Search

The purpose of this study is to investigate whether there are differences in handwritten Chinese signatures on different media including paper and electronic devices. Participants were asked to sign specified names on various types of media and the signatures were scanned or saved digitally for subsequent analysis. In this study, using convolutional neural networks and Siamese neural networks as classifiers and comparators, the performance plunge is revealed and thus considerable dissimilarity between the signatures on different media is implied. To further explore this, cubic Bézier curves are fitted to the signatures using the least square method for quantitative statistical analysis. By analyzing the visual changes in the morphology of strokes, several features of signatures are selected and computed, and the paired t‐test and the Wilcoxon signed‐rank test are implemented, which provides a deeper substantiation and explanation of the findings. [ABSTRACT FROM AUTHOR]

The research groups in computer vision, graphics, and machine learning have dedicated a substantial amount of attention to the areas of 3D object reconstruction, augmentation, and registration. Deep learning is the predominant method used in artificial intelligence for addressing computer vision challenges. However, deep learning on three-dimensional data presents distinct obstacles and is now in its nascent phase. There have been significant advancements in deep learning specifically for three-dimensional data, offering a range of ways to address these issues. This study offers a comprehensive examination of the latest advancements in deep learning methodologies. We examine many benchmark models for the tasks of 3D object registration, augmentation, and reconstruction. We thoroughly analyse their architectures, advantages, and constraints. In summary, this report provides a comprehensive overview of recent advancements in three-dimensional deep learning and highlights unresolved research areas that will need to be addressed in the future. [ABSTRACT FROM AUTHOR]

The majority of Android smartphone apps are free. When an application is used, advertisements are displayed in order to generate revenue. Adware-related advertising fraud costs billions of dollars each year. Adware is a form of advertising-supported software, that turns into malware when it automatically installs additional malware and adware on an infected device, steals user data, and exposes other vulnerabilities. Better techniques for detecting adware are needed due to the evolution of increasingly sophisticated evasive malware, particularly adware. Even though significant work has been done in the area of malware detection, the adware family has received very little attention. This paper presents a deep learning-based scheme called MadDroid to detect malicious Android adware based on static features. Moreover, this paper delivers a novel dataset that consists of malicious Adware and benign applications and an optimised Convolutional neural network (CNN) for detecting Adware infected by malware based on the permissions of the applications. The results indicate an average classification rate that is higher than previous work for individual adware family classification in terms of well-known evaluation metrics. [ABSTRACT FROM AUTHOR]

Deep learning, a subset of machine learning, stands at the forefront of artificial intelligence, striving to bridge the gap to its ultimate goal. This paper employs summary and induction methodologies to research into the area of deep learning. It begins by surveying the global development and current landscape of deep learning. Next, it elucidates the structural principles, characteristics, and key models, including stacked auto encoders, deep belief networks, deep Boltzmann machines, and convolutional neural networks. Furthermore, it examines the latest advancements and applications of deep learning across diverse domains such as speech processing, computer vision, natural language processing, and medical diagnostics. Finally, the paper outlines the challenges and future research directions within the realm of deep learning. [ABSTRACT FROM AUTHOR]

The objectives of this paper are to investigate the trade-offs between a physically constrained neural network and a deep, convolutional neural network and to design a combined ML approach ("VarioCNN"). Our solution is provided in the framework of a cyberinfrastructure that includes a newly designed ML software, GEOCLASS-image (v1.0), modern high-resolution satellite image data sets (Maxar WorldView data), and instructions/descriptions that may facilitate solving similar spatial classification problems. Combining the advantages of the physically-driven connectionist-geostatistical classification method with those of an efficient CNN, VarioCNN provides a means for rapid and efficient extraction of complex geophysical information from submeter resolution satellite imagery. A retraining loop overcomes the difficulties of creating a labeled training data set. Computational analyses and developments are centered on a specific, but generalizable, geophysical problem: The classification of crevasse types that form during the surge of a glacier system. A surge is a glacial catastrophe, an acceleration of a glacier to typically 100–200 times its normal velocity. GEOCLASS-image is applied to study the current (2016-2024) surge in the Negribreen Glacier System, Svalbard. The geophysical result is a description of the structural evolution and expansion of the surge, based on crevasse types that capture ice deformation in six simplified classes. [ABSTRACT FROM AUTHOR]

