Search Results (75)

In response to the inability to quickly assess wind noise performance during the early stages of automotive styling design, this paper proposes a method for predicting interior wind noise by integrating automotive point cloud models with the Gray Wolf Optimization Residual Network model (GWO-ResNet). Based on wind tunnel test data under typical operating conditions, the point cloud model of the test vehicle is compressed using an auto-encoder and used as input features to construct a nonlinear mapping model between the whole vehicle point cloud and the wind noise level at the driver’s left ear. Through adaptive optimization of key hyperparameters of the ResNet model using the gray wolf optimization algorithm, the accuracy and generalization of the prediction model are improved. The prediction results on the test set indicate that the proposed GWO-ResNet model achieves prediction results that are consistent with the actual measured values for the test samples, thereby validating the effectiveness of the proposed method. A comparative analysis with traditional ResNet models, GWO-LSTM models, and LSTM models revealed that the GWO-ResNet model achieved Mean Absolute Percentage Error (MAPE) and mean squared error (MSE) of 9.72% and 20.96, and 9.88% and 19.69, respectively, on the sedan and SUV test sets, significantly outperforming the other comparison models. The prediction results on the independent validation set also demonstrate good generalization ability and stability (MAPE of 10.14% and 10.15%, MSE of 23.97 and 29.15), further proving the reliability of this model in practical applications. The research results provide an efficient and feasible technical approach for the rapid evaluation of wind noise performance in vehicles and provide a reference for wind noise control in the early design stage of vehicles. At the same time, due to the limitations of the current test data, it is impossible to predict the wind noise during the actual driving of the vehicle. Subsequently, the wind noise during actual driving can be predicted by the test data of multiple working conditions. Full article

Recently, with the rapid development of underwater resource exploration and underwater activities, underwater acoustic (UA) target recognition has become crucial in marine resource exploration. However, traditional underwater acoustic recognition systems face challenges such as low energy efficiency, poor accuracy, and slow response times. Systems for UA target recognition using deep learning networks have garnered widespread attention. Convolutional neural network (CNN) consumes significant computational resources and energy during convolution operations, which exacerbates the issues of energy consumption and complicates edge deployment. This paper explores a high-energy-efficiency UA target recognition system. Based on the DenseNet CNN, the system uses fine-grained pruning for sparsification and sparse convolution computations. The UA target recognition CNN was deployed on FPGAs and chips to achieve low-power recognition. Using the noise-disturbed ShipsEar dataset, the system reaches a recognition accuracy of 98.73% at 0 dB signal-to-noise ratio (SNR). After 50% fine-grained pruning, the accuracy is 96.11%. The circuit prototype on FPGA shows that the circuit achieves an accuracy of 95% at 0 dB SNR. This work implements the circuit design and layout of the UA target recognition chip based on a 65 nm CMOS process. DC synthesis results show that the power consumption is 90.82 mW, and the single-target recognition time is 7.81 ns. Full article

Micro-sprinkling fertigation, a novel irrigation and fertilization way, can improve the grain yield (GY) and nitrogen use efficiency (NUE) of winter wheat to meet sustainable agriculture requirements. In order to clarify the physiological basis behind the improvements, a field experiment with a split-plot design was conducted during the 2020–2021 and 2021–2022 growing seasons. The main plot encompassed two irrigation and fertilization modes, namely, conventional irrigation and fertilization (CIF) and micro-sprinkling fertigation (MSF), and the subplots included four nitrogen application rates (0, 120, 180, and 240 kg ha⁻¹, denoted as N0, N120, N180, and N240, respectively). Moreover, a ¹⁵N isotopic tracer experiment was performed to determine the distributions of nitrogen in the soil. Compared with those under CIF, the GY under MSF at N180 and N240 significantly increased by 9.09% and 9.72%, which was driven mainly by increases in the grain number (GN) and thousand-grain weight (TGW). The increase in the TGW under MSF was the result of the significantly increased net photosynthesis rate at the grain-filling stage. Notably, the number and dry weight of inefficient tillers and the number of ears with fewer than 10 grains were significantly lower under MSF than those under CIF. In addition, the ¹⁵N isotopic tracer experiment revealed that nitrogen was primarily concentrated in the 0–30 cm soil layers under MSF, which conforms well with the spatial distributions of the roots and water, and subsequently improved the NUE under N180 and N240. In conclusion, MSF enhanced both the GY and NUE at the N180 level by optimizing root–water–nitrogen spatiotemporal coordination and reducing redundant tillering. Full article

