Search Results (1,933)

The fermentation of oolong tea is a critical process that determines its quality and flavor. Current fermentation control relies on tea makers’ sensory experience, which is labor-intensive and time-consuming. In this study, using Tieguanyin oolong tea as the research object, features including the tea water loss rate, aroma, image color, and texture were obtained using weight sensors, a tin oxide-type gas sensor, and a visual acquisition system. Support vector regression (SVR), random forest (RF) machine learning, and long short-term memory (LSTM) deep learning algorithms were employed to establish models for assessing the fermentation degree based on both single features and fused multi-source features, respectively. The results showed that in the test set of the fermentation degree models based on single features, the mean absolute error (MAE) ranged from 4.537 to 6.732, the root mean square error (RMSE) ranged from 5.980 to 9.416, and the coefficient of determination (R²) values varied between 0.898 and 0.959. In contrast, the data fusion models demonstrated superior performance, with the MAE reduced to 2.232–2.783, the RMSE reduced to 2.693–3.969, and R² increased to 0.982–0.991, confirming that feature fusion enhanced characterization accuracy. Finally, the Sparrow Search Algorithm (SSA) was applied to optimize the data fusion models. After optimization, the models exhibited a MAE ranging from 1.703 to 2.078, a RMSE from 2.258 to 3.230, and R² values between 0.988 and 0.994 on the test set. The application of the SSA further enhanced model accuracy, with the Fusion-SSA-LSTM model demonstrating the best performance. The research results enable online real-time monitoring of the fermentation degree of Tieguanyin oolong tea, which contributes to the automated production of Tieguanyin oolong tea. Full article

Single-image super-resolution (SISR) methods based on convolutional neural networks (CNNs) have achieved breakthrough progress in reconstruction quality. However, their high computational costs and model complexity have limited their applications in resource-constrained devices. To address this, we propose the MSWSR (multi-scale wavelet super-resolution) method, a lightweight multi-scale feature selection network that exploits both symmetric and asymmetric feature patterns. MSWSR achieves efficient feature extraction and fusion through modular design. The core modules include a mixed feature module (MFM) and a gated attention unit (GAU). The MFM employs a symmetric multi-branch structure to efficiently integrate multi-scale features and enhance low-frequency information modeling. The GAU combines the spatial attention mechanism with the gating mechanism to further optimize symmetric feature representation capability. Moreover, a lightweight spatial selection module (SSA) adaptively assigns weights to key regions while maintaining structural symmetry in feature space. This significantly improves reconstruction quality in complex scenes. In 4× super-resolution tasks, compared to SPAN, MSWSR improves PSNR by 0.22 dB on Urban100 and 0.26 dB on Manga109 datasets. The model contains only 316K parameters, which is substantially lower than existing approaches. Extensive experiments demonstrate that MSWSR significantly reduces computational overhead while maintaining reconstruction quality, providing an effective solution for resource-constrained applications. Full article

Accurate soil moisture (SM) estimates with high spatial resolution are highly desirable for agricultural, hydrological, and environmental applications. This study developed a two-step reconstruction approach to obtain a high-quality and high-spatial-resolution (0.05°) SM dataset from microwave and model-based SM products, combining Bayesian three-cornered hat (BTCH) merging and machine/deep learning downscaling algorithms. Firstly, a three-cornered hat (TCH) method was used to analyze the uncertainty of seven SM products on four main land cover types in the Pearl River Basin (PRB). On this basis, the SM products with low uncertainty were merged using the BTCH method. Secondly, two machine/deep learning algorithms (random forest, RF, and long short-term memory, LSTM) were applied to downscale the merged SM data from 0.25° to 0.05° based on the relationship between SM and auxiliary variables. The overall performance of RF and LSTM downscaling models with/without antecedent precipitation were compared. The merged and downscaled SM results were validated against in situ observations and the China Meteorological Administration (CMA) Land Data Assimilation System (CLDAS) SM data. The results indicated the following: (1) The BTCH-based SM estimate outperformed the parent products and the AVE-based SM estimate (the arithmetic average), indicating that BTCH is a fusion approach that can effectively reduce data uncertainties and optimize weights. (2) The optimal time scale for the cumulative effect of precipitation on SM was 35 days during 2015–2020 in the PRB. SM estimations using RF and LSTM downscaling algorithms both had substantial improvement by considering the antecedent precipitation variable, both at the 0.25° and 0.05° spatial scales. Feature importance assessment also revealed the most important role of antecedent precipitation (30.01%). Moreover, the LSTM model with antecedent precipitation performed slightly better than the RF model with antecedent precipitation. (3) The downscaled SM results all mitigated the overestimation inherent in the original SM data, though they were inevitably limited by the performance of the original SM data and difficult to surpass. The developed two-step reconstruction approach was effective in generating an accurate SM dataset at a finer spatial scale for wide regional applications. Full article

