Search

This paper presents a metallic object classification method using various electromagnetic pulses. Each electromagnetic pulse irradiated eight metallic objects placed at increasing distances from 10 mm to 40 mm relative to the electromagnetic sensing system. The electromagnetic sensing system consisted of two RL circuits placed in close proximity. Objects were classified using linear (perceptron and multiclass logistic regression) and non-linear (neural network, 1D convolutional neural network (CNN) and 2D CNN) machine learning classifiers. The machine learning classifiers were trained on experimental data collected in an electromagnetically shielded laboratory. A 10-fold cross-validation mean classification accuracy of 99.4 ± 0.3% for the 1D CNN classifier, and 92.9 ± 1.2% for the 2D CNN classifier, was achieved using a rectangular chirp electromagnetic pulse. The rectangular chirp pulse outperformed two-sided decaying exponential, Gaussian, triangular, raised cosine, and rectangular pulses. All pulses had equal energy. While the rectangular chirp performed best overall, other pulses more accurately distinguished between some objects. [ABSTRACT FROM AUTHOR]

Potato is one of the most nutritious foods rich in fiber and essential vitamins and minerals. However, potato plants may suffer from diseases such as early blight, late blight, septoria leaf spot or skin diseases such as greening, silver scurf, common scab, black rot etc. These diseases may lead to huge losses in the potato yield annually. Hence, an early prediction of such diseases is required so that they can be controlled at an early stage. Several machine learning, IoT based and image processing techniques have been utilized for this purpose, and this paper aims to survey all such methods and prediction models. A total of 116 studies were analyzed, and out of them, 77 relevant studies belonging to (60%) journals, (34%) conferences and (6%) other sources have been surveyed. It has been observed that most of the selected studies (64%) have used RGB image data (proprietary or PlantVillage dataset). Also, majority of the studies (48%) have worked with imbalanced data. Late blight and early blight are the two diseases that have gained the most attention by the researchers, being included in 58% and 34% of the studies. Moreover, feature extraction/selection has been used only with image data (RGB and hyperspectral). Convolutional Neural Network is the most widely used classifier, followed by Support Vector Machines. This review will help the researchers gain an insight into the work done for disease detection in potato crop and what techniques or diseases need intervention so that yield losses can further be minimized. [ABSTRACT FROM AUTHOR]

Because of the Internet of Things (IoT) and wearable devices, information obtained is subject to cyber attacks, making intrusion detection an essential component. The increased number of attacks on IoT devices exposes them to ongoing exploitation and data theft. Mirai, denial of Service (DoS), scan, etc are the major types of attacks conducted on IoT. Traditional attack detection algorithms have more disadvantages like lack of adaptability in all scenarios, low local minima computational complexity, etc. Thus developing a method that is suitable for all environments and has good convergence speed is taken as the motivation of this study. This paper presents a novel Symbiotic Organisms Search Algorithm (SOSA) optimized Faster region-based convolutional neural network (FRCNN) for attack detection and data type classification. The data to be stored in the cloud is analyzed whether they have restricted access, confidential, or unclassified. Depending upon the variety of data, the Optimal homomorphic encryption (OHE) approach is provided for security. The key selection process is done by an Elastic Collision Seeker Optimization Algorithm (ECSOA) which offers secure access to the data owner and prevents the data from unauthorized access. The model is optimized using the algorithm which improves the feature extraction performance. The effectiveness of the proposed model in attack detection is evaluated using two datasets namely the CSE-CIC-ID2018 dataset and the IoTID20 dataset. When compared to the existing techniques, the proposed model offers optimal performance in terms of multiclass attack detection. [ABSTRACT FROM AUTHOR]

Deep learning technologies like convolutional neural networks have recently become popular in the field of image denoising. A combined discrete wavelet transform (DWT) and denoising CNN (DnCNN)-based technique suggested in this paper can be used to adaptively boost image contrast. Images were captured in a wide variety of lighting circumstances, which means that not all of them are of the highest quality. As a result of the limited dynamic range of the pixel values, the overall image quality suffers when a shot is taken in low light. We employ a lossy method based on a structural similarity index to keep as much of the original texture in the images as feasible. Current advancements in image denoising, such as energy band analysis, very deep architecture, learning algorithms, dense-sparse-dense training, and regularization approaches, were applied in the hybrid DWT-Denoising convolutional neural networks. DnCNN eliminates the latent information in the hidden layers by design, resulting in a clean image. The DWT-DnCNN delivers SSIM values that are 2% higher than those of the standard RIDNet. Our hybrid DWT-DnCNN-based contrast enhancement strategy surpasses existing methods, according to simulation outcomes. [ABSTRACT FROM AUTHOR]

