Search

Co-seismic landslide detection is essential for post-disaster rescue and risk assessment after an earthquake event. However, a variety of ground objects, including roads and bare land, have spectral characteristics similar to those of co-seismic landslides, making it difficult to gather information and assess their impact rapidly and accurately. Therefore, an automatic detection method based on a deep learning model, named ENVINet5, with multiple features (ENVINet5_MF) was proposed to solve this problem and improve the detection accuracy of co-seismic landslides. The ENVINet5_MF method is advantageous for co-seismic landslide detection because it features a landslide gain index (LGI) that effectively eliminates the spectral interference of bare land and roads. We conducted two experiments using multi-temporal PlanetScope images acquired in Hokkaido, Japan, and Mainling, China. The accuracy evaluation and rationality analysis show that ENVINet5_MF performed better than comparative methods and that the co-seismic landslide areas detected by ENVINet5_MF were the most consistent with ground reference data. The findings of this study suggest that ENVINet5_MF can provide an efficient and accurate method for coseismic landslide detection to ensure a rapid response to co-seismic landslide disasters. [ABSTRACT FROM AUTHOR]

In order to accurately monitor the environmental information of agricultural greenhouses, achieve remote automatic control, and improve crop yield, the author proposes an application method of Internet of Things technology in automatic intelligent control systems. This method utilizes IoT technologies such as WSN, Android, and cloud platforms to design an intelligent agricultural greenhouse monitoring system, taking sensors such as soil moisture, lighting, temperature and humidity as examples, and using shading, water spraying, fans, and fill lights as control devices. Design from aspects such as system architecture, perception control system, cloud database, and mobile terminal management system to achieve automatic monitoring of agricultural greenhouse environmental information. Experimental results show that: The data collected by the sensor is compared with the actual monitoring data of the instrument, taking temperature as an example, the errors are all within ±0.5°C of multiple measurements. Conclusion: The system has the advantages of good scalability, convenient networking, and high cost performance, which makes up for the difficulties in wiring and inconvenient use of the traditional agricultural greenhouse monitoring system, and has high practical value. [ABSTRACT FROM AUTHOR]

Background: This study evaluates the diagnostic accuracy of an AI-assisted tool in assessing the proximity of the mandibular canal (MC) to the root apices (RAs) of mandibular teeth using computed tomography (CT). Methods: This study involved 57 patients aged 18–30 whose CT scans were analyzed by both AI and human experts. The primary aim was to measure the closest distance between the MC and RAs and to assess the AI tool's diagnostic performance. The results indicated significant variability in RA-MC distances, with third molars showing the smallest mean distances and first molars the greatest. Diagnostic accuracy metrics for the AI tool were assessed at three thresholds (0 mm, 0.5 mm, and 1 mm). Results: The AI demonstrated high specificity but generally low diagnostic accuracy, with the highest metrics at the 0.5 mm threshold with 40.91% sensitivity and 97.06% specificity. Conclusions: This study underscores the limited potential of tested AI programs in reducing iatrogenic damage to the inferior alveolar nerve (IAN) during dental procedures. Significant differences in RA-MC distances between evaluated teeth were found. [ABSTRACT FROM AUTHOR]

Background/Objectives: The purpose of this preliminary study was to evaluate the diagnostic performance of an AI-driven platform, Diagnocat (Diagnocat Ltd., San Francisco, CA, USA), for assessing endodontic treatment outcomes using panoramic radiographs (PANs). Materials and Methods: The study included 55 PAN images of 55 patients (15 males and 40 females, aged 12–70) who underwent imaging at a private dental center. All images were acquired using a Hyperion X9 PRO digital cephalometer and were evaluated using Diagnocat, a cloud-based AI platform. The AI system assessed the following endodontic treatment features: filling probability, obturation adequacy, density, overfilling, voids in filling, and short filling. Two human observers independently evaluated the images, and their consensus served as the reference standard. The diagnostic accuracy metrics were calculated. Results: The AI system demonstrated high accuracy (90.72%) and a strong F1 score (95.12%) in detecting the probability of endodontic filling. However, the system showed variable performance in other categories, with lower accuracy metrics and unacceptable F1 scores for short filling and voids in filling assessments (8.33% and 14.29%, respectively). The accuracy for detecting adequate obturation and density was 55.81% and 62.79%, respectively. Conclusions: The AI-based system showed very high accuracy in identifying endodontically treated teeth but exhibited variable diagnostic accuracy for other qualitative features of endodontic treatment. [ABSTRACT FROM AUTHOR]

Cows mounting behavior is a significant manifestation of estrus in cows. The timely detection of cows mounting behavior can make cows conceive in time, thereby improving milk production of cows and economic benefits of the pasture. Existing methods of mounting behavior detection are difficult to achieve precise detection under occlusion and severe scale change environments and meet real-time requirements. Therefore, this study proposed a Cow-YOLO model to detect cows mounting behavior. To meet the needs of real-time performance, YOLOv5s model is used as the baseline model. In order to solve the problem of difficult detection of cows mounting behavior in an occluded environment, the CSPDarknet53 of YOLOv5s is replaced with Non-local CSPDarknet53, which enables the network to obtain global information and improves the model's ability to detect the mounting cows. Next, the neck of YOLOv5s is redesigned to Multiscale Neck, reinforcing the multi-scale feature fusion capability of model to solve difficulty detection under dramatic scale changes. Then, to further increase the detection accuracy, the Coordinate Attention Head is integrated into YOLOv5s. Finally, these improvements form a novel cow mounting detection model called Cow-YOLO and make Cow-YOLO more suitable for cows mounting behavior detection in occluded and drastic scale changes environments. Cow-YOLO achieved a precision of 99.7%, a recall of 99.5%, a mean average precision of 99.5%, and a detection speed of 156.3 f/s on the test set. Compared with existing detection methods of cows mounting behavior, Cow-YOLO achieved higher detection accuracy and faster detection speed in an occluded and drastic scale-change environment. Cow-YOLO can assist ranch breeders in achieving real-time monitoring of cows estrus, enhancing ranch economic efficiency. [ABSTRACT FROM AUTHOR]

Because of the vast ocean area and the large amount of high-resolution image data, ship detection and data processing have become more difficult. These difficulties can be solved using the artificial intelligence interpretation method. The efficient and accurate detection ability of ship target detection has been widely recognized with the increasing application of deep learning technology. It is widely used in the practice of ship target detection. Firstly, we set up a data set concerning ship targets by collecting and training a large number of images. Then, we improved the YOLO v5 algorithm. The feature specify module (FSM) is used in the improved algorithm. The improved YOLO v5 algorithm was applied to ship detection practice under the framework of Anaconda. Finally, the training results were optimized, and the false alarm rate was reduced. The detection rate was improved. According to the statistics pertaining to experimental results with other algorithm models, the improved YOLO v5 algorithm can effectively suppress conflicting information, and the detection ability of ship details is improved. This work has accumulated valuable experience for related follow-up research. [ABSTRACT FROM AUTHOR]

Cognitive engagement involves mental and physical involvement, with observable behaviors as indicators. Automatically measuring cognitive engagement can offer valuable insights for instructors. However, object occlusion, inter-class similarity, and intra-class variance make designing an effective detection method challenging. To deal with these problems, we propose the Object-Enhanced–You Only Look Once version 8 nano (OE-YOLOv8n) model. This model employs the YOLOv8n framework with an improved Inner Minimum Point Distance Intersection over Union (IMPDIoU) Loss to detect cognitive engagement. To evaluate the proposed methodology, we construct a real-world Students' Cognitive Engagement (SCE) dataset. Extensive experiments on the self-built dataset show the superior performance of the proposed model, which improves the detection performance of the five distinct classes with a precision of 92.5%. [ABSTRACT FROM AUTHOR]

This paper presents an approach to eliminate one of the most common defects in hyperspectral images—the appearance of spiked points at some wavelengths. The elimination of this defect was carried out by means of polynomial regression. The Bayes Information Criterion (BIC) was used to determine the correct order of the polynomial. Comparison between polynomial regression and classical filtration with the Savitsky–Golay method shows the advantage of the proposed approach, from the point of view of eliminating the defect in a local area, without changing the typical behavior of the spectral feature in the affected image pixels. [ABSTRACT FROM AUTHOR]

Copyright of Railway Construction Technology is the property of Railway Construction Technology Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The most frequent left thyroid nodule is the presence of thyroid nodules that have never been seen before. With X-ray computed tomography (CT) being used more often in diagnosing thyroid disorders, however, image processing has not been applied frequently to standard machine learning due to the high density and artefacts found in CT images of the thyroid gland. The last section suggests a Convolutional Neural Network (CNN)-based end-to-end approach for automatic detection and classification of different types of thyroid nodules. The recommended model includes an improved segmentation network that effectively divides the regions within which each nodule may be detected and an image processing technique that optimizes these areas. For example, 98% accuracy was obtained in accurately categorising illness cases by examining aberrant modules of X-rays. According to our study, CNN can accurately detect different degrees of severity caused by nodules located in various parts of the body, thereby providing a means through which this procedure can be done automatically without requiring human intervention all the time. Overall, this study demonstrates how deep learning models may be used to automatically identify and diagnose thyroid nodules using CT imaging, which could increase the precision and effectiveness of diagnosing thyroid disease.

Active infrared thermography (IRT) in non-destructive testing is an attractive technique used to detect wide areas in real-time on site. Most of the objects inspected on site generally have rough surfaces and foreign substances, which significantly affects their detectability. To solve this problem, in this study, line scanning (LS)-based induction thermography was used to acquire thermal image data of a specimen containing foreign substances. The heat distribution caused by foreign substances was removed using the Gaussian filtering-based Fast Fourier Transform (FFT) algorithm. After that, the data augmentation was performed by analyzing the correlation, and crack detection for the images was performed using you only look once (YOLO) deep learning. This study presents a method for removing non-uniform heat sources using the FFT algorithm, securing virtual data augmentation, and a detection mechanism for moving inspection objects using AI deep learning.

Background/Objectives: Periapical lesions (PLs) are frequently detected in dental radiology. Accurate diagnosis of these lesions is essential for proper treatment planning. Imaging techniques such as orthopantomogram (OPG) and cone-beam CT (CBCT) imaging are used to identify PLs. The aim of this study was to assess the diagnostic accuracy of artificial intelligence (AI) software Diagnocat for PL detection in OPG and CBCT images. Methods: The study included 49 patients, totaling 1223 teeth. Both OPG and CBCT images were analyzed by AI software and by three experienced clinicians. All the images were obtained in one patient cohort, and findings were compared to the consensus of human readers using CBCT. The AI's diagnostic accuracy was compared to a reference method, calculating sensitivity, specificity, accuracy, positive predictive value (PPV), negative predictive value (NPV), and F1 score. Results: The AI's sensitivity for OPG images was 33.33% with an F1 score of 32.73%. For CBCT images, the AI's sensitivity was 77.78% with an F1 score of 84.00%. The AI's specificity was over 98% for both OPG and CBCT images. Conclusions: The AI demonstrated high sensitivity and high specificity in detecting PLs in CBCT images but lower sensitivity in OPG images. [ABSTRACT FROM AUTHOR]

Tectonic features on the Moon can reflect the state of stress during the formation of the structure, and sinuous rilles can provide further insight into the tectonic-thermal evolution of the Moon. Manual visual interpretation is the primary method for extracting these linear structures due to their complex morphology. However, extracting these features from the vast amount of lunar remote sensing data requires significant time and effort from researchers, especially for small-scale tectonic features, such as wrinkle ridges, lobate scarps, and high-relief ridges. In order to enhance the efficiency of linear structure detection, this paper conducts research on the automatic detection method of linear structures using sinuous rilles as an example case. In this paper, a multimodal semantic segmentation method, "Sinuous Rille Network (SR-Net)", for detecting sinuous rilles is proposed based on DeepLabv3+. This method combines advanced techniques such as ECA-ResNet and dynamic feature fusion. Compared to other networks, such as PSPNet, ResUNet, and DeepLabv3+, SR-Net demonstrates superior precision (95.20%) and recall (92.18%) on the multimodal sinuous rille test set. The trained SR-Net was applied in detecting lunar sinuous rilles within the range of 60°S to 60°N latitude. A new catalogue of sinuous rilles was generated based on the results of the detection process. The methodology proposed in this paper is not confined to the detection of sinuous rilles; with further improvements, it can be extended to the detection of other linear structures. [ABSTRACT FROM AUTHOR]

We present an automated solar flare detection software tool to automatically process solar observed images, detect and track solar flares, and finally compile an event catalog. It can identify and track flares that happen simultaneously or temporally close together. The method to identify a flare is based on the local intensity changes in macropixels. The basic characteristics, such as the time and location information of a flare, are determined with a triple-threshold scheme, with the first threshold (global threshold) to determine the occurrence (location) of the flare and the second and third thresholds (local thresholds) to determine the real start and end times of the flare. We have applied this tool to one month of continuous solar ultraviolet (UV) images obtained by the Solar Disk Imager (SDI) onboard the Advanced Space-based Solar Observatory (ASO-S), which show active phenomena such as flares, filaments or prominences, and solar jets. Our automated tool efficiently detected a total number of 226 solar events. After a visual inspection, we found that only one event was misidentified (unrelated to an active event). We compared the detected events with the GOES X-ray flare list and found that our tool can detect 81% of GOES M-class and above flares (29 out of 36), from which we conclude that the intensity increase in SDI UV images can be considered as a good indicator of a solar flare. [ABSTRACT FROM AUTHOR]

In industrial manufacturing, bearings are crucial for machinery stability and safety. Undetected wear or cracks can lead to severe operational and financial setbacks. Thus, accurately identifying bearing defects is essential for maintaining production safety and equipment reliability. This research introduces an improved bearing defect detection model, YOLOv8-LMG, which is based on the YOLOv8n framework and incorporates four innovative technologies: the VanillaNet backbone network, the Lion optimizer, the CFP-EVC module, and the Shape-IoU loss function. These enhancements significantly increase detection efficiency and accuracy. YOLOv8-LMG achieves a mAP@0.5 of 86.5% and a mAP@0.5–0.95 of 57.0% on the test dataset, surpassing the original YOLOv8n model while maintaining low computational complexity. Experimental results reveal that the YOLOv8-LMG model boosts accuracy and efficiency in bearing defect detection, showcasing its significant potential and practical value in advancing industrial inspection technologies. [ABSTRACT FROM AUTHOR]

To achieve automatic recognition of lightning images, which cannot easily be handled using the existing methods and still requires significant human resources, we propose a lightning image dataset and a preprocessing method. The lightning image data over five months were collected using a camera based on two optical observation stations, and then a series of batch labeling methods were applied, which greatly reduced the workload of subsequent manual labeling, and a dataset containing more than 30,000 labeled samples was established. Considering that lightning varies rapidly over time, we propose a time sequence composite (TSC) preprocessing method that inputs lightning's time-varying characteristics into a model for better recognition of lightning images. The TSC method was evaluated through an experiment on four backbones, and it was found that this preprocessing method enhances the classification performance by 40%. The final trained model could successfully distinguish between the "lightning" and "non-lightning" samples, and a recall rate of 86.5% and a false detection rate of 0.2% were achieved. [ABSTRACT FROM AUTHOR]

The polar regions of Mars, including the South and North Poles, are crucial for studying Martian climate and geological history, as they contain the largest reservoir of subsurface water ice. This study introduces a new approach for reflector detection, which includes radargram denoising to effectively enhance the signal of underground reflectors, peak detection to extract the positions of subsurface stratification from the radar echoes, and peak points connection to form continuous layers. The mapped enhancement denoising process involves a linear brightness adjustment and a fourth-order diffusion equation to enhance the signal of the subsurface layers for effective detection. The subsurface detection extracts the surface and subsurface peak points based on a peak detection algorithm, while using locally window-enhanced peak filtering and Kullback–Leibler (KL) divergence mapping to filter out non-stratified peak points. Finally, the layered connection process uses the proximity parameter to connect peak points in the same layer. Applied to multiple SHARAD (Shallow Radar) images at the Martian poles, this algorithm demonstrated a false detection rate below 5%. Compared to other methods, this method has a missed detection rate of less than 5% and, additionally, exhibits fewer discontinuities in layer connectivity. Therefore, this algorithm shows exceptional proficiency and applicability in analyzing the complex subsurface structures of the Martian polar regions. [ABSTRACT FROM AUTHOR]

Pavement markings serve to convey information to drivers, regulate driving behavior, and effectively mitigate traffic congestion and reduce accidents. Nonetheless, due to traffic exposure and temperature stress, pavement markings may develop defects to diverse degrees. Consequently, the inspection and maintenance of pavement markings has been paid high attention. Traditional manual detection methods prove time-consuming, subjective, and present security risks. Therefore, we employed four object detection models [You Only Look Once version 5 (YOLOv5), YOLOv7, faster region convolutional neural networks (Faster R-CNN) with visual geometry group laboratory (VGG), and Faster R-CNN with residual network (ResNet)] to achieve intelligent recognition of pavement marking defects through deep learning. Each model underwent 1,000 epochs of training and utilized 2,000 annotated road inspection images. Through data augmentation, module optimization, and anchor redesign, these models can locate pavement markings and classify their defects. The accuracy and efficiency of the model were evaluated by mean average precision (mAP) and frames per second. In addition, we introduced evaluation indicators that focused on defect types to assist in selecting models with high applicability in detecting markings. Among these models, the optimized Faster R-CNN with VGG as the backbone network has an mAP of 93.96% and can detect over 28 images per second, which meets the engineering requirements. Pavement markings play a crucial role in guiding driver behavior, and they significantly contribute to alleviating traffic congestion and reducing traffic accidents. As the demand for autonomous driving technology increases, the maintenance of pavement markings has become more important. To address this, it is essential to determine which pavement markings require maintenance through inspection. However, traditional manual inspection methods suffer from issues such as low efficiency, high cost, and safety hazards. In this work, we developed four models utilizing artificial intelligence to automatically detect pavement markings in road inspection vehicle images. This approach significantly reduces the need for manual operation and ensures efficient and safe detection of pavement markings. The automatic detection results accurately match the actual position of the pavement markings, thus providing valuable guidance for maintenance work. [ABSTRACT FROM AUTHOR]

Annual outbreaks of floating Ulva prolifera blooms in the Yellow Sea have caused serious local environmental and economic problems. Rapid and effective monitoring of Ulva blooms from satellite observations with wide spatial-temporal coverage can greatly enhance disaster response efforts. Various satellite sensors and remote sensing methods have been employed for Ulva detection, yet automatic and rapid Ulva detection remains challenging mainly due to complex observation scenarios present in different satellite images, and even within a single satellite image. Here, a reliable and fully automatic method was proposed for the rapid extraction of Ulva features using the Tasseled-Cap Greenness (TCG) index from satellite top-of-atmosphere reflectance (RTOA) data. Based on the TCG characteristics of Ulva and Ulva-free targets, a local adaptive threshold (LAT) approach was utilized to automatically select a TCG threshold for moving pixel windows. When tested on HY1C/D-Coastal Zone Imager (CZI) images, the proposed method, termed the TCG-LAT method, achieved over 95% Ulva detection accuracy though cross-comparison with the TCG and VBFAH indexes with a visually determined threshold. It exhibited robust performance even against complex water backgrounds and under non-optimal observing conditions with sun glint and cloud cover. The TCG-LAT method was further applied to multiple HY1C/D-CZI images for automatic Ulva bloom monitoring in the Yellow Sea in 2023. Moreover, promising results were obtained by applying the TCG-LAT method to multiple optical satellite sensors, including GF-Wide Field View Camera (GF-WFV), HJ-Charge Coupled Device (HJ-CCD), Sentinel2B-Multispectral Imager (S2B-MSI), and the Geostationary Ocean Color Imager (GOCI-II). The TCG-LAT method is poised for integration into operational systems for disaster monitoring to enable the rapid monitoring of Ulva blooms in nearshore waters, facilitated by the availability of near-real-time satellite images. [ABSTRACT FROM AUTHOR]

Copyright of Chinese Medical Equipment Journal is the property of Chinese Medical Equipment Journal Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The study was aimed at developing a new automatic search technique for specific invariant patterns of movement-related brain potentials reflected in multidimensional electroencephalogram (EEG) signals. An adaptive band-pass filter with bandwidth closely matching the spectrum of the desired EEG pattern at the observed moment was synthesized based on the Singular Spectrum Analysis methodology. The preliminary filtering of the original EEG signals provides the required sensitivity for subsequent searching of time boundaries in patterns. The correctness of the developed method was confirmed with standard machine learning tools through the validation of the adaptive search method carried out on the general set of initial data. It is shown that the synthesized method has provided a reliable automatic search for induced pre-movement EEG patterns and the correct determination of their time boundaries (accuracy up 29% on average and reached maximum values to 100% for some individuals). The developed method expands the existing tools to improve the functionality and reliability of various Brain-computer interfaces for various purposes, including medical applications for paralyzed patients. [ABSTRACT FROM AUTHOR]

The control process of welding requires manual operations, and this consumes time. Robot classifier can help by automatic detection of welding defect and by taking rapid actions to correct in situ the defect. This paper presents a convolutional neural network (CNN) model developed to classify the welding defect like splash, twisty, overlap, edge and copper adhesion based on machine vision. Using a resistance spot welding (RSW) dataset the CNN model was trained and evaluated to achieve the best performance. The batch size was varied to quantify its effect on the precision of the model. The model can predict the type of welding surface by confidence of 99.86%. [ABSTRACT FROM AUTHOR]

Purpose: This study aimed to evaluate the performance of the commercially available artificial intelligence-based software CXR-AID for the automatic detection of pulmonary nodules on the chest radiographs of patients suspected of having lung cancer. Materials and methods: This retrospective study included 399 patients with clinically suspected lung cancer who underwent CT and chest radiography within 1 month between June 2020 and May 2022. The candidate areas on chest radiographs identified by CXR-AID were categorized into target (properly detected areas) and non-target (improperly detected areas) areas. The non-target areas were further divided into non-target normal areas (false positives for normal structures) and non-target abnormal areas. The visibility score, characteristics and location of the nodules, presence of overlapping structures, and background lung score and presence of pulmonary disease were manually evaluated and compared between the nodules detected or undetected by CXR-AID. The probability indices calculated by CXR-AID were compared between the target and non-target areas. Results: Among the 450 nodules detected in 399 patients, 331 nodules detected in 313 patients were visible on chest radiographs during manual evaluation. CXR-AID detected 264 of these 331 nodules with a sensitivity of 0.80. The detection sensitivity increased significantly with the visibility score. No significant correlation was observed between the background lung score and sensitivity. The non-target area per image was 0.85, and the probability index of the non-target area was lower than that of the target area. The non-target normal area per image was 0.24. Larger and more solid nodules exhibited higher sensitivities, while nodules with overlapping structures demonstrated lower detection sensitivities. Conclusion: The nodule detection sensitivity of CXR-AID on chest radiographs was 0.80, and the non-target and non-target normal areas per image were 0.85 and 0.24, respectively. Larger, solid nodules without overlapping structures were detected more readily by CXR-AID. [ABSTRACT FROM AUTHOR]

Astrocytes are non-neural cells, restricted to the brain and spinal cord, whose functions and morphology depend on their location. Astrocyte–astrocyte and astrocyte–neuron interactions occur through cytoplasmic Ca2+ level changes that are assessed to determine cell function and response (i.e., drug testing). The evaluation of alterations in intracellular Ca2+ levels primarily relies on fluorescence imaging techniques, performed through video recording of cells incubated with Ca2+-sensitive dyes. By observing ion concentration shifts over time in a delimited region of interest (ROI) encompassing a single cell, it is possible to draw conclusions on cell responses to specific stimuli. Our work describes a tool named SIGAA—signaling automated analysis, for astrocyte ROI-based fluorescent imaging. This tool is specifically tailored for two wavelengths excited dyes by using two inputs of Ca2+ signaling recorded frames/videos and outputting a set of features relevant to the experiment's conclusions and cell characterization. SIGAA performs automatic drift correction for the two recorded videos with a template matching algorithm, followed by astrocyte identification (ROI) using morphological reconstruction techniques. Subsequently, SIGAA extracts intracellular Ca2+ evolution functions for all identified ROIs detects function transients, and estimates a set of features for each signal. These features closely resemble those obtained through traditional methods and software used thus far. SIGAA is a new fully automated tool, which can speed up hour-long studies and analysis to a few minutes, showing reliable results as the validity tests indicate. [ABSTRACT FROM AUTHOR]

This study summarizes the application of automatic recognition technologies for patient-ventilator asynchrony (PVA) during mechanical ventilation. In the early stages, the method of setting rules and thresholds relied on manual interpretation of ventilator parameters and waveforms. While these methods were intuitive and easy to operate, they were relatively sensitive in threshold setting and rule selection and could not adapt well to minor changes in patient status. Subsequently, machine learning and deep learning technologies began to emerge and develop. These technologies automatically extract and learn data characteristics through algorithms, making PVA detection more robust and universal. Among them, logistic regression, support vector machines, random forest, hidden Markov models, convolutional autoencoders, long short-term memory networks, one-dimensional convolutional neural networks, etc., have all been successfully used for PVA recognition. Despite the significant advancements in feature extraction through deep learning methods, their demand for labelled data is high, potentially consuming significant medical resources. Therefore, the combination of reinforcement learning and self-supervised learning may be a viable solution. In addition, most algorithm validations are based on a single dataset, so the need for cross-dataset validation in the future will be an important and challenging direction for development.

The date fruit, scientifically known as Phoenix dactylifera, is a significant dietary component due to its high nutritional value and abundance of essential vitamins and minerals. The process of discerning the classification of this fruit, which exhibits a multitude of variations within its natural domain, needs a specialized skill set. The automated recognition of species based on images of agricultural goods has gained significant prevalence in recent times. In this objective, the present study employed machine learning algorithms to automatically identify seven types of date fruit. In the investigation, decision tree, K-nearest neighbor, artificial neural networks, and support vector machine through their different hyperparameters are employed for the purpose of classifying date fruit. The dataset was divided into ratios of 80% and 20% for training and testing, respectively, and the training process employed the five-fold cross-validation technique to avoid overfitting. In summary, the results indicate that the best algorithm is neural network with a layer size of 25. In this study, this proposed algorithm achieved a test accuracy rate of 93.85%. Given the absence of computational complexity in the investigation, it can be effortlessly incorporated into diverse tools, thereby facilitating the identification of the types of date fruit.

Due to the increased mortality caused by brain tumors, accurate and fast diagnosis of brain tumors is necessary to implement the treatment of this disease. In this research, brain tumor classification performed using a network based on ResNet architecture in MRI images. MRI images that available in the cancer image archive database included 159 patients. First, two filters called median and Gaussian filters were used to improve the quality of the images. An edge detection operator is also used to identify the edges of the image. Second, the proposed network was first trained with the original images of the database, then with Gaussian filtered and Median filtered images. Finally, accuracy, specificity and sensitivity criteria have been used to evaluate the results. Proposed method in this study was lead to 87.21%, 90.35% and 93.86% accuracy for original, Gaussian filtered and Median filtered images. Also, the sensitivity and specificity was calculated 82.3% and 84.3% for the original images, respectively. Sensitivity for Gaussian and Median filtered images was calculated 90.8% and 91.57%, respectively and specificity was calculated 93.01% and 93.36%, respectively. As a conclusion, image processing approaches in preprocessing stage should be investigated to improve the performance of deep learning networks.

With the advancement of text-generation technology, misuse has increasingly challenged academic research sustainability. The Chinese academic community, vast and active with millions of researchers and extensive literature, faces an inevitable generator misuse. However, research on the automatic detection of Chinese academic texts remains scarce, necessitating the thorough exploration of detection methods to support ongoing academic development. This study explored automatic detection technology for Chinese academic texts, focusing on TK2A dataset construction, generation models, and detection methods to assess their practical impact. TK2A covers papers across disciplines, such as computer science, engineering, and medicine, ensuring broad applicability and forming a solid foundation for model training and evaluation. Using advanced natural language processing, models trained on TK2A showed strong performance across disciplines. Rigorous manual evaluation verified their reliability in terms of grammar, semantics, and logic. The study employed the widely adopted BERT model for detection, achieving high accuracy in distinguishing human-written content from AI-generated content on TK2A. This research underscores TK2A’s practical value by offering crucial support to journals with an accuracy exceeding 84%, institutions, and education in swiftly detecting AI-generated content, preventing misconduct, and enhancing academic publication quality.

Impact craters represent the most prevalent and prominent topographical features on the surfaces of planets. They provide crucial insights into the internal and surface-level geological activities of planets but are difficult to identify from digital topographic data due to heterogeneous planetary surfaces and lack of distinguishing features. Previous studies, which implemented convolutional neural networks to automatically detect the planetary impact craters, focus on designing the state-of-the-art architectures to achieve optimal detection performance, without taking topographic knowledge into consideration. Therefore, we construct a topographic knowledge-aware network aimed at the automatic detection of small-scale impact craters utilizing lunar digital elevation models. In our work, we investigate the transfer-learning performances of one detector and conduct experiments on transferability from the perspectives of the geographic or topographic differences, which shows the knowledge transfer from source domain to target domain works well. Moreover, we calculate some quantitative metrics to describe the complexity of terrains and further find that the selected representative samples provide more valuable source of information for the generalization of one detector. For evaluative purposes, both qualitative and quantitative, each detector is comprehensively trained and then utilized for the detection of impact craters, drawing from the integrated digital elevation model of the Lunar Reconnaissance Orbiter (LRO) and Kaguya that extends over latitudes of ± 60° and the complete longitudinal spectrum, as well as its detection outcomes are benchmarked with the pre-existing crater catalog LU1319373. Experimental results that the topographic knowledge-aware detection outperforms traditional detection, with average differences of approximately 5 % in mAP and approximately 4 % in F1-score. The benefits of topographic knowledge-aware progressive detector training solution primarily derive from discrepancies in visual characteristics, heterogeneous lunar surfaces around the impact craters for generalization purposes. Our findings would be significantly applied to the discovery of scientific insights in both existing and new planetary datasets through the use of machine learning.

A self-driving car is necessary to implement traffic intelligence because it can vastly enhance both the safety of driving and the comfort of the driver by adjusting to the circumstances of the road ahead. Road hazards such as potholes can be a big challenge for autonomous vehicles, increasing the risk of crashes and vehicle damage. Real-time identification of road potholes is required to solve this issue. To this end, various approaches have been tried, including notifying the appropriate authorities, utilizing vibration-based sensors, and engaging in three-dimensional laser imaging. Unfortunately, these approaches have several drawbacks, such as large initial expenditures and the possibility of being discovered. Transfer learning is considered a potential answer to the pressing necessity of automating the process of pothole identification. A Convolutional Neural Network (CNN) is constructed to categorize potholes effectively using the VGG-16 pre-trained model as a transfer learning model throughout the training process. A Super-Resolution Generative Adversarial Network (SRGAN) is suggested to enhance the image's overall quality. Experiments conducted with the suggested approach of classifying road potholes revealed a high accuracy rate of 97.3%, and its effectiveness was tested using various criteria. The developed transfer learning technique obtained the best accuracy rate compared to many other deep learning algorithms.

Fundus Fluorescein Angiography (FFA) is an important invasive diagnostic tool employed in ophthalmology for the assessment of retinal and choroidal blood flow, components situated at the rear of the eye. Identifying lesions within FFA images, indicative of anomalies in the retina and choroid visualized through the injection of a fluorescein dye, is a critical step in diagnosing and managing chronic ocular diseases. Such lesions often hint at a range of eye disorders, including but not limited to diabetic retinopathy, age-related macular degeneration, and retinal vein occlusions. In conventional practice, these images are interpreted manually by a skilled ophthalmologist. Nonetheless, due to the intricate nature of these images, the manual process is often time-consuming and subject to individual interpretation. The advent of advanced technologies has instigated the development of automated lesion detection techniques, thereby alleviating these constraints.In this study, we introduce FFA-Lens, a web-based application engineered to detect 25 prevalent lesions in FFA images, serving as a crucial resource in diagnosing and treating chronic ocular diseases. Notably, FFA-Lens has demonstrated remarkable precision and recall values exceeding 0.8 in lesion detection, emphasizing its significant potential. By enabling early detection of ocular conditions, automating lesion identification, and enhancing diagnostic efficiency, FFA-Lens can substantially improve clinical disease management strategies.

This article explores the relationship between vehicle speed and pothole detection using a mobile phone. The study aims to develop a system to automatically detect potholes on roads. Real-time video recordings were made at different speeds, and the pothole detection process was conducted using object detection algorithms. The results showed that there was no exact relationship between speed and pothole detection, and YOLOv7 demonstrated partial superiority over YOLOv8. The study concludes that the proposed system has the potential to improve traffic safety and comfort in urban transportation. The article also discusses other studies on road damage detection using object detection models and provides details on the models used in this study. [Extracted from the article]

A major aim in the study of crustal fluids is the development of automatic methodologies for monitoring deep‐source, non‐volcanic gas emissions' spatio‐temporal evolution. Crustal fluids play a significant role in the generation of large earthquakes and the characterization of their emissions on the surface can be essential for better understanding crustal processes generating earthquakes. We investigate seismic tremors recorded over 4 days in 2019 at the Mefite d'Ansanto (southern Apennines, Italy) that is located at the northern end of the fault system that generated the Mw 6.9 1980 Irpinia Earthquake. The Mefite d'Ansanto is hypothesized to be the largest natural, non‐volcanic, CO2‐rich gas emission on Earth. The seismic tremor is studied by employing a dense temporary seismic network and an automated detection algorithm based on non‐parametric statistics of the recorded signal amplitudes. We extracted signal characteristics (RMS amplitude and statistical moments of amplitudes both in time and frequency domains) for use in the subsequent supervised machine‐learning classification of the target tremor and accidently detected anthropogenic and background noise. The data set is used for the training and optimization of station‐based KNN (k‐Nearest‐Neighbors) binary classifiers obtaining good classification performances with a median overall accuracy across all stations of 92.8%. The classified tremor displayed common features at all stations: variable duration (16 s to 30–40 min), broad peak frequency (4–20 Hz) with varying amplitudes, and two types of signals: (a) long‐duration, high‐amplitude tremor and (b) pulsating tremor. Higher tremor amplitudes recorded at stations closer to local bubbling and pressurized vents suggest multiple local tremor sources. Key Points: A dense temporary seismic array enabled the acquisition of emission‐related seismic tremor at the Mefite d'Ansanto siteA detection algorithm and supervised machine‐learning approach for the identification and classification of tremors has been developedNew insights on the emission tremor would help to monitor the CO2 degassing at the Mefite d'Ansanto and its temporal evolution [ABSTRACT FROM AUTHOR]

The approach of dynamic tracking and counting for obscured citrus based on machine vision is a key element to realizing orchard yield measurement and smart orchard production management. In this study, focusing on citrus images and dynamic videos in a modern planting mode, we proposed the citrus detection and dynamic counting method based on the lightweight target detection network YOLOv7-tiny, Kalman filter tracking, and the Hungarian algorithm. The YOLOv7-tiny model was used to detect the citrus in the video, and the Kalman filter algorithm was used for the predictive tracking of the detected fruits. In order to realize optimal matching, the Hungarian algorithm was improved in terms of Euclidean distance and overlap matching and the two stages life filter was added; finally, the drawing lines counting strategy was proposed. ln this study, the detection performance, tracking performance, and counting effect of the algorithms are tested respectively; the results showed that the average detection accuracy of the YOLOv7-tiny model reached 97.23%, the detection accuracy in orchard dynamic detection reached 95.12%, the multi-target tracking accuracy and the precision of the improved dynamic counting algorithm reached 67.14% and 74.65% respectively, which were higher than those of the pre-improvement algorithm, and the average counting accuracy of the improved algorithm reached 81.02%. The method was proposed to effectively help fruit farmers grasp the number of citruses and provide a technical reference for the study of yield measurement in modernized citrus orchards and a scientific decision-making basis for the intelligent management of orchards. [ABSTRACT FROM AUTHOR]

As a continuity of our previous work with an emphasis mainly on temporal variations, this research aims to statistically investigate the temporal-spatial characteristics on seismo-ionospheric influence associated with strong earthquakes. Firstly, the latest electron density and ion density data measured by the CSES satellite for more than three years have been utilized to globally search ionospheric disturbances by limiting spatial scale 140–2,100 km (in-situ measurement time t = 20–300 s if the satellite velocity 7 km/s is considered) and without limit on amplitude (A). At the same time, 3,577 strong earthquakes with a magnitude equal to or > 5.0 occurring during this period and three-hourly averaged Kp index have also been collected. It has shown that ionospheric variations with large scale (t > 200 s) and large amplitude (| A | > 100%) majorly reveal the major large-scale ionosphere structures, such as EIA, WN3/4, WSA, MIT, and so on, as well as strengthened varieties globally induced by strong solar activities especially on daytime, although electron density and ion density vary with different properties. Secondly, by large ionospheric perturbations eliminated, the sensitivity of nighttime plasma variations (here, | A | < 100% and t < 200 s) to different group strong earthquakes with respect to several aspects has been tentatively testified. Kp index is kept < 3 during this period to avoid its global effect from solar activities. The results have demonstrated that the seismic activities are more sensitive to ionospheric anomalies predominantly appearing 7 days before and with the spatial size < 120 s. Finally, nighttime plasma perturbations with various sizes and amplitudes have been further applied to a worldwide correlation in space and time with total 3,577 strong earthquakes happening within 1,500 km and 15 day's delay. The statistical results show that seismo-electron influence subtracted by an averaged variation significantly occurs 5 days prior to events and shifts 500–700 km away instead of right above the epicenters, which highly complies theoretically with the physical seismoionospheric model based on zonal electric field propagating along magnetic lines. While seismo-ion effect shows a specified temporal feature but without a confirmed spatial distribution and further work on validation and reliability of ion data is needed. [ABSTRACT FROM AUTHOR]

In order to solve the problems of tedious, insufficient manpower, low efficiency, and easy to cause human errors in the verification of relay protection equipment settings with the development of the power grid, an automatic verification method of relay protection equipment settings combining cell image gray enhancement and AI recognition is studied. In this method, Gaussian mixture and particle swarm algorithm are used to enhance the gray level of the original image captured, and the binary method is used to further denoise the image; The histogram is used to segment the cells in the denoised constant value image one by one; The OCR technology in AI technology uses the maximum width backtracking segmentation algorithm to segment a coherent text in a cell into multiple single words, and collects the 13 dimensional characteristics of the text to be detected to compare with the text in the database. The text with the smallest error is the detected text, which completes the text extraction in the cell; Store the extracted text data in the database, check the data in the notification constant value sheet and the device constant value sheet, and give an abnormal prompt of different data. The experimental results show that the image pre processed by this method is clear, the fixed value single cell segmentation is accurate, and the OCR text extraction efficiency is high. Through a large number of data experiments, the final verification accuracy can reach 99.8%. [ABSTRACT FROM AUTHOR]

Background: There is an urgent need worldwide for qualified health professionals. High attrition rates among health professionals, combined with a predicted rise in life expectancy, further emphasize the need for additional health professionals. Work-related stress is a major concern among health professionals, affecting both the well-being of health professionals and the quality of patient care. Objective: This scoping review aims to identify processes and methods for the automatic detection of work-related stress among health professionals using natural language processing (NLP) and text mining techniques. Methods: This review follows Joanna Briggs Institute Methodology and PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) guidelines. The inclusion criteria for this scoping review encompass studies involving health professionals using NLP for work-related stress detection while excluding studies involving other professions or children. The review focuses on various aspects, including NLP applications for stress detection, criteria for stress identification, technical aspects of NLP, and implications of stress detection through NLP. Studies within health care settings using diverse NLP techniques are considered, including experimental and observational designs, aiming to provide a comprehensive understanding of NLP's role in detecting stress among health professionals. Studies published in English, German, or French from 2013 to present will be considered. The databases to be searched include MEDLINE (via PubMed), CINAHL, PubMed, Cochrane, ACM Digital Library, and IEEE Xplore. Sources of unpublished studies and gray literature to be searched will include ProQuest Dissertations & Theses and OpenGrey. Two reviewers will independently retrieve full-text studies and extract data. The collected data will be organized in tables, graphs, and a qualitative narrative summary. This review will use tables and graphs to present data on studies' distribution by year, country, activity field, and research methods. Results synthesis involves identifying, grouping, and categorizing. The final scoping review will include a narrative written report detailing the search and study selection process, a visual representation using a PRISMA-ScR flow diagram, and a discussion of implications for practice and research. Results: We anticipate the outcomes will be presented in a systematic scoping review by June 2024. Conclusions: This review fills a literature gap by identifying automated work-related stress detection among health professionals using NLP and text mining, providing insights on an innovative approach, and identifying research needs for further systematic reviews. Despite promising outcomes, acknowledging limitations in the reviewed studies, including methodological constraints, sample biases, and potential oversight, is crucial to refining methodologies and advancing automatic stress detection among health professionals. International Registered Report Identifier (IRRID): PRR1-10.2196/56267 [ABSTRACT FROM AUTHOR]

Addressing the persistent delay problem in traditional network security antivirus protection systems, this paper introduces an innovative approach utilizing virtual reality (VR) technology. The primary objective is to significantly reduce detection delays and enhance the efficiency of network security measures. An enhanced decision-making algorithm is proposed to identify relevant features associated with network security. These features are then weighted and optimized to improve the overall detection process. An injection list is generated through web crawling techniques to strengthen security measures. A virtual protection block is also developed to serve as a barrier against potential threats. The proposed method claims a detection delay of only 75.33 milliseconds, significantly outperforming two traditional methods that recorded 290.11 milliseconds and 337.30 milliseconds, respectively. This substantial decrease in detection delay emphasizes the effectiveness of automatic detection within the context of VR technology. Practical implementation and empirical evidence further validate the success of this approach. The automatic detection of network security vulnerabilities within the VR technology framework is efficient and exhibits considerable progress. As such, this research offers a promising solution to the delay problem in network security antivirus protection. Embracing VR technology achieves shorter detection delays, ultimately improving the security posture of network systems. [ABSTRACT FROM AUTHOR]