Search

This paper focuses on exploring and comparing different machine learning algorithms in the context of diabetes management. The aim is to understand their characteristics, mathematical foundations, and practical implications specifically for predicting blood glucose levels. The study provides an overview of the algorithms, with a particular emphasis on deep learning techniques such as Long Short-Term Memory Networks. Efficiency is a crucial factor in practical machine learning applications, especially in the context of diabetes management. Therefore, the paper investigates the trade-off between accuracy, resource utilisation, time consumption, and computational power requirements, aiming to identify the optimal balance. By analysing these algorithms, the research uncovers their distinct behaviours and highlights their dissimilarities, even when their analytical underpinnings may appear similar. [ABSTRACT FROM AUTHOR]

The 2019 new coronavirus illness (COVID-19) is an international public health emergency. Our social and healthcare systems are under a great deal of strain as a result of the daily increase in infection rates and fatalities. Doctors typically perform a chest Xray to identify the diseased areas of the lungs since pneumonia is a common type of infection that spreads in the lungs. In this paper, we propose a Convolution Neural Network via the li regularization model to detect COVID-19 patients using chest X-Ray images. Due to the lack of the COVID-19 benchmark dataset, we use deep learning techniques to identify the best pre-trained CNN model for this job by comparing 15 models. The suggested algorithm was tested on 1316 photos (116 COVID-19 cases, 328 healthy controls, and 872 pneumonia cases), with 66% for training, 17% for validation, and 17% for testing. The classification accuracy, loss, valueaccuracy, and value-loss values obtained by the suggested technique are 0.9912, 0.0187, 0.1119, and 0.9506 respectively. Additionally, the model effectively decreases training loss while boosting accuracy. The results show that proposed procedures are more effective than existing ones at identifying COVID-19 cases from chest X-ray pictures. [ABSTRACT FROM AUTHOR]

This paper proposes a new framework for leak diagnosis in pipelines using leak-augmented scalograms and deep learning. Acoustic emission (AE) scalogram images obtained from the continuous wavelet transform have been useful for pipeline health diagnosis, particularly when combined with deep learning. However, background noise has a significant impact on AE signals, which can reduce the accuracy of pipeline health identification using classification models. To address this issue, a new type of scalograms called leak-augmented scalogram is introduced, which enhances the variation in colour intensities of AE scalogram images. The leak-augmented scalograms are obtained by pre-processing them using image-enhancing Gaussian and Laplacian filters. The proposed method utilizes convolutional neural networks (CNNs) and convolutional autoencoders (CAEs) for feature extraction. The CNN extracts patterns specific to local changes, while the CAE extracts holistic patterns from the leak-augmented scalograms. The resulting leak susceptible and leak holistic indicators are merged into a single feature pool and provided as input to a shallow artificial neural network (ANN) to evaluate pipeline health conditions. The proposed method achieves high classification as well as accuracy, precision, F-1 Score and recall, compared to existing state of the art methods. [ABSTRACT FROM AUTHOR]

Reliable evaluation of damage in vehicles is a primary concern in the insurance industry. Consequently, solutions enhanced with Artificial Intelligence (AI) have become the norm. During the assessment, precise damage segmentation plays a crucial role. Dent is a type of damage that can commonly occur in vehicles. It is difficult to pinpoint and tends to blend in with the background. This paper proposes a novel loss function to improve dent segmentation accuracy in vehicle insurance claims. Centre and Pixel-based Weighted DICE (CPW-DICE) is a loss function that performs pixel-based weighting. The CPW-DICE aims to concentrate on the centre of the dent damage to lessen faulty segmentations. CPW-DICE generates a weight mask during training by employing ground truth (GT) and prediction masks. Simultaneously, the weight mask is incorporated into DICE loss. Experiments conducted on our comprehensive internal dataset show a 3% improvement in Intersection over Union (IoU) score for three state-of-the-art (SOTA) approaches compared to DICE loss. Finally, CPW-DICE is evaluated in similar tasks to demonstrate its benefits beyond car damage segmentation. [ABSTRACT FROM AUTHOR]

Most studies on privacy in machine learning have primarily focused on supervised learning, with little research on privacy concerns in reinforcement learning. However, our study has demonstrated that observation information can be extracted through trajectory analysis. In this paper, we propose a variable information inference attack targeting the observation space of policy models, which is categorised into two types: observed value inference attack and observed variable inference. Our algorithm has demonstrated a high success rate in privacy inference attacks for both types of observation information. [ABSTRACT FROM AUTHOR]

This paper focuses on exploring and comparing different machine learning algorithms in the context of diabetes management. The aim is to understand their characteristics, mathematical foundations, and practical implications specifically for predicting blood glucose levels. The study provides an overview of the algorithms, with a particular emphasis on deep learning techniques such as Long Short-Term Memory Networks. Efficiency is a crucial factor in practical machine learning applications, especially in the context of diabetes management. Therefore, the paper investigates the trade-off between accuracy, resource utilisation, time consumption, and computational power requirements, aiming to identify the optimal balance. By analysing these algorithms, the research uncovers their distinct behaviours and highlights their dissimilarities, even when their analytical underpinnings may appear similar. [ABSTRACT FROM AUTHOR]

Application of deep learning technology in remote sensing image target detection(RSITD)has made remarkable progress in recent years. However, existing methods usually fuse spatial context information at the pixel level while ignoring the mining of spatial relationships between ground objects. This paper proposes a high-resolution remote sensing object detection network fusion of road-adjacent relationships (HRRSODN) that integrates road proximity relations. Taking artificial features such as toll stations adjacent to roads as an example, the spatial relationship of road proximity is used to assist visual information and improve the extraction accuracy. The method optimizes detection by: Using the spatial relationship as prior information; fusing coordinate attention that captures the spatial relationship between objects; and adding the attention generated by the spatial relationship to the attention generated in the original X and Y directions. This enables the model to understand the spatial layout of objects in the image. The distance loss function concretizes the spatial relationship into a distance index. The distance loss is incorporated into the training process by measuring the spatial distance between feature targets. Thus, during training, the network focuses not only on the positional information of the targets but also pays more attention to the spatial layout of the features. Experimental results show that, compared with conventional methods, the proposed method has achieved significant improvements in detection performance and mining spatial relationships. This verifies the importance of considering the spatial relationship of ground objects in remote sensing target detection. Further, this paper proposes a new method for target detection in remote sensing images (RSIs), which effectively utilizes the spatial relationship information between targets, and provides a new idea for further improving target detection in RSI. [ABSTRACT FROM AUTHOR]

