Method For Automatic Identification Research Articles

Brain tumor detection model based on CNN and threshold segmentation

Brain tumours pose a substantial global health issue, emphasising the criticality of timely and precise identification to ensure optimal treatment outcomes. This research introduces an innovative methodology for the identification of brain tumours by employing a fusion of Convolutional Neural Networks (CNNs) with threshold segmentation techniques. The objective of the suggested model is to improve the precision and effectiveness of brain tumour identification in medical imaging, namely Magnetic Resonance Imaging (MRI) scans. Fast and precise diagnosis is necessary in the medical profession for effective treatment, but current technologies lack this capability. For successful therapy, it is therefore necessary to develop an effective diagnosis application. Global threshold segmentation for pre-processing is used in this study. Image capture and de-noising were completed in the first stage, while classification and regression were completed in the second stage using ML approaches. A computer-aided automated identification method is the computational technique used in this study. This investigation uses one hundred twenty (120) brain scans from a real-time MRI brain database, of them 15 normal and 105 abnormal. According to performance metrics, the accuracy of training and testing pictures was 99.46%. Comparing this method to recently published methods, it is determined that LR-ML with the threshold segmentation has a rapid, precise brain diagnostic system.

A method for automatic identification and separation of wildlife images using ensemble learning

Camera traps have revolutionized wildlife resource surveys by enabling the acquisition of comprehensive ecosystem information. Camera traps usually produce massive images. Snapshot datasets captured in nature reserves proximate to human habitation often comprise a significant volume of human activity images containing humans or livestock. Manually identifying and labeling wildlife images from large-scale datasets is a labor-intensive task that necessitates a substantial number of professionals and incurs expensive personnel costs. By harnessing the capabilities of deep learning technology to automatically differentiate between wildlife and human activity images, ecologists can solely focus on manually labeling wildlife images that account for a minor fraction of the dataset. This strategic shift can significantly reduce personnel expenses and enhance work efficiency. Existing research usually treats human activity images as ordinary categories and utilizes species recognition methods to automatically identify and filter them. However, when human activity images overwhelmingly predominate the dataset, established species recognition methods are susceptible to misclassifying a substantial proportion of wildlife images as human activity images. This misclassification can potentially result in ecologists missing opportunities to discover or observe wildlife. To tackle this challenge, we proposed an ensemble learning method based on a conservative strategy and current mainstream deep learning frameworks to automatically identify wildlife and human activity images. We validated our method on a camera trap dataset from Lasha Mountain (LSM) in Yunnan, China. The experimental results demonstrated that our method automatically identified wildlife images from the dataset with accuracy, recall, and precision of 95.75%, 94.07%, and 83.89%, respectively. This led to an approximately 80% reduction in personnel costs.

High-order features of a single linear corneal laceration image are valuable biomarkers in an intelligent multimodal analytic strategy for corneal laceration reconstruction

BackgroundIn corneal lacerations, the absence of high-order image features as biomarkers to guide surgical strategy is a limiting factor. The absence of multimodal data restricts the development of automated reconstruction designs for corneal laceration. The present study is aimed at training and optimizing the model based on high-order features from corneal laceration images and real suture samples and completing the intelligent promotion of whole corneal laceration suture auxiliary decision-making with the two-step method of automatic wound identification and stitch position prediction. MethodsBased on the images of isolated corneal wound samples, a fully supervised U-Net learning method and consistent regular semisupervised learning method based on the mean-teacher model were used to identify the wounds. The DDice coefficient was used to evaluate the segmentation and recognition effect. Traditional image processing technology was used to predict the needle entry and exit points of wound sutures based on medical suture principles. The prediction effect was evaluated by viewpoint similarity. ResultsAfter training the wound recognition model based on 2400 corneal images and corresponding incision labels, the DDice coefficients of supervised U-Net with or without postprocessing results were 0.902 and 0.817, respectively. The Dice coefficients of the semisupervisedmean-teacher model with or without postprocessing were 0.921 and 0.843, respectively. The key point similarity of wound stitch position prediction was 0.872 ± 0.021. ConclusionThis new automated method for corneal laceration identification and stitch position generation based on novel biomarkers and multimodal data is expected to assist doctors treating corneal lacerations to quickly formulate a primary suturing strategy.

