Search

Every year, more than two million Muslim pilgrims from all over the world visit Mecca to perform Hajj worship. The challenge of location identification in dense crowds is significant, leading to dangerous consequences such as injury or loss. Existing works for person localization remain challenged, especially in crowded places like Mecca during Hajj. In this work, we propose a novel location identification method using image pre-processing and different machine learning classifiers, with the creation of a new image dataset for hotspot locations in Mecca. Image pre-processing algorithms are applied to enhance the geographic information present in the images, and the obtained features are classified using CNN, ANN, and SVM classifiers. Extensive evaluations reveal that the proposed pre-processing algorithm with CNN achieves the best localization performance with an accuracy of 90%, followed by ANN with an accuracy of 84%, and SVM with an accuracy of 80.50%. Without pre-processing, the accuracies are significantly lower: 63% for CNN, 73% for ANN, and 71.50% for SVM. In addition, the proposed approach was compared with other deep learning models, VGG16, AlexNet and ResNet50 on our dataset achieving an accuracy of 61%, 65% and 62%, respectively. Results demonstrate the effectiveness of our proposed method in comparison with other deep transfer learning methods on a small dataset, offering promising solutions for crowded place navigation. [ABSTRACT FROM AUTHOR]

Background: Seed vigor identification is critical to guaranteeing the quality and yield of maize. Although seeds with impaired vigor may germinate under normal conditions, planting under unfavorable conditions makes it difficult to produce healthy plants. Therefore, non-destructive and rapid detection of seed vigor using hyperspectral imaging (HSI) technology is crucial for improving crop production efficiency. Methods: Hyperspectral images of maize seeds were acquired employing the HSI system, the original spectra were preprocessed using Savitzky–Golay smoothing and multiplicative scatter correction, and the feature wavelengths were extracted using the successive projections algorithm (SPA). Discriminant models were constructed based on support vector machine (SVM), random forest, artificial neural network (ANN), and convolutional neural network (CNN-DC). Results: The results showed that SVM, ANN, and CNN-DC could discriminate well between maize seeds with different vigor levels, and their accuracy rate was over 70%. The SPA algorithm showed that the RMSE value achieved a minimum of 0.3406, while the number of variables was 49. The CNN-DC model outperformed the other models, which reached the highest accuracy of 92.06%. This study demonstrates that DL combined with HSI has excellent potential for identifying seed vigor. Conclusions: This study shows that the proposed method has excellent results for hyperspectral image data processing and can accurately identify maize seed vigor. [ABSTRACT FROM AUTHOR]

The primary motivation behind this study is the aspiration to design a prosthetic foot that demonstrates enhanced functionality, enabling more active and prompt responses, particularly tailored for individuals with below-knee amputations. This goal underscores the intention to create a prosthetic foot with the capability to execute foot movements in a more natural and effective manner. A new 1D-ResCNN model has been proposed for the rapid and accurate classification of foot movements based on user intent in the context of a prosthetic limb. This research introduces an innovative approach by integrating inertial measurement units with deep learning algorithms to advance the development of more functional prosthetic feet, specifically tailored for below-knee amputees. Leveraging wearable technologies, this method allows for the prolonged monitoring of foot movements within the users' natural environments. The dual benefits of cost reduction and enhanced user experience are achieved through this combination of advanced technologies, providing a promising avenue for the evolution of prosthetic foot design and usage. The results obtained with this model are satisfying both in terms of speed and accuracy with 99.8% compared to other methods in the literature. [ABSTRACT FROM AUTHOR]

Land subsidence (LS) and pipe collapse (PC) as the major types of geomorphologic hazards lead to noticeable changes in landscape alterations, land damage, loss of soil and water, surface erosion, and sediment buildup in affected areas. To overcome this, the susceptibility to LS and CP was investigated using three deep learning convolutional neural network (DL-CNN) architectures, including Res-Net, AlexNet, and VGG-Network. We used various predictor variables, and then, trained and tested our DL-CNN models using ReLu, Cross-Entropy, and Adam as activation, loss, and optimization functions, respectively. Our findings showed that DL-CNN models achieved an overall accuracy of 0.9836, 0.9721, and 0.9642 for the Res-Net, AlexNet, and VGG-Network, respectively, for CP sensitivity detection. In addition, the Res-Net, AlexNet, and VGG-Network with an overall accuracy of 0.9698, 0.9654, and 0.9519, respectively, showed satisfying performances for LS detection. We also applied univariate summary statistics, including L(r), the pair correlation function (g(r)), and the O-ring function (O(r)), to investigate the spatial pattern and distribution of CP and LS. The L(r) function graph showed that the spatial patterns of CP and LS were clustered across all the investigated distance scales. The value of this function fell outside the Monte Carlo range, indicating that the accumulation of CP and LS at the mentioned distance scale was statistically significant. The results of the O(r) function for the distribution pattern of CP in the study area indicated that this phenomenon was mostly distributed next to each other, implying the facilitating effect of CP on the creation and expansion of each other across all the investigated distance scales. Similarly, the univariate function g(r) also showed the dispersed distribution of subsidence LS at all distances next to each other. In summary, the results of this research revealed that much of the study area was susceptible to CP and LS. The proposed methodology and findings of this study would be useful for land managers, stakeholders, and researchers. [ABSTRACT FROM AUTHOR]

Plant diseases cause significant agricultural losses, demanding accurate detection methods. Traditional approaches relying on expert knowledge may be biased, but advancements in computing, particularly deep learning, offer non-experts effective tools. This study focuses on fine-tuning cutting-edge pre-trained CNN and vision transformer models to classify grape leaves and diagnose grape leaf diseases through digital images. Our research examined a PlantVillage dataset, which comprises 4062 leaf images distributed across four categories. Additionally, we utilized the Grapevine dataset, consisting of 500 leaf images. This dataset is organized into five distinct groups, with each group containing 100 images corresponding to one of the five grape types. The PlantVillage dataset focuses on four classes related to grape diseases, namely Black Rot, Leaf Blight, Healthy, and Esca leaves. On the other hand, the Grapevine dataset includes five classes for leaf recognition, specifically Ak, Alaidris, Buzgulu, Dimnit, and Nazli. In experiments with 14 CNN and 17 vision transformer models, deep learning demonstrated high accuracy in distinguishing grape diseases and recognizing leaves. Notably, four models achieved 100% accuracy on PlantVillage and Grapevine datasets, with Swinv2-Base standing out. This approach holds promise for enhancing crop productivity through early disease detection and providing insights into grape variety characterization in agriculture. [ABSTRACT FROM AUTHOR]

On-shelf availability (OSA) refers to the number of products available in saleable condition to a customer at the place he expects and at the time he wants to buy the product. OSA of the products in retail stores is important to enhance the customer shopping experience and profitability. The products on the retail store shelves are arranged strategically. This arrangement may be changed during shopping, because it is observed that customers may not move the products in the same or at the right place when they pick them up from the shelf. In such real-time scenarios, it would be appropriate to perform shelf image analysis to detect and identify these misplaced objects. This will help the shopkeeper to maintain a large-scale store effortlessly, otherwise it will require massive human effort and labour along with time. Many computer vision-based technology solutions have been developed by researchers to solve this problem. This article discusses a convolutional neural network (CNN)-based method for classifying shelf imagery into the correct semantic classes (that is whether it has misplaced products or not). The proposed architecture was evaluated with a modified COIL-100 dataset. The results of the proposed CNN model were compared with the variant of the proposed model in addition to lightweight pre-trained deep learning models viz; mobilenetV2, densenet121, efficientnetb0, efficientnetb3, and NASNetMobile using transfer learning (TL) concept. According to this study, it has been found that the TL-based MobilenetV2 model is lightweight and achieves better classification performance with 91.28% accuracy. Furthermore, a CNN-based model with 11 user-defined layers provides an accuracy of 90.36%. This shows the efficacy of the proposed models for change detection. [ABSTRACT FROM AUTHOR]