With advances in digital technology, including deep learning and big data analytics, new methods have been developed for autism diagnosis and intervention. Emotion recognition and the detection of autism in children are prominent subjects in autism research. Typically using single-modal data to analyze the emotional states of children with autism, previous research has found that the accuracy of recognition algorithms must be improved. Our study creates datasets on the facial and speech emotions of children with autism in their natural states. A convolutional vision transformer-based emotion recognition model is constructed for the two distinct datasets. The findings indicate that the model achieves accuracies of 79.12% and 83.47% for facial expression recognition and Mel spectrogram recognition, respectively. Consequently, we propose a multimodal data fusion strategy for emotion recognition and construct a feature fusion model based on an attention mechanism, which attains a recognition accuracy of 90.73%. Ultimately, by using gradient-weighted class activation mapping, a prediction heat map is produced to visualize facial expressions and speech features under four emotional states. This study offers a technical direction for the use of intelligent perception technology in the realm of special education and enriches the theory of emotional intelligence perception of children with autism. Full article

Ships are the main carriers of maritime transportation. Real-time object detection of ships through remote sensing satellites is of great significance in ocean rescue, maritime traffic, border management, etc. In remote sensing ship detection, the complexity and diversity of ship shapes, along with scenarios involving ship aggregation, often lead to false negatives and false positives. The diversity of ship shapes can cause detection algorithms to fail in accurately identifying different types of ships. In cases where ships are clustered together, the detection algorithm may mistakenly classify multiple ships as a single target or miss ships that are partially obscured. These factors can affect the accuracy and robustness of the detection, increasing the challenges in remote sensing ship detection. In view of this, we propose a remote sensing ship detection method, E-WFF Net, based on YOLOv8s. Specifically, we introduced a data enhancement method based on elliptical rotating boxes, which increases the sample diversity in the network training stage. We also designed a dynamic attention mechanism feature fusion module (DAT) to make the network pay more attention to ship characteristics. In order to improve the speed of network inference, we designed a residual weighted feature fusion method; by adding a feature extraction branch while simplifying the network layers, the inference speed of the network was accelerated. We evaluated our method on the HRSC2016 and DIOR datasets, and the results show some improvements compared to YOLOv8 and YOLOv10, especially on the HRSC2016 dataset. The results show that our method E-WFF Net achieves a detection accuracy of 96.1% on the HRSC2016 dataset, which is a 1% improvement over YOLOv8s and a 1.1% improvement over YOLOv10n. The detection speed is 175.90 FPS, which is a 3.2% improvement over YOLOv8 and a 9.9% improvement over YOLOv10n. Full article

Point cloud completion reconstructs incomplete, sparse inputs into complete 3D shapes. However, in the current 3D completion task, it is difficult to effectively extract the local details of an incomplete one, resulting in poor restoration of local details and low accuracy of the completed point clouds. To address this problem, this paper proposes a multi-scale point cloud completion method based on local neighborhood dynamic fusion (LNDF: adaptive aggregation of multi-scale local features through dynamic range and weight adjustment). Firstly, the farthest point sampling (FPS) strategy is applied to the original incomplete and defective point clouds for down-sampling to obtain three types of point clouds at different scales. When extracting features from point clouds of different scales, the local neighborhood aggregation of key points is dynamically adjusted, and the Transformer architecture is integrated to further enhance the correlation of local feature extraction information. Secondly, by combining the method of generating point clouds layer by layer in a pyramid-like manner, the local details of the point clouds are gradually enriched from coarse to fine to achieve point cloud completion. Finally, when designing the decoder, inspired by the concept of generative adversarial networks (GANs), an attention discriminator designed in series with a feature extraction layer and an attention layer is added to further optimize the completion performance of the network. Experimental results show that LNDM-Net reduces the average Chamfer Distance (CD) by 5.78% on PCN and 4.54% on ShapeNet compared to SOTA. The visualization of completion results demonstrates the superior performance of our method in both point cloud completion accuracy and local detail preservation. When handling diverse samples and incomplete point clouds in real-world 3D scenarios from the KITTI dataset, the approach exhibits enhanced generalization capability and completion fidelity. Full article

