Detection Efficiency Research Articles

Automated system for calving time prediction and cattle classification utilizing trajectory data and movement features

Accurately predicting the calving time in cattle is essential for optimizing livestock management and ensuring animal welfare. Our research focuses on developing a robust system for calving cattle classification and calving time prediction, utilizing 12-h trajectory data for 20 cattle. Our system classifies cattle as abnormal (requiring human assistance) or normal (not requiring assistance) and predicts calving times based on their individual behaviors. We employed a tailored YOLOv8 model for efficient and precise cattle detection, effectively filtering out noise such as people and trucks. Our Customized Tracking Algorithm (CTA) maintains continuous identity tracking for each cow, enabling accurate re-identification even during occlusions. To minimize some ID switching errors over extended tracking periods, we integrated IDs optimization in the CTA utilizing Global IDs identification. We extracted and compared three total movement features for classifying cattle as abnormal or normal. For predicting calving times for each cow, we utilized and compared three cumulative movement features. Our system is fully automated, detecting and tracking all 20 cattle continuously for 12 h without manual assistance, and achieving an overall accuracy of 99%. By comparing three features derived from the trajectory tracking data for each point in a frame, we achieve 100%, 95%, 85% accuracy in classifying cattle as abnormal or normal and predict their calving times with a precision of within the next 6 h, within the next 9 h, within the next 8 h, respectively. Our system enables farmers to provide timely assistance, ensuring the health and safety of both the cow and the calf. Furthermore, it aids in optimizing resource allocation and enhancing overall farm efficiency, emphasizing the critical importance of calving time prediction in sustainable livestock farming.

A small underwater object detection model with enhanced feature extraction and fusion

In the underwater domain, small object detection plays a crucial role in the protection, management, and monitoring of the environment and marine life. Advancements in deep learning have led to the development of many efficient detection techniques. However, the complexity of the underwater environment, limited information available from small objects, and constrained computational resources make small object detection challenging. To tackle these challenges, this paper presents an efficient deep convolutional network model. First, a CSP for small object and lightweight (CSPSL) module is introduced to enhance feature retention and preserve essential details. Next, a variable kernel convolution (VKConv) is proposed to dynamically adjust the convolution kernel size, enabling better multi-scale feature extraction. Finally, a spatial pyramid pooling for multi-scale (SPPFMS) method is presented to preserve the features of small objects more effectively. Ablation experiments on the UDD dataset demonstrate the effectiveness of the proposed methods. Comparative experiments on the UDD and DUO datasets demonstrate that the proposed model delivers the best performance in terms of computational cost and detection accuracy, outperforming state-of-the-art methods in real-time underwater small object detection tasks.

Polydopamine-encapsulated carbon dots to boost analytical performance for microplastics detection in fluorescence mode.

Akind of sulfur-doped carbon dots was preparedwhich were encapsulated with polydopamine (S-CDs@PDA) that has fluorescence response on polyethylene (PE) microplastics (MPs). Modified membranes were constructed using S-CDs@PDA for MP detection. Through heating and vacuum filtration process, yellow emission from the modified membrane appeared because of the combination between S-CDs@PDA and PE MPs. Notably, the fluorescence signal value of PE MPs detected by S-CDs@PDA-modified membrane was 21.3% higher than that of unmodifiedS-CDs membrane, and the detection efficiency was 8% higher than that of S-CDs membrane. The minimum detection limit for modified membranes was 4mg. Due to the good adhesion of polydopamine (PDA), S-CDs@PDA-modified membrane was more easily adhered to PE MPs, showing its excellent detection ability. The rapid quantitative detection of PE MPs in 10min was realized with a linear equation of y = 3081x + 3686.1 in a linear range of 4-14mg. Such modified membrane exhibited excellent anti-photobleaching using continuous 365-nm excitation and its sensing performance was further confirmed in sea and river water samples. S-CDs@PDA could detect solid MP powders as well as MPs dispersed in liquids. The detection method constructed with a modified glass fiber filter membrane enables rapid identification and quantitative detection of PE MPs without relying on large-scale instrumentation. This study provided research ideas for fluorescent tracing of PE MPs and paved the way for quantitative detection of micron-sized plastics with smaller particle sizes.