Electroencephalography (EEG) is a complex signal that may require several years of training, advanced signal processing, and feature extraction methodologies to interpret correctly. Recently, many methods have been used to extract and classify EEG data. This study reviews 62 papers that used EEG signals to detect driver drowsiness, published between January 2018 and 2022. We extract trends and highlight interesting approaches from this large body of literature to inform future research and formulate recommendations. To find relevant papers published in scientific journals, conferences, and electronic preprint repositories, researchers searched major databases covering the domains of science and engineering. For each investigation, many data items about (1) the data, (2) the channels used, (3) the extraction and classification procedure, and (4) the outcomes were extracted. These items were then analyzed one by one to uncover trends. Our analysis reveals that the amount of EEG data used across studies varies. We saw that more than half the studies used simulation driving experimental. About 21% of the studies used support vector machine (SVM), while 19% used convolutional neural networks (CNN). Overall, we can conclude that drowsiness and fatigue impair driving performance, resulting in drivers who are more exposed to risky situations. [ABSTRACT FROM AUTHOR]

The rapid expansion of coronavirus illness (COVID-19) became a global problem, with over 40 million confirmed individuals infected as of February 2022. Medical imaging, such as CT scans, can be used for diagnostics to counteract its spread. Automatic COVID detection tools are required to ease the process using CT scan images. This work categorizes the healthy and COVID patients based on CT scan images. As such, a GIL-CNN model is proposed to detect COVID patients in the present paper. The proposed model provides the global, intermediate, and local features that help better CT scan image feature representation by avoiding spatial loss. The support vector machine, a standard machine learning classifier, is used to classify the normal and COVID images using the GIL-CNN features. The proposed model is trained and tested on publicly available COVID-19 CT scan images. The proposed model has produced better results than state-of-the-art techniques. The proposed model can assist in the automated identification of COVID-19 patients, reducing the strain on healthcare systems. [ABSTRACT FROM AUTHOR]

Finite-sum problems appear as the sample average approximation of a stochastic optimization problem and often arise in machine learning applications with large scale data sets. A very popular approach to face finite-sum problems is the stochastic gradient method. It is well known that a proper strategy to select the hyperparameters of this method (i.e. the set of a-priori selected parameters) and, in particular, the learning rate, is needed to guarantee convergence properties and good practical performance. In this paper, we analyse standard and line search based updating rules to fix the learning rate sequence, also in relation to the size of the mini batch chosen to compute the current stochastic gradient. An extensive numerical experimentation is carried out in order to evaluate the effectiveness of the discussed strategies for convex and non-convex finite-sum test problems, highlighting that the line search based methods avoid expensive initial setting of the hyperparameters. The line search based approaches have also been applied to train a Convolutional Neural Network, providing very promising results. [ABSTRACT FROM AUTHOR]

This paper presents a novel approach for enhancing long-term runoff simulations through the integration of empirical mode decomposition (EMD) with four machine learning (ML) models: ensemble, support vector machine (SVM), convolutional neural networks (CNN), and artificial neural networks with backpropagation (ANN-BP). The proposed methodology uses EMD to decompose precipitation and temperature time-series into intrinsic mode functions, thereby revealing underlying data patterns. Subsequently, these components are incorporated into the ML models to simulate the runoff time-series. The effectiveness of the hybrid models is evaluated using streamflow runoff data obtained from the Grand, Winnipeg, and Moosonee Rivers in Ontario, Canada. Four widely used performance indices, namely, correlation coefficient, root mean square error (RMSE), mean absolute relative error, and Nash--Sutcliffe efficiency, are employed to assess the models' performance. The results demonstrate that the hybrid EMD-ML models exhibit significantly superior performance compared with the standalone ML methods. During the validation phase, the EMD-Ensemble, EMD-SVM, EMD-CNN, and EMD-ANN-BP models exhibit notable reductions in the RMSEs of monthly streamflow estimates for the Grand River, amounting to 11%, 22%, 8%, and 33%, respectively, compared with their non-EMD counterparts. Additionally, these hybrid models exhibit improved RMSEs for yearly simulations in the Winnipeg River, with reductions of 54%, 0.08%, 6%, and 4.5% respectively. To further enhance the accuracy of monthly and yearly streamflow estimates, an SVM-recursive feature elimination technique is employed to select a more appropriate EMD dataset in all study cases. This research underscores the potential of integrating EMD with ML models to enhance long-term runoff simulations. The outcomes highlight the superior performance of the hybrid EMD-ML models, demonstrating their ability in generating lower biases than the standalone ML methods. These findings hold significant implications for the field of computational fluid mechanics and can contribute to the understanding of hydrological processes. [ABSTRACT FROM AUTHOR]

Crack detection on roads' surfaces is an important issue in pavement management, as it provides an indication of the quality of the road and its deterioration over time. Pavement cracks are one of the most common types of damage observed on roads, and they can be seen visually. Despite the fact that it does not provide immediate resolution to the issue, understanding the extent of crack damage is essential for the upkeep of roads. This paper presents a novel approach to automatically detecting pavement cracks using the orthoimage generated by a consumer-grade photogrammetric Unmanned Aerial Vehicle (UAV) and a deep learning algorithm. We used an autoencoder Convolutional Neural Network (CNN) to train a dataset full of challenging factors such as road lines and marks, oil and colour spots, and water stains. The model was tested on a dataset of RGB patches of different patterns of cracks and achieved an overall accuracy (OA) and F1 score of about 0.98. The results demonstrate the effectiveness of the proposed method in accurately detecting pavement cracks in challenging real-world conditions. This approach provides an efficient and cost-effective solution for pavement crack detection, that can be used for measuring the road's quality and monitoring it. [ABSTRACT FROM AUTHOR]

