of pleasantness and eventfulness, along with contradictions for vibrant, monotonous, and calm. The two-dimensional circumplex models visually map the differences in perceptual responses between the two PAQ groups, displaying distinct circular distortions along the monotone-vibrant axis for Arabic PAQs and the chaotic-calm axis for the French PAQs. The findings of this study suggest that further investigations are needed to understand whether the differences in the urban soundscape perception between these two PAQs are due to linguistic factors or other factors. Full article