Automatic identification method of bridge structure damage area based on digital image

It is of great scientific and practical value to use effective technical means to monitor and warn the structural damage of bridges in real time and for a long time. Traditional image recognition network models are often limited by the lack of on-site images. In order to solve the problem of automatic recognition and parameter acquisition in digital images of bridge structures in the absence of data information, this paper proposes an automatic identification method for bridge structure damage areas based on digital images, which effectively achieves contour carving and quantitative characterization of bridge structure damage areas. Firstly, the digital image features of the bridge structure damage area are defined. By making full use of the feature that the pixel value of the damaged area is obviously different from that of the surrounding image, an image pre-processing method of the structure damaged area that can effectively improve the quality of the field shot image is proposed. Then, an improved Ostu method is proposed to organically fuse the global and local threshold features of the image to achieve the damaged area contour carving of the bridge structure surface image. The scale of damage area, the proportion of damage area and the calculation rule of damage area orientation are constructed. The key inspection and characteristic parameter diagnosis of bridge structure damage area are realized. Finally, test and analysis are carried out in combination with an actual project case. The results show that the method proposed in this paper is feasible and stable, which can improve the damage area measurement accuracy of the current bridge structure. The method can provide more data support for the detection and maintenance of the bridge structure.

Development and validation of a specialized system for self-tapping medical bone screw testing.

A specialized system for accurate self-tapping medical bone screw testing is developed, fully meeting the requirements of ASTM F543-A4 (YY/T 1505-2016). The onset of self-tap is identified automatically according to a change in the slope of the torque curve. Precise load control is applied to determine the self-tapping force accurately. A simple mechanical platform is embedded to ensure the automatic axial alignment of a tested screw with the pilot hole in a test block. In addition, comparative experiments are conducted on different self-tapping screws to verify the system's effectiveness. By the automatic identification and alignment method, both torque curves and axial force curves for each screw exhibit significant consistency. The self-tapping time point derived from the torque curve agrees well with the turning point of the axial displacement curve. The determined self-tapping forces' mean values and standard deviations are both small, which are proved to be effective and accurate in the insertion tests. This work contributes to improving the standard test method for accurate determination of the self-tapping performance of medical bone screws.

Lunar Dome Detection Method Based on Few-Shot Object Detection

Lunar domes have always been one of the important windows to understand lunar volcanic activities, but traditional geological dome identification methods are costly. This study attempts to establish an automatic identification method for lunar volcanic domes through FSOD (Few-Shot Object Detection). Since our previous research has been trying to automatically identify lunar volcanic hills using traditional recognition algorithms, our team will try Few-Shot Object Detection this time. In this study, the researchers first obtained the dome coordinates from the list of known lunar domes and intercepted the data this research need from the corresponding coordinates on the DEM moon images. Subsequently, this research used the existing data to train six traditional recognition algorithms and FSOD and compared their performance to verify the feasibility of this study. This research use AP50 and AP75 to evaluate the performance of the model. Finally, this research found that the AP50 of FSOD can reach 0.76, and the AP75 can reach 0.43. However, although FSOD does perform better than other traditional identification methods, this research believe its accuracy is still far from our expectations. Admittedly, compared with YOLO v5, the performance of FSOD has not been significantly improved, but this study still verifies that it is feasible to apply FSOD to the identification of lunar volcanic domes.

Rapid Identification and Location of Defects behind Tunnel Lining Based on Ground-Penetrating Radar

Ground-penetrating radar (GPR) is a mainstream tool to detect defects behind tunnel linings, but the difficulty in interpreting GPR signals limits its application. This paper proposes an intelligent way to differentiate the defects behind tunnel linings by means of a model test and feature parameter analysis, to achieve an efficient and accurate analysis of GPR signals. The model test reveals the differences between defect and non-defect GPR data in amplitude, signal entropy, standard deviation, and other feature parameters. The amplitude of the defect data was on average six times as large as that of non-defect data, and the signal entropy was about 1.2 times larger. The two feature parameters lay the basis for defect detection by GPR. On this basis, a GPR-based automatic identification method was proposed, and the program was compiled on MATLAB. The program achieved a defect recognition rate as high as 96% through a field test at a rapid speed. The program is highly accurate and feasible for detecting defects behind tunnel linings with the aid of GPR.