At present, in end-to-end network combined with deep learning in stereo matching, how to perceive ample image details within an acceptable range of computational cost, so as to improve the final matching accuracy, has become a hot research topic. In this paper, we design a cascaded disparity correction network based on DispNet, which can refine the initial disparity image by combining the process output results in the trunk network. The method proposed in this paper is named ETE–DC–CNN (end to end–disparity correction–convolutional neural network). In the trunk network, the mixed dilated convolution module is employed to extract the features of the original image, and the feature image is constructed into a 3D disparity space volume through depth-separable convolution, after which the initial disparity image can be obtained through 2D encoder–decoder module. In the correction network, the gradient information of the initial feature image is combined to reconstruct the modified matching cost body guided by the initial disparity image and then a smaller encoder–decoder module is trained and processed to make the final result at the sub-pixel level. The algorithm in this paper has been verified in SceneFlow and KITTI 2012/2015 data sets. The method proposed in this article achieves 3.46, 2.12, 1.19, and 0.6 results in the non-occluded area and 4.04, 2.55, 1.58, and 0.7 results in the global area on the Er (> 2 px), Er (> 3 px), Er (> 5 px), and Epe indicators in the KITTI 2012 test set, which are higher than those of the backbone network DispNet. [ABSTRACT FROM AUTHOR]

The use of Artificial Intelligence (AI) to preserve and promote cultural heritage has experienced significant growth in recent years. Among the various areas of cultural heritage, numismatics have emerged as a particularly promising field where we can develop AI solutions. Numismatics refers to the study of coins, tokens, paper money, and medals, which play a critical role in understanding human history and culture. However, there are still limited resources available to help researchers and collectors in the identification of coins. This is due to the vast number of coins in circulation, which presents a significant challenge in developing smart tools for classification tasks. This paper aims to provide a contribution to this setting. In particular, we start by creating a new dataset called EURO-Coin, which consists of images showing the side of coins with reliefs and is designed to facilitate the training and testing of AI models for euro coin classification. Then, we propose two approaches that leverage Convolutional Neural Networks and self-attention layers to classify the country and value of the coins. In our experiments, we obtain an accuracy of 86.9% for country classification and an accuracy of 96.4% for value classification. Finally, we conduct an ablation study to evaluate the impact of the preprocessing activities and attention layers in our approaches. [ABSTRACT FROM AUTHOR]

To tackle the difficulty of extracting features from one-dimensional spectral signals using traditional spectral analysis, a metabolomics analysis method is proposed to locate two-dimensional correlated spectral feature bands and combine it with deep learning classification for wine origin traceability. Metabolomics analysis was performed on 180 wine samples from 6 different wine regions using UPLC-Q-TOF-MS. Indole, Sulfacetamide, and caffeine were selected as the main differential components. By analyzing the molecular structure of these components and referring to the main functional groups on the infrared spectrum, characteristic band regions with wavelengths in the range of 1000–1400 nm and 1500–1800 nm were selected. Draw two-dimensional correlation spectra (2D-COS) separately, generate synchronous correlation spectra and asynchronous correlation spectra, establish convolutional neural network (CNN) classification models, and achieve the purpose of wine origin traceability. The experimental results demonstrate that combining two segments of two-dimensional characteristic spectra determined by metabolomics screening with convolutional neural networks yields optimal classification results. This validates the effectiveness of using metabolomics screening to determine spectral feature regions in tracing wine origin. This approach effectively removes irrelevant variables while retaining crucial chemical information, enhancing spectral resolution. This integrated approach strengthens the classification model's understanding of samples, significantly increasing accuracy. [ABSTRACT FROM AUTHOR]

The formation dip angle is an important characteristic parameter that reflects underground structures, and it is widely used in seismic exploration and geological interpretation. However, the routine dip angle calculation method suffers from the problems of artifact interference and insufficient accuracy, which restricts the development of fine exploration technology. More accurately obtaining the formation dip angle has become a general concern. To solve these problems, this paper proposes a method for calculating the formation dip angle using deep learning. The dip angle calculation is considered a regression problem. By establishing a database of synthetic seismic data and dip data tags, data-driven fitting of nonlinear functional relationships between the seismic data and dip angles are achieved, and intelligent dip calculations are realized. The method is verified using the synthetic sedimentary model and actual data and is compared with the mainstream dip angle calculation method in the industry. The results show that this method more realistically reflects the undulating characteristics of a structure with both high accuracy and anti-interference ability. [ABSTRACT FROM AUTHOR]

Development of a reliable and intelligent traffic monitoring system is highly desired to improve the transportation safety and establish future transportation plans due to the fast growth of vehicle population. Vehicle classification is one of the most critical subsystems where existing ones suffer from privacy concerns, requirements of complicated systems, and high maintenance cost. This paper reports a novel vehicle classification method by utilizing a triboelectric sensor to accurately identify vehicles. Novelty of this method originates from using triboelectric sensor and machine learning method with important advantages over current alternatives by providing an easy installation, simple operation, noninvasive measurement, cost-effective manufacturing, and highly accurate classification. To make a classification, vehicle toys' signals were acquired from triboelectric sensor and then applied to a deep learning algorithm. The 1932 sensor output data were grouped into a set of seven vehicle toys with different wheelbases, and number of tires passing on are used to train and optimize 1D-CNN model. The utilized 1D-CNN model achieved accuracy, f1-score, precision, and recall as 96.38%, 0.9638, 0.9658, and 0.9637, respectively. [ABSTRACT FROM AUTHOR]

In recent years, although significant progress has been made in infrared and visible image fusion, existing methods typically assume that the source images have been rigorously registered or aligned prior to image fusion. However, the difference in modalities of infrared and visible images poses a great challenge to achieve strict alignment automatically, affecting the quality of the subsequent fusion procedure. To address this problem, this paper proposes a deep learning framework for misaligned infrared and visible image fusion, aiming to free the fusion algorithm from strict registration. Technically, we design a convolutional neural network (CNN)-Transformer Hierarchical Interactive Embedding (CTHIE) module, which can combine the respective advantages of CNN and Transformer, to extract features from the source images. In addition, by characterizing the correlation between the features extracted from misaligned source images, a Dynamic Re-aggregation Feature Representation (DRFR) module is devised to align the features with a self-attention-based feature re-aggregation scheme. Finally, to effectively utilize the features at different levels of the network, a Fully Perceptual Forward Fusion (FPFF) module via interactive transmission of multi-modal features is introduced for feature fusion to reconstruct the fused image. Experimental results on both synthetic and real-world data demonstrate the effectiveness of the proposed method, verifying the feasibility of directly fusing infrared and visible images without strict registration. [ABSTRACT FROM AUTHOR]

Purpose: Deep convolutional neural networks (CNN) are promising for automatic classification of dopamine transporter (DAT)-SPECT images. Reporting the certainty of CNN-based decisions is highly desired to flag cases that might be misclassified and, therefore, require particularly careful inspection by the user. The aim of the current study was to design and validate a CNN-based system for the identification of uncertain cases. Methods: A network ensemble (NE) combining five CNNs was trained for binary classification of [123I]FP-CIT DAT-SPECT images as "normal" or "neurodegeneration-typical reduction" with high accuracy (NE for classification, NEfC). An uncertainty detection module (UDM) was obtained by combining two additional NE, one trained for detection of "reduced" DAT-SPECT with high sensitivity, the other with high specificity. A case was considered "uncertain" if the "high sensitivity" NE and the "high specificity" NE disagreed. An internal "development" dataset of 1740 clinical DAT-SPECT images was used for training (n = 1250) and testing (n = 490). Two independent datasets with different image characteristics were used for testing only (n = 640, 645). Three established approaches for uncertainty detection were used for comparison (sigmoid, dropout, model averaging). Results: In the test data from the development dataset, the NEfC achieved 98.0% accuracy. 4.3% of all test cases were flagged as "uncertain" by the UDM: 2.5% of the correctly classified cases and 90% of the misclassified cases. NEfC accuracy among "certain" cases was 99.8%. The three comparison methods were less effective in labelling misclassified cases as "uncertain" (40–80%). These findings were confirmed in both additional test datasets. Conclusion: The UDM allows reliable identification of uncertain [123I]FP-CIT SPECT with high risk of misclassification. We recommend that automatic classification of [123I]FP-CIT SPECT images is combined with an UDM to improve clinical utility and acceptance. The proposed UDM method ("high sensitivity versus high specificity") might be useful also for DAT imaging with other ligands and for other binary classification tasks. [ABSTRACT FROM AUTHOR]