In this paper, we present automatic, deep-learning methods for pipeline detection in underwater environments. Seafloor pipelines are critical infrastructure for oil and gas transport. The inspection of those pipelines is required to verify their integrity and determine the need for maintenance. Underwater conditions present a harsh environment that is challenging for image recognition due to light refraction and absorption, poor visibility, scattering, and attenuation, often causing poor image quality. Modern machine-learning object detectors utilize Convolutional Neural Network (CNN), requiring a training dataset of sufficient quality. In the paper, six different deep-learning CNN detectors for underwater object detection were trained and tested: five are based on the You Only Look Once (YOLO) architectures (YOLOv4, YOLOv4-Tiny, CSP-YOLOv4, YOLOv4@Resnet, YOLOv4@Den seNet), and one on the Faster Region-based CNN (RCNN) architecture. The models' performances were evaluated in terms of detection accuracy, mean average precision (mAP), and processing speed measured with the Frames Per Second (FPS) on a custom dataset containing underwater pipeline images. In the study, the YOLOv4 outperformed other models for underwater pipeline object detection resulting in an mAP of 94.21% with the ability to detect objects in real-time. Based on the literature review, this is one of the pioneering works in this field. [ABSTRACT FROM AUTHOR]

Deep Learning (DL) is a type of machine learning used to model big data to extract complex relationship as it has the advantage of automatic feature extraction. This paper presents a review on DL showing all its network topologies along with their advantages, limitations, and applications. The most popular Deep Neural Network (DNN) is called a Convolutional Neural Network (CNN), the review found that the most important issue is designing better CNN topology, which needs to be addressed to improve CNN performance further. This paper addresses this problem by proposing a novel nature inspired hybrid algorithm that combines the Bees Algorithm (BA), which is known to mimic the behavior of honey bees, with Bayesian Optimization (BO) in order to increase the overall performance of CNN, which is referred to as BA-BO-CNN. Applying the hybrid algorithm on Cifar10DataDir benchmark image data yielded an increase in the validation accuracy from 80.72% to 82.22%, while applying it on digits datasets showed the same accuracy as the existing original CNN and BO-CNN, but with an improvement in the computational time by 3 min and 12 s reduction, and finally applying it on concrete cracks images produced almost similar results to existing algorithms. [ABSTRACT FROM AUTHOR]

Many blue and white porcelain are unearthed in Jingdezhen every year. The patterns on the sherds have important research significance. At present, the classification of porcelain shards is mainly based on manual work, which has the disadvantages of large workload. The use of automatic classification methods also faces complex patterns and sample sizes. In order to solve these problems, this paper proposes a new automatic recognition method based on deep learning, including data preprocessing method combined with color segmentation algorithm, a new data augmentation method FCutMix for regions of interest, a new integration strategy and the redesigned deep network model FFCNet that integrates multiple features. After experiments, the data preprocessing method, feature fusion method and integration strategy proposed in the paper can effectively improve the performance of the model by removing redundant information and adding effective features. The FCutMix method can also obtain more accurate mixed samples than the traditional CutMix. The method proposed in this paper improves the accuracy of tasks in 14 categories from 71.7% to 83.2% in a dataset containing only 373 images of porcelain sherds. In the future, this research will further design the network structure and multi-level feature fusion. [ABSTRACT FROM AUTHOR]

With the rapid development of network technology, a variety of new malicious attacks appear while attack methods are constantly updated. As the attackers exploit the vulnerabilities of popular third-party components to invade target websites, further improving the classification accuracy of malicious network traffic is the key to improving the performance of abnormal traffic detection. Existing intrusion detection systems may suffer from incomplete feature extraction and low classification accuracy. Thus, this paper proposes an efficient hybrid parallel deep learning model (HPM) for intrusion detection based on margin learning. First, HPM constructs two parallel CNN architectures and fuses the spatial features obtained through full convolution. Secondly, the temporal information of the fused features is parsed separately using two parallel LSTMs. Finally, the extracted spatial-temporal features are fed into the CosMargin classifier for classification detection after global convolution and global pooling. Besides, this paper proposes an improved traffic feature extraction method, which not only reduces redundant features but also speeds up the convergence speed of the network. In the experiment, our HPM has achieved 99% detection accuracy of each malicious class, ranging from 5%–10% improvement with other models, which demonstrates the superiority of our proposed model. [ABSTRACT FROM AUTHOR]

This paper aims to fill in the missing time series of hourly surface water levels of some stations installed along the River Seine, using the long short-term memory (LSTM) algorithm. In our study, only the water level data from the same station, containing many missing parts, were used as input and output variables, in contrast to other works where several features are available to take advantage of e.g. other station data/physical variables. A sensitive analysis is presented on both the network properties and how the input and output data are reentered to better determine the appropriate strategy. Numerous scenarios are presented, each an updated version of the previous one. Ultimately, the final version of the model can impute missing values of up to one year of hourly data with great flexibility (one-year Root-Mean-Square Error (RMSE) = 0.14 m) regardless of the location of the missing gaps in the series or their size. [ABSTRACT FROM AUTHOR]

With the rapid development of network technology, a variety of new malicious attacks appear while attack methods are constantly updated. As the attackers exploit the vulnerabilities of popular third-party components to invade target websites, further improving the classification accuracy of malicious network traffic is the key to improving the performance of abnormal traffic detection. Existing intrusion detection systems may suffer from incomplete feature extraction and low classification accuracy. Thus, this paper proposes an efficient hybrid parallel deep learning model (HPM) for intrusion detection based on margin learning. First, HPM constructs two parallel CNN architectures and fuses the spatial features obtained through full convolution. Secondly, the temporal information of the fused features is parsed separately using two parallel LSTMs. Finally, the extracted spatial-temporal features are fed into the CosMargin classifier for classification detection after global convolution and global pooling. Besides, this paper proposes an improved traffic feature extraction method, which not only reduces redundant features but also speeds up the convergence speed of the network. In the experiment, our HPM has achieved 99% detection accuracy of each malicious class, ranging from 5%–10% improvement with other models, which demonstrates the superiority of our proposed model. [ABSTRACT FROM AUTHOR]