By accurate predicting of pipe bursts, it is possible to schedule pipe maintenance, rehabilitation and improve level of services in Water Distribution Networks (WDNs). In recent years, artificial intelligence techniques have been used vastly in pipe burst prediction. These techniques need big input dataset for deep learning but big dataset might not be available in old WDNs. This paper aimed to compare the performance of multivariate adaptive regression splines (MARS) and regressive convolution neural network with least square support vector regression (RCNN-LSSVR) for predicting of Pipe Burst Rate (PBR) with limited dataset. Pipes age, diameter, depth of installation, length, average and maximum hydraulic pressure are considered as effective parameters of PBR. Data collected from real-case study in Iran include 158 cases for polyethylene and 124 cases for asbestos cement pipes during 2012–2019. The results indicate that RCNN-LSSVR model has a great performance of PBR prediction on limited dataset. [ABSTRACT FROM AUTHOR]

The majority of conventional alcohol detection approaches are based on traditional machine learning approaches and are unable to retrieve the deeply hidden attributes of alcohol-based electroencephalography (EEG) signals. The intention of this research is to evolve a deep learning-based method for detecting alcohol-related EEG signals automatically. It also investigates whether a deep learning method for alcoholism classification is effective without using any explicit feature extraction and selection steps. To assess this, the paper implements and compares deep learning-based strategies to classify alcohol-related EEG signals. A framework that uses prerecorded raw EEG data as input to a deep learning algorithm called convolutional neural network (CNN), long short-term memory (LSTM), and a cascade model called CNN + LSTM is also implemented for detecting alcoholism on an openly accessible UCI Alcoholic EEG dataset. Some conventional techniques are also implemented on prerecorded raw EEG signals, and the classification results are compared with the proposed methods. The results of the experiments show that the proposed models are capable of achieving average classification accuracies of 99.60%, 98.12%, and 95.95% on the training dataset and 92.77%, 89%, and 91% on the testing dataset along with error rates of 7.5%, 11.90%, and 8.7% from CNN, LSTM, and CNN + LSTM, respectively. [ABSTRACT FROM AUTHOR]

Crack detection on roads' surfaces is an important issue in pavement management, as it provides an indication of the quality of the road and its deterioration over time. Pavement cracks are one of the most common types of damage observed on roads, and they can be seen visually. Despite the fact that it does not provide immediate resolution to the issue, understanding the extent of crack damage is essential for the upkeep of roads. This paper presents a novel approach to automatically detecting pavement cracks using the orthoimage generated by a consumer-grade photogrammetric Unmanned Aerial Vehicle (UAV) and a deep learning algorithm. We used an autoencoder Convolutional Neural Network (CNN) to train a dataset full of challenging factors such as road lines and marks, oil and colour spots, and water stains. The model was tested on a dataset of RGB patches of different patterns of cracks and achieved an overall accuracy (OA) and F1 score of about 0.98. The results demonstrate the effectiveness of the proposed method in accurately detecting pavement cracks in challenging real-world conditions. This approach provides an efficient and cost-effective solution for pavement crack detection, that can be used for measuring the road's quality and monitoring it. [ABSTRACT FROM AUTHOR]

In this work, we propose a DnCNN-based method to enhance the contrast of images. Fundus images are widely used in clinical practice for detecting retinal dark spots. These spots trouble ophthalmologists to distinguish and decipher diseases for diabetic retinopathy. This work aims is to describe a fundus picture noise removal with enhancement technique. Our simulation results demonstrate that our DnCNN-based method outperforms other contrast enhancement methods. This paper presents a denoising Convolutional Neutral Network (DnCNN)-based technique to enhance images for diabetic retinopathy. The contrast of images can be adaptively improved. Denoising convolutional neural networks (DnCNNs) show progress in image denoising architecture, learning algorithm, and regularization method. DnCNN removes the latent clean image in the hidden layers implicitly. Our proposed (DnCNN) method, compared with the various histogram (Equalization (HE), Adaptive Histogram Equalization (ADHE), Contrast Limited Adaptive Histogram Equalization (CLAHE), and Exposure based Sub-Image Histogram Equalization (ESIHE)) pre-processes fundus images for identifying diabetic retinopathy. The fundus images were collected from the DRIVE database. The Denoising Convolutional Neural Network strategy is analyzed with the execution parameter measurements of PSNR and SSIM. According to the simulation results, the DnCNN method has a higher visual quality than the previous method. In addition, the proposed method's average PSNR values 25.4303 and 11 dB are higher than those of the existing methods. However, the DnCNN method has a slightly ∼0.2 lower SSIM value of 0.3584 than the previous methods. The decrease in SSIM value indicates a loss of detailed information. [ABSTRACT FROM AUTHOR]