During robot operation, robot components like links and joints may experience collisions or excess loads that can lead to structural damages or cracks. A crack in a structural component can degrade the overall performance of the structure. This study examines the influence of cracks on the vibration characteristics of a baseline robot link. The approach uses the finite element method to simulate the dynamics of planar robot link models with and without artificial cracks with different sizes, locations, and orientations in the ABAQUS software. The robot link models include one intact model and five defective models with cracks. A rectangular crack with a fixed length of 1 mm and a varying width from 0.001 to 0.1 mm is applied to a specific location along the robot link. Finite element analysis and machine learning are used to simulate and characterize the vibration of each robot link with one fixed end and one free end. The vibration responses are measured at the free end. The measured vibration data are then transformed into two-dimensional (2D) image data using the Gramian Angular Summation Field method. A convolutional neural network is then trained with the image data for crack detection and analysis. The results indicate that the proposed method demonstrates 98.25% accuracy on the data generated by the simulation experiments. [ABSTRACT FROM AUTHOR]

Thunderstorm gusts are a common form of severe convective weather in the warm season in North China, and it is of great importance to correctly forecast them. At present, the forecasting of thunderstorm gusts is mainly based on traditional subjective methods, which fails to achieve high-resolution and high-frequency gridded forecasts based on multiple observation sources. In this paper, we propose a deep learning method called Thunderstorm Gusts TransU-net (TG-TransUnet) to forecast thunderstorm gusts in North China based on multi-source gridded product data from the Institute of Urban Meteorology (IUM) with a lead time of 1 to 6 h. To determine the specific range of thunderstorm gusts, we combine three meteorological variables: radar reflectivity factor, lightning location, and 1-h maximum instantaneous wind speed from automatic weather stations (AWSs), and obtain a reasonable ground truth of thunderstorm gusts. Then, we transform the forecasting problem into an image-to-image problem in deep learning under the TG-TransUnet architecture, which is based on convolutional neural networks and a transformer. The analysis and forecast data of the enriched multi-source gridded comprehensive forecasting system for the period 2021–23 are then used as training, validation, and testing datasets. Finally, the performance of TG-TransUnet is compared with other methods. The results show that TG-TransUnet has the best prediction results at 1–6 h. The IUM is currently using this model to support the forecasting of thunderstorm gusts in North China. [ABSTRACT FROM AUTHOR]

Purpose: To develop and validate a deep learning model for distinguishing healthy vocal folds (HVF) and vocal fold polyps (VFP) on laryngoscopy videos, while demonstrating the ability of a previously developed informative frame classifier in facilitating deep learning development. Methods: Following retrospective extraction of image frames from 52 HVF and 77 unilateral VFP videos, two researchers manually labeled each frame as informative or uninformative. A previously developed informative frame classifier was used to extract informative frames from the same video set. Both sets of videos were independently divided into training (60%), validation (20%), and test (20%) by patient. Machine-labeled frames were independently verified by two researchers to assess the precision of the informative frame classifier. Two models, pre-trained on ResNet18, were trained to classify frames as containing HVF or VFP. The accuracy of the polyp classifier trained on machine-labeled frames was compared to that of the classifier trained on human-labeled frames. The performance was measured by accuracy and area under the receiver operating characteristic curve (AUROC). Results: When evaluated on a hold-out test set, the polyp classifier trained on machine-labeled frames achieved an accuracy of 85% and AUROC of 0.84, whereas the classifier trained on human-labeled frames achieved an accuracy of 69% and AUROC of 0.66. Conclusion: An accurate deep learning classifier for vocal fold polyp identification was developed and validated with the assistance of a peer-reviewed informative frame classifier for dataset assembly. The classifier trained on machine-labeled frames demonstrates improved performance compared to the classifier trained on human-labeled frames. Level of evidence: 4. [ABSTRACT FROM AUTHOR]

Social networks are widely used platforms for sharing various information and content, including text, images, and videos.The main challenge in social networking today is the verification of data credibility and the identification of genuine social media profiles. Cybercriminals take advantage of this by utilizing fake profiles to disseminate false information. However, current research mainly concentrates on spam filtering and analyzing malicious behavior separately, disregarding the interrelated nature of these issues. We propose a more desirable global, hybrid solution that encompasses both malicious profile detection and spam detection to mitigate the spread of spam effectively. This paper offers a deep learning-based method for detecting malicious profiles and spam tweets. For the profiles to interact with them as legitimate profiles, we first provide the detection of fake profiles using an automated honeypot. Next, we detect those who make interactions as malicious profiles, and finally, we collect their shared content to find spam tweets using a convolution neural network algorithm. We suggest using collaborative filtering and content filtering algorithms from recommender systems to define accounts similar to harmful profiles and spam similar to spam material picked up by convolution neural networks. We get a highly compelling and intriguing outcome with higher accuracy (99.23%) and lesser loss than typical learning algorithms. [ABSTRACT FROM AUTHOR]

The increasing availability of hydrological and physiographic spatiotemporal data has boosted machine learning's role in rapid flood mapping. Yet, data scarcity, especially high-resolution DEMs, challenges regions with limited access. This paper examines how DEM type and resolution affect flood prediction accuracy, utilizing a cutting-edge deep learning (DL) method called 1D convolutional neural network (CNN). It utilizes synthetic hydrographs as training input and water depth data obtained from LISFLOOD-FP, a 2D hydrodynamic model, as target data. This study investigates digital surface models (DSMs) and digital terrain models (DTMs) derived from a 1 m LIDAR-based DTM, with resolutions from 15 to 30 m. The methodology is applied and assessed in a established benchmark, city of Carlisle, UK. The models' performance is then evaluated and compared against an observed flood event using RMSE, Bias, and Fit indices. Leveraging the insights gained from this region, the paper discusses the applicability of the methodology to address the challenges encountered in a data-scarce flood-prone region, exemplified by Pakistan. Results indicated that utilizing a 30 m DTM outperformed a 30 m DSM in terms of flood depth prediction accuracy by about 21% during the flood peak stage, highlighting the superior performance of DTM at lower resolutions. Increasing the resolution of DTM to 15 m resulted in a minimum 50% increase in RMSE and a 20% increase in fit index across all flood stages. The findings emphasize that while a coarser resolution DEM may impact the accuracy of machine learning models, it remains a viable option for rapid flood prediction. However, even a slight improvement in data resolution in data-scarce regions would provide significant added value, ultimately enhancing flood risk management. [ABSTRACT FROM AUTHOR]

This study aimed to (1) replicate a deep-learning-based model for cerebral aneurysm segmentation in TOF-MRAs, (2) improve the approach by testing various fully automatic pre-processing pipelines, and (3) rigorously validate the model's transferability on independent, external test-datasets. A convolutional neural network was trained on 235 TOF-MRAs acquired on local scanners from a single vendor to segment intracranial aneurysms. Different pre-processing pipelines including bias field correction, resampling, cropping and intensity-normalization were compared regarding their effect on model performance. The models were tested on independent, external same-vendor and other-vendor test-datasets, each comprised of 70 TOF-MRAs, including patients with and without aneurysms. The best-performing model achieved excellent results on the external same-vendor test-dataset, surpassing the results of the previous publication with an improved sensitivity (0.97 vs. ~ 0.86), a higher Dice score coefficient (DSC, 0.60 ± 0.25 vs. 0.53 ± 0.31), and an improved false-positive rate (0.87 ± 1.35 vs. ~ 2.7 FPs/case). The model further showed excellent performance in the external other-vendor test-datasets (DSC 0.65 ± 0.26; sensitivity 0.92, 0.96 ± 2.38 FPs/case). Specificity was 0.38 and 0.53, respectively. Raising the voxel-size from 0.5 × 0.5×0.5 mm to 1 × 1×1 mm reduced the false-positive rate seven-fold. This study successfully replicated core principles of a previous approach for detecting and segmenting cerebral aneurysms in TOF-MRAs with a robust, fully automatable pre-processing pipeline. The model demonstrated robust transferability on two independent external datasets using TOF-MRAs from the same scanner vendor as the training dataset and from other vendors. These findings are very encouraging regarding the clinical application of such an approach. [ABSTRACT FROM AUTHOR]