Identification and classification for multiple cyber attacks in power grids based on the deep capsule CNN

Cyber-attacks have become one of the main threats to the security, reliability, and economic operation of power systems. Detection and classification of multiple cyber-attacks pose challenges for ensuring the stability and security of power systems. To address this issue, this study proposes an automatic identification and classification method for multiple cyber-attacks based on the deep capsule convolution neural network. Spatial correlations among different nodes and temporal features from history operation status in the transmitted data packets are extracted by the convolution neural network. Capsules in the proposed structure have important implications for maintaining the topological consistency contained in the measurement matrix. Furthermore, the proposed method is model-free and avoids the impact of system parameters uncertainties on detection performance. Multiple kinds of typical cyber-attacks, including false data injection attacks, replay attacks, denial of service attacks, time-delay attacks, and deception attacks, are considered and modeled in this paper. Numerical results on the IEEE 39-bus test system show that the proposed method can achieve 99.97% detection accuracy on single cyber-attacks and 96.25% detection accuracy on multiple cyber-attacks. Comparative results illustrate the proposed method outperforms than traditional neural networks. This approach provides a solution for the problem of multiple cyber-attack detection and classification.

A depth information-based method to enhance rainfall-induced landslide deformation area identification

Accurately recognizing landslide deformation regions is important for understanding the mechanisms of landslides and predicting landslide disasters. Using slopes in Dayu County, China, as the research background, this paper simulates slopes using a similar test model test and proposes a new method of automatic identification based on depth information. By comparing the depth information of the initial point cloud with that of the landslide point cloud, the landslide deformation area is preliminarily extracted. The preliminarily extracted landslide deformation area is oversegmented by the k-means clustering algorithm. The slope equation fitted with the initial point cloud data is used to distinguish each segmentation block, and the error caused by the initial segmentation is removed to obtain the final recognition result. For validation, 12 images of landslides were quickly identified. The identification time was approximately 281 s. The average relative error of the method in the X and Y directions is 2.34 % and 0.71 %, respectively. The traditional two-dimensional recognition method, on the other hand, has a recognition time of approximately 720 s; the average relative errors in the X and Y directions are 6.61 % and 3.90 %, respectively. The advantages of our method are listed as follows: 1) It improves the segmentation quality of the landslide deformation area, especially in the deformation boundary. 2) Landslide areas with similar colors but large depth variation can be more accurately identified by using depth information. 3) It has the characteristics of real-time monitoring and fast operation. In addition, the new method is used to identify the area and volume of the landslide in the three states, and the results are in accordance with the theory.

Deep Learning-Based Image Classification for Major Mosquito Species Inhabiting Korea.

Mosquitoes are one of the deadliest insects, causing harm to humans worldwide. Preemptive prevention and forecasting are important to prevent mosquito-borne diseases. However, current mosquito identification is mostly conducted manually, which consumes time, wastes labor, and causes human error. In this study, we developed an automatic image analysis method to identify mosquito species using a deep learning-based object detection technique. Color and fluorescence images of live mosquitoes were acquired using a mosquito capture device and were used to develop a deep learning-based object detection model. Among the deep learning-based object identification models, the combination of a swine transformer and a faster region-convolutional neural network model demonstrated the best performance, with a 91.7% F1-score. This indicates that the proposed automatic identification method can be rapidly applied for efficient analysis of species and populations of vector-borne mosquitoes with reduced labor in the field.

ScLiverDB: a Database of Human and Mouse Liver Transcriptome Landscapes at Single-Cell Resolution.

The liver is critical for the digestive and immune systems. Although the physiology and pathology of liver have been well studied and many scRNA-seq data are generated, a database and landscape for characterizing cell types and gene expression in different liver diseases or developmental stages at single-cell resolution are lacking. Hence, scLiverDB is developed, a specialized database for human and mouse liver transcriptomes to unravel the landscape of liver cell types, cell heterogeneity and gene expression at single-cell resolution across various liver diseases/cell types/developmental stages. To date, 62 datasets including 9,050 samples and 1,741,734 cells is curated. A uniform workflow is used, which included quality control, dimensional reduction, clustering, and cell-type annotation to analyze datasets on the same platform; integrated manual and automatic methods for accurate cell-type identification and provided a user-friendly web interface with multiscale functions. There are two case studies to show the usefulness of scLiverDB, which identified the LTB (lymphotoxin Beta) gene as a potential biomarker of lymphoid cells differentiation and showed the expression changes of Foxa3 (forkhead box A3) in liver chronic progressive diseases. This work provides a crucial resource to resolve molecular and cellular information in normal, diseased, and developing human and mouse livers.

Methods and models of organization and processing of data and knowledge in an intelligent decision support system for the identification of cultural values

The problem of developing an intellectual decision support system for the identification of cultural values (on the basis of works of art), the issue of choosing and justifying methods and tools for its construction is considered. Methods of research and construction of complex objects, prospects of using similar systems based on modern artificial neural networks as a tool for developing an intelligent decision support system are considered. Considerable attention is paid to the issues of methods of automatic identification and classification of works of art, as the main elements of an intelligent decision support system. Prospects and ways of further research and use of this subject area are also defined.