Efficient adsorption and detection of steroid hormones in foods through the combination of novel magnetic TAPB-COF materials with click isotope probes.

Matrix effects pose a significant challenge in food analysis for the quantitative analysis of complex food samples. Herein, a novel magnetic covalent organic framework nanocomposite and the copper(I)-catalyzed azide-alkyne cycloaddition (CuAAC) click reaction-based stable isotope labeling (SIL) method were presented for highly selective and sensitive detection of steroid hormones in food samples using HPLC-MS/MS. The nanocomposite, Fe3O4@TAPB-COF, with acore-shell structure exhibited high adsorption capacities for steroid hormones. Combined with a SIL method based on the CuAAC click reaction, steroid hormones were accurately quantified in food samples with high sensitivity and selectivity. A pair of SIL agents, N-(2-azidoethyl)aniline (d0-NAEA) and d5-N-(2-azidoethyl)aniline (d5-NAEA), was synthesized to label steroid hormones in the samples and standard solutions, respectively. The labeling reaction is highly specific, and the formation of the derivatives is easily ionized by MS, thus overcoming matrix effects. More surprisingly, the ionization efficiency of steroid hormones increased by a factor of 4 to 56, with matrix effects ranging from 87.3 to 99.3%. Under optimal conditions, this method exhibited a low limit of detection (LOD) ranging from 0.1 to 2.6 μg L-1 and overcame the interference of matrix effects for trace-level steroid hormone analysis in foodstuffs.

Classification and Analysis of Agaricus bisporus Diseases with Pre-Trained Deep Learning Models

This research evaluates 20 advanced convolutional neural network (CNN) architectures for classifying mushroom diseases in Agaricus bisporus, utilizing a custom dataset of 3195 images (2464 infected and 731 healthy mushrooms) captured under uniform white-light conditions. The consistent illumination in the dataset enhances the robustness and practical usability of the assessed models. Using a weighted scoring system that incorporates precision, recall, F1-score, area under the ROC curve (AUC), and average precision (AP), ResNet-50 achieved the highest overall score of 99.70%, demonstrating outstanding performance across all disease categories. DenseNet-201 and DarkNet-53 followed closely, confirming their reliability in classification tasks with high recall and precision values. Confusion matrices and ROC curves further validated the classification capabilities of the models. These findings underscore the potential of CNN-based approaches for accurate and efficient early detection of mushroom diseases, contributing to more sustainable and data-driven agricultural practices.

EFE-UNet: efficient detection of tunnel cracks under seam linear interference and multiscale crack differences

EFE-UNet: efficient detection of tunnel cracks under seam linear interference and multiscale crack differences

A novel machine learning model for screening the risk of obstructive sleep apnea using craniofacial photography with questionnaires.

Undiagnosed or untreated moderate to severe obstructive sleep apnea (OSA) increases cardiovascular risks and mortality. Early and efficient detection is critical, given its high prevalence. We aimed to develop a practical and efficient approach for obstructive sleep apnea screening, using simple facial photography and sleep questionnaires. We retrospectively included 748 participants who completed polysomnography, sleep questionnaires (STOP-BANG, SBQ), and facial photographs at a university hospital between 2012 and 2023. Owing to class imbalance, we randomly undersampled the participants, categorized into the moderate/severe or no/mild OSA group, based on an apnea-hypopnea index of 15 events/h. Using a validated convolutional neural network, we extracted the OSA probability scores from photographs, which were used as the input for the questionnaires. Four machine learning models were employed to classify the moderate/severe versus no/mild groups and evaluated in the test dataset. We analyzed 426 participants (213 each in the moderate/severe and no/mild groups). The mean (standard deviation) age was 44.6 (14.7) years; 80.8% were men. Logistic regression achieved the highest performance: the area under the receiver operator curve was 97.2%, and accuracy was 91.9%. Adding OSA probability, retrieved from facial photographs, to the questionnaires improved performance, compared with using questionnaires or photographs alone (area under the receiver operator curve: 97.2%, 64% and 79.1% for threshold SBQ 3 and 4, and 85.7%, respectively). Using simple facial photographs and sleep questionnaires, a two-stage approach (convolutional neural network + machine learning) accurately classified OSA into moderate/severe versus no/mild OSA groups. This method may facilitate optimal OSA treatment and avoid unnecessary costly evaluations.