Millions of traffic accidents occur worldwide each year, resulting in tens of thousands of deaths. The primary cause is the distracted behavior of drivers during the driving process. If the distracted behaviors of drivers during driving can be detected and recognized in time, drivers can regulate their driving and the goal of reducing the number of traffic fatalities can be achieved. A deep learning model is proposed to detect driver distractions in this paper. The model can identify ten behaviors including one normal driving behavior and nine distracted driving behaviors. The proposed model consists of two modules. In the first module, the cross-domain complementary learning (CDCL) algorithm is used to detect driver body parts in the input images, which reduces the impact of environmental factors in vehicles on the convolutional neural network. Then the output images of the first module are sent to the second module. The Resnet50 and Vanilla networks are ensembled in the second module, and then the driver behavior can be classified. The ensemble architecture used in the second module can reduce the sensitivity of only a single network on the data, and then the detection accuracy can be improved. Through the experiments, it can be seen that the proposed model in this paper can achieve an average accuracy of 99.0%. [ABSTRACT FROM AUTHOR]

This paper presents the latest advances in machine learning techniques and highlights deep learning (DL) methods in recent studies. This technology has recently received great attention as it can solve complex problems. This paper focuses on covering one of the deep learning algorithms (deep neural network) and learning about its types such as convolutional neural network (CNN), Recurrent Neural Networks (RNN), etc. We have discussed recent changes, such as advanced DL technologies. Next, we continue analyzing and discussing the challenges and possible solutions of machine learning, such as big data and object detection, studying more papers in deep learning, and knowing the main experiments and future directions. In addition, this review also identifies some successful deep learning applications in recent years. Moreover, in this paper, one of the deep learning methods, convolutional neural networks, is applied to detect objects in images by using the You Only Look One model and comparing it with RetinaNet using pre-trained models. The results found that CNN (using YOLOv3) is a more accurate model than RetinaNet. [ABSTRACT FROM AUTHOR]

Underwater pipelines are exposed to harsh environments, including high salinity, multi-modal vortex corrosion, and severe wave interference. Their safety is essential for the development and transportation of marine energy. Therefore, real-time safety monitoring of long-distance energy pipelines is of great strategic importance for ensuring the safety of life and property and energy security. With the rapid development of energy development, the corrosion and leakage mechanisms of natural gas pipelines, as well as their identification and early warning, have become the focus of attention. Optical fiber sensing technology has been applied to various energy safety monitoring fields. However, the mechanism of sound source fluctuations in pipeline leakage and the mutual coupling mechanism between distributed optical fiber sensing technology and leakage sound waves are not yet clear. This paper establishes a model based on sound wave propagation and leakage noise response, derives a quadratic fitting relationship between pipeline pressure fluctuations and leakage orifices and a relationship between leakage noise source standard deviation and orifices, and proposes a complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) permutation entropy underwater natural gas pipeline leakage signal recognition method based on distributed optical fiber acoustic sensing technology. The results of theoretical analysis are verified by experiments. It shows that the signal processing method of CEEMDAN permutation entropy is superior to traditional noise reduction methods, which can better preserve the features of the original signal; the radial basis function (RBF) neural network model can accurately identify four different leakage features with an accuracy of 88.15%, and its recognition stability and generalization ability are superior to convolutional neural network, backpropagation, and random forest. Therefore, the research results of this paper provide a new method for safety monitoring in the application of energy pipeline transportation engineering, and expand the potential application scenarios of distributed acoustic sensing sensor systems and RBF neural networks. [ABSTRACT FROM AUTHOR]