Maize seedling information extraction from UAV images based on semi-automatic sample generation and Mask R-CNN model

ContextThe emergence rate and growth of maize seedlings are crucial for variety selection and farm managers; however, the complex planting environment and seedling morphological differences pose great challenges for seedling detection. ObjectiveThis study aims to rapidly quickly and accurately extract maize seedling information in the field environment based on UAV images with reduced labor cost. MethodsIn this paper, we proposed an automatic identification method for maize seedlings adapted to complex scenarios (different varieties and different seedling development stages) by fine-tuning the Mask R-CNN model. Aiming at the difficulty of obtaining the training data required by the deep learning algorithm, this paper proposes a semi-automatic labeling method for the deep learning sample data of maize seedlings. At last, we proposed a method to identify the locations of disrupted monopoly and extract seedling information such as coverage and seedling area uniformity, the mapping covers the whole experimental field. Results and conclusionsThis paper includes a discussion on the effect of real flight data and resampling data on model detection results. Indeed, the results show that the identification precision of the real flight data under the same resolution is lower than that of the resampled data. The detection precision of the model decreased as the spatial resolution decreased. To ensure AP@ 0.5IOU above 0.8, the minimum image spatial resolution is 2.1 cm. We finally selected a model which had the training data with a spatial resolution of 0.8 cm in 2019 and the average precision AP@0.5IOU was 0.887, the average accuracy of emergence rate monitoring in 2019 was 98.87 % and migration to 2020 is 95.70 %, 2021 is 98.77 %. SignificanceThis work can quickly and effectively extract maize seedlings, and provide accurate seedling information, which can provide support for timely supplementation and subsequent seed selection.

SE_SPnet: Rice leaf disease prediction using stacked parallel convolutional neural network with squeeze‐and‐excitation

AbstractRice is one of the significant crops, and the early identification and prevention of its diseases are essential to ensure adequate and healthy availability to the world's growing population. The use of image processing is an encouraging method for automatic rice leaf disease identification and detection. In particular, the recent advancements indicate the effectiveness of convolutional neural network (CNN) based deep learning approaches. In this direction, the present work proposes a novel stacked parallel convolution layers‐based network (SPnet) with the squeeze‐and‐excitation (SE) architecture, named (SE_SPnet), for classifying diseased rice leaf images. The stacked parallel network block comprises four parallel convolution layers with different kernel sizes for abstractions of the global and local features. The SE block extracts feature information automatically while removing invalid ones. We compare the SE_SPnet model with state‐of‐the‐art CNN models such as VGG16, DenseNet121, and InceptionV3 based on computational effort, accuracy, sensitivity, specificity, precision, recall, and F1‐score. The experimental results show that the SE_SPnet outperforms standard CNN models for the considered rice leaf disease image datasets. In particular, the SE_SPnet achieves the highest accuracy (99.2%), sensitivity (98.2%), specificity (98.5%), precision (98.4%), recall (98.2%), and F1‐score (98.5%) while using stochastic gradient descent (with momentum) optimizer with a 0.01 learning rate. Furthermore, the SE_SPnet also exhibits to outperform when compared with some of the most recent and relevant existing works.

Image-based methods for automatic identification of elongated and flat aggregate particles

The content of elongated and flat aggregates is a critical detection index in road engineering. In this study, using image sequences of falling aggregates, two multi-view morphological methods were proposed for aggregate shape classification. The multi-view features of the aggregates were constructed by combining multiple single-view features from different views. Furthermore, a joint-view normalization method was proposed to improve the three-dimensional shape characterization capability of the multi-view features. Based on the multi-view features, a support vector machine was adopted to achieve aggregate shape classification. In addition, multiple two-dimensional aggregate morphologies from different views were directionally guided and fused to construct a multi-view image, which could reflect the three-dimensional shape of the aggregates. The multi-view images were then fed into ResNet18 for aggregate-shape classification. Notably, compared with single-view morphological methods based on the aggregate morphology in the vertical and random views, the two multi-view morphological methods developed herein significantly improved the classification accuracy. Moreover, it was found experimentally that increasing the height of the field of view improved the classification accuracy of the multi-view morphological methods. The proposed multi-view morphological methods demonstrate significant potential for application in the automatic identification of elongated and flat aggregates in road construction.