With climate change, decreases in winter snow storage and increases in precipitation duration and intensities will alter the occurrence of floods in high-latitude countries. The state-of-the-art hydrological climate-impact model chain consists of one or more global climate models, downscaling and bias-correction techniques, and one or more hydrological models. Machine learning offers a complementary approach to hydrological climate-impact modelling by facilitating direct downscaling from large-scale atmospheric variables to streamflow. This paper presents the development of multilayer perceptron (MLP) and long short-term memory (LSTM) neural networks benchmarked against regression tree models for reconstruction of daily streamflow and floods from atmospheric reanalysis data with comparable resolution to global climate model outputs. Catchment-specific, physically-based input features representing the dominant flood drivers were identified for 27 catchments in Norway. Overall, the LSTM obtained the highest accuracy. This article provides a springboard for future research on hydrological climate-impact modelling with neural networks in high-latitude countries. [ABSTRACT FROM AUTHOR]

In recent days, COVID-19 pandemic has affected several people's lives globally and necessitates a massive number of screening tests to detect the existence of the coronavirus. At the same time, the rise of deep learning (DL) concepts helps to effectively develop a COVID-19 diagnosis model to attain maximum detection rate with minimum computation time. This paper presents a new Residual Network (ResNet) based Class Attention Layer with Bidirectional LSTM called RCAL-BiLSTM for COVID-19 Diagnosis. The proposed RCAL-BiLSTM model involves a series of processes namely bilateral filtering (BF) based preprocessing, RCAL-BiLSTM based feature extraction, and softmax (SM) based classification. Once the BF technique produces the preprocessed image, RCAL-BiLSTM based feature extraction process takes place using three modules, namely ResNet based feature extraction, CAL, and Bi-LSTM modules. Finally, the SM layer is applied to categorize the feature vectors into corresponding feature maps. The experimental validation of the presented RCAL-BiLSTM model is tested against Chest-X-Ray dataset and the results are determined under several aspects. The experimental outcome pointed out the superior nature of the RCAL-BiLSTM model by attaining maximum sensitivity of 93.28%, specificity of 94.61%, precision of 94.90%, accuracy of 94.88%, F-score of 93.10% and kappa value of 91.40%. [ABSTRACT FROM AUTHOR]

Reliable evaluation of damage in vehicles is a primary concern in the insurance industry. Consequently, solutions enhanced with Artificial Intelligence (AI) have become the norm. During the assessment, precise damage segmentation plays a crucial role. Dent is a type of damage that can commonly occur in vehicles. It is difficult to pinpoint and tends to blend in with the background. This paper proposes a novel loss function to improve dent segmentation accuracy in vehicle insurance claims. Centre and Pixel-based Weighted DICE (CPW-DICE) is a loss function that performs pixel-based weighting. The CPW-DICE aims to concentrate on the centre of the dent damage to lessen faulty segmentations. CPW-DICE generates a weight mask during training by employing ground truth (GT) and prediction masks. Simultaneously, the weight mask is incorporated into DICE loss. Experiments conducted on our comprehensive internal dataset show a 3% improvement in Intersection over Union (IoU) score for three state-of-the-art (SOTA) approaches compared to DICE loss. Finally, CPW-DICE is evaluated in similar tasks to demonstrate its benefits beyond car damage segmentation. [ABSTRACT FROM AUTHOR]

Most studies on privacy in machine learning have primarily focused on supervised learning, with little research on privacy concerns in reinforcement learning. However, our study has demonstrated that observation information can be extracted through trajectory analysis. In this paper, we propose a variable information inference attack targeting the observation space of policy models, which is categorised into two types: observed value inference attack and observed variable inference. Our algorithm has demonstrated a high success rate in privacy inference attacks for both types of observation information. [ABSTRACT FROM AUTHOR]

Polarimetric synthetic aperture radar (PolSAR) images are classified mainly according to the backscattering information of ground objects. For regions with complex backscattering information, misclassification is easy to occur, which leads to challenges in improving the classification accuracy of the PolSAR image. Given this situation, this paper combines the Deep Learning Model and traditional classifiers to classify PolSAR image. First, the Convolution Neural Network (CNN) was used to classify the PolSAR image and according to the category prediction probability of pixels, the key pixels easily misclassified are located. Then, the adaptive boosting (AdaBoost) algorithm combined the three shallow classifiers (the Support Vector Machine (SVM), the Wishart and the Decision Tree classifier) into strong classifiers to reclassify the key pixels. Finally, the labels of key pixels and other pixels are output as the final classification result. Experiments on two PolSAR images show that the proposed method can improve classification performance and obtain better classification results. [ABSTRACT FROM AUTHOR]

Black and odorous water seriously affects the ecological balance of rivers and the health of people living nearby. Satellite remote sensing technology with its advantages of a large range, long-time series, low cost, and high efficiency, has provided a new area for water quality detection. Much archived remote sensing satellite data can be further processed and used as a data source for black and odorous water detection. In this paper, Gaofen-2 remote sensing data with a spatial resolution of 1 m is leveraged as the data source. To enrich the data source in the northern coastal zone of China, we have built a high-quality remote sensing dataset, called the remote sensing images for black and odorous water detection (RSBD) dataset, which is collected from the Gaofen-2 satellite in Yantai, China. In addition, we propose a network with an encoder-decoder discriminant structure for black and odorous water detection. In the network, an augmented attention module is designed to capture a more comprehensive semantic feature representation. Further, the median balancing loss function is adopted to solve the imbalance issues. Experimental results demonstrate that the network is superior to other state-of-the-art semantic segmentation methods on our dataset. [ABSTRACT FROM AUTHOR]

In this study, we searched for the latest literature on the use of deep learning applications to combat COVID-19 and these were identified from several search engines including IEEE Xplore, Google Scholar, PubMed, and Scopus. This involved a comprehensive analysis of the studies to identify the challenges associated with the use of deep learning models with a view to highlight the possible future trends in the development of deep learning systems that are efficient and more reliable for the diagnosis of COVID-19 patients. This paper provides information related to the deep learning techniques used to detect COVID-19. This paper discusses the Convolutional Neural Networks’ (CNNs) structure, how to train CNNs, and highlights the different pre-trained models of CNNs that can be used for the detection of COVID-19. This paper explores the latest developments in the diagnosis of COVID-19 using deep learning applications that rely on the use of X-ray images taken from medical imaging samples. A review of the different models developed to facilitate effective diagnosis of COVID-19 provides information regarding the experimental data, the data splitting techniques used, as well as the proposed architecture for detecting COVID-19 and the different evaluation metrics for each model. This paper is a useful resource for medical and technical experts, as it helps them to develop a sound understanding of how deep learning techniques can be harnessed to stop the spread of COVID-19. [ABSTRACT FROM AUTHOR]