Electric motors play a crucial role in self-driving vehicles. Therefore, fault diagnosis in motors is important for ensuring the safety and reliability of vehicles. In order to improve fault detection performance, this paper proposes a motor fault diagnosis method based on vibration signals. Firstly, the vibration signals of each operating state of the motor at different frequencies are measured with vibration sensors. Secondly, the characteristic of Gram image coding is used to realize the coding of time domain information, and the one-dimensional vibration signals are transformed into grayscale diagrams to highlight their features. Finally, the lightweight neural network Xception is chosen as the main tool, and the attention mechanism Convolutional Block Attention Module (CBAM) is introduced into the model to enforce the importance of the characteristic information of the motor faults and realize their accurate identification. Xception is a type of convolutional neural network; its lightweight design maintains excellent performance while significantly reducing the model's order of magnitude. Without affecting the computational complexity and accuracy of the network, the CBAM attention mechanism is added, and Gram's corner field is combined with the improved lightweight neural network. The experimental results show that this model achieves a better recognition effect and faster iteration speed compared with the traditional Convolutional Neural Network (CNN), ResNet, and Xception networks. [ABSTRACT FROM AUTHOR]

This paper presents a new edge detection process implemented in an embedded IoT device called Bee Smart Detection node to detect catastrophic apiary events. Such events include swarming, queen loss, and the detection of Colony Collapse Disorder (CCD) conditions. Two deep learning sub-processes are used for this purpose. The first uses a fuzzy multi-layered neural network of variable depths called fuzzy-stranded-NN to detect CCD conditions based on temperature and humidity measurements inside the beehive. The second utilizes a deep learning CNN model to detect swarming and queen loss cases based on sound recordings. The proposed processes have been implemented into autonomous Bee Smart Detection IoT devices that transmit their measurements and the detection results to the cloud over Wi-Fi. The BeeSD devices have been tested for easy-to-use functionality, autonomous operation, deep learning model inference accuracy, and inference execution speeds. The author presents the experimental results of the fuzzy-stranded-NN model for detecting critical conditions and deep learning CNN models for detecting swarming and queen loss. From the presented experimental results, the stranded-NN achieved accuracy results up to 95%, while the ResNet-50 model presented accuracy results up to 99% for detecting swarming or queen loss events. The ResNet-18 model is also the fastest inference speed replacement of the ResNet-50 model, achieving up to 93% accuracy results. Finally, cross-comparison of the deep learning models with machine learning ones shows that deep learning models can provide at least 3–5% better accuracy results. [ABSTRACT FROM AUTHOR]

In this paper, the experimental results on microphone virtualization in realistic automotive scenarios are presented. A Temporal Convolutional Network (TCN) was designed in order to estimate the acoustic signal at the driver's ear positions based on the knowledge of monitoring microphone signals at different positions—a technique known as virtual microphone. An experimental setup was implemented on a popular B-segment car to acquire the acoustic field within the cabin while running on smooth asphalt at variable speeds. In order to test the potentiality of the TCN, microphone signals were recorded in two different scenarios, either with or without the front passenger. Our experimental results show that, when training is performed in both scenarios, the adopted TCN is able to robustly adapt to different conditions and guarantee a good average performance. Furthermore, an investigation on the parameters of the Neural Network (NN) that guarantee the sufficient accuracy of the estimation of the virtual microphone signals while maintaining a low computational complexity is presented. [ABSTRACT FROM AUTHOR]

The complete characterization of the almost-entropic region yields rate regions for network coding problems. However, this characterization is difficult and open. In this paper, we propose a novel algorithm to determine whether an arbitrary vector in the entropy space is entropic or not, by parameterizing and generating probability mass functions by neural networks. Given a target vector, the algorithm minimizes the normalized distance between the target vector and the generated entropic vector by training the neural network. The algorithm reveals the entropic nature of the target vector, and obtains the underlying distribution, accordingly. The proposed algorithm was further implemented with convolutional neural networks, which naturally fit the structure of joint probability mass functions, and accelerate the algorithm with GPUs. Empirical results demonstrate improved normalized distances and convergence performances compared with prior works. We also conducted optimizations of the Ingleton score and Ingleton violation index, where a new lower bound of the Ingleton violation index was obtained. An inner bound of the almost-entropic region with four random variables was constructed with the proposed method, presenting the current best inner bound measured by the volume ratio. The potential of a computer-aided approach to construct achievable schemes for network coding problems using the proposed method is discussed. [ABSTRACT FROM AUTHOR]