Real-time and accurate acquisition of ash content is crucial for coal flotation monitoring but existing modeling approaches have been hindered from a large dataset labeled by the target task. The method proposed in this paper relies on a transfer learning approach that is able to exploit the knowledge of a source domain (ImageNet and S1) to improve the result of a task performed on the target domain (S2). The ResNet 101 is selected as the main Convolutional neural network (CNN) framework of transfer learning among six state-of-the-art CNN modules in this study. Freeze and fine-tune are used to transfer the weights of the CNN layers to the industry ash content classification task. The tuning results of neurons and fully connected layers show that the classification results based on the weights knowledge of S1 obtained through the proposed transfer method outperform the training direct method by achieving an accuracy of 86.26% and F1-score of 85.19% over the small-sized industry dataset. The 3-D discriminant feature score and ROC curves demonstrate satisfactory prediction performance in coal flotation industrial ash content prediction. Generally, this work provides new options for flotation monitoring in tasks of training ash content labels shortage. [ABSTRACT FROM AUTHOR]

Machine learning specific scholarly full-text documents contain a number of result-figures expressing valuable data, including experimental results, evaluations, and cross-model comparisons. The scholarly search system often overlooks this vital information while indexing important terms using conventional text-based content extraction approaches. In this paper, we propose creating semantically enriched document summaries by extracting meaningful data from the results-figures specific to the evaluation metric of the area under the curve (AUC) and their associated captions from full-text documents. At first, classify the extracted figures and analyze them by parsing the figure text, legends, and data plots - using a convolutional neural network classification model with a pre-trained ResNet-50 on 1.2 million Images from ImageNet. Next, we extract information from the result figures specific to AUC by approximating the region under the function's graph as a trapezoid and calculating its area, i.e., the trapezoidal rule. Using over 12,000 figures extracted from 1000 scholarly documents, we show that figure specialized summaries contain more enriched terms about figure semantics. Furthermore, we empirically show that the trapezoidal rule can calculate the area under the curve by dividing the curve into multiple intervals. Finally, we measure the quality of specialized summaries using ROUGE, Edit distance, and Jaccard Similarity metrics. Overall, we observed that figure specialized summaries are more comprehensive and semantically enriched. The applications of our research are enormous, including improved document searching, figure searching, and figure focused plagiarism. The data and code used in this paper can be accessed at the following URL: https://github.com/slab-itu/fig-ir/. [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]

Satellite-Derived Bathymetry (SDB) can be calculated using analytical or empirical approaches. Analytical approaches require several water properties and assumptions, which might not be known. Empirical approaches rely on the linear relationship between reflectances and in-situ depths, but the relationship may not be entirely linear due to bottom type variation, water column effect, and noise. Machine learning approaches have been used to address nonlinearity, but those treat pixels independently, while adjacent pixels are spatially correlated in depth. Convolutional Neural Networks (CNN) can detect this characteristic of the local connectivity. Therefore, this paper conducts a study of SDB using CNN and compares the accuracies between different areas and different amounts of training data, i.e., single and multi-temporal images. Furthermore, this paper discusses the accuracies of SDB when a pre-trained CNN model from one or a combination of multiple locations is applied to a new location. The results show that the accuracy of SDB using the CNN method outperforms existing works with other methods. Multi-temporal images enhance the variety in the training data and improve the CNN accuracy. SDB computation using the pre-trained model shows several limitations at particular depths or when water conditions differ. [ABSTRACT FROM AUTHOR]

Natural Language Processing (NLP) acts towards the processing of linguistics between human and computer. The application of NLP in the chemical industry has proven to be a boon in the past decade. This paper presents a survey of deep learning (DL) models on NLP fundamentals for battery materials domain-related research. Various DL models like convolutional neural networks, recursive neural networks, recurrent neural networks, long short-term memory networks, and attention networks have been discussed while comparing their efficacy for different NLP tasks. Innovations in presented DL models provide enhanced performance for the NLP-based tasks. This paper will enlighten researchers, to get an insight into the current practices and scope for future developments on battery materials. They can apply NLP techniques for various applications like structural recognition and extraction, understanding of chemical features without a domain expert, and understanding the chemical structure and summarization approaches. Moreover, this paper will help chemists and researchers in the chemical industry to explore various areas to work upon. To empower this, various applications and future scope is discussed in this paper. [ABSTRACT FROM AUTHOR]

This paper presents a new model, the Weighted Extreme Learning Machine optimized Diagonal-Kernels Convolution (WELM-ODKC), for automatic skin cancer detection that addresses imbalanced data and eliminates inter-operator variability. The model combines the WELM and the Enhanced Remora Optimization Algorithm (EROA) with the Diagonal-Kernels Convolution Neural Network (DKCNN) to enhance the weight function and accurately predict skin lesion class. The model was evaluated on the MNIST HAM10000 and PAD-UFES-20 datasets and outperformed other existing skin cancer classification methods such as SVM BWO, CNN, DGC-NB, and GWO-CNN. The accuracy, recall, precision, and F1-score were used to evaluate the performance of WEL-ODKC, and the results show a high accuracy during training and validation. The proposed model efficiently classifies different types of skin cancer images from the two baseline datasets and provides promising results for automatic skin cancer detection. [ABSTRACT FROM AUTHOR]