A pruned VGG19 model subjected to Axial Coronal Sagittal (ACS) convolutions and a custom VGG16 model are benchmarked to predict 3D fabric descriptors from a set of 2D images. The data used for training and testing are extracted from a set of 600 3D biphase microstructures created numerically. Fabric descriptors calculated from the 3D microstructures constitute the ground truth, while the input data are obtained by slicing the 3D microstructures in each direction of space at regular intervals. The computational cost to train the custom ACS-VGG19 model increases linearly with p (the number of images extracted in each direction of space), and increasing p does not improve the performance of the model - or only does so marginally. The best performing ACS-VGG19 model provides a MAPE of 2 to 5% for the means of aggregate size, aspect ratios and solidity, but cannot be used to estimate orientations. The custom VGG16 yields a MAPE of 2% or less for the means of aggregate size, distance to nearest neighbor, aspect ratios and solidity. The MAPE is less than 3% for the mean roundness, and in the range of 5-7% for the aggregate volume fraction and the mean diagonal components of the orientation matrix. Increasing p improves the performance of the custom VGG16 model, but becomes cost ineffective beyond 3 images per direction. For both models, the aggregate volume fraction is predicted with less accuracy than higher order descriptors, which is attributed to the bias given by the loss function towards highly-correlated descriptors. Both models perform better to predict means than standard deviations, which are noisy quantities. The custom VGG16 model performs better than the pruned version of the ACS-VGG19 model, likely because it contains 3 times (p = 1) to 28 times (p = 10) less parameters than the ACS-VGG19 model, allowing better and faster cnvergence, with less data. The custom VGG16 model predicts the second and third invariants of the orientation matrix with a MAPE of 2.8% and 8.9%, respectively, which suggests that the model can predict orientation descriptors regardless of the orientation of the input images. [ABSTRACT FROM AUTHOR]

Objectives: With smartphones and wearable devices becoming ubiquitous, they offer an opportunity for large-scale voice sampling. This systematic review explores the application of deep learning models for the automated analysis of voice samples to detect vocal cord pathologies. Methods: We conducted a systematic literature review following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) reporting guidelines. We searched MEDLINE and Embase databases for original publications on deep learning applications for diagnosing vocal cord pathologies between 2002 and 2022. Risk of bias was assessed using Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2). Results: Out of the 14 studies that met the inclusion criteria, data from a total of 3037 patients were analyzed. All studies were retrospective. Deep learning applications targeted Reinke's edema, nodules, polyps, cysts, unilateral cord paralysis, and vocal fold cancer detection. Most pathologies had detection accuracy above 90%. Thirteen studies (93%) exhibited a high risk of bias and concerns about applicability. Conclusions: Technology holds promise for enhancing the screening and diagnosis of vocal cord pathologies. While current research is limited, the presented studies offer proof of concept for developing larger-scale solutions. [ABSTRACT FROM AUTHOR]

Time series forecasting is crucial in various domains, ranging from finance and economics to weather prediction and supply chain management. Traditional statistical methods and machine learning models have been widely used for this task. However, they often face limitations in capturing complex temporal dependencies and handling multivariate time series data. In recent years, deep learning models have emerged as a promising solution for overcoming these limitations. This paper investigates how deep learning, specifically hybrid models, can enhance time series forecasting and address the shortcomings of traditional approaches. This dual capability handles intricate variable interdependencies and non-stationarities in multivariate forecasting. Our results show that the hybrid models achieved lower error rates and higher R 2 values, signifying their superior predictive performance and generalization capabilities. These architectures effectively extract spatial features and temporal dynamics in multivariate time series by combining convolutional and recurrent modules. This study evaluates deep learning models, specifically hybrid architectures, for multivariate time series forecasting. On two real-world datasets - Traffic Volume and Air Quality - the TCN-BiLSTM model achieved the best overall performance. For Traffic Volume, the TCN-BiLSTM model achieved an R 2 score of 0.976, and for Air Quality, it reached an R 2 score of 0.94. These results highlight the model's effectiveness in leveraging the strengths of Temporal Convolutional Networks (TCNs) for capturing multi-scale temporal patterns and Bidirectional Long Short-Term Memory (BiLSTMs) for retaining contextual information, thereby enhancing the accuracy of time series forecasting. [ABSTRACT FROM AUTHOR]

Summary: This study utilized deep learning to classify osteoporosis and predict bone density using opportunistic CT scans and independently tested the models on data from different hospitals and equipment. Results showed high accuracy and strong correlation with QCT results, showing promise for expanding osteoporosis screening and reducing unnecessary radiation and costs. Purpose: To explore the feasibility of using deep learning to establish a model for osteoporosis classification and bone density value prediction based on opportunistic CT scans and to verify its generalization and diagnostic ability using an independent test set. Methods: A total of 1219 cases of opportunistic CT scans were included in this study, with QCT results as the reference standard. The training set: test set: independent test set ratio was 703: 176: 340, and the independent test set data of 340 cases were from 3 different hospitals and 4 different CT scanners. The VB-Net structure automatic segmentation model was used to segment the trabecular bone, and DenseNet was used to establish a three-classification model and bone density value prediction regression model. The performance parameters of the models were calculated and evaluated. Results: The ROC curves showed that the mean AUCs of the three-category classification model for categorizing cases into "normal," "osteopenia," and "osteoporosis" for the training set, test set, and independent test set were 0.999, 0.970, and 0.933, respectively. The F1 score, accuracy, precision, recall, precision, and specificity of the test set were 0.903, 0.909, 0.899, 0.908, and 0.956, respectively, and those of the independent test set were 0.798, 0.815, 0.792, 0.81, and 0.899, respectively. The MAEs of the bone density prediction regression model in the training set, test set, and independent test set were 3.15, 6.303, and 10.257, respectively, and the RMSEs were 4.127, 8.561, and 13.507, respectively. The R-squared values were 0.991, 0.962, and 0.878, respectively. The Pearson correlation coefficients were 0.996, 0.981, and 0.94, respectively, and the p values were all < 0.001. The predicted values and bone density values were highly positively correlated, and there was a significant linear relationship. Conclusion: Using deep learning neural networks to process opportunistic CT scan images of the body can accurately predict bone density values and perform bone density three-classification diagnosis, which can reduce the radiation risk, economic consumption, and time consumption brought by specialized bone density measurement, expand the scope of osteoporosis screening, and have broad application prospects. [ABSTRACT FROM AUTHOR]

Brain–computer interfacing (BCI) research, fueled by deep learning, integrates insights from diverse domains. A notable focus is on steady-state visual evoked potential (SSVEP) in BCI applications, requiring in-depth assessment through deep learning. EEG research frequently employs SSVEPs, which are regarded as normal brain responses to visual stimuli, particularly in investigations of visual perception and attention. This paper tries to give an in-depth analysis of the implications of deep learning for SSVEP-adapted BCI. A systematic search across four stable databases (Web of Science, PubMed, ScienceDirect, and IEEE) was developed to assemble a vast reservoir of relevant theoretical and scientific knowledge. A comprehensive search yielded 177 papers that appeared between 2010 and 2023. Thence a strict screening method from predetermined inclusion criteria finally generated 39 records. These selected works were the basis of the study, presenting alternate views, obstacles, limitations and interesting ideas. By providing a systematic presentation of the material, it has made a key scholarly contribution. It focuses on the technical aspects of SSVEP-based BCI, EEG technologies and complex applications of deep learning technology in these areas. The study delivers more penetrating reporting on the latest deep learning pattern recognition techniques than its predecessors, together with progress in data acquisition and recording means suitable for SSVEP-based BCI devices. Especially in the realms of deep learning technology orchestration, pattern recognition techniques, and EEG data collection, it has effectively closed four important research gaps. To increase the accessibility of this critical material, the results of the study take the form of easy-to-read tables just generated. Applying deep learning techniques in SSVEP-based BCI applications, as the research shows, also has its downsides. The study concludes that a radical framework will be presented which, includes intelligent decision-making tools for evaluation and benchmarking. Rather than just finding a comparable or similar analogy, this framework is intended to help guide future research and pragmatic applications, and to determine which SSVEP-based BCI applications have succeeded at responsibility for what they set out with. [ABSTRACT FROM AUTHOR]

The preservation and transmission of traditional villages is crucial to the prosperity and development of ethnic cultures. However, current traditional village surveys usually require a large number of experts and scholars to conduct field research, which is an expensive and time-consuming method, especially for large-scale tasks. Therefore, this study proposes an automatic classification method based on deep learning (DL) for the identification of traditional village heritage value elements (TVHVE). The study evaluates four selected convolutional neural network (CNN) frames using traditional villages in Hubei Province as a sample dataset. The results show that Residual Network152 (ResNet152) is the most suitable CNN frame for identifying TVHVE in Hubei. The stability and consistency of various TVHVE present in the ResNet152 model were evaluated using Area Under Curve (AUC) and Precision Recall Curve (PRC), which indicated satisfactory prediction performance for most elements, except for specific elements such as tombstones and stone carvings, which showed lower accuracy. In addition, the study sheds light on the areas of concern of the model with respect to different TVHVE images and elucidates the reasons behind the confusion between elements through semantic clustering based on image classification and interpretability analysis using the Gradient-Weighted Class Activation Mapping (Grad-CAM) heat map. By using an automated classification method based on DL, this study significantly reduces the cost and effort associated with traditional surveys. At the same time, insight into areas of concern and confusion in the model improves guidance for conservation efforts and provides valuable references for subsequent research. [ABSTRACT FROM AUTHOR]