Simultaneous Localization and Mapping (SLAM) has been widely used in emergency response, self-driving and city-scale 3D mapping and navigation. Recent deep-learning based feature point extractors have demonstrated superior performance in dealing with the complex environmental challenges (e.g. extreme lighting) while the traditional extractors are struggling. In this paper, we have successfully improved the robustness and accuracy of a monocular visual SLAM system under various complex scenes by adding a deep learning based visual localization thread as an augmentation to the visual SLAM framework. In this thread, our feature extractor with an efficient lightweight deep neural network is used for absolute pose and scale estimation in real time using the highly accurate georeferenced prior map database at 20cm geometric accuracy created by our in-house and low-cost LiDAR and camera integrated device. The closed-loop error provided by our SLAM system with and without this enhancement is 1.03m and 18.28m respectively. The scale estimation of the monocular visual SLAM is also significantly improved (0.01 versus 0.98). In addition, a novel camera-LiDAR calibration workflow is also provided for large-scale 3D mapping. This paper demonstrates the application and research potential of deep-learning based vision SLAM with image and LiDAR sensors. [ABSTRACT FROM AUTHOR]

Anomaly detection in Hyperspectral Imagery (HSI) has received considerable attention because of its potential application in several areas. Numerous anomaly detection algorithms for HSI have been proposed in the literature; however, due to the use of different datasets in previous studies, an extensive performance comparison of these algorithms is missing. In this paper, an overview of the current state of research in hyperspectral anomaly detection is presented by broadly dividing all the previously proposed algorithms into eight different categories. In addition, this paper presents the most comprehensive comparative analysis to-date in hyperspectral anomaly detection by evaluating 22 algorithms on 17 different publicly available datasets. Results indicate that attribute and edge-preserving filtering-based detection (AED), local summation anomaly detection based on collaborative representation and inverse distance weight (LSAD-CR-IDW) and local summation unsupervised nearest regularized subspace with an outlier removal anomaly detector (LSUNRSORAD) perform better as indicated by the mean and median values of area under the receiver operating characteristic (ROC) curves. Finally, this paper studies the effect of various dimensionality reduction techniques on anomaly detection. Results indicate that reducing the number of components to around 20 improves the performance; however, any further decrease deteriorates the performance. [ABSTRACT FROM AUTHOR]

Multi-class change detection can make various ground monitoring projects more efficient and convenient. With the development of deep learning, the multi-class change detection methods have introduced Deep Neural Network (DNN) to improve the accuracy and efficiency of traditional methods. The class imbalance in the image will affect the feature extraction effect of DNN. Existing deep learning methods rarely consider the impact of data on DNN. To solve this problem, this paper proposes a class rebalancing algorithm based on data distribution. The algorithm iteratively trains the SSL model, obtains the distribution of classes in the data, then expands the original dataset according to the distribution of classes, and finally trains the baseline SSL model using the expanded dataset. The trained semantic segmentation model is used to detect multi-class changes in two-phase images. This paper is the first time to introduce the image class balancing method in the multi-class change detection task, so a control experiment is designed to verify the effectiveness and superiority of this method for the unbalanced data. The mIoU of the class rebalancing algorithm in this paper reaches 0.4615, which indicates that the proposed method can effectively detect ground changes and accurately distinguish the types of ground changes. [ABSTRACT FROM AUTHOR]

As one of the most severe natural disasters in the world, floods caused substantial economic losses and casualties every year. Timely and accurate acquisition of flood inundation extent could provide technical support for relevant departments in the field of flood emergency response and disaster relief. Given the accuracy of existing research works extracting flood inundation extent based on Synthetic Aperture Radar (SAR) images and deep learning methods is relatively low, this study utilized Sentinel-1 SAR images as the data source and proposed a novel model named flood water body extraction convolutional neural network (FWENet) for flood information extraction. Then three classical semantic segmentation models (UNet, Deeplab v3 and UNet++) and two traditional water body extraction methods (Otsu global thresholding method and Object-Oriented method) were compared with the FWENet model. Furthermore, this paper analyzed the water body area change situations of Poyang Lake. The main results of this paper were as follows: Compared with other five water body extraction methods, the FWENet model achieved the highest water body extraction accuracy, its F1 score and mean intersection over union (mIoU) were 0.9871 and 0.9808, respectively. This study could guarantee the subsequent research on flood extraction based on SAR images. [ABSTRACT FROM AUTHOR]

The ship hull form optimization using the Computational Fluid Dynamics (CFD) method is increasingly employed in the early design of a ship, as an optimal ship hull form can obtain good hydrodynamics. However, it is time-consuming due to its many CFD simulations for the optimization. This paper presents a ship hull form optimization loop using the surrogate model, deep belief network (DBN), to reduce the wave-making resistance of the Wigley ship. The prediction performance of the wave-making resistance of the Wigley ship using the DBN method is discussed and compared with the traditional surrogate models found in this study. The results show that the resistance obtained using the deep belief network algorithm is superior to that obtained using the typical surrogate models. Then, a ship hull form optimization framework is built by integrating the Free From Deformation, non-linear programming by quadratic Lagrangian and deep belief network algorithms. The optimization results show that the deep belief network-based ship hull form optimization loop can be used to optimize the Wigley ship. The study presented in this paper could provide a deep learning algorithm for the ship design optimization. [ABSTRACT FROM AUTHOR]