Fusarium head blight (FHB), a globally significant agricultural disaster, causes annual losses of dozens of millions of tons of wheat toxins produced by FHB, such as deoxyroscyliaceol, further pose serious threats to human and livestock health. Consequently, rapid and non-destructive determination of FHB severity is crucial for implementing timely and precise scientific control measures, thereby ensuring wheat supply security. Therefore, this study adopts hyperspectral imaging (HSI) combined with a lightweight deep learning model. Firstly, the wheat ears were inoculated with Fusarium fungi at the spike’s midpoint, and HSI data were acquired, yielding 1660 samples representing varying disease severities. Through the integration of multiplicative scatter correction (MSC) and uninformative variable elimination (UVE) methods, features are extracted from spectral data in a manner that optimizes the reduction of feature dimensionality while preserving elevated classification accuracy. Finally, a lightweight FHB severity discrimination model based on MobileNetV2 was developed and deployed as an easy-to-use analysis system. Analysis revealed that UVE-selected characteristic bands for FHB severity predominantly fell within 590–680 nm (chlorophyll degradation related), 930–1043 nm (water stress related) and 738 nm (cell wall polysaccharide decomposition related). This distribution aligns with the synergistic effect of rapid chlorophyll degradation and structural damage accompanying disease progression. The resulting MobileNetV2 model achieved a mean average precision (mAP) of 99.93% on the training set and 98.26% on the independent test set. Crucially, it maintains an 8.50 MB parameter size, it processes data 2.36 times faster, significantly enhancing its suitability for field-deployed equipment by optimally balancing accuracy and operational efficiency. This advancement empowers agricultural workers to implement timely control measures, dramatically improving precision alongside optimized field deployment. Full article

Early traffic accident risk prediction in complex road environments poses significant challenges due to the heterogeneous nature and incomplete semantic alignment of multimodal data. To address this, we propose a novel Early Accident Risk Cross-modal Collaborative Perception Mechanism Network (EAR-CCPM-Net) that integrates hierarchical fusion modules and cross-modal attention mechanisms to enable semantic interaction between visual, motion, and textual modalities. The model is trained and evaluated on the newly constructed CAP-DATA dataset, incorporating advanced preprocessing techniques such as bilateral filtering and a rigorous MINI-Train-Test sampling protocol. Experimental results show that EAR-CCPM-Net achieves an AUC of 0.853, AP of 0.758, and improves the Time-to-Accident (TTA_0.5) from 3.927 s to 4.225 s, significantly outperforming baseline methods. These findings demonstrate that EAR-CCPM-Net effectively enhances early-stage semantic perception and prediction accuracy, providing an interpretable solution for real-world traffic risk anticipation. Full article

Timely, objective pain recognition in dairy cattle is essential for welfare assurance, productivity, and ethical husbandry yet remains elusive because evolutionary pressure renders bovine distress signals brief and inconspicuous. Without verbal self-reporting, cows suppress overt cues, so automated vision is indispensable for on-farm triage. Although earlier systems tracked whole-body posture or static grimace scales, frame-level detection of facial micro-expressions has not been explored fully in livestock. We translate micro-expression analytics from automotive driver monitoring to the barn, linking modern computer vision with veterinary ethology. Our two-stage pipeline first detects faces and 30 landmarks using a custom You Only Look Once (YOLO) version 8-Pose network, achieving a 96.9% mean average precision ($mAP$) at an Intersection over the Union (IoU) threshold of 0.50 for detection and 83.8% Object Keypoint Similarity (OKS) for keypoint placement. Cropped eye, ear, and muzzle patches are encoded using a pretrained MobileNetV2, generating 3840-dimensional descriptors that capture millisecond muscle twitches. Sequences of five consecutive frames are fed into a 128-unit Long Short-Term Memory (LSTM) classifier that outputs pain probabilities. On a held-out validation set of 1700 frames, the system records 99.65% accuracy and an F1-score of 0.997, with only three false positives and three false negatives. Tested on 14 unseen barn videos, it attains 64.3% clip-level accuracy (i.e., overall accuracy for the whole video clip) and 83% precision for the pain class, using a hybrid aggregation rule that combines a 30% mean probability threshold with micro-burst counting to temper false alarms. As an early exploration from our proof-of-concept study on a subset of our custom dairy farm datasets, these results show that micro-expression mining can deliver scalable, non-invasive pain surveillance across variations in illumination, camera angle, background, and individual morphology. Future work will explore attention-based temporal pooling, curriculum learning for variable window lengths, domain-adaptive fine-tuning, and multimodal fusion with accelerometry on the complete datasets to elevate the performance toward clinical deployment. Full article