In recent decades, automatic human emotion detection plays a crucial role in human and machine interaction. Electroencephalograph (EEG) based human emotion detection is a challenging process due to the diversity, and complexity of human emotions. For recognizing diverse emotions, a novel model is presented in this paper. Initially, an average mean reference technique is used to eliminate the environmental artifacts, instrumentation artifacts, and biological artifacts from the EEG signals, which are collected from DEAP dataset. Next, feature extraction is carried out using Fast Fourier transform (FFT) with Power Spectral Density (PSD) to extract feature vectors from the denoised EEG signals. Further, feature dimensionality reduction is performed utilizing Principal Component Analysis (PCA) to diminish the dimensions of the extracted features. A total of 230 EEG feature vectors are given as the input to Artificial Neural Network (ANN) for classifying valence and arousal emotion states. The proposed PCA-ANN model performance is validated in terms of average classification accuracy and f-score. The experimental outcome demonstrates that the proposed PCA-ANN model achieved an improved accuracy in emotion classification, which is effective compared to the existing models such as ensemble learning algorithm, a convolutional neural network with the statistical method, and sparse autoencoder with logistic regression. The proposed PCA-ANN model achieved 87.14% and 86.31% of accuracy in valence and arousal states, and obtained 90.45% and 92.03% of f-score value in valence and arousal emotion states. [ABSTRACT FROM AUTHOR]

Deep Learning has been applied for the crop yield prediction problem, however, there is a lack of systematic analysis of the studies. Therefore, this study aims to provide an overview of the state-of-the-art application of Deep Learning in crop yield prediction. We performed a Systematic Literature Review (SLR) to identify and analyze the most relevant papers. We retrieved 456 relevant studies of which we selected 44 primary studies for further analysis after applying selection and quality assessment criteria to the relevant studies. A thorough analysis and synthesis of the primary studies were performed with respect to the key motivations, the target crops, the algorithms applied, the features used, and the data sources used. We observed that Convolutional Neural Network (CNN) is the most common algorithm and it has the best performance in terms of Root Mean Square Error (RMSE). One of the most important challenges is the lack of a large training dataset and thus, the risk of overfitting and as a result, lower model performance in practice. For researchers in this field, it is valuable to indicate the current challenges and the possibility for further research, because they tend to focus on the importance of missing research topics. [ABSTRACT FROM AUTHOR]

This paper proposes a computer-aided methodology for detecting and segmenting the tumor regions in ultrasound thyroid images using machine and deep learning algorithms. This proposed tumor detection methodology uses Kirsch's edge detector for enhancing the edge region pixels in thyroid image and then Dual Tree Contourlet Transform (DTCT) was applied on the enhanced image for obtaining the coefficients. Then, features are computed from this transformed thyroid image and these features are trained and classified using the Co-Active Adaptive Neuro Expert System (CANFES) classifier. Then, the morphological segmentation method is applied on the abnormal thyroid image to segment the tumor regions. Finally, the Convolutional Neural Network (CNN) algorithm is applied on the segmented tumor regions for diagnosing them into mild, moderate and severe. [ABSTRACT FROM AUTHOR]

Predictive analytics utilizing machine learning algorithms play a pivotal role in various domains, including the profiling of carbon dioxide (CO2) emissions. This research paper delves into an extensive exploration of different algorithms, encompassing neural networks with diverse architectures, optimization, training, ensemble, and specialized algorithms. The primary objective of this research is to evaluate the efficacy of supervised and unsupervised algorithms, including Deep Belief Networks, Feed Forward Neural Networks, Gradient Boosting, and Regression, as well as Convolutional Neural Networks, Gaussian, Grey, and Markov models, and clustering and optimization algorithms. The study places particular emphasis on data-driven methodologies and cross-validation techniques with an evaluation of the learning models entailing comprehensive training, validation, and testing, employing evaluation metrics such as R2, MAE, and RMSE. The study employs correlation analysis to examine the relationship between input parameters and emission characteristics. The research highlights the advantageous attributes of these algorithms in accurately forecasting CO2 emissions, evaluating energy sources, improving prediction accuracy, and estimating emissions. Notably, deep learning, Artificial Neural Networks (ANN), and Support Vector Machines (SVM) demonstrate effectiveness across diverse industries, while the Modified Regularized Fast Orthogonal-Extreme Learning Machine (MRFO-ELM) algorithm optimizes predictions specifically related to coal chemical emissions. Hybrid techniques demonstrate accuracy in predicting carbon emissions and energy consumption, whereas gray prediction models provide reliable estimates even with limited data. However, it is important to acknowledge certain limitations, including data requirements, potential inaccuracies arising from complex factors, constraints faced by developing countries, and the impact of electric vehicle expansion on the power grid. To optimize models, a survey is conducted, involving customization of parameters and learning rates, while exploring various performance metrics to evaluate model accuracy. The research outcomes contribute to the effective monitoring of CO2 emissions in operational environments, thereby aiding executive decision-making processes. [ABSTRACT FROM AUTHOR]

In recent years, deep learning algorithm has been used in many applications mainly in image processing of object detection and classification. The use of image processing techniques is becoming more interesting with the existence of drone technology with the employ of deep learning in aerial view image processing because of the high resolution and heaps of images taken. This paper aims to review neural networks specifically on the aerial view image by drones and to discuss the work principles and classic architectures of convolutional neural networks, its latest research trend and typical models along with target detection in object detection, image classification and semantic segmentation. In addition, this study also provided a specific application in the aerial image. Finally, the limitations of the convolutional network and expected future development trends were also discussed. Based on the findings, the deep learning algorithm was observed to provide high accuracy, it outperformed other generally image processing-based techniques. [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]