Accurate turbidity classification is essential for maintaining water quality in various contexts, from drinking water to industrial processes. Traditional turbidimeters face challenges, including interference from colored substances, particle shape and size variations, and the need for regular calibration and maintenance. This paper implements a convolutional neural network (CNN) to classify water samples based on their turbidity levels. The dataset consisted of images captured under controlled laboratory conditions, with turbidity levels measured using a 2100P Portable Turbidimeter. The CNN achieved a classification accuracy of 97.00% in laboratory settings. When tested on real-world water body samples, the model maintained an accuracy of 85.00%. The results demonstrate that deep learning can effectively classify turbidity levels, offering a promising solution to overcome the limitations of traditional methods. The study highlights the potential of CNNs for accurate and efficient turbidity measurement, balancing accuracy with practical applicability in field conditions. [ABSTRACT FROM AUTHOR]

Achieving accurate classification of benign and malignant pulmonary nodules is essential for treating some diseases. However, traditional typing methods have difficulty obtaining satisfactory results on small pulmonary solid nodules, mainly caused by two aspects: (1) noise interference from other tissue information; (2) missing features of small nodules caused by downsampling in traditional convolutional neural networks. To solve these problems, this paper proposes a new typing method to improve the diagnosis rate of small pulmonary solid nodules in CT images. Specifically, first, we introduce the Otsu thresholding algorithm to preprocess the data and filter the interference information. Then, to acquire more small nodule features, we add parallel radiomics to the 3D convolutional neural network. Radiomics can extract a large number of quantitative features from medical images. Finally, the classifier generated more accurate results by the visual and radiomic features. In the experiments, we tested the proposed method on multiple data sets, and the proposed method outperformed other methods in the small pulmonary solid nodule classification task. In addition, various groups of ablation experiments demonstrated that the Otsu thresholding algorithm and radiomics are helpful for the judgment of small nodules and proved that the Otsu thresholding algorithm is more flexible than the manual thresholding algorithm. [ABSTRACT FROM AUTHOR]

Deep learning is a subfield of artificial intelligence that has gained significant attention in recent years due to its remarkable success in various domains. The main objective of this research paper is to provide a comprehensive study of deep learning algorithms, including their architecture, training techniques, and applications. In this paper, we have reviewed the literature on deep learning algorithms, highlighting their strengths and limitations. We have also discussed the current trends in deep learning research and provided insights into the future scope of deep learning algorithms. Our findings suggest that deep learning algorithms have the potential to revolutionize various industries and bring significant advancements in the field of artificial intelligence. [ABSTRACT FROM AUTHOR]

Quality of Experience (QoE) is a critical aspect of multimedia applications, which directly impacts user satisfaction and adoption. QoE predictions are used to optimize various parameters such as video quality, bitrate, and network bandwidth to enhance the user experience. However, accurate QoE prediction is a challenging task, as it involves various factors such as network conditions, video content, and user preferences. Therefore, there is a need for enhancing QoE predictions with advanced techniques to improve user satisfaction and adoption. This paper proposes incorporating more complex neural network architectures and using more diverse datasets to improve the accuracy and generalization of Quality of Experience (QoE) predictions. The paper suggests experimenting with more advanced architectures such as convolutional neural networks and recurrent neural networks, which have been shown to be effective in various applications. Additionally, the paper highlights the limitation of using a single dataset and proposes using more diverse datasets that capture different types of video content and network conditions. Enhancing QoE predictions with complex neural networks and diverse datasets include improved accuracy, better generalization, more sophisticated models, enhanced user satisfaction and increased adoption. These enhancements are expected to lead to more accurate and reliable QoE predictions, which are crucial for improving user experience in multimedia applications. [ABSTRACT FROM AUTHOR]