Bats are a taxa of high conservation concern and are facing numerous threats including widespread mortality due to White-Nose Syndrome (WNS) in North America. With this decline comes increasing difficulty in monitoring imperiled bat species due to lower detection probabilities of both mist-netting and acoustic surveys. Lure technology shows promise to increase detection while decreasing sampling effort; however, to date research has primarily focused on increasing physical captures during mist-net surveys using sound lures. Because much bat monitoring is now performed using acoustic detection, there is a similar need to increase detection probabilities during acoustic surveys. Ultraviolet (UV) lights anecdotally have been shown to attract insects and thereby attract foraging bats for observational studies and to experimentally provide a food source for WNS-impacted bats before and after hibernation. Therefore, we constructed a field-portable and programmable UV lure device to determine the value of lures for increasing acoustic detection of bats. We tested if the lure device increased both the echolocation passes and feeding activity (feeding buzzes) across a transect of bat detectors. There was an increase in feeding activity around the UV light, with a nuanced, species-specific and positionally dependent effect on echolocation passes received. The UV light lure increased echolocation passes for the eastern red bat (Lasiurus borealis), little brown bat (Myotis lucifugus), and evening bat (Nycticeius humeralis), but decreased passes of the North American hoary bat (Lasiurus cinereus). The northern long-eared bat (Myotis septentrionalis) showed a negative response within the illuminated area but increased echolocation activity outside the illuminated area during lure treatment and activity was elevated at all positions after the lure was deactivated. Our study demonstrates some potential utility of UV lures in increasing the feeding activity and acoustic detection of bats. Additional research and development of UV lure technology may be beneficial, including alternating on and off periods to improve detection of light-averse species, and improving echolocation call quality along with the increase in received passes. Full article

The male flower of the maize plant, known as the tassel, is a strong indicator of the growth, development, and reproductive stages of maize crops. Monitoring maize tassels under natural conditions is significant for maize breeding, management, and yield estimation. Unmanned aerial vehicle (UAV) remote sensing combined with deep learning-based semantic segmentation offers a novel approach for monitoring maize tassel phenotypic traits. The morphological and size variations in maize tassels, together with numerous similar interference factors in the farmland environment (such as leaf veins, female ears, etc.), pose significant challenges to the accurate segmentation of tassels. To address these challenges, we propose DECC-Net, a novel segmentation model designed to accurately extract maize tassels from complex farmland environments. DECC-Net integrates the Dynamic Kernel Feature Extraction (DKE) module to comprehensively capture semantic features of tassels, along with the Lightweight Channel Cross Transformer (LCCT) and Adaptive Feature Channel Enhancement (AFE) modules to guide effective fusion of multi-stage encoder features while mitigating semantic gaps. Experimental results demonstrate that DECC-Net achieves advanced performance, with IoU and Dice scores of 83.3% and 90.9%, respectively, outperforming existing segmentation models while exhibiting robust generalization across diverse scenarios. This work provides valuable insights for maize varietal selection, yield estimation, and field management operations. Full article

Late sowing and spring low temperatures have a great impact on the growth and maturation of wheat in the rice–wheat rotation region. In order to analyze the impacts of cold stress in February in early spring on yield formation and agronomic traits of wheat on different sowing dates, a controlled pot experiment was performed using the widely promoted and applied spring-type wheat variety Yangmai23 (YM23). The yield of wheat treated with late sowing date II (SDII, 21 November) and overly late sowing date III (SDIII, 9 December) were both lower than that of wheat sown on the suitable date I (SDI, 1 November). The yield of late-sown wheat decreased by 40.82% for SDII and by 66.77% for SDIII, compared with SDI, and these three treatments of wheat all grew under the natural conditions as the control treatments. The plant height, stem diameter of the internode below the ear, flag leaf length and area, and total awn length of the spike, as well as the spike length of late-sown wheat, were all significantly lower than those of wheat in SDI treatment. Early spring low temperatures exacerbated the decline in yield of wheat sown on different dates, to some extent. Despite showing higher net photosynthetic rate, stomatal conductance, and transpiration rate in flag leaves of the SDIII treatment under low-temperature stress than those of the other treatments at anthesis, overly late sowing led to minimal leaf area, shorter plant height, fewer tillers, and smaller ears, ultimately resulting in the lowest yield. Our study suggested that additional focus and some regulation techniques are needed to be studied further to mitigate the combined negative impacts of late sowing and low-temperature stress in early spring on wheat production. Full article