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]

In this paper, a hybrid classification method based on dual-channel convolutional neural network (DC-CNN) and kernel extreme learning machine (KELM), namely PLDC-KELM, is proposed to improve the spatial-spectral feature extraction ability and hyperspectral remote sensing image (HRSI) classification accuracy. In the proposed PLDC-KELM, principal component analysis (PCA) is employed to reduce the dimensionality of original HRSI, and local binary pattern (LBP) is utilized to extract spatial features from the data after dimensionality reduction, and the one-dimensional convolutional neural network (1D-CNN) model is constructed to extract deep spatial features from the dimensionality-reduced spatial features. The secure connection layers of two 1D-CNN models are connected to fuse deep spectral and spatial features. Finally, the fused features are input into KELM in order to realize an HRSI classification method. Indian Pines data, Pavia University data, and Salinas data are used to prove the effectiveness of the PLDC-KELM. The experimental results show that the PLDC-KELM method can achieve classification accuracy of 99.95%, 99.98%, and 99.97%, respectively. It is an effective method for hyperspectral remote sensing image classification. [ABSTRACT FROM AUTHOR]

Geohazard risk is high in Arab countries due to ineffective disaster preparedness measures, mismanagement, lack of public awareness, inadequate funding and lack of stakeholder support. One such country is Egypt, which is hit by floods every year that cost lives and bring the economy to a standstill. Moreover, not much has been done to map flood-prone areas. In this paper, flood susceptibility modelling was evaluated in the Ras Gharib region of Egypt using two effective techniques machine learning techniqueMLT (Support Vector Machine (SVM)) and deep learning methodDL (Convolutional Neural Networks (CNN)). Thirteen flood related factors and flood inventory layer were prepared to construct these models. Validation was performed with 30% of the flood locations where receiver operating characteristic (ROC) curves showed that the deep learning technique (CNN) gave a prediction accuracy of 86.5% (high performance), while the MLTs (SVM) gave 71.6% (medium performance). The results show that CNN provides 17% better than SVM which indicates a powerful and accurate model in flood susceptibility mapping. Results were confirmed using the Astro Digital images shortly after the 2016 flood, in which the CNN model provides a good agreement. [ABSTRACT FROM AUTHOR]

3D printing has become highly applicable in modern life recently. The industry has brought a facelift to most others. However, this technology still exists some shortcomings, and it therefore has not been generalised to bring the best benefits to users. In this paper, based on multilayer perceptron and convolution neural network models, we propose a new data-driven machine learning platform for predicting optimised parameters of the 3D printing process from a model design to a complete product. This finding can open up great advances in the current 3D printing technology. Accordingly, the results obtained allow us to predict quickly and accurately some decisive parameters of the traditional 3D printing process such as time, weight and length while the input was fuzzy with a part of the initial information missing. The proposed approach does not need to account for the shape, size and material of the printed object, but it can perform the process automatically without other extra factors. After completing the model, a configurator is proposed to set the parameters for the respective printer types, which makes the 3D printing process simple and fast. [ABSTRACT FROM AUTHOR]

Convolutional Neural Network (CNN) has been proved excellent for hyperspectral image(HSI) classification on the basis of large training set. However, the lack of available samples degrades the performance of CNNs in practical HSI classification. Although transfer learning is a typical strategy to address the issue of limited training samples, such methods tend to reload source model's feature extractors directly ignoring their generalization. Furthermore, most existing adaptive transfer learning algorithms pay attention to spectral features of HSI while the obvious difference between RGB image and HSI's spatial features is overlooked. In this paper, the proposed method can solve the mentioned problems to some extent. Firstly, the proposed adaptive heterogeneous transfer (AHT) can measure their transferability and find appropriate solution to transfer knowledge. It computes feature extractors' transferability based on feature maps and influences the learning process of target model through backpropagation, therefore, target model is prone to receive knowledge from feature extractors with high generalization. Secondly, the proposed method lays emphasis on HSI's spatial features. It adopts the methodology of spatial attention and calculates the regularization loss based on spatial features. Experiments were conducted on two widely used HSI datasets. The results demonstrate the method's effectiveness when few samples are available. [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]

Animal Vehicle Collision, commonly called roadkill, is an emerging threat to drivers and wild animals, increasing fatalities every year. Currently, prevalent methods using visible light cameras are efficient for animal detection in daylight time. This paper focuses on locating wildlife close to roads during nocturnal hours by utilizing thermographic obtained images, thus enhancing vehicle safety. In particular, it proposes an intelligent system for animal detection during nighttime that combines the technique of Histogram of Oriented Gradients (HOG) with a Convolutional Neural Network (CNN). The proposed intelligent system is benchmarked against a variety of CNN's like basic CNN and VGG16-based CNN and also with the machine learning algorithms such as Support Vector Machine (SVM), Random Forest (RF), Decision Tree Algorithm (DT), Linear Regression (LR), and Gaussian Naïve Bayes (GNB). The proposed detection system was tested on a set of real-world data acquired with a thermal camera on the move in the city of San Antonio, TX, USA that includes images of wild deer. Obtained results exhibit that the HOG-CNN combination achieved approximately 91% correct detection accuracy of wild deer on roadsides, while it outperformed the rest of the tested machine learning algorithms. [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]