Building structural type information is the foundation for seismic risk assessment and management since it reflects the behavior of buildings under seismic load. However, in earthquake-prone regions, most of this information is out-of-date or nonexistent. This paper proposes a deep learning-based method for automatically identifying building structural types from unmanned aerial vehicle (UAV) oblique images. The method consists of four steps: (1) collect facades of buildings with different structural types by web crawler technology as a sample set; (2) construct a convolutional neural network with a facade prior knowledge attention branch and train the model using the sample set; (3) extract building facades from UAV oblique images based on the georeferencing results of feature points as the test set; (4) identify building structural types by inputting the test set into the trained model. Three cases have been selected to verify the feasibility and applicability of the method. The average recall rate of 85% and the average F1 score of 83% have been achieved in areas with regular building distribution. This method integrates multidisciplinary knowledge to provide a solution for rapid collection of building vulnerability information, and expands the role of oblique photography data in urban management and disaster prevention planning. [ABSTRACT FROM AUTHOR]

Deep learning algorithms show good prospects for remote sensing flood monitoring. They mostly rely on huge amounts of labeled data. However, there is a lack of available labeled data in actual needs. In this paper, we propose a high-resolution multi-source remote sensing dataset for flood area extraction: GF-FloodNet. GF-FloodNet contains 13388 samples from Gaofen-3 (GF-3) and Gaofen-2 (GF-2) images. We use a multi-level sample selection and interactive annotation strategy based on active learning to construct it. Compare with other flood-related datasets, GF-FloodNet not only has a spatial resolution of up to 1.5 m and provides pixel-level labels, but also consists of multi-source remote sensing data. We thoroughly validate and evaluate the dataset using several deep learning models, including quantitative analysis, qualitative analysis, and validation on large-scale remote sensing data in real scenes. Experimental results reveal that GF-FloodNet has significant advantages by multi-source data. It can support different deep learning models for training to extract flood areas. There should be a potential optimal boundary for model training in any deep learning dataset. The boundary seems close to 4824 samples in GF-FloodNet. We provide GF-FloodNet at and . [ABSTRACT FROM AUTHOR]

Hyperspectral images carry numerous spectral bands, and their wealth of band data is a valuable source of information for the accurate classification of ground objects. Three-dimensional (3D) convolution, although an excellent spectral information extraction method, is limited by its huge number of parameters and long model training time. To allow better integration of 3D convolution with the most popular transformer models currently available, a new architecture called mobile 3D convolutional vision transformer (MDvT) is proposed. The MDvT introduces inverted residual structure to reduce the number of model parameters and balance the data mining efficiency of low-dimensional data input. Simultaneously, a square patch is used to cut the sequence of tokens to accelerate the model operation. Through extensive experiments, we evaluated the classification overall performance of the proposed MDvT on the WHU-Hi and Pavia University datasets, and demonstrated significant improvements in classification accuracy and model runtime compared with classical deep learning models. It is worth noting that compared with directly integrating 3D convolution into the transformer model, the MDvT architecture improves the accuracy while reducing the time to train an epoch by approximately 58.54%. To facilitate the reproduction of the work in this paper, the model code is available at . [ABSTRACT FROM AUTHOR]

To quickly detect and count the number of bayberry trees, this paper improves the YOLO-v4 model and proposes an optimal YOLO-v4 method for detecting bayberry trees based on UAV images. We used the Leaky_ReLU activation function to accelerate the model extraction speed and used the DIoU NMS to retain the most accurate prediction boxes. In order to increase the recall rate of the object detection and construct the optimal YOLO-v4 model, the K-Means clustering method was embedded into DIoU NMS. We trained the model using UAV images of bayberry trees, it was determined that the optimal YOLO-v4 model threshold was 0.25, which had the best extraction effect. The optimal YOLO-v4 model had a detection accuracy of up to 97.78% and a recall rate of up to 98.16% on the dataset. The optimal YOLO-v4 model was compared with YOLO-v4, YOLO-v4 tiny, the YOLO-v3 model, and the Faster R-CNN model. With guaranteed accuracy, the recall rate was higher, up to 97.45%, and the detection of bayberry trees was better in different contexts. The result shows that the optimal YOLO-v4 model can accurately achieve the rapid detection and statistics of the number of bayberry trees in large-area orchards. [ABSTRACT FROM AUTHOR]

The point segmentation of power lines and towers aims to use unmanned aerial vehicles (UAVs) for the inspection of power facilities, risk detection and modelling. Because of the unclear spatial relationship between the point clouds, the point segmentation of power lines and towers is challenging. In this paper, the power line and tower point datasets are constructed using Light Detection and Ranging (LiDAR) and a point segmentation method is proposed based on multiscale density features and a point-based deep learning network. First, the data are blocked and the neighbourhood is constructed. Second, the point clouds are downsampled to produce sparse point clouds. The point clouds before and after sampling are rotated, and their density is calculated. Next, a direct mapping method is selected to fuse the density information; a lightweight network is built to learn the features. Finally, the point clouds are segmented by concatenating the local features provided by PointCNN. The algorithm performs effectively on different types of power lines and towers. The mean interaction over union is 82.73%, and the overall accuracy can reach 91.76%. This approach can achieve the end-to-end integration of segmentation and provide theoretical support for the segmentation of large scenic point clouds. [ABSTRACT FROM AUTHOR]

Ancient geographical maps are our window into the past for understanding the spatial dynamics of last centuries. This paper proposes a novel approach to address this problem using deep learning. Convolutional neural networks (CNNs) are today the state-of-the-art methods in handling a variety of problems in the fields of image processing. The Cassini map, created in the eighteenth century, is used to illustrate our methodology. This approach enables us to extract the surfaces of classes of lands in the Cassini map: forests, heaths, arboricultural, and hydrological. The evolution of land use between the end of the eighteenth century andtoday was quantified by comparison with Corine Land Cover (CLC) database. For the Rhone watershed, the results show that forests, arboriculture, and heaths are more extensive on the CLC map, in contrast to the hydrological network. These unprecedented results are new findings that reveal the major anthropo-climatic changes. [ABSTRACT FROM AUTHOR]