Surface defect detection plays a quality assurance role in industrial manufacturing processes. However, the diversity of defects and the presence of complex backgrounds bring significant challenges to salient object detection. To this end, this study proposes a new adaptive multi-scale feature fusion network (AMSFF-Net) to solve the SOD problem of object surface defects. The upsampling fusion module used adaptive weight fusion, global feature adaptive fusion, and differential feature adaptive fusion to fuse information of different scales and levels. In addition, the spatial attention (SA) mechanism was introduced to enhance the effective fusion of multi-feature maps. Preprocessing techniques such as aspect ratio adjustment and random rotation were used. Aspect ratio adjustment helps to identify and locate defects of different shapes and sizes, and random rotation enhances the ability of the model to detect defects at different angles. The negative samples and non-uniform-distribution samples in the magnetic tile defect dataset were further removed to ensure data quality. This study conducted comprehensive experiments, demonstrating that AMSFF-Net outperforms existing state-of-the-art technologies. The proposed method achieved an S-measure of 0.9038 and an $F_{\mathsf{\beta }}^{\mathrm{m}\mathrm{a}\mathrm{x}}$ of 0.8782, which represents a 1% improvement in $F_{\mathsf{\beta }}^{\mathrm{m}\mathrm{a}\mathrm{x}}$ compared to the best existing methods. Full article

While deep learning techniques, such as Convolutional neural networks (CNNs), show significant potential in medical applications, real-time detection of parathyroid glands (PGs) during complex surgeries remains insufficiently explored, posing challenges for surgical accuracy and outcomes. Previous studies highlight the importance of leveraging prior knowledge, such as shape, for feature extraction in detection tasks. However, they fail to address the critical multi-scale variability of PG objects, resulting in suboptimal performance and efficiency. In this paper, we propose an end-to-end framework, MSWF-PGD, for Multi-Scale Weighted Fusion Parathyroid Gland Detection. To improve accuracy and efficiency, our approach extracts feature maps from convolutional layers at multiple scales and re-weights them using cluster-aware multi-scale alignment, considering diverse attributes such as the size, color, and position of PGs. Additionally, we introduce Multi-Scale Aggregation to enhance scale interactions and enable adaptive multi-scale feature fusion, providing precise and informative locality information for detection. Extensive comparative experiments and ablation studies on the parathyroid dataset (PGsdata) demonstrate the proposed framework’s superiority in accuracy and real-time efficiency, outperforming state-of-the-art models such as RetinaNet, FCOS, and YOLOv8. Full article

High-precision three-dimensional geological modeling of mining faces is crucial for intelligent coal mining and disaster prevention. Accurate spatial interpolation is essential for building high-quality models. This study focuses on the 25214 workface of the Hongliulin coal mine, addressing challenges in interpolating terrain elevation, stratum thickness, and coal seam thickness data. We evaluate eight interpolation methods (four kriging methods, an inverse distance weighting method, and three radial basis function methods) for terrain and stratum thickness, and nine methods (including the Bayesian Maximum Entropy method) for coal seam thickness, using cross-validation to assess their accuracy. Research results indicate that for terrain elevation data with dense and evenly distributed sampling points, linear kriging achieves the highest accuracy (MAE = 1.01 m, RMSE = 1.20 m). For the optimal interpolation methods of five layers of thickness data with sparse sampling points, the results are as follows: Q₄, spherical kriging (MAE = 2.13 m, RMSE = 2.83 m); N₂b, IDW (p = 2), MAE = 2.08 m, RMSE = 2.44 m; J₂y³, RS-RBF (MAE = 0.89 m, RMSE = 1.05 m); J₂y², TPS-RBF (MAE = 1.96 m, RMSE = 2.25 m); J₂y¹, HS-RBF (MAE = 2.36 m, RMSE = 2.71 m). A method for accurately delineating the zero line of strata thickness by assigning negative values to virtual thickness in areas of missing strata has been proposed. For coal seam thickness data with uncertain data (from channel wave exploration), a soft-hard data fusion interpolation method based on Bayesian Maximum Entropy has been introduced, and its interpolation results (MAE = 0.64 m, RMSE = 0.66 m) significantly outperform those of eight other interpolation algorithms. Using the optimal interpolation methods for terrain, strata, and coal seams, we construct a high-precision three-dimensional geological model of the workface, which provides reliable support for intelligent coal mining. Full article