Introduction: Mpox (formerly monkeypox) is an infectious disease that spreads mostly through direct contact with infected animals or people's blood, bodily fluids, or cutaneous or mucosal lesions. In light of the global outbreak that occurred in 2022-2023, in this paper, we analyzed global Mpox univariate time series data and provided a comprehensive analysis of disease outbreaks across the world, including the USA with Brazil and three continents: North America, South America, and Europe. The novelty of this study is that it delved into the Mpox time series data by implementing the data-driven methods and a mathematical model concurrently--an aspect not typically addressed in the existing literature. The study is also important because implementing these models concurrently improved our predictions' reliability for infectious diseases. Methods: We proposed a traditional compartmental model and also implemented deep learning models (1D-convolutional neural network (CNN), long-short term memory (LSTM), bidirectional LSTM (BiLSTM), hybrid CNN-LSTM, and CNNBiLSTM) as well as statistical time series models: autoregressive integrated moving average (ARIMA) and exponential smoothing on the Mpox data. We also employed the least squares method fitting to estimate the essential epidemiological parameters in the proposed deterministic model. Results: The primary finding of the deterministic model is that vaccination rates can flatten the curve of infected dynamics and influence the basic reproduction number. Through the numerical simulations, we determined that increased vaccination among the susceptible human population is crucial to control disease transmission. Moreover, in case of an outbreak, our model showed the potential for epidemic control by adjusting the key epidemiological parameters, namely the baseline contact rate and the proportion of contacts within the human population. Next, we analyzed data-driven models that contribute to a comprehensive understanding of disease dynamics in different locations. Additionally, we trained models to provide short-term (eight-week) predictions across various geographical locations, and all eight models produced reliable results. Conclusion: This study utilized a comprehensive framework to investigate univariate time series data to understand the dynamics of Mpox transmission. The prediction showed that Mpox is in its die-out situation as of July 29, 2023. Moreover, the deterministic model showed the importance of the Mpox vaccination in mitigating the Mpox transmission and highlighted the significance of effectively adjusting key epidemiological parameters during outbreaks, particularly the contact rate in high-risk groups. [ABSTRACT FROM AUTHOR]

The applications of deep learning and artificial intelligence have permeated daily life, with time series prediction emerging as a focal area of research due to its significance in data analysis. The evolution of deep learning methods for time series prediction has progressed from the Convolutional Neural Network (CNN) and the Recurrent Neural Network (RNN) to the recently popularized Transformer network. However, each of these methods has encountered specific issues. Recent studies have questioned the effectiveness of the self-attention mechanism in Transformers for time series prediction, prompting a reevaluation of approaches to LTSF (Long Time Series Forecasting) problems. To circumvent the limitations present in current models, this paper introduces a novel hybrid network, Temporal Convolutional Network-Linear (TCN-Linear), which leverages the temporal prediction capabilities of the Temporal Convolutional Network (TCN) to enhance the capacity of LSTF-Linear. Time series from three classical chaotic systems (Lorenz, Mackey–Glass, and Rossler) and real-world stock data serve as experimental datasets. Numerical simulation results indicate that, compared to classical networks and novel hybrid models, our model achieves the lowest RMSE, MAE, and MSE with the fewest training parameters, and its R2 value is the closest to 1. [ABSTRACT FROM AUTHOR]

This paper presents a novel approach to sentiment analysis specifically customized for predicting stock market movements, bypassing the need for external dictionaries that are often unavailable for many languages. Our methodology directly analyzes textual data, with a particular focus on context-specific sentiment words within neural network models. This specificity ensures that our sentiment analysis is both relevant and accurate in identifying trends in the stock market. We employ sophisticated mathematical modeling techniques to enhance both the precision and interpretability of our models. Through meticulous data handling and advanced machine learning methods, we leverage large datasets from Twitter and financial markets to examine the impact of social media sentiment on financial trends. We achieved an accuracy exceeding 75%, highlighting the effectiveness of our modeling approach, which we further refined into a convolutional neural network model. This achievement contributes valuable insights into sentiment analysis within the financial domain, thereby improving the overall clarity of forecasting in this field. [ABSTRACT FROM AUTHOR]

This paper presents the results of a study on data preprocessing and modeling for predicting corrosion in water pipelines of a steel industrial plant. The use case is a cooling circuit consisting of both direct and indirect cooling. In the direct cooling circuit, water comes into direct contact with the product, whereas in the indirect one, it does not. In this study, advanced machine learning techniques, such as extreme gradient boosting and deep neural networks, have been employed for two distinct applications. Firstly, a virtual sensor was created to estimate the corrosion rate based on influencing process variables, such as pH and temperature. Secondly, a predictive tool was designed to foresee the future evolution of the corrosion rate, considering past values of both influencing variables and the corrosion rate. The results show that the most suitable algorithm for the virtual sensor approach is the dense neural network, with MAPE values of (25 ± 4)% and (11 ± 4)% for the direct and indirect circuits, respectively. In contrast, different results are obtained for the two circuits when following the predictive tool approach. For the primary circuit, the convolutional neural network yields the best results, with MAPE = 4% on the testing set, whereas for the secondary circuit, the LSTM recurrent network shows the highest prediction accuracy, with MAPE = 9%. In general, models employing temporal windows have emerged as more suitable for corrosion prediction, with model performance significantly improving with a larger dataset. [ABSTRACT FROM AUTHOR]