Landslide susceptibility mapping (LSM) research is vital for averting and mitigating regional landslide disasters. Nevertheless, there has been a lack of systematic analysis regarding LSM's developmental drivers. Utilizing SciMAT, a scientometric tool, we analyzed 1661 papers on LSM from the Web of Science core collection database, spanning 1993 to 2022. We employed cluster and thematic evolution analysis in SciMAT to unveil trends. The results indicate a consistent upward trend over the past three decades. LSM modeling methods, geological data, and contributing factors are major focal points. Notably, the evolution of LSM models, with a rising adoption of machine learning and deep learning for risk assessment, emerges as a central knowledge pathway. This study offers valuable insights to scholars by identifying literature gaps and highlighting crucial research directions, facilitating informed decision-making in the realm of LSM. SciMAT tool initially employs cluster analysis and thematic evolution analysis to pinpoint the current popular themes and evolutionary trends of landslide susceptibility. The main trajectory of knowledge lies in the progression of landslide modeling methods. The latest trend in landslide susceptibility research is centered on the use of deep learning techniques, particularly convolutional neural networks, to achieve precise risk zonation. The study aims to highlight critical research directions, predict the future of LSM technology, and provide guidance for scholars. [ABSTRACT FROM AUTHOR]

The manual process of plant leaves disease detection takes more time to perform. To achieve successful classification results, a flawless feature extraction process is required for a detection model. Aiming at the localization of diseased-plant leaves, this paper performs complex tasks like segmentation, and multi-disease classification of plant leaves using 'improved segmentation, feature extraction, and classification' models. Here, the Adaptive Fusion of K-Means Region Growing (AFKMRG) accomplishes the abnormality segmentation of leaves. The extracted features are subjected to the Enhanced Long short-term memory (LSTM) for performing the multi-disease classification. Here, the segmentation, classification, and feature extraction are improved by the Fitness Sorted Jaya-Forest Optimization Algorithm (FSJ-FOA). From the empirical results, the accuracy and precision of the designed method is attains 98.35% and 98.40% for all kinds of leaves. Results show that the designed multi-disease classification of plant leaves method provides elevated performance with diverse performance metrics. [ABSTRACT FROM AUTHOR]

In the present era, deep learning algorithms are the key elements of several state-of-the-art solutions. But developing these algorithms for production requires a huge volume of data, computational resources, and human expertise. Thus, illegal reproduction, distribution, and modification of these models can cause economic damage to developers and can lead to copyright infringement. We propose a novel watermarking algorithm for deep recurrent neural networks based on adversarial examples that can verify the ownership of the model in a black-box way. In this paper, a novel algorithm to watermark a popular pre-trained speech-to-text deep recurrent neural network model Deep Speech without affecting the accuracy of the model is demonstrated. Watermarking is done by generating a set of adversarial examples by adding noise to the input such that the DeepSpeech model predicts the given input as the target string. In the case of copyright infringement, these adversarial examples can be used to verify ownership of the model. If the alleged stolen model predicts the same target string for the adversarial examples, the ownership of the model is verified. This novel watermarking algorithm can minimize the economic damage to the owners of the deep learning models due to stealing and plagiarizing. [ABSTRACT FROM AUTHOR]

Land Cover or Land Use (LCLU) classification is an important, challenging problem in remote sensing (RS) images. RS image classification is a recent technology used to extract hidden information from remotely sensed images in the observed earth environment. This classification is essential for sustainable development in agricultural decisions and urban planning using deep learning (DL) methods. DL gets more attention for accuracy and performance improvements in large datasets. This paper is aimed to apply one of the DL methods called transfer learning (TL). TL is the recent research problem in machine learning and DL approaches for image classification. DL consumes much time for training when starting from scratch. This problem could be overcome in the TL modeling technique, which uses pre-trained models to build deep TL models efficiently. We applied the TL model using bottleneck feature extraction from the pre-trained models: InceptionV3, Resnet50V2, and VGG19 to LCLU classification in the UC Merced dataset. With these experiments, the TL model has been built the outdate performance of 92.46, 94.38, and 99.64 in Resnet50V2, InceptionV3, and VGG19, respectively. [ABSTRACT FROM AUTHOR]

The stock market is viewed as an unpredictable, volatile, and competitive market. The prediction of stock prices has been a challenging task for many years. In fact, many analysts are highly interested in the research area of stock price prediction. Various forecasting methods can be categorized into linear and non-linear algorithms. In this paper, we offer an overview of the use of deep learning networks for the Indian National Stock Exchange time series analysis and prediction. The networks used are Recurrent Neural Network, Long Short-Term Memory Network, and Convolutional Neural Network to predict future trends of NIFTY 50 stock prices. Comparative analysis is done using different evaluation metrics. These analysis led us to identify the impact of feature selection process and hyperparameter optimization on prediction quality and metrics used in the prediction of stock market performance and prices. The performance of the models was quantified using MSE metric. These errors in the LSTM model are found to be lower compared to RNN and CNN models. [ABSTRACT FROM AUTHOR]

In recent years, contactless fraud crimes via telecommunication and Internet have grown rapidly. Meanwhile, the rate of solved criminal cases is much lower, which is mainly due to two reasons. Firstly, the definition of risk factors in the field of new Internet and telecommunication fraud crime is not comprehensive, resulting in the problem not being well defined. Secondly, Internet fraud crime information is mostly recorded using natural language with huge volume, and there is a lack of auto-mated and intelligent way to deeply analyze and extract the risk factor. To better analyze the Internet and telecommunication fraud crime to help solve more cases, in this paper, we propose a new Internet and telecommunication fraud crime risk factor extraction system. After studying the existing related research, we propose a novel risk factor extraction technology based on BERT. This novel technology can gracefully deal with multi- sources and heterogeneous data problems during the extraction of risk factors in multiple dimensions; meanwhile, it can significantly reduce the need for computation resources and improve the online serving performance. After experimentation, this technique can significantly reduce training time by 60%-70%, and meanwhile, it can reduce the computation resources by 80% and improve serving performance by 5 times during serving. In our approach, we propose a novel approach to set sample weight and loss weight based on data characteristics and data distribution during model training, which can significantly improve extraction precision. With adjusting the sample weight during model training, we can get 1.56% precision improved. Moreover, setting the loss weight during model training, the precision can be improved by 1.63% compared to base-line mode. [ABSTRACT FROM AUTHOR]

Most web-based educational systems contain some drawbacks, as compared to traditional classrooms. Particularly, it becomes difficult for teachers to guide students to choose an appropriate learning resource due to the large number of online learning resources. Meanwhile, student decisions make it more difficult to choose educational resources according to their circumstances. In this matter, the resource recommender system can be employed as an educational environment to recommend the educational resource advice for students, so that these recommendations can be coordinated to each student's preferences and needs. This paper presents the resource recommender system as a combination of MLP, BiLSTM, and LSTM improved deep learning networks using the attention method. Compared to similar studies conducted using DBN networks and focus only on the near past interests and preferences of users, the proposed system provides higher accuracy and more appropriate recommendations considering current interests, in addition to the user's long-term past interests. The proposed recommender system with accuracy of 0.96 and a loss of 0.0822 contains a better performance to recommend resources to students compared to other methods. [ABSTRACT FROM AUTHOR]