Cesium-Based Molecular Perovskites With Superior Stability for High-Performance X-Ray Detection.

Metal-free molecular perovskites have shown great potential for X-ray detection due to their tunable chemical structures, low toxicity, and excellent photophysical properties. However, their limited X-ray absorption and environmental instability restrict their practical application. In this study, cesium-based molecular perovskites (MDABCO-CsX3, X = Cl, Br, I) are developed by introducing Cs+ at the B-site to enhance X-ray absorption while retaining low toxicity. The effects of halide modulation on the physical properties and device performance are systematically investigated. Among the variants, MDABCO-CsBr3 exhibited superior environmental stability, attributed to the optimal ionic radius and high chemical stability of Br-. This stability is further enhanced by a higher tolerance factor, which promotes a stable 3D cubic structure and suppresses ion migration within the crystal. Consequently, MDABCO-CsBr3-based X-ray detectors demonstrated reduced ionic migration, minimal dark current drift, and a stable current response under X-ray exposure, achieving a high sensitivity of 4124 µC Gy-1 cm-2 and a low detection limit of 0.45 µGy s-1. Moreover, the devices exhibit excellent thermal stability, operating effectively at temperatures up to 130 °C. These results highlight MDABCO-CsBr3 as a promising candidate for stable and efficient X-ray detection, expanding the applicability of molecular perovskites in advanced radiation detection technologies.

PEPPI-MS: gel-based sample pre-fractionation for deep top-down and middle-down proteomics.

Top-down analysis of intact proteins and middle-down analysis of proteins subjected to limited digestion require efficient detection of traces of proteoforms in samples, necessitating the reduction of sample complexity by thorough pre-fractionation of the proteome components in the sample. SDS-PAGE is a simple and inexpensive high-resolution protein-separation technique widely used in biochemical and molecular biology experiments. Although its effectiveness for sample preparation in bottom-up proteomics has been proven, establishing a method for highly efficient recovery of intact proteins from the gel matrix has long been a challenge for its implementation in top-down and middle-down proteomics. As a much-awaited solution to this problem, we present an experimental protocol for efficient proteoform fractionation from complex biological samples using passively eluting proteins from polyacrylamide gels as intact species for mass spectrometry (PEPPI-MS), a rapid method for extraction of intact proteins separated by SDS-PAGE. PEPPI-MS allows recovery of proteins below 100 kDa separated by SDS-PAGE in solution with a median efficiency of 68% within 10 min and, unlike conventional electroelution methods, requires no special equipment, contributing to a remarkably economical implementation. The entire protocol from electrophoresis to protein purification can be performed in <5 h. By combining the resulting PEPPI fraction with other protein-separation techniques, such as reversed-phase liquid chromatography and ion mobility techniques, multidimensional proteome separations for in-depth proteoform analysis can be easily achieved.

Artificial intelligence in financial auditing: improving efficiency and addressing ethical and regulatory challenges

Artificial Intelligence has been increasingly reshaping the face of financial auditing for improved efficiency and effectiveness in fraud detection, serving also to strengthen stakeholder trust. This study examines the impact of adopting AI on audit practices, in terms of effectiveness in improving efficiency, fraud detection, ethical challenges, regulatory barriers, and stakeholder trust. In this paper, 460 professional auditors, accountants, and organizational stakeholders have been analyzed using descriptive statistics, correlation, regression, and structural equation modeling. The results indicate that AI has a positive influence on efficiency, value creation, and fraud detection ability, while positively influencing stakeholder trust in organizations. However, ethical concerns from algorithmic bias to a lack of transparency and regulatory risks associated with compliance through data protection laws are also significant barriers. It thus concludes that AI has a enormous potential in revolutionizing auditing practices, and that addressing these barriers through training, transparent AI models, ethical safeguards, and supportive regulatory frameworks is also very important for its widespread adoption. Recommendations and future research avenues are presented to guide the responsible integration of AI into the auditing profession.