With the increasing importance of animal welfare, behavioral indicators such as changes in head and ear posture are widely recognized as non-invasive and field-applicable markers for evaluating the emotional state and stress levels of animals. However, traditional visual observation methods are often subjective, as assessments can vary between observers, and are unsuitable for long-term, quantitative monitoring. This study proposes an artificial intelligence (AI)-based system for the detection and pose estimation of cattle heads and ears using deep learning techniques. The system integrates Mask R-CNN for accurate object detection and FSA-Net for robust 3D pose estimation (yaw, pitch, and roll) of cattle heads and left ears. Comprehensive datasets were constructed from images of Japanese Black cattle, collected under natural conditions and annotated for both detection and pose estimation tasks. The proposed framework achieved mean average precision (mAP) values of 0.79 for head detection and 0.71 for left ear detection and mean absolute error (MAE) of approximately 8–9° for pose estimation, demonstrating reliable performance across diverse orientations. This approach enables long-term, quantitative, and objective monitoring of cattle behavior, offering significant advantages over traditional subjective stress assessment methods. The developed system holds promise for practical applications in animal welfare research and real-time farm management. Full article

Underwater sonar target recognition is crucial in fields such as national defense, navigation, and environmental monitoring. However, it faces issues such as the complex characteristics of ship-radiated noise, imbalanced data distribution, non-stationarity, and bottlenecks of existing technologies. This paper proposes the MultiFuseNet-AID network, aiming to address these challenges. The network includes the TriFusion block module, the novel lightweight attention residual network (NLARN), the long- and short-term attention (LSTA) module, and the Mamba module. Through the TriFusion block module, the original, differential, and cumulative signals are processed in parallel, and features such as MFCC, CQT, and Fbank are fused to achieve deep multi-domain feature fusion, thereby enhancing the signal representation ability. The NLARN was optimized based on the ResNet architecture, with the SE attention mechanism embedded. Combined with the long- and short-term attention (LSTA) and the Mamba module, it could capture long-sequence dependencies with an O(N) complexity, completing the optimization of lightweight long sequence modeling. At the same time, with the help of feature fusion, and layer normalization and residual connections of the Mamba module, the adaptability of the model in complex scenarios with imbalanced data and strong noise was enhanced. On the DeepShip and ShipsEar datasets, the recognition rates of this model reached 98.39% and 99.77%, respectively. The number of parameters and the number of floating point operations were significantly lower than those of classical models, and it showed good stability and generalization ability under different sample label ratios. The research shows that the MultiFuseNet-AID network effectively broke through the bottlenecks of existing technologies. However, there is still room for improvement in terms of adaptability to extreme underwater environments, training efficiency, and adaptability to ultra-small devices. It provides a new direction for the development of underwater sonar target recognition technology. Full article

In the context of ear-based biometric identity authentication, symmetry between the left and right ears emerges as a pivotal factor, particularly when registration involves one ear and authentication utilizes its contralateral counterpart. The extent to which bilateral ear symmetry supports consistent identity verification warrants significant investigation. This study addresses this challenge by proposing a novel framework, the Symmetry Alignment–Feature Interaction Network, designed to enhance authentication robustness. The proposed network incorporates a Symmetry Alignment Module, leveraging differentiable geometric alignment and a dual-attention mechanism to achieve precise feature correspondence between the left and right ears, thereby mitigating the robustness deficiencies of conventional methods under pose variations. Additionally, a Feature Interaction Network is introduced to amplify nonlinear interdependencies between binaural features, employing a difference–product dual-path architecture to enhance feature discriminability through Dual-Path Feature Interaction and Similarity Fusion. Experimental validation on a dataset from the University of Science and Technology of Beijing demonstrates that the proposed method achieves a similarity detection accuracy of 99.03% (a 9.11% improvement over the baseline ResNet18) and an F1 score of 0.9252 in identity authentication tasks. Ablation experiments further confirm the efficacy of the Symmetry Alignment Module, reducing the false positive rate by 3.05%, in combination with the Feature Interaction Network, shrinking the standard deviation of similarity distributions between the positive and negative samples by 67%. A multi-task loss function, governed by a dynamic weighting mechanism, effectively balances feature learning objectives. This work establishes a new paradigm for the authentication of biometric features with symmetry, integrating symmetry modeling with Dual-Path Feature Interaction and Similarity Fusion to advance the precision of ear authentication. Full article