Metropolitan areas, as pivotal hubs for global tourism and economic growth, necessitate sustainable spatial planning to balance development with ecological preservation. As critical geospatial datasets, nighttime light (NTL) and point of interest (POI) data enable the robust analysis of urban structural patterns. Building upon coupling coordination theory and polycentric spatial frameworks, this study investigates the spatial interdependencies between tourism POI and NTL data in China’s Changsha–Zhuzhou–Xiangtan Metropolitan Area (CZTMA). Key findings reveal high spatial coupling homogeneity, with three urban cores exhibiting radial value attenuation from city centers toward the tri-city intersection; concentric zonation patterns where NTL-dominant rings encircle high-coupling nuclei, contrasting with sporadic POI-intensive clusters in peri-urban towns; and sector-specific luminosity responses, where sightseeing infrastructure demonstrates the strongest localized NTL impacts through multiscale geographically weighted regression (MGWR). These findings establish a novel “data fusion-spatial coupling-governance” analytical framework and provide actionable insights for policymakers to harmonize tourism-driven urbanization with ecological resilience, contributing to United Nations Sustainable Development Goal (SDG) 11 (Sustainable Cities). Full article

Due to its unique geometric configuration, passive radar offers enhanced surveillance capabilities for low-altitude targets. Traditional passive radar signal processing typically relies on energy accumulation and Constant False Alarm Rate (CFAR) detection. However, insufficient accumulation gain or mismatched statistical models in complex electromagnetic environments can compromise detection performance. To address these challenges, this paper proposes an intelligent target detection method for passive radar. Specifically, a residual network is integrated with a Squeeze-and-Excitation (SE) module, which preserves the powerful feature extraction capabilities of the residual network while improving the model’s ability to adaptively adjust channel weights. This fusion effectively enhances the target detection process. Furthermore, based on the particle swarm algorithm, a gray wolf population search strategy and a multi-target iterative search mechanism are introduced to enable the rapid extraction of time-frequency difference parameters for multiple targets. Both simulation and field experiments demonstrate that the proposed method enables intelligent detection of low–slow–small targets in passive radar, ensuring efficient time-frequency parameter extraction while maintaining a high detection success rate. Full article

Speaker recognition is essential in smart voice applications for personal identification. Current state-of-the-art techniques primarily focus on ideal acoustic conditions. However, the traditional spectrogram struggles to differentiate between noise, reverberation, and speech. To overcome this challenge, MFCC can be replaced with the output from a self-supervised learning model. This study introduces a TDNN enhanced with a pre-trained model for robust performance in noisy and reverberant environments, referred to as PNR-TDNN. The PNR-TDNN employs HuBERT as its backbone, while the TDNN is an improved ECAPA-TDNN. The pre-trained model employs the Canopy/Mini Batch k-means++ strategy. In the TDNN architecture, several enhancements are implemented, including a cross-channel fusion mechanism based on Res2Net. Additionally, a non-average attention mechanism is applied to the pooling operation, focusing on the weight information of each channel within the Squeeze-and-Excitation Net. Furthermore, the contribution of individual channels to the pooling of time-domain frames is enhanced by substituting attentive statistics with multi-head attention statistics. Validated by zhvoice in noisy conditions, the minimized PNR-TDNN demonstrates a 5.19% improvement in EER compared to CAM++. In more challenging environments with noise and reverberation, the minimized PNR-TDNN further improves EER by 3.71% and 9.6%, respectively, and MinDCF by 3.14% and 3.77%, respectively. The proposed method has also been validated on the VoxCeleb1 and cn-celeb_v2 datasets, representing a significant breakthrough in the field of speaker recognition under challenging conditions. This advancement is particularly crucial for enhancing safety and protecting personal identification in voice-enabled microphone applications. Full article