Advances and Challenges in Small Object Detection: A Comparative Analysis of State-of-the-Art Models and Future Directions

Object detection involves the precise and efficient identification and localization of multiple predefined object categories within images. With the advent of deep learning, both the accuracy and efficiency of object detection have significantly improved. Nevertheless, challenges remain in optimizing the performance of mainstream detection algorithms, improving the accuracy of small object detection, enabling multi-class detection, and developing lightweight models. In response to these challenges, this paper provides a comprehensive literature review, analyzing approaches to enhance mainstream object detection by exploring advancements in backbone networks, expanding the visual receptive field, feature fusion, and various training strategies. We also evaluate the performance of leading detection models across established datasets, identifying current limitations and proposing future research directions. These directions include enhancing small object representation in datasets, enriching semantic information, and improving model interpretability. Small object detection remains a critical focus in computer vision, and we anticipate the continued development of algorithms with higher accuracy and efficiency

LightweightUNet: Multimodal Deep Learning with GAN-Augmented Imaging Data for Efficient Breast Cancer Detection

Breast cancer ranks as the second most prevalent cancer globally and is the most frequently diagnosed cancer among women; therefore, early, automated, and precise detection is essential. Most AI-based techniques for breast cancer detection are complex and have high computational costs. Hence, to overcome this challenge, we have presented the innovative LightweightUNet hybrid deep learning (DL) classifier for the accurate classification of breast cancer. The proposed model boasts a low computational cost due to its smaller number of layers in its architecture, and its adaptive nature stems from its use of depth-wise separable convolution. We have employed a multimodal approach to validate the model’s performance, using 13,000 images from two distinct modalities: mammogram imaging (MGI) and ultrasound imaging (USI). We collected the multimodal imaging datasets from seven different sources, including the benchmark datasets DDSM, MIAS, INbreast, BrEaST, BUSI, Thammasat, and HMSS. Since the datasets are from various sources, we have resized them to the uniform size of 256 × 256 pixels and normalized them using the Box-Cox transformation technique. Since the USI dataset is smaller, we have applied the StyleGAN3 model to generate 10,000 synthetic ultrasound images. In this work, we have performed two separate experiments: the first on a real dataset without augmentation and the second on a real + GAN-augmented dataset using our proposed method. During the experiments, we used a 5-fold cross-validation method, and our proposed model obtained good results on the real dataset (87.16% precision, 86.87% recall, 86.84% F1-score, and 86.87% accuracy) without adding any extra data. Similarly, the second experiment provides better performance on the real + GAN-augmented dataset (96.36% precision, 96.35% recall, 96.35% F1-score, and 96.35% accuracy). This multimodal approach, which utilizes LightweightUNet, enhances the performance by 9.20% in precision, 9.48% in recall, 9.51% in F1-score, and a 9.48% increase in accuracy on the combined dataset. The LightweightUNet model we proposed works very well thanks to a creative network design, adding fake images to the data, and a multimodal training method. These results show that the model has a lot of potential for use in clinical settings.

Enhanced broadband quantum efficiency in LWIR T2SL detectors with guided-mode resonance structure

Type-II superlattice (T2SL) detectors are emerging as key technologies for next-generation long-wavelength infrared (LWIR) applications, particularly in the 8–14 µm range, offering advantages in space exploration, medical imaging, and defense. A major challenge in improving quantum efficiency (QE) lies in achieving sufficient light absorption without increasing the active layer (AL) thickness, which can elevate dark current and complicate manufacturing. Traditional methods, such as thickening the absorber, are limited by the short carrier lifetime in T2SLs, necessitating alternative solutions. In this study, we introduced a guided-mode resonance (GMR) structure into T2SL LWIR detectors to enhance QE while maintaining a thin AL for efficient carrier collection. The GMR structure was fabricated by introducing a grating array on the surface of the detector and an Au mirror beneath the absorber. This configuration enhanced light trapping, which introduced additional resonance modes. The optimized grating design, with a 5 µm period and a fill factor of 0.6, significantly increased absorption, as predicted by finite-difference time-domain (FDTD) simulations and confirmed experimentally. The GMR-enhanced T2SL detector demonstrated a 2.58-fold improvement in QE over conventional LWIR detectors and a 1.33-fold increase compared to Fabry-Pérot (FP) resonance-based detectors in the 6–11 µm range. Despite exhibiting an almost identical dark current density, the GMR LWIR detector demonstrated superior performance, featuring a broader cut-off wavelength of 9.3 µm and higher QE compared to FP LWIR detectors.