The operation of fluid engineering systems is usually governed by a wide range of different parameters. Investigations of the entire parameter spectrum using classical, first-principle based CFD methods are costly with regards to CPU and wall-clock time. Therefore, a near real-time assessment of complex flows using CFD to support the operation is deemed unfeasible. The paper is concerned with methods for data-based surrogate models to predict the forces exerted by the aerodynamic pressure field on the superstructure of a full-scale container ship for different container loading conditions and wind directions. The strategy aims to assist a fuel-efficient operation and is based on a two-step approach. During an initial step, a reduced representation of pressure fields obtained from 3D Navier–Stokes simulations is compiled. To this extent, a classical proper orthogonal decomposition is compared with convolutional neural network autoencoders. A subsequent parameterization employs a feedforward neural network to link the reduced model with the operational parameters, i.e. the angle of attack and container loading condition, and to enable a rapid on board assessment. Both methods provide a similar agreement for the pressure fields, as well as the resulting forces, with the CNN-based surrogate model being significantly more compact. [ABSTRACT FROM AUTHOR]

Low visibility in foggy weather can easily cause accidents and affect normal life. Accurate visibility estimate is critical to transportation, aviation, marine and other fields. For visibility estimation, this paper proposes a visibility estimation algorithm Mean Square Error Based on Convolution Neural Network (MSEBCNN) based on continuous surveillance video, which is an improved neural network deep learning algorithm. In this paper, the images of airport surveillance video were extracted every 15 s and the Region of Interest (ROI) in each image was selected as the measurement area. The improved Convolution Neural Network (CNN) was constructed by replacing the Softmax layer of the last layer of the convolutional neural network with the Mean Square Error (MSE) layer of the objective regression function, and the gradient descent method was used for fitting training to achieve the continuous prediction of visibility. By experiment, the accuracy of prediction at a range of 0–500 m is 97.51%, while the accuracy of prediction at a range of 500–1600 m is 91.67%, which obtained a high prediction accuracy. [ABSTRACT FROM AUTHOR]

The facial expressions recognition (FER) is crucial to many applications. As technology advances and our needs evolve, compound emotion recognition is becoming increasingly important, along with basic emotion recognition. In the literature, Although, FER can be conducted primarily using multiple sensors. However, research shows that using facial images/videos to recognize facial expressions is better because visual presentation can convey more efficiently. Among state-of-the-art methods for FER systems, to improve the accuracy of the basic and compound FER systems, detection of facial action units (AUs) must be combined to detect basic and compound facial expressions. State-of-the-art results show that machine learning and deep learning-based approaches are more potent than conventional FER approaches. This paper surveys various learning frameworks for facial emotion recognition systems for detecting basic and compound emotions using the diverse database and summarizing state-of-the-art results to give good understanding of impact of each learning framework used in FER systems. [ABSTRACT FROM AUTHOR]

Water Body Extraction (WBE) is a challenging task in remote sensing, owing to the complexity of recognizing surface body objects with rich texture, spatial, spectral, temporal, and radiometric features. The use of spectral indices has shown to be successful in separating surface water from its surroundings at the cost of knowledge of appropriate threshold values. In the absence of knowledge on threshold values, extracting the water from remote sensing data is challenging, which is addressed by several Machine Learning (ML) and Deep Learning (DL) algorithms. However, the effectiveness of both ML and DL classifications is witnessed from visual features to semantic categories at the cost of distinct recognition between the water body and non-water body features. In this paper, a novel Multi Scale Feature Extraction Network (MSFEN) for extracting the pixel-level features from medium resolution remote sensing images is proposed and used traditional ML classifiers to extract the surface water bodies using pixel-level features extracted by MSFEN. The proposed framework is trained and tested on Linear Imaging Self Scanning Sensor – III (LISS-III) multispectral satellite images over major water reservoirs in Tamilnadu, Karnataka, Madhya Pradesh, and Odisha. Experimental results indicate that the proposed model MSFEN+SVM provides accurate extraction results by outperforming the existing state-of-the-art models (Fully Convolutional Network (FCN), Unet, SegNet, Multi Scale Convolutional Neural Network (MSCNN), Deepwater Map, Pyramid Scene Parsing Network (PSPNet), Improved PSPNet, Multi-scale Water Extraction Convolutional Neural Network (MWEN) and Multi-Scale Lake Water Extraction Network (MSLWENet) in terms of performance metrics considered. [ABSTRACT FROM AUTHOR]