Background/Objectives: Antimicrobial resistance is one of the foremost global health concerns of today, and it could offset much of the progress accrued in healthcare over the last century. Excessive antibiotic use accelerates this problem, but it is recognised that specific agents differ in their capacity to promote resistance, a concept recently promoted by the World Health Organisation in the form of its Access, Watch, Reserve (AWaRe) schema. Which, if any, agents should be construed as having a high proclivity for selection of resistance has been contested. The European Antimicrobial Resistance Surveillance Network (EARS-NET) and European Surveillance of Antimicrobial Consumption Network (ESAC-NET) curate population level data over time and throughout the European Economic Area (EEA). EARS-NET monitors resistance to antimicrobials amongst invasive isolates of sentinel pathogens whereas ESAC-NET tracks usage of systemic antimicrobials. Together, data from these networks were interrogated to delineate correlations between antimicrobial consumption and resistance. Methods: Using univariate and multivariate regression analyses, spatiotemporal associations between the use of specific antimicrobial classes and 14 key resistance phenotypes in five sentinel pathogens were assessed methodically for 29 EEA countries. Results: Use of second and third generation cephalosporins, extended spectrum penicillin/β-lactamase inhibitor combinations, carbapenems, fluoroquinolones, nitroimidazoles and macrolides strongly correlated with key resistance phenotypes, as did overall antimicrobial consumption. Conclusions: The data obtained mostly support the WHO AWaRe schema with critical caveats. They have the potential to inform antimicrobial stewardship initiatives in the EEA, highlighting obstacles and shortcomings which may be modified in future to minimise positive selection for problematic resistance. Full article

Underwater acoustic target recognition (UATR) technology plays a significant role in marine exploration, resource development, and national defense security. To address the limitations of existing methods in computational efficiency and recognition performance, this paper proposes an improved WS-ViT model based on Vision Transformers (ViTs). By introducing the Wavelet Transform Convolution (WTConv) module and the Simplified Linear Attention (SLAttention) module, WS-ViT can effectively extract spatiotemporal complex features, enhance classification accuracy, and significantly reduce computational costs. The model is validated using the ShipsEar dataset, and the results demonstrate that WS-ViT significantly outperforms ResNet18, VGG16, and the classical ViT model in classification accuracy, with improvements of 7.3%, 4.9%, and 2.1%, respectively. Additionally, its training efficiency is improved by 28.4% compared to ViT. This study demonstrates that WS-ViT not only enhances UATR performance but also maintains computational efficiency, providing an innovative solution for efficient and accurate underwater acoustic signal processing. Full article

The process of winter bread wheat (WW) nutrient management in the Critical Cereal Window (CCW) has a decisive impact on yield component formation and, consequently, the grain yield (GY) and grain protein content (GPC). This hypothesis was verified in a single-factor field experiment carried out in the 2013/2014, 2014/2015, and 2015/2016 seasons. It consisted of seven nitrogen-fertilized variants: 0, 40, 80, 120, 160, 200, and 240 kg N ha⁻¹. The mass of nutrients in ears was determined in the full flowering stage. The mass balance of nutrients (N, P, K, Mg, Ca, Fe, Mn, Zn, and Cu) was determined in leaves and stems. These sets of data were first used to calculate the soil nutrient uptake and then to predict the GY and GPC. Three nutrients, i.e., N, Ca, and Mg, were the main predictors of ear biomass. The set of ear nutrients significantly predicting GY and GE consisted of Ca, P, and Zn. Overall, this indirectly indicates a balanced N status for the ear. A positive nutrient balance in leaves, indicating their remobilization, was found for N, P, Fe, Zn, and Cu. Negative values, indicating a net nutrient accumulation in the non-ear organs of WW, were found for the remaining nutrients. The greatest impact on the GY and its components was observed for the balance of Mg and P but not N. The predictive worth of the nutrient balance for stems was much lower. The GPC, regardless of the type of indicator, depended solely on the N balance. Meanwhile, the main nutrient sources of N and Fe in ears were leaves and stems due to their uptake from the soil. For Cu, the primary source was soil, completed by its remobilization from leaves. For the remaining nutrients examined, the key source for the ear was soil, which was completed by remobilization from leaves and stems. Mg and Ca differed from other nutrients because their source for ears was exclusively soil. They were invested by WW in the ears and non-ear organs, mainly in the stems. The effective use of the yield potential of WW and other cereals requires insight into the nutritional status of the canopy at the beginning of the booting stage. This knowledge is necessary to develop an effective N management strategy and to correct and possibly apply fertilizers to improve both the yield and the GPC. Full article