Automatic recognition of slide mass and inversion analysis of landslide based on discrete element method

The slip surface is an important structure for analyzing the landslide mechanism, and it will be deformed by the traction and shear of the slide mass. For the landslide accident without artificial monitoring, if the slip surface can be restored according to the slope morphology before and after the landslide, information such as the safety factor before the damage to the slope and the volume of the slide mass can be obtained by the position of slip surface, which helps engineers to analyze the cause of the landslide. In this paper, an automatic slide mass identification and landslide inversion analysis method based on discrete element simulation is proposed. The method combines Gaussian Mixture Model (GMM), alpha shape algorithm, discrete element simulation, and the morphology of the slope before and after the landslide to invert the slip surface of the slope. This method is suitable for two and three dimensional slope models. In addition, the effect of the slope angle on the deformation of the slip surface is analyzed.

Hyperparameter-tuned batch-updated stochastic gradient descent: Plant species identification by using hybrid deep learning

The accurate identification of plant species is crucial for the conservation of biodiversity. However, traditional methods for identifying plant species are often complicated, time-consuming, and prone to errors. Therefore, it is essential to address these challenges and develop automated identification methods to enhance the efficiency and accuracy of plant species identification. In this study, a step-by-step method was utilized to identify and classify plant species. The dataset was first loaded, and then preprocessing was performed to remove noisy data. Following that, data augmentation was carried out to improve model accuracy. The deep convolutional neural network (CNN) and visual geometry group-16 (VGG-16) were then employed to extract only the relevant features, owing to their efficient learning capabilities. Feature-level fusion was accomplished by utilizing dimensionality reduction, and enhanced Spearman's principal component analysis (ESPCA) was employed to address the overfitting problem, eliminate redundant data, and reduce storage space and training time requirements. For classification, the hyperparameter-tuned batch-updated stochastic gradient descent (HP-BSGD) method was utilized. The Flavia and Swedish datasets were utilized in the experiments. The proposed hybrid classifier yielded excellent results due to its high convergence speed, good computational effectiveness, and high flexibility. To validate the experimental results, performance and comparative analyses were carried out using standard metrics. The analytical results demonstrated the superior efficiency and suitability of the proposed method in the classification of plant species over existing methods. The hybrid method achieved approximately 97% and 98.85% accuracy in the Flavia and Swedish datasets, respectively, when considering combined features. The performance of the proposed method was further enhanced by considering leaves at different stages, such as seedlings, tiny, mature, and dried leaves.

Automatic Identification Method of HPLC Platform Topology Based on Characteristic Data Extraction

The topological structure of distribution network system is complex, and the operation state changes frequently, so the obtained distribution network topological information has a high error. Therefore, this article proposes a clustering feature extraction method of load curve based on singular value decomposition. The load curve is given by the invariance of singular vectors to improve the generalization ability of feature processing. On the basis of considering the weight of load feature, the data integrity is ensured by singular value curve, and the clustering accuracy is high, which makes the load feature have practical physical significance. The experimental results show that this method can achieve good clustering effect, reduce the clustering time, improve the reliability of data transmission and communication coverage, and meet the communication access requirements of the power Internet of Things sensing layer.

Correction to: Automatic lithology identification method based on efficient deep convolutional network

Correction to: Automatic lithology identification method based on efficient deep convolutional network

Prevalence and Antibiotic Resistance of Enterococcus spp.: A Retrospective Study in Hospitals of Southeast Romania

Enterococci cause infections with various localizations, the most common being urinary infections. The purpose of the study was to identify the profile of the antimicrobial resistance of enterococci species (AMRE) isolated from patients hospitalized in three hospitals in Romania. We evaluated AMRE retrospectively (2019–2021) in various biological samples. The microbiological diagnosis was sustained by classical methods of bacteria culture and automatic identification. The sensitivity testing was performed by the Kirby–Bauer method, and the antibiotic minimum inhibitory concentration was tested by the automated Vitek system. We analyzed 86 strains of Enterococcus spp., identifying the following species: 47.7% E. faecalis, 47.7% E. faecium, 3.55% E. gallinarum, and 1% E. hirae. Most of the bacterial strains were isolated from urocultures (38.4%) and hemocultures (32.6%). Overall, the rate of vancomycin resistance was 5.8% for E. faecalis and 15.1%. for E. faecium. The prevalence of multidrug-resistant (MDR) strains was found to be 100% in E. gallinarum, 75.6% in E. faecium, and 21.9% in E. faecalis. The results confirm the high level of AMRE, which creates difficulties with adequate antibiotic prescriptions. The continuous monitoring of AMRE is essential for updating the local diagnostic and treatment protocols for enterococcal infections.