Many studies using deep learning methods for automatic ship detection from SAR images have good detection accuracy. Researchers are mainly focused on classifying large ships with distinct features like tankers, cargo vessels, and container ships. So, more research is needed for the classification of the seen ships into subclasses. Deep learning-based complete full-fledged ship detection and classification is challenging because of the unavailability of SAR data sets with localization details and class information (sub-class details). This paper proposes a ship detection and classification system for classifying the seen ships into 16 classes. In this method, the 2D SAR data are preprocessed to generate 'SarNeDe' data using image processing and despeckling techniques to increase accuracy by reducing false predictions and wrong classifications. This 'SarNeDe' is used to train and test the deep learning model for detection and classification. This model is designed based on a two-stage object detection style without compromising the speed and accuracy. The detection part (L-model), developed mostly using depthwise separable CNNs with multi-scale and multianchor box detection schemes, estimates the accurate position of all ships in the SAR data. These seen ships' SarNeDes data are given as input to the classification part (C-model), based on a one-shot learning-based classification technique built from scratch to classify 16 ship classes. Detection experimental results on the public SAR ship detection data set (SSDD) and Dataset of Ship Detection for Deep Learning under Complex Backgrounds (SDCD) and experimental classification results in OpenSARShip data set for ship classification validate the proposed method's feasibility. The proposed system is lightweight and can be used in real-time applications. [ABSTRACT FROM AUTHOR]

Identification of wool and cashmere fibers is one of the most important topics in the textile industry. In order to recognize these similar fibers, a novel identification method based on the convolution neural network and deep learning was proposed in this paper. As we all know, training a new identification network commonly requires lots of sample images and needs an amount of time, so the transfer learning was adopted for the fiber identification. The four pre-trained convolution neural networks, which consist of AlexNet, VGG-16, VGG-19, GoogLeNet, were used for the transfer learning to identify these similar fibers. Then, 65 fiber images of four kinds of fiber samples including goat hair, yellow wool, sheep wool, and cashmere fibers, were collected, respectively, and processed by the methods including random interception and rotation to obtain a total of 390 fiber images, respectively, for the experiment analysis. After comparing different network models, the results showed that the highest identification accuracy was 99.15%, obtained by the VGG-16 transfer learning model and the proportion of training set to testing set was 7:3. In addition, compared with the traditional machine learning algorithmics, this method also had a great improvement in the model performance and identification accuracy. [ABSTRACT FROM AUTHOR]

Laser-based optical links offer the possibility of secure, high data rate underwater communication. Challenges include quickly modulating the light, and rapidly and reliably decoding the received symbols, despite degradation due to optical turbulence and scattering. This paper builds upon a framework introduced in 2016 to address these challenges. We constructed two novel 5-beam Laguerre-Gaussian basis sets, creating 25 symbol alphabets via superposition. We collected 139,000 images of the symbols, transmitted 4.3 meters through water with very strong optical turbulence. We use a novel convolutional neural network to decode them. We believe this work is the first to achieve high accuracy (93.7–99.9%) in an environment with extremely high levels (2∼107-108 m-2/3) of carefully documented experimentallyinduced optical turbulence. We improve upon previous work in several ways: using a larger alphabet (47 vs. 32), faster classification rates (10,000 Hz vs. 1,000 Hz), and a larger set of test images (96,000 vs 9,600). [ABSTRACT FROM AUTHOR]

Locating populations in rural areas of developing countries has attracted the attention of humanitarian mapping projects since it is important to plan actions that affect vulnerable areas. Recent efforts have tackled this problem as the detection of buildings in aerial images. However, the quality and the amount of rural building annotated data in open mapping services like OpenStreetMap (OSM) is not sufficient for training accurate models for such detection. Although these methods have the potential of aiding in the update of rural building information, they are not accurate enough to automatically update the rural building maps. In this paper, we explore a human-computer interaction approach and propose an interactive method to support and optimize the work of volunteers in OSM. The user is asked to verify/correct the annotation of selected tiles during several iterations and therefore improving the model with the new annotated data. The experimental results, with simulated and real user annotation corrections, show that the proposed method greatly reduces the amount of data that the volunteers of OSM need to verify/correct. The proposed methodology could benefit humanitarian mapping projects, not only by making more efficient the process of annotation but also by improving the engagement of volunteers. [ABSTRACT FROM AUTHOR]

Elephant entry in human settlements causes a major threat to human–elephant conflict (HEC), but the rapid detection thereof while crossing boundary remains a difficult role, due to the lack of necessary boundary sensing infrastructure. A combination of wireless sensor networks and recent advances in deep learning has paved an effective way for elephant detection. This paper presents and evaluates a Boundary Sense Deep Learning architecture (BSDL) for automated detection of elephants, integrating, elephant image feature learning and elephant classification. A novelty in this approach enhances the deep learning Boundary Sense (BS) architecture to include a background subtraction module which highlights the visual region important for elephant recognition. The objective of the proposed BSDL architecture is validated by achieving better accuracy when compared with the raw image, time efficiency, simplifying and boosting up of Deep Convolution Neural Network (DCNN) by introducing preliminaries; elephant recognition with Multi view dataset dramatically improves the state of art and fine tuning using back-propagation. The dataset includes 1,28,069 images of various postures of elephants collected under different circumstances from different regions (Hosur, Bannerghatta, Shimoga (Sakrebailu) and Dubare). The trained model is designed for identifying only one target species, the elephants. The conclusions drawn from our work prove that the achievement percentage is 97% accuracy in the BSDL architecture, when compared with the existing deep learning algorithms using raw image. [ABSTRACT FROM AUTHOR]