The emergence of various e-commerce sites has led to an increase in review sites for various services and products. People nowadays easily get information about products and services that will be used through reviews. Here sentiment analysis plays an important role in classifying the polarity of product reviews. However, with a large number of reviews, a sentiment analysis that only gives overall polarity is not sufficient. This will make it difficult to find the reviews of certain aspects (features) of the product. Aspect-based sentiment analysis as fine-grained sentiment analysis is able to provide specific polarity for each aspect contained in a sentence. Various kinds of development methods have been carried out to provide accurate results in aspect-based sentiment analysis. This paper will discuss the various deep learning methods that have been carried out and provide the possibility of research that can be carried out from Aspect-Based Sentiment Analysis. [ABSTRACT FROM AUTHOR]

In recent years, the rates of firearm-related violent acts worldwide have risen significantly. It is a severe social problem that compromises the safety of every individual to some extent. This situation has motivated researchers to find new ways to improve the current state-of-the-art solutions, such as automatic surveillance systems, to detect and classify the presence of firearms within a specific scene. These systems reduce the drawbacks of using direct human supervision. Among the available solutions for the classification task, the performance of Deep Learning models stands out, especially those based on Convolutional Neural Networks. Since they start learning directly from raw data (e.g., images), their learning process can be improved even further by using Transfer Learning techniques. However, the classification accuracy depends significantly on choosing the optimum set of values for the different hyper-parameters composing them. Thus, this paper analyses the improvement in the performance of an image-based handgun classification algorithm when tuning its hypermeters values instead of using its default values. In this work, we evaluated the performance variation using two benchmarks Convolutional Neural Networks architectures: AlexNet and Inception V3. We obtained a maximum accuracy of 94.11% when using the Inception V3 network and transfer learning. We employed Nadam as the optimizer and a learning rate equal to 0.0001, a batch size equal 256, and a total of 13 epochs. Experimental results suggest an essential relationship between the performance of the classification model and the data set, the specific combinations of values for the selected optimizer, the batch size, and the learning rate. The obtained improvement in the accuracy was up to 10.33% after the tuning process. [ABSTRACT FROM AUTHOR]

Deep learning methods allow computational models involving multiple processing layers to discover intricate structures in data sets. Classifying an image is one such problem where these methods are found to be very useful. Although different approaches have been proposed in the literature, this paper illustrates a successful implementation of the Bayesian Convolution Neural Networks (BCNN)-based classification procedure to classify microscopic images of blood samples (lymphocyte cells) without involving manual feature extractions. The data set contains 260 microscopic images of cancerous and noncancerous lymphocyte cells. We experiment with different network structures and obtain the model that returns the lowest error rate in classifying the images. Our developed models not only produce high accuracy in classifying cancerous and non- cancerous lymphocyte cells but also provide useful information regarding uncertainty in predictions. [ABSTRACT FROM AUTHOR]

Different types of research have been done on video data using Artificial Intelligence (AI) deep learning techniques. Most of them are behavior analysis, scene understanding, scene labeling, human activity recognition (HAR), object localization, and event recognition. Among all these, HAR is one of the challenging tasks and thrust areas of video data processing research. HAR is applicable in different areas, such as video surveillance systems, human-computer interaction, human behavior characterization, and robotics. This paper aims to present a comparative review of vision-based human activity recognition with the main focus on deep learning techniques on various benchmark video datasets comprehensively. We propose a new taxonomy for categorizing the literature as CNN and RNN-based approaches. We further divide these approaches into four sub-categories and present various methodologies with their experimental datasets and efficiency. A short comparison is also made with the handcrafted feature-based approach and its fusion with deep learning to show the evolution of HAR methods. Finally, we discuss future research directions and some open challenges on human activity recognition. The objective of this survey is to give the current progress of vision-based deep learning HAR methods with the up-to-date study of literature. [ABSTRACT FROM AUTHOR]

This study aimed to develop a novel deep learning model for reliable quantification of dentinal tubule occlusions instead of manual assessment techniques, and the performance of the model was compared to other methods in the literature. Ninetysix dentin samples were cut and prepared with desensitizing agents to occlude dentinal tubules on different levels. After obtaining images via scanning electron microscope (SEM), 2793 single dentinal tubule images with 48 x 48 resolution were segmented and labeled. Data augmentation techniques were applied for improvement in the learning rate. The augmented data having a total of 10700 images belonging to five classes were used as the network training dataset. The proposed convolutional neural network (CNN) is a class of deep learning model and was able to classify the degree of dentinal tubule occlusions into five classes with an overall accuracy rate of 90.24%. This paper primarily focuses on developing a CNN architecture for detecting the level of dentin tubule occlusions imaged by SEM. The results showed that the proposed CNN architecture is an immensely successful alternative and allowed for objective and automatic classification of segmented dentinal tubule images. [ABSTRACT FROM AUTHOR]

Predictive analytics is being increasingly used to predict various aspects of applications and users. It offers vast opportunities in the growth of the modern era's business transformation by enabling automated decision-making processes. Being able to determine the intention of users in an automated way is one of the important factors in enabling automated decision-making for applications and businesses using such applications. In this paper, we utilize and build upon the existing works, and propose a comprehensive intention assessment model that detects different possible intents of users by analyzing their text-based reviews on online forums, retail market websites, or on social media. If the information about a product or service experience is present somewhere in a review or post, our technique can accurately segregate different possible purchase intention labels (i.e., positive, negative, and unknown). Our proposed comprehensive model for intention assessment includes extensive data pre-processing, extended feature selection model, utilization of artificial intelligence (machine learning and deep learning) techniques, and customized cost and loss functions. We built a comprehensive testbed and carried out evaluations and comparisons. Our solution demonstrates high accuracy, precision, and F1 score. The proposed solution helps in mining and gaining deeper insights into behavior of consumers and market tendencies and can help in making informed decisions. [ABSTRACT FROM AUTHOR]