In this work, we used the convolutional neural network (CNN) method to invert sea surface height (SSH) from the Global Navigation Satellite System (GNSS) delayed Doppler map (DDM) data during 2009–2017 and compared the CNN inversion data with those obtained from traditional simple random forest (RF) method. SSH observations from the OSTM/Jason-2 satellite were used to judge the merits of the two methods. The results show that both methods yield good SSH inversion results, but when the training set is 9000, the root mean square errors of the SSH inversion results based on the CNN and the RF method are 16.78 and 15.96 respectively; as the training set increases above 9000, the accuracy of the CNN method is significantly better than that of the RF method. This suggests that SSH inversion based on the CNN method will become more advantageous as more data become available. [ABSTRACT FROM AUTHOR]

The 3D pavement surface images provide a great opportunity for transportation agencies to digitally and effectively assess jointed plain concrete pavement (JPCP) conditions. An automated and accurate JPCP slab joint detection algorithm, which can support slab separation and faulting evaluation, is a critical prerequisite for applying 3D pavement images on JPCP condition assessments. However, there is no existing study on automated slab joint detection except for commercial software, and the detected joints of the software require massive manual revisions due to insufficient accuracy. In this study, a novel slab joint detection algorithm is proposed, which leverages the power of deep learning to achieve accurate slab joint detection on 3D pavement images. The proposed algorithm consists of a convolutional neural network-based joint segmentation model and a joint coordinates extractor. The joint segmentation model is trained to generate pixel-wise joint segmentation masks from the pavement images, which provide preliminary localization information of the slab joints. Then, with the joint segmentation mask, the joint coordinate extractor is designed to eliminate the false positive predictions and accurately extract the joint coordinates. The proposed algorithm is evaluated on large-scale 3D pavement images collected from multiple interstate highways in the state of Georgia with diverse conditions. In the performance evaluation, the proposed algorithm achieved the highest F1 score of 0.956, which largely outperformed the commercial software with a 10% improvement. The evaluation results demonstrate the effectiveness of the proposed algorithm, which can further support effective and efficient assessments of JPCP conditions. [ABSTRACT FROM AUTHOR]

With the massive amount of data available on the Internet, many users face problems when they need access to the information and goods they need. Adapting information to user needs has become a complex and time-consuming process. Recommender systems are powerful tools for guiding users in electronic settings to information, services, and goods of interest. With the ability to identify users and predict their preferences, recommender systems can extract information likely to be of interest to users from vast amounts of data and save time and energy by providing them with relevant recommendations. Therefore, in this paper, a framework for a recommender system is proposed, which consists of four main phases. In the first phase, the preprocessing operation is performed. The purpose of this phase is to create an ontology model for products based on the convolutional neural network method. Data collection operations are carried out in the second phase. The purpose of this phase is to receive and store user information based on behavior and different criteria. The third phase is related to creating an ontology. The purpose of this phase is to create an ontology model for user behavior using OWL libraries. Finally, in the last phase, finding similarities and presented a proposal. The purpose of this phase is the necessary calculations of the proposed framework in the similarity finding section using ontology models. Simulation results show that the proposed framework measures MAE (more than 10 and 15%), RMSE (more than 12 and 16%), precision (less than 10 and 13%), recall (more than 25 and 28%), F1-score (higher than 25 and 30%) and Score of User (higher than 15 and 17%) outperform two related approaches, namely CF and CF+ Ontology, respectively. [ABSTRACT FROM AUTHOR]

Objectives: Transcranial sonography has been used as a valid neuroimaging tool to diagnose Parkinson's disease (PD). This study aimed to develop a modified transcranial sonography (TCS) technique based on a deep convolutional neural network (DCNN) model to predict Parkinson's disease. Methods: This retrospective diagnostic study was conducted using 1529 transcranial sonography images collected from 854 patients with PD and 775 normal controls admitted to the Second Affiliated Hospital of Soochow University (Suzhou, Jiangsu, China) between September 2019 and May 2022. The data set was divided into training cohorts (570 PD patients and 541 normal controls), and the validation set (184 PD patients and 234 normal controls). Using these datasets, we developed four different DCNN models (ResNet18, ResNet50, ResNet152, and DenseNet121). We then assessed their diagnostic performance, including the area under the receiver operating characteristic (AUROC) curve, specificity, sensitivity, positive predictive value (PPV), negative predictive value (NPV), and F1 score and compared with traditional diagnostic criteria. Results: Among the 1529 TCS images, 570 PD patients and 541 normal controls from 4 of 6 sonographers of the TCS team were selected as the training cohort, and 184 PD patients and 234 normal controls from the other 2 sonographers were chosen as the validation cohort. There were no sex and age differences between PD patients and normal control subjects in the training and validation cohorts (P values > 0.05). All DCNN models achieved good performance in distinguishing PD patients from normal control subjects on the validation datasets, with diagnostic AUROCs and accuracy of 0.949 (95% CI 0.925, 0.965) and 86.60 for the RestNet18 model, 0.949 (95% CI 0.929, 0.971) and 87.56 for ResNet50, 0.945 (95% CI 0.931, 0.969) and 88.04 for ResNet152, 0.953 (95% CI 0.935, 0.971) and 87.80 for DenseNet121, respectively. On the other hand, the diagnostic accuracy of the traditional diagnostic method was 82.30. The accuracy of all DCNN models was higher than that of traditional diagnostic method. Moreover, the 5k-fold cross-validation results in train datasets showed that these DCNN models are robust. Conclusion: The developed transcranial sonography-based DCNN models performed better than traditional diagnostic criteria, thus improving the sonographer's accuracy in diagnosing PD. [ABSTRACT FROM AUTHOR]

In practical engineering environments, rolling bearing vibration signal is often interfered by strong noise, which negatively affects the diagnostic accuracy of intelligent diagnosis models. To solve the above problem, a fault diagnosis model (MDCAE-CACNN) that fuses a multi-scale dilated convolutional auto-encoder (MDCAE) and a channel attention-based convolutional neural network (CACNN) is proposed. First, the MDCAE model is used to capture the feature information of different time scales in rolling bearing vibration signal by using convolutional kernels with different receptive field sizes. Through unsupervised learning, the noise is removed to obtain high-quality reconstructed signals. Then, the fault features in the reconstructed signal are effectively extracted by CACNN model and the fault type is accurately diagnosed. The experimental results show that the proposed MDCAE-CACNN model exhibits remarkable improvements in fault diagnosis accuracy and effectiveness. Additionally, it showcases high levels of precision, robustness, and generalization ability. [ABSTRACT FROM AUTHOR]

In the current era, remote sensing is a powerful platform for detecting and predicting landslides. Moreover, the advancement in computing technologies has proven significant in artificial intelligence (AI) research. Researchers have made significant attempts in the existing literature by introducing landslide detection procedures from remote sensing images (RSIs) through deep learning (DpLr) algorithms. This research work aims to survey those methods. Our database consists of 204 published research articles. In addition, 50% (approximately) of the papers are directly related to landslide information extraction from satellite and unmanned aerial vehicles (UAV) images exploiting DpLr models. The suggested methods have been categorized into seven parts based on the applied model. Further, the evaluation methods have been discussed. The quantitative results are based on the following parameters: (1) contributing nations, (2) key study locations, (3) data set distribution, and (4) model utilization. Lastly, challenges in the studies of DpLr algorithms and the opportunities in landslide detection problems are discussed to motivate future research. [ABSTRACT FROM AUTHOR]

Background: Imaging is vital for assessing rectal cancer, with endoanal ultrasound (EAUS) being highly accurate in large tertiary medical centers. However, EAUS accuracy drops outside such settings, possibly due to varied examiner experience and fewer examinations. This underscores the need for an AI-based system to enhance accuracy in non-specialized centers. This study aimed to develop and validate deep learning (DL) models to differentiate rectal cancer in standard EAUS images. Methods: A transfer learning approach with fine-tuned DL architectures was employed, utilizing a dataset of 294 images. The performance of DL models was assessed through a tenfold cross-validation. Results: The DL diagnostics model exhibited a sensitivity and accuracy of 0.78 each. In the identification phase, the automatic diagnostic platform achieved an area under the curve performance of 0.85 for diagnosing rectal cancer. Conclusions: This research demonstrates the potential of DL models in enhancing rectal cancer detection during EAUS, especially in settings with lower examiner experience. The achieved sensitivity and accuracy suggest the viability of incorporating AI support for improved diagnostic outcomes in non-specialized medical centers. [ABSTRACT FROM AUTHOR]