In complex agricultural settings, accurately and rapidly identifying the growth and health conditions of strawberries remains a formidable challenge. Therefore, this study aims to develop a deep framework, Disease-YOLO (D-YOLO), based on the YOLOv8s model to monitor the health status of strawberries. Key innovations include (1) replacing the original backbone with MobileNetv3 to optimize computational efficiency; (2) implementing a Bidirectional Feature Pyramid Network for enhanced multi-scale feature fusion; (3) integrating Contextual Transformer attention modules in the neck network to improve lesion localization; and (4) adopting weighted intersection over union loss to address class imbalance. Evaluated on our custom strawberry disease dataset containing 1301 annotated images across three fruit development stages and five plant health states, D-YOLO achieved 89.6% mAP on the train set and 90.5% mAP on the test set while reducing parameters by 72.0% and floating-point operations by 75.1% compared to baseline YOLOv8s. The framework’s balanced performance and computational efficiency surpass conventional models including Faster R-CNN, RetinaNet, YOLOv5s, YOLOv6s, and YOLOv8s in comparative trials. Cross-domain validation on a maize disease dataset demonstrated D-YOLO’s superior generalization with 94.5% mAP, outperforming YOLOv8 by 0.6%. The framework’s balanced performance (89.6% training mAP) and computational efficiency surpass conventional models, including Faster R-CNN, RetinaNet, YOLOv5s, YOLOv6s, and YOLOv8s, in comparative trials. This lightweight solution enables precise, real-time crop health monitoring. The proposed architectural improvements provide a practical paradigm for intelligent disease detection in precision agriculture. Full article

Laser space networks are an important development direction for inter-satellite communication. Detecting the angle of arrival (AOA) of multiple satellites in a wide field of view (FOV) is the key to realize inter-satellite laser communication networking. The traditional AOA detection method based on the lens system has a limited FOV. In this paper, we demonstrate a system that uses a spatially distributed sensor array to detect the AOA in a wide FOV. The basic concept is to detect AOA using the signal strength of each sensor at different spatial angles. An AOA detection model was developed, and the relationship of key structural parameters of the spatially distributed sensor array on the FOV and angular resolution was analyzed. Furthermore, a spatially distributed sensor array prototype consisting of 5 InGaAs PIN photodiodes distributed on a 3D-printed structure with an inclination angle of 30° was developed. In order to improve the angle calculation accuracy, a multi-sensor data fusion algorithm is proposed. The experimental results show that the prototype’s maximum FOV is 110°. The root mean square error (RMSE) for azimuth is 0.6° within a 60° FOV, whereas the RMSE for elevation is 0.67°. The RMSE increases to 1.1° for azimuth and 1.7° for elevation when the FOV expands to 110°. The designed spatially distributed sensor array has the advantages of a wide FOV and low size, weight, and power (SWaP), presenting great potential for multi-satellite laser communication applications. Full article

Real-time image dehazing is crucial for remote sensing systems, particularly in applications requiring immediate and reliable visual data. By restoring contrast and fidelity as images are captured, real-time dehazing enhances image quality on the fly. Existing dehazing algorithms often prioritize visual quality and color restoration but rely on computationally intensive methods, making them unsuitable for real-time processing. Moreover, these methods typically perform well under moderate to dense haze conditions but lack adaptability to varying haze levels, limiting their general applicability. To address these challenges, this paper presents an autonomous image dehazing method and its corresponding FPGA-based accelerator, which effectively balance image quality and computational efficiency for real-time processing. Autonomous dehazing is achieved by fusing the input image with its dehazed counterpart, where fusion weights are dynamically determined based on the local haziness degree. The FPGA accelerator performs computations with strict timing requirements during the vertical blanking interval, ensuring smooth and flicker-free processing of input data streams. Experimental results validate the effectiveness of the proposed method, and hardware implementation results demonstrate that the FPGA accelerator achieves a processing rate of $45.34$ frames per second at DCI 4K resolution while maintaining efficient utilization of hardware resources. Full article