Malaria fever is a potentially fatal disease caused by the Plasmodium parasite. Identifying Plasmodium parasites in blood smear images can help diagnose malaria fever rapidly and precisely. According to the World Health Organization (WHO), there were 241 million malaria cases and 627 000 deaths worldwide in 2020, while 95% of malaria cases and 96% of malaria deaths occurred in Africa. Also in Africa, children that are less than five years old accounted for an estimated 80% of all malaria deaths. To address the menace of malaria, this paper proposes a novel deep learning model, called a data augmentation convolutional neural network (DACNN), trained by reinforcement learning to tackle this problem. The performance of the proposed DACNN model is compared with CNN and directed acyclic graph convolutional neural network (DAGCNN) models. Results show that DACNN outperforms previous studies in processing and classification images. It achieved 94.79% classification accuracy in malaria blood sample images of balanced class dataset obtained from the Kaggle dataset. The proposed model can serve as an effective tool for the detection of malaria parasites in blood smear images. [ABSTRACT FROM AUTHOR]

Solar activity has significant impacts on human activities and health. One most commonly used measure of solar activity is the sunspot number. This paper compares three important non-deep learning models, four popular deep learning models, and their five ensemble models in forecasting sunspot numbers. In particular, we propose an ensemble model called XGBoost-DL, which uses XGBoost as a two-level nonlinear ensemble method to combine the deep learning models. Our XGBoost-DL achieves the best forecasting performance (RMSE = 25:70 and MAE = 19:82) in the comparison, outperforming the best non-deep learning model SARIMA (RMSE = 54:11 and MAE = 45:51), the best deep learning model Informer (RMSE = 29:90 and MAE = 22:35) and the NASA's forecast (RMSE = 48:38 and MAE = 38:45). Our XGBoost-DL forecasts a peak sunspot number of 133.47 in May 2025 for Solar Cycle 25 and 164.62 in November 2035 for Solar Cycle 26, similar to but later than the NASA's at 137.7 in October 2024 and 161.2 in December 2034. An open-source Python package of our XGBoost-DL for the sunspot number prediction is available at https://github.com/yd1008/ts_ensemble_ sunspot. [ABSTRACT FROM AUTHOR]

Vortex detection plays a fundamental role in turbulence research and engineering problems. However, due to the lack of a mathematically rigorous vortex definition, as well as the absence of any vortex-oriented database, both traditional and machine learning detection methods achieve only limited performance. In this paper, we develop a deep learning model for vortex detection using a weak supervision approach. In order to avoid the need for a vast amount of manual labeling work, we employ an automatic clustering approach to encode vortex-like behavior as the basis for programmatically generating large-scale, highly reliable training labels. Moreover, to speed up the clustering method, a multi-view U-Net (MVU-Net) model is proposed to approximate the clustering results using the knowledge distillation technique. A multi-view learning strategy is further applied to integrate the information across multiple variables. In addition, we propose a physics-informed loss function, which enables our model to explicitly consider the characteristics of flow fields. The results on eight real-world scientific simulation applications show that the proposed MVU-Net model significantly outperforms other state-of-the-art methods on both efficiency and accuracy. [ABSTRACT FROM AUTHOR]

Streamlined weirs, which are a nature-inspired type of weir, have gained tremendous attention among hydraulic engineers, mainly owing to their established performance with high discharge coefficients. Computational fluid dynamics (CFD) is considered as a robust tool to predict the discharge coefficient. To bypass the computational cost of CFD-based assessment, the present study proposes data-driven modeling techniques, as an alternative to CFD simulation, to predict the discharge coefficient based on an experimental dataset. To this end, after splitting the dataset using a k-fold cross-validation technique, the performance assessment of classical and hybrid machine learning–deep learning (ML-DL) algorithms is undertaken. Among ML techniques, linear regression (LR), random forest (RF), support vector machine (SVM), k-nearest neighbor (KNN) and decision tree (DT) algorithms are studied. In the context of DL, long short-term memory (LSTM), convolutional neural network (CNN) and gated recurrent unit (GRU), and their hybrid forms, such as LSTM-GRU, CNN-LSTM and CNN-GRU techniques, are compared using different error metrics. It is found that the proposed three-layer hierarchical DL algorithm, consisting of a convolutional layer coupled with two subsequent GRU levels, which is also hybridized with the LR method (i.e. LR-CGRU), leads to lower error metrics. This paper paves the way for data-driven modeling of streamlined weirs. [ABSTRACT FROM AUTHOR]

In recent years, image aesthetic quality assessment has attracted considerable attention due to the massive growth of digital images in social platforms and the Internet. However, automatically assessing aesthetic quality of an image is a challenging task, because image aesthetic is affected by various factors, and the criteria for judging the aesthetic of images with diverse semantic information are different. To this end, a Semantic-Aware Multi-task convolution neural network (SAM-CNN) for evaluating image aesthetic quality is proposed in this paper. The network can fuse intermediate features of different layers at different scales in CNN to obtain a more comprehensive and accurate aesthetic expression, under the joint supervision of image aesthetic quality assessment task and semantic classification task in a multi-task learning manner. Besides, by applying the attention mechanism, semantic information with a large receptive field extracted from deep layers is utilised to guide the network to focus on the key parts of features to be fused, to improve the effectiveness of feature fusion. Experimental results on the AVA dataset and Photo.net dataset demonstrate the effectiveness and superiority of the proposed SAM-CNN. [ABSTRACT FROM AUTHOR]

Lane detection is an indispensable technology for environmental perception and is a function of autonomous vehicles. Although many researchers have applied deep learning to lane detection and achieved good results, their application scenarios were relatively simple. When a lane is blocked, lost, or met with other challenges, the accuracy of lane detection decreases tremendously. This paper proposes a novel semantic segmentation network for lane detection that includes IBN-Net, an attention module, and an encoder-decoder structure called IAED. IBN-Net improves the modelling and generalisation capability with little computational complexity. The attention module can better capture context information and improve the performance of the network. We evaluated the performance of the proposed method, which improved by 6.3% over ResNet34 on the TuSimple datasets. Tests on the CULane datasets showed that our method is at least 3% better than existing methods. Experimental results showed that the proposed method has strong robustness under complex conditions such as insufficient illumination and shadow occlusion. [ABSTRACT FROM AUTHOR]