Numerical simulation of multiphase flow in porous media is an important step in understanding the dynamic behavior of geologic CO 2 storage (GCS). Scaling up GCS requires fast and accurate high-resolution modeling of the storage reservoir pressure and saturation plume migration; however, such modeling is challenging due to the high computational costs of traditional physics-based simulations. Deep learning models trained with numerical simulation data can provide a fast and reliable alternative to expensive physics-based numerical simulations. We propose a Stochastic pix2vid neural network architecture for solving multiphase fluid flow problems with significant speed, accuracy, and efficiency. The Stochastic pix2vid model is designed based on the principles of computer vision and video synthesis and is able to generate dynamic spatiotemporal predictions of fluid flow from static reservoir models, closely mimicking the performance of traditional numerical simulation. We apply the Stochastic pix2vid model to a highly-complex CO 2 -water multiphase problem with a wide range of reservoir models in terms of porosity and permeability heterogeneity, facies distribution, and injection configurations. The Stochastic pix2vid method is first-of-its-kind in static-to-dynamic prediction of reservoir behavior, where a single static input is mapped to its dynamic response with a fixed number of timesteps. The Stochastic pix2vid method provides notable performance in highly heterogeneous geologic formations and complex estimation such as CO 2 saturation and pressure buildup plume determination. The trained model can serve as a general-purpose, static-to-dynamic (image-to-video) alternative to traditional numerical reservoir simulation of 2D CO 2 injection problems with up to 6,500 × speedup compared to traditional numerical simulation using the MATLAB Reservoir Simulation Toolbox. [ABSTRACT FROM AUTHOR]

Multicomponent seismic data can be used to predict unconventional reservoirs; however, this is a challenging task. Although machine learning (ML), particularly deep learning, can be used in this regard, its accuracy in reservoir prediction depends largely on the amount of data available for training and the complexity of the architecture. This study attempted to address this problem using transfer learning (TL) and a compact convolutional neural network with a self-attention mechanism (SACNN). We developed a framework for unconventional reservoir prediction by expanding the data samples and optimizing model performance. First, the synthetic data for both oil and gas reservoirs were used as the source data; their effectiveness was tested using the SACNN model. Subsequently, a real dataset was obtained by optimizing the real multicomponent seismic attributes. The TL dataset was constructed by transferring synthetic gas reservoir data to real dataset. Finally, the constructed SACNN model was used to predict the gas-bearing distribution in tight sandstone gas reservoirs. The results showed the superiority of the proposed model over conventional ML models, with lower error in the unconventional reservoir distribution prediction. Moreover, the proposed model exhibited superior prediction performance (R2 = 0.9731) on the testing dataset compared to models trained solely on synthetic (R2 = 0.9389) and real (R2 = 0.9627) data. Moreover, uncertainty analysis showed that the proposed model is robust and efficient. The proposed framework provides a basis for constructing data-driven models for energy conversion and utilization. [ABSTRACT FROM AUTHOR]

Alphonso, a renowned mango variety cultivated in India, is commercially valuable for its delightful taste, vibrant saffron color, texture, and prolonged shelf life, attracts global attention. Spongy Tissue (ST) disorder is prevalent in mangoes, especially in the Alphonso variety, leading to spongy and corky texture in the fruit's pulp. This issue has been identified in as much as 30% of mangoes in a single lot, resulting in the entire lot being rejected during export due to the delayed detection of the disorder. Current mango quality assessment involves destructive cutting, causing fruit damage, leading to significant loss. Limited physical checks don't ensure overall batch quality. By considering above challenges present study demonstrates on use of X-ray imaging technique for detecting internal quality of mango non-destructively along with machine learning algorithms for automatic binary classification (Non spongy vs. Spongy). For evaluation 648 original X-ray images of mangoes were captured and augmented to 3888 images using different augmentation techniques. For automated classification purposes deep learning (DL) models were used. For automated classification, DL models were employed and fine-tuned through grid search hyperparameter optimization within a 5-fold cross-validation framework. Among the DL models, namely CNN, ResNet50, AlexNet, VGG16, and VGG19, they achieved notable overall accuracy rates of 87.27%, 89.18%, 90.21%, 91.75% and 95.82%, respectively, on the test dataset. Significantly, the VGG19 model demonstrated superior performance with highest classification accuracy by TukeyHSD test. DL in X-ray imaging shows promise for detecting internal issues in fruits, enhancing inspection capabilities for diverse purposes, such as identifying diseases or damages. Highlights: •'Alphonso' is variety of mango that has suffered from spongy tissue malady. •Potential of X-ray imaging was tested for identifying internal spongy tissue defects. •CNN, AlexNet, ResNet, VGG16 and VGG19 models were used for automatic classification. •Models were optimized by hyperparameter tuning and cross-validation technique. •Deep transfer learning models achieved >90% mango binary classification accuracy. [ABSTRACT FROM AUTHOR]

Introduction: We developed a convolutional neural network (CNN) model to predict treatment outcomes of transforaminal epidural steroid injection (TFESI) for controlling cervical radicular pain due to cervical foraminal stenosis. Methods: We retrospectively recruited 293 patients with cervical TFESI due to cervical radicular pain caused by cervical foraminal stenosis. We obtained a single oblique cervical radiograph from each patient. We cut each oblique cervical radiograph image into a square shape, including the foramen that was targeted for TFESI, the intervertebral disc, the facet joint of the corresponding level with the targeted foramen, and the pedicles of the vertebral bodies just above and below the targeted foramen. Therefore, images including the targeted foramen and structures around the targeted foramen were used as input data. A favorable outcome was defined as a ≥ 50% reduction in the numeric rating scale (NRS) score at 2 months post TFESI compared to the pretreatment NRS score. A poor outcome was defined as a < 50% reduction in the NRS score at 2 months post TFESI vs. the pretreatment score. Results: The area under the curve of our developed model for predicting the treatment outcome of cervical TFESI in patients with cervical foraminal stenosis was 0.823. Conclusion: A CNN model trained using oblique cervical radiographs can be helpful in predicting treatment outcomes after cervical TFESI in patients with cervical foraminal stenosis. If the predictive accuracy is increased, we believe that the deep learning model using cervical radiographs as input data can be easily and widely used in clinics or hospitals. [ABSTRACT FROM AUTHOR]

This paper discussed an efficient technique to detect near-duplicate images with higher accuracy. The proposed method improved the existing accuracy of near-duplicate image detection and classification using Haar wavelet feature extraction and classification algorithm. Due to advancements in digital image acquisition and image editing software, near-duplicate image counterfeiting has become predictable. This expanding problem needs the creation of sophisticated detection algorithms capable of effectively preventing the spread of near-duplicate image deception. Support vector machine (SVM) and K-near neighbor (KNN) classifiers are used in the classification stage of a modified deep learning model with a convolutional neural network (CNN). The classification model finds the better result on the Imperial College London dataset, with 99.12% using CNN with KNN classifier and 98.63% for CNN with SVM classifier. The classification model also gives better results on the Nanyang Technological University dataset, with 98.36% using CNN with the KNN classifier and 97.85% for CNN with the SVM classifier. The model is tested using publicly available images to find the results. According to the comparison results, this model performed significantly better result than the previous model. As a result, digital image forensics has become more critical, particularly in identifying image duplication. [ABSTRACT FROM AUTHOR]

This paper aims at applying different architectures of hybrid deep learning methods and an RBF (Radial Basis Functions)-based approach, with a comparison to traditional deep learning models, for air pollution forecasting which is the key of the air quality control management. The hybrid deep learning models are based on the combination between 1D convolutional neural network which prove during the research literature its excellent ability for features extraction, with recurrent neural network (RNN) which is appropriated for prediction tasks. The RBF-based approach is another way of approximating a nonlinear autoregressive model, using that RBF are powerful interpolation tool. The traditional deep learning methods used for comparison in this work are the simple RNN and the NARMAX model (Non-Linear AutoRegressive Moving Average with eXogenous inputs). The prediction methods are based on a real data base of pollutant concentrations and other influencing environmental air quality parameters (temperature, humidity, pressure, wind speed and wind direction) tested for different locations. All available data values are hourly recorded. As a result of this research work, it was proven that the hybrid deep learning architectures succeeded to provide the best forecasting results based on different errors measurements used as comparison criteria between all the proposed methods. [ABSTRACT FROM AUTHOR]