This paper introduces a new method for compressing images in energy-starved systems, like satellites, unmanned aerial vehicles, and Internet of Things nodes, which is based on coordinated group signal transformation (CGST). The transformation algorithm is a type of difference coding and may be classified as a non-transform-based image-compression method. CGST simplifies the difference signal conversion scheme using a single group codec for all signals. It considers color channels as correlated signals of a multi-channel communication system. The performance of CGST was evaluated using a dataset of 128 × 128 pixel images from satellite remote sensing systems. To adapt CGST to image compression, some modifications were introduced to the algorithm, such as fixing the procedure of the difference signals calculation to prevent any "zeroing" of brightness and supplementing the group codec with a neural network to improve the quality of restored images. The following types of neural networks were considered: fully connected, recurrent, convolution, and convolution in the Fourier space. Based on the simulation results, fully connected neural networks are recommended if the goal is to minimize processing delay time. These networks have a response time of 13 ms. Conversely, suppose the priority is to improve quality in cases where delays are not critical. In that case, convolution neural networks in the Fourier space should be used, providing an image compression ratio of 4.8 with better minimum square error and Mikowsky norm values than JPEG with the same compression ratio. [ABSTRACT FROM AUTHOR]

Black heart disease is one of the screening indicators of seed potatoes, which has a serious impact on the quality and yield of potato, and at present there are fewer non-destructive testing methods for internal defects of seed potatoes. This paper aims to utilize non-destructive testing technology to quickly identify qualified and black hearted seed potatoes, and then to protect yield and food security. In this paper, transmission spectroscopy system was utilized to collect the spectral data of 104 qualified seed potatoes and 104 black hearted seed potatoes in 450~940 nm band. Subsequently, four algorithms, namely Savitzky-Golay (SG), Standard Normal Variate (SNV), Multiplicative Scatter Correction (MSC) and First-order Derivative (FD), were utilized to pre-process the seed potatoes spectral data to improve the data noise ratio. Feature wavelength extraction was made using Competitive Adaptive Reweighted Sampling (CARS) and Successive Projections Algorithm (SPA) to enhance the sample data characteristics and improve the model interpretability. The construction of classification models for qualified and black hearted seed potatoes relied on two deep learning techniques, Convolutional Neural Networks (CNN) and Recurrent Neural Network (RNN), which were trained and tested for the feature bands respectively. The experimental results showed that SG-CARS-CNN was the optimal combination of classification algorithms, and the classification accuracies of both the training set and the test set reached 100%, which improved the accuracy of the test set by 3.85% compared with that of the traditional machine learning algorithms, and provided an accurate method for the rapid screening of qualified seed potatoes. [ABSTRACT FROM AUTHOR]

EDITORIAL published: 22 March 2021 doi: 10.3389/fnbot.2021.671519 Frontiers in Neurorobotics | www.frontiersin.org 1 March 2021 | Volume 15 | Article 671519 Edited and reviewed by: Jae-Ho Han, Korea University, South Korea *Correspondence: Jose de Jesus Rubio rubio.josedejesus@gmail.com Received: 24 February 2021 Accepted: 01 March 2021 Published: 22 March 2021 Citation: Rubio JdJ, Pan Y, Pieper J, Chen M-Y and Sossa Azuela JH (2021) Editorial: Advances in Robots Trajectories Learning via Fast Neural Networks. The paper titled "CNN Based Detectors on Planetary Environments: A Performance Evaluation" by Furlán et al. presents a convolutional neural network algorithm and an exploration robot for the detection of rocks in environments similartoMars. Some examples of fast neural networks, and their variants, are long short-term memory, convolutional neural network, recurrent neural network, deep deterministic policy gradient, cascade neural network, genetic algorithm, machine learning, and fuzzy model. [Extracted from the article]