Application of Convolutional Neural Networks and Recurrent Neural Networks in Food Safety

This review explores the application of convolutional neural networks (CNNs) and recurrent neural networks (RNNs) in food safety detection and risk prediction. This paper highlights the advantages of CNNs in image processing and feature recognition, as well as the powerful capabilities of RNNs (especially their variant LSTM) in time series data modeling. This paper also makes a comparative analysis in many aspects: Firstly, the advantages and disadvantages of traditional food safety detection and risk prediction methods are compared with deep learning technologies such as CNNs and RNNs. Secondly, the similarities and differences between CNNs and fully connected neural networks in processing image data are analyzed. Furthermore, the advantages and disadvantages of RNNs and traditional statistical modeling methods in processing time series data are discussed. Finally, the application directions of CNNs in food safety detection and RNNs in food safety risk prediction are compared. This paper also discusses combining these deep learning models with technologies such as the Internet of Things (IoT), blockchain, and federated learning to improve the accuracy and efficiency of food safety detection and risk warning. Finally, this paper mentions the limitations of RNNs and CNNs in the field of food safety, as well as the challenges in the interpretability of the model, and suggests the use of interpretable artificial intelligence (XAI) technology to improve the transparency of the model.

Clinical Performance of MAGLUMI Diagnostic Tests for the Automated Detection of Dengue Virus

Aims: The screening and diagnosis of dengue virus infection play a crucial role in controlling the epidemic of dengue fever, highlighting the urgent need for a highly sensitive, simple, and rapid laboratory testing method. This study aims to assess the clinical performance of MAGLUMI Denv NS1 in detecting dengue virus NS1 antigen. Methods: A retrospective study was conducted to assess the sensitivity and specificity of MAGLUMI Denv NS1 using residual samples. Dengue-confirmed and excluded samples, validated by qPCR, were subjected to testing with MAGLUMI Denv NS1 in accordance with the manufacturer’s instructions. The linear range, endogenous interference, and cross-reactivity of MAGLUMI Denv NS1 were verified, and a consistency analysis with commercial comparator products was carried out. Results: The diagnostic specificity of MAGLUMI Denv NS1 is 98.41% (62/63), and the sensitivity is 98.32% (117/119). It effectively detects various serotypes of dengue virus, with no observed endogenous interference or cross-reactivity. Additionally, the consistency of NS1, IgM, and IgG tests on the MAGLUMI platform compared to commercial comparator reagents reaches 85.71%, 99.25%, and 98.97%, respectively. Conclusions: The MAGLUMI Denv NS1 represents a highly sensitive laboratory testing method capable of enhancing the diagnostic accuracy and efficiency of dengue virus infection detection.

Thermal imaging-based fault detection and energy efficiency analysis in a 1.6 MW photovoltaic system in Bağyurdu OIZ, Türkiye

The present study assesses the influence of thermal imaging defect detection on the energy efficiency of a 1.6 MW solar power facility in the Bağyurdu Organized Industrial Zone (OIZ) in İzmir, Turkey. Thermal imaging has demonstrated efficacy in detecting serious problems in photovoltaic (PV) panels, including hot spots, inoperative modules, faulty connections, and shadowing, which substantially impact system performance. A comprehensive investigation revealed that around 15% of the photovoltaic panels displayed defects, resulting in a 16% decrease in system performance and an estimated yearly energy loss of 0.35 GWh. The study emphasizes the benefits of thermal imaging compared to conventional fault detection techniques, including its capacity for swift and non-invasive identification of localized overheating, which may lead to fires, and its ability to discern fluctuations in energy output due to shading or malfunctioning modules. The results underscore the necessity for routine thermal evaluations and maintenance to guarantee photovoltaic systems’ operational efficacy and dependability. This study enhances the sparse data on large-scale photovoltaic systems in Türkiye and illustrates the effectiveness of thermal imaging as an economical and accurate diagnostic instrument. Future studies should amalgamate thermal imaging with sophisticated diagnostic techniques, like electroluminescence testing and machine learning, to augment fault detection precision and optimize photovoltaic system efficacy.

All-Optical Generation and Detection of Coherent Acoustic Vibrations in Single Gallium Phosphide Nanoantennas Probed near the Anapole Excitation.

Nanostructured high-index dielectrics have shown great promise as low-loss photonic platforms for wavefront control and enhancing optical nonlinearities. However, their potential as optomechanical resonators has remained unexplored. In this work, we investigate the generation and detection of coherent acoustic phonons in individual crystalline gallium phosphide nanodisks on silica in a pump-probe configuration. By pumping the dielectric above its bandgap energy and probing over its transparent region, we observe the radial breathing mode of the disk with an oscillation frequency around 10 GHz. We find that the detection efficiency peaks near the fundamental anapole state, matching numerical simulations. By comparing to reference gold plasmonic resonators, the dielectric nanoantennas display a modulation amplitude up to ∼5 times larger. We further demonstrate the launching of acoustic waves through the underlaying substrate and the mechanical coupling between two nanostructures placed 3 μm apart, laying the basis for photonic-phononic signal processing using dielectric nanoantennas.

Detection Method of Key Ship Parts Based on YOLOv11

The current ship target detection algorithm is not adaptable to changes in target size and position, and its detection accuracy and speed are difficult to balance in the process of algorithm improvement. In particular, there is little research on the detection of key parts of ships. In this paper, an improved YOLOv11 ship key location detection algorithm is proposed. It is difficult to balance the relationship between detection efficiency and model complexity using current key parts detection algorithms. The processing performance of deforming key parts according to the algorithms is not strong. Moreover, the algorithms’ detection performance of occluding overlapping targets and small-size targets is not high. In view of the practical problems existing in the algorithms and the realistic demand for real-time and accurate detection of key parts of targets on dynamic ships at sea, three aspects of improvement on YOLOv11 are proposed. The visible light ship key position dataset is then constructed for the experiment. The experimental results show that the improved YOLOv11 network in this paper can detect the key position information of ships more accurately and efficiently, effectively balance the relationship between model accuracy and speed, overcome the interference of dynamic factors, improve the fine interpretation of dynamic ship information at sea, and provide a feasible technical approach for accurately and precisely mastering ship information at sea and realizing real-time sea area detection.

A Face Fatigue Detection Model for Edge Information Extraction

In contemporary society, fatigue driving is a major cause of traffic accidents, making accurate and timely detection critical for improving driving safety. In this study, we propose a novel fatigue detection model, CSA-YOLO, designed to enhance the accuracy and efficiency of facial fatigue detection. The model is based on the YOLOv9s network model and introduces several key improvements to address the limitations of traditional methods, which often lose critical edge information. First, the Cross-Stage Partial Network (C3 module) replaces the RepNCSPELAN4 module to enhance the model’s ability to extract edge information effectively. Second, the incorporation of the SimAM attention mechanism improves feature selection, while the Content-Aware ReAssembly of Features (CARAFE) upsampling operator enhances the quality of reconstructed image details. Experimental results demonstrate that the proposed CSA-YOLO model achieves significant performance improvements, with a 2.24% increase in accuracy, a 2.58% improvement in recall, and a 2.44% boost in mAP compared to the original YOLOv9s model. These results highlight the model’s potential for practical application in reducing the risks of fatigue-related accidents.

Smart Defect Detection in Aero-Engines: Evaluating Transfer Learning with VGG19 and Data-Efficient Image Transformer Models

This study explores the impact of transfer learning on enhancing deep learning models for detecting defects in aero-engine components. We focused on metrics such as accuracy, precision, recall, and loss to compare the performance of models VGG19 and DeiT (data-efficient image transformer). RandomSearchCV was used for hyperparameter optimization, and we selectively froze some layers during training to help better tailor the models to our dataset. We conclude that the difference in performance across all metrics can be attributed to the adoption of the transformer-based architecture by the DeiT model as it does this well in capturing complex patterns in data. This research demonstrates that transformer models hold promise for improving the accuracy and efficiency of defect detection within the aerospace industry, which will, in turn, contribute to cleaner and more sustainable aviation activities.