The primary cause of decline in cassava production are various diseases on cassava leaves. It has direct adverse impact on farmers' income. The detection of diseases in cassava leaves traditionally relies on laboratory tests or expert intervention, that is time-consuming and costly. To address these challenges, an intelligent system that can be capable of accurately and efficiently identifying cassava leaf diseases is needed. In this research, a lightweight deep learning model is proposed that take fewer parameters and gives higher accuracy for the classification of cassava leaf diseases. The proposed model incorporates depthwise separable convolution, channel, spatial attention, and a novel modified channel attention module to reduce parameters and improve classification accuracy. All the training and testing images are from the agricultural field with natural background. The model has used the dedicated testing dataset to get the real effectiveness of the model. The testing images are separate images that not used for training and validation purposes. The proposed model has achieved the 98% validation accuracy and 75% testing accuracy. The primary objective of this proposed model is to promptly identify cassava leaf diseases directly from the agricultural field to address the need of farmers. A mobile application is developed to deploy the proposed lightweight deep learning model to address farmer requirements. [ABSTRACT FROM AUTHOR]

In the domain of digital steganography, the problem of efficient and accurate steganalysis is of utmost importance. Steganalysis seeks to detect the presence of hidden data within digital media, a task that is continually evolving due to advancements in steganographic techniques. This study undertakes a detailed exploration of the SRNet model, a prominent deep learning model for steganalysis. We aim to evaluate the impact of various factors, including choice of deep learning framework, model initialization and optimization parameters, and architectural modifications on the model's steganalysis performance. Three separate implementations of the SRNet model are examined in this study: our custom implementation, an implementation using TensorFlow, and another utilizing PyTorch. Each model is evaluated on its ability to detect different payloads, or bytes of hidden data per pixel, in digital images. This investigation includes a thorough comparative analysis of different performance metrics including accuracy, recall, precision, and F1-score. Our findings indicate that the choice of deep learning framework and the parameters utilized for model initialization and optimization play significant roles in influencing the model's steganalysis effectiveness. Notably, the TensorFlow implementation, enhanced with an additional dense layer, outperforms all other models. In contrast, our custom SRNet implementation, trained with fewer epochs, offers a balance between computational cost and steganalysis performance. This study thus provides valuable insights into the adaptability and potential of the SRNet model for steganalysis, illustrating the model's performance under different configurations and implementations. It underscores the importance of continued exploration and optimization in the field of steganalysis, offering guidance for future research in this evolving domain. [ABSTRACT FROM AUTHOR]

Citrus fruit and leaf diseases pose a significant threat to citrus production worldwide, leading to substantial yield declines and economic losses. Diagnosing these diseases timely and accurately is essential to implement effective disease management strategies and preserve citrus crop yields. The main limitations of the existing approaches are substantial data requirement, computational complexity, limited discriminative power and scalability. This research proposes an automated detection system, CitrusDiseaseNet that integrates a pre-trained Convolutional Neural Network (CNN) backbone with a Kernel Extreme Learning Machine (KELM) classifier. In CitrusDiseaseNet model, the FCNN encodes high-level features from the input citrus images that captures important visual information to distinguish healthy and unhealthy cases. The KELM model is selected to convert the extracted features into high-dimensional feature space by using different kernel functions. The KELM classifier is employed as the classification head to differentiate the diseased as well as healthy citrus samples. The backpropagation algorithm is employed for model training, and the CNN backbone and KELM classifier are fine-tuned simultaneously. The proposed ACSSO algorithm efficiently explores the hyperparameter space, identifying optimal hyperparameter values for the KELM classifier. ACSSO incorporates adaptive strategies, such as variable step sizes and enhanced exploration–exploitation balance, to accelerate convergence and robustly find the best hyperparameters. The performance validation is conducted based on the significant classification related measures and the quantitative analyses. From the quantitative analysis, the proposed method achieved the accuracy rate of 98.9% and precision rate of 98.3%, recall rate of 98%, F1-score rate of 97.9% and specificity of 98.2%. The experimental result demonstrates that the proposed model attained better performances than existing approaches. [ABSTRACT FROM AUTHOR]

Mean fragment size is an important index in mine blasting since it significantly influences downstream work efficiency. Therefore, it is necessary to carry out the characteristic particle size prediction of rock fragments. Aiming at this topic, this study presents convolutional neural network (CNN), multilayer perceptron (MLP) and grey wolf optimization (GWO) algorithm, for predicting mean fragment size. The blasting data from multiple open pit mines is collected and augmented, and a large-scale database is established to conduct various parametric studies for both CNN and MLP models to obtain the best one. Then, the GWO algorithm is used to optimize the training process of the above model with the best training and validation performance to further improve the model performance. The results show that the best CNN model has a higher capacity in predicting mean fragment size than the MLP model and the GWO optimization algorithm can further improve the model performance. The model performance can be evaluated by four statistical indices, including mean square error (MSE), root mean square error (RMSE), prediction accuracy and coefficient of determination (R2). The GWO-CNN model and data augmentation method proposed in this study can be introduced as an applicable method for estimating the mean fragment size in mine blasting. [ABSTRACT FROM AUTHOR]

The bone marrow overproduces immature cells in the malignancy known as Acute Lymphoblastic Leukemia (ALL). In the United States, about 6500 occurrences of ALL are diagnosed each year in both children and adults, comprising nearly 25% of pediatric cancer cases. Recently, many computer-assisted diagnosis (CAD) systems have been proposed to aid hematologists in reducing workload, providing correct results, and managing enormous volumes of data. Traditional CAD systems rely on hematologists' expertise, specialized features, and subject knowledge. Utilizing early detection of ALL can aid radiologists and doctors in making medical decisions. In this study, Deep Dilated Residual Convolutional Neural Network (DDRNet) is presented for the classification of blood cell images, focusing on eosinophils, lymphocytes, monocytes, and neutrophils. To tackle challenges like vanishing gradients and enhance feature extraction, the model incorporates Deep Residual Dilated Blocks (DRDB) for faster convergence. Conventional residual blocks are strategically placed between layers to preserve original information and extract general feature maps. Global and Local Feature Enhancement Blocks (GLFEB) balance weak contributions from shallow layers for improved feature normalization. The global feature from the initial convolution layer, when combined with GLFEB-processed features, reinforces classification representations. The Tanh function introduces non-linearity. A Channel and Spatial Attention Block (CSAB) is integrated into the neural network to emphasize or minimize specific feature channels, while fully connected layers transform the data. The use of a sigmoid activation function concentrates on relevant features for multiclass lymphoblastic leukemia classification The model was analyzed with Kaggle dataset (16,249 images) categorized into four classes, with a training and testing ratio of 80:20. Experimental results showed that DRDB, GLFEB and CSAB blocks' feature discrimination ability boosted the DDRNet model F1 score to 0.96 with minimal computational complexity and optimum classification accuracy of 99.86% and 91.98% for training and testing data. The DDRNet model stands out from existing methods due to its high testing accuracy of 91.98%, F1 score of 0.96, minimal computational complexity, and enhanced feature discrimination ability. The strategic combination of these blocks (DRDB, GLFEB, and CSAB) are designed to address specific challenges in the classification process, leading to improved discrimination of features crucial for accurate multi-class blood cell image identification. Their effective integration within the model contributes to the superior performance of DDRNet. [ABSTRACT FROM AUTHOR]

Chemical molecular structures are a direct and convenient means of expressing chemical knowledge, playing a vital role in academic communication. In chemistry, hand drawing is a common task for students and researchers. If we can convert hand-drawn chemical molecular structures into machine-readable formats, like SMILES encoding, computers can efficiently process and analyze these structures, significantly enhancing the efficiency of chemical research. Furthermore, with the progress of educational technology, automated grading is gaining popularity. When machines automatically recognize chemical molecular structures and assess the correctness of the drawings, it offers great convenience to teachers. We created ChemReco, a tool designed to identify chemical molecular structures involving three atoms: C, H, and O, providing convenience for chemical researchers. Currently, there are limited studies on hand-drawn chemical molecular structures. Therefore, the primary focus of this paper is constructing datasets. We propose a synthetic image method to rapidly generate images resembling hand-drawn chemical molecular structures, enhancing dataset acquisition efficiency. Regarding model selection, the hand-drawn chemical molecule structural recognition model developed in this article achieves a final recognition accuracy of 96.90%. This model employs the encoder-decoder architecture of EfficientNet + Transformer, demonstrating superior performance compared to other encoder-decoder combinations. [ABSTRACT FROM AUTHOR]

Children suffering with spontaneous speech impairment or inappropriate communication abilities like disordered speech or delayed speech face challenges when involved in conversations. One of the motivating reasons for this work is to use the potential of deep learning models along with an effective feature extractor to automate the detection of specific language impairment (SLI) in children. Clinicians or speech pathologists use standard assessment tools that are time consuming as well as prone to various behavioural factors which can compromise the timely identification of the SLI in children. Moreover, the scarcity of annotated disordered children's speech adds to the complexity of training the reliable SLI detection model. The recent work focuses mainly on the utterance of vowels, scanning the acoustic features or the texture of the children's speech signals to detect the SLI. This work seeks to evaluate different components of children's speech like vowels, consonants and sentences to diagnose healthy and disordered speech. Speech samples are collected from Indian children in the age-group of 5-15 years speaking a secondary language English. The proposed method makes use of a combination of mel frequency cepstral co-efficients and i-vectors as a feature vector to identify SLI and distinguish it from mispronunciations due to second language usage. Moreover, analysis of variance (ANOVA) test has been implemented to choose the most significant MFCC and i-vector features. Finally, the selected features are given as input to pretrained models like VGG-16, MobileNet-v2, ResNet-50 and ResNet-101. Eventually, we study and evaluate the effect of parameters like age and model used on different parameters of speech like vowels, consonants, 3-word, 4-word and 5-word sentences in the dataset to diagnose healthy and disordered speech samples. 5-fold cross validation (CV) has been used to compensate for the limited size of dataset and achieve robust results. The experimental results show that with the proposed implementation method highest accuracy of 98.70% can be achieved on the vowels component in identifying the disordered children speech signals using MobileNet-v2 model. [ABSTRACT FROM AUTHOR]

Nowadays, there is an increase in attention to the college student's mental health, and to enhance the awareness related to college students' mental health, colleges and universities have executed an immense range of mental health publicity activities. In order to better combine deep learning with classroom teaching, this paper puts forward a deep learning algorithm formulated on convolutional neural networks. The purpose of this research is to investigate the development and use of a cultivation mechanism for mental health education of college students in campus culture creation from the perspective of deep learning. The study's primary goal is to comprehend college students' mental health training in campus culture creation. The study's objective is to develop experimental outcomes of college students utilizing mental health education courses as an optional or mandatory course. Finally, investigations related to college students' mental health from the current situation in China, the investigation, statistics and analysis related to the college students in China are carried out in this situation. The experimental results of this study show that 62 of the 156 schools and universities assessed provide courses on mental health education for college students that are both obligatory and optional. According to the students questionnaire survey, 86.7% of respondents believe that it is critical to establish mental health related educational courses, 61.9% believe that compulsory courses should be established, and students want to add group guidance or activities to the teaching process to improve their experience and participation. [ABSTRACT FROM AUTHOR]

It is desired to apply deep learning models (DLMs) to assist physicians in distinguishing abnormal/normal lung sounds as quickly as possible. The performance of DLMs depends on feature-related and model-related parameters heavily. In this paper, the relationship between performance and feature-related parameters of a DLM, i.e., convolutional neural network (CNN) is analyzed through experiments. ICBHI 2017 is selected as the lung sounds dataset. The sensitivity analysis of classification performance of the DLM on three parameters, i.e., the length of lung sounds frame, overlap percentage (OP) of successive frames and feature type, is performed. An augmented and balanced dataset is acquired by the way of white noise addition, time stretching and pitch shifting. The spectrogram and mel frequency cepstrum coefficients of lung sounds are used as features to the CNN, respectively. The results of training and test show that there exists significant difference on performance among various parameter combinations. The parameter OP is performance sensitive. The higher OP, the better performance. It is concluded that for fixed sampling frequency 8 kHz, frame size 128, OP 75% and spectrogram feature is optimum under which the performance is relatively better and no extra computation or storage resources are required. [ABSTRACT FROM AUTHOR]

The vast majority of online media rely heavily on the revenues generated by their readers' views, and due to the abundance of such outlets, they must compete for reader attention. It is a common practise for publishers to employ attention-grabbing headlines as a means to entice users to visit their websites. These headlines, commonly referred to as clickbaits, strategically leverage the curiosity gap experienced by users, enticing them to click on hyperlinks that frequently fail to meet their expectations. Therefore, the identification of clickbaits is a significant NLP application. Previous studies have demonstrated that language models can effectively detect clickbaits. Deep learning models have attained great success in text-based assignments, but these are vulnerable to adversarial modifications. These attacks involve making undetectable alterations to a small number of words or characters in order to create a deceptive text that misleads the machine into making incorrect predictions. The present work introduces "Non-Alpha-Num", a newly proposed textual adversarial assault that functions in a black box setting, operating at the character level. The primary goal is to manipulate a certain NLP model in a manner that the alterations made to the input data are undetectable by human observers. A series of comprehensive tests were conducted to evaluate the efficacy of the suggested attack approach on several widely-used models, including Word-CNN, BERT, DistilBERT, ALBERTA, RoBERTa, and XLNet. These models were fine-tuned using the clickbait dataset, which is commonly employed for clickbait detection purposes. The empirical evidence suggests that the attack model being offered routinely achieves much higher attack success rates (ASR) and produces high-quality adversarial instances in comparison to traditional adversarial manipulations. The findings suggest that the clickbait detection system has the potential to be circumvented, which might have significant implications for current policy efforts. [ABSTRACT FROM AUTHOR]

Coastal aquifer vulnerability assessment (CAVA) studies are essential for mitigating the effects of seawater intrusion (SWI) worldwide. In this research, the vulnerability of the coastal aquifer in the Lahijan region of northwest Iran was investigated. A vulnerability map (VM) was created applying hydrogeological parameters derived from the original GALDIT model (OGM). The significance of OGM parameters was assessed using the mean decrease accuracy (MDA) method, with the current state of SWI emerging as the most crucial factor for evaluating vulnerability. To optimize GALDIT weights, we introduced the biogeography-based optimization (BBO) and gray wolf optimization (GWO) techniques to obtain to hybrid OGM-BBO and OGM-GWO models, respectively. Despite considerable research focused on enhancing CAVA models, efforts to modify the weights and rates of OGM parameters by incorporating deep learning algorithms remain scarce. Hence, a convolutional neural network (CNN) algorithm was applied to produce the VM. The area under the receiver-operating characteristic curves for OGM-BBO, OGM-GWO, and VMCNN were 0.794, 0.835, and 0.982, respectively. According to the CNN-based VM, 41% of the aquifer displayed very high and high vulnerability to SWI, concentrated primarily along the coastline. Additionally, 32% of the aquifer exhibited very low and low vulnerability to SWI, predominantly in the southern and southwestern regions. The proposed model can be extended to evaluate the vulnerability of various coastal aquifers to SWI, thereby assisting land use planers and policymakers in identifying at-risk areas. Moreover, deep-learning-based approaches can help clarify the associations between aquifer vulnerability and contamination resulting from SWI. [ABSTRACT FROM AUTHOR]

To use a novel deep learning system to localize the hip joints and detect findings of cam-type femoroacetabular impingement (FAI). A retrospective search of hip/pelvis radiographs obtained in patients to evaluate for FAI yielded 3050 total studies. Each hip was classified separately by the original interpreting radiologist in the following manner: 724 hips had severe cam-type FAI morphology, 962 moderate cam-type FAI morphology, 846 mild cam-type FAI morphology, and 518 hips were normal. The anteroposterior (AP) view from each study was anonymized and extracted. After localization of the hip joints by a novel convolutional neural network (CNN) based on the focal loss principle, a second CNN classified the images of the hip as cam positive, or no FAI. Accuracy was 74% for diagnosing normal vs. abnormal cam-type FAI morphology, with aggregate sensitivity and specificity of 0.821 and 0.669, respectively, at the chosen operating point. The aggregate AUC was 0.736. A deep learning system can be applied to detect FAI-related changes on single view pelvic radiographs. Deep learning is useful for quickly identifying and categorizing pathology on imaging, which may aid the interpreting radiologist. [ABSTRACT FROM AUTHOR]