This paper concerns the development of a machine learning tool to detect anomalies in the molecular structure of Gallium Arsenide. We employ a combination of a CNN and a PCA reconstruction to create the model, using real images taken with an electron microscope in training and testing. The methodology developed allows for the creation of a defect detection model, without any labeled images of defects being required for training. The model performed well on all tests under the established assumptions, allowing for reliable anomaly detection. To the best of our knowledge, such methods are not currently available in the open literature; thus, this work fills a gap in current capabilities. [ABSTRACT FROM AUTHOR]

To convey neural network architectures in publications, appropriate visualizations are of great importance. While most current deep learning papers contain such visualizations, these are usually handcrafted just before publication, which results in a lack of a common visual grammar, significant time investment, errors, and ambiguities. Current automatic network visualization tools focus on debugging the network itself and are not ideal for generating publication visualizations. Therefore, we present an approach to automate this process by translating network architectures specified in Keras into visualizations that can directly be embedded into any publication. To do so, we propose a visual grammar for convolutional neural networks (CNNs), which has been derived from an analysis of such figures extracted from all ICCV and CVPR papers published between 2013 and 2019. The proposed grammar incorporates visual encoding, network layout, layer aggregation, and legend generation. We have further realized our approach in an online system available to the community, which we have evaluated through expert feedback, and a quantitative study. It not only reduces the time needed to generate network visualizations for publications, but also enables a unified and unambiguous visualization design. [ABSTRACT FROM AUTHOR]

Image semantic segmentation technology is one of the core research contents in the field of computer vision. With the improvement of computer performance and the continuous development of deep learning technology, researchers have more and more enthusiasm to study the actual effect and performance of image semantic segmentation. The results of deep semantic segmentation allow computers to have a more detailed and accurate understanding of images, and have a wide range of application needs in the fields of autonomous driving, intelligent security, medical imaging, remote sensing images, etc. However, the existing image semantic segmentation algorithms have the disadvantages of easy discontinuous results and insufficient prediction accuracy. In this paper, we take deep learning-based image semantic segmentation technology as the research object to explore the improvement of the image semantic segmentation algorithm and its application in road scenarios. First, this paper proposes MCU-Net method based on residual fusion and multi-scale contextual information. MCU-Net uses residual fusion module to deepen the network structure and improve the ability of U-Net to acquire deeper features. Then a top-down and bottom-up path is constructed for feature information between different levels, and the spatial and semantic information contained in shallow and deep features in the network is fully utilized by fusing features from different levels. In addition, an enhanced void space pyramid pooling module is added for feature information between the same levels, which enables the output features to have a larger range of semantic information. Second, this paper proposes the DAMCU-Net method based on attention mechanism and edge detection based on MCU-Net. DAMCU-Net extracts global contextual information by the attention mechanism optimization module, while fusing features using dense jump connections to facilitate the network to recover more spatial detail information during upsampling, and uses the FReLU activation function to improve the segmentation capability of the network for complex targets. For the edge information lost in the feature extraction process, the edge detection branch is added to supplement the feature information of the main path by feature fusion to achieve the optimization of the edge information. [ABSTRACT FROM AUTHOR]

The advancement of unmanned aerial vehicles (UAVs) enables early detection of numerous disasters. Efforts have been made to automate the monitoring of data from UAVs, with machine learning methods recently attracting significant interest. These solutions often face challenges with high computational costs and energy usage. Conventionally, data from UAVs are processed using cloud computing, where they are sent to the cloud for analysis. However, this method might not meet the real-time needs of disaster relief scenarios. In contrast, edge computing provides real-time processing at the site but still struggles with computational and energy efficiency issues. To overcome these obstacles and enhance resource utilization, this paper presents a convolutional neural network (CNN) model with an early exit mechanism designed for fire detection in UAVs. This model is implemented using TSMC 40 nm CMOS technology, which aids in hardware acceleration. Notably, the neural network has a modest parameter count of 11.2 k. In the hardware computation part, the CNN circuit completes fire detection in approximately 230,000 cycles. Power-gating techniques are also used to turn off inactive memory, contributing to reduced power consumption. The experimental results show that this neural network reaches a maximum accuracy of 81.49% in the hardware implementation stage. After automatic layout and routing, the CNN hardware accelerator can operate at 300 MHz, consuming 117 mW of power. [ABSTRACT FROM AUTHOR]

Advances in information and signal processing, driven by artificial intelligence techniques and recent breakthroughs in deep learning, have significantly impacted autonomous driving by enhancing safety and reducing the dependence on human intervention. Generally, prevailing ADASs (advanced driver assistance systems) incorporate costly components, making them financially unattainable for a substantial portion of the population. This paper proposes a solution: an embedded system designed for real-time pedestrian and priority sign detection, offering affordability and universal applicability across various vehicles. The suggested system, which comprises two cameras, an NVIDIA Jetson Nano B01 low-power edge device and an LCD (liquid crystal system) display, ensures seamless integration into a vehicle without occupying substantial space and provides a cost-effective alternative. The primary focus of this research is addressing accidents caused by the failure to yield priority to other drivers or pedestrians. Our study stands out from existing research by concurrently addressing traffic sign recognition and pedestrian detection, concentrating on identifying five crucial objects: pedestrians, pedestrian crossings (signs and road paintings separately), stop signs, and give way signs. Object detection was executed using a lightweight, custom-trained CNN (convolutional neural network) known as SSD (Single Shot Detector)-MobileNet, implemented on the Jetson Nano. To tailor the model for this specific application, the pre-trained neural network underwent training on our custom dataset consisting of images captured on the road under diverse lighting and traffic conditions. The outcomes of the proposed system offer promising results, positioning it as a viable candidate for real-time implementation; its contributions are noteworthy in advancing the safety and accessibility of autonomous driving technologies. [ABSTRACT FROM AUTHOR]

In mountainous landscapes, the diverse geotechnical conditions amplify landslide susceptibility. Factors such as precipitation and seismic activity can trigger landslides, while inherent hazards such as voids, fissures, and compaction deficits jeopardize long-term slope stability. Detecting and forecasting these susceptibilities accurately is crucial. In this paper, the time-domain finite- difference approach and the gprMax software are used to conduct forward modeling of landslide susceptibility. An electrical model of subsurface aqueous structures is created, including water-filled and air-filled cavities, fracture zones, and fault lines. The distinctive radar signal responses within these environments are examined, and a dataset of B-scan images associated with their electrical models is constructed. By employing deep learning algorithms and the robust nonlinear mapping ability of convolutional neural networks in the Pix2Pix generative adversarial network, we accelerate the intelligent inversion of the geological radar data on landslide susceptibility. This innovative approach effectively reconstructs hazard models, offering a reliable basis for interpretation of radar signals. [ABSTRACT FROM AUTHOR]

Robust visual place recognition (VPR) enables mobile robots to identify previously visited locations. For this purpose, the extracted visual information and place matching method plays a significant role. In this paper, we critically review the existing VPR methods and group them into three major categories based on visual information used, i.e., handcrafted features, deep features, and semantics. Focusing the benefits of convolutional neural networks (CNNs) and semantics, and limitations of existing research, we propose a robust appearance-based place recognition method, termed SVS-VPR, which is implemented as a hierarchical model consisting of two major components: global scene-based and local feature-based matching. The global scene semantics are extracted and compared with pre-visited images to filter the match candidates while reducing the search space and computational cost. The local feature-based matching involves the extraction of robust local features from CNN possessing invariant properties against environmental conditions and a place matching method utilizing semantic, visual, and spatial information. SVS-VPR is evaluated on publicly available benchmark datasets using true positive detection rate, recall at 100% precision, and area under the curve. Experimental findings demonstrate that SVS-VPR surpasses several state-of-the-art deep learning-based methods, boosting robustness against significant changes in viewpoint and appearance while maintaining efficient matching time performance. [ABSTRACT FROM AUTHOR]

Reconfigurable intelligent surfaces (RIS) offer the potential to customize the radio propagation environment for wireless networks, and will be a key element for 6G communications. However, due to the unique constraints in these systems, the optimization problems associated to RIS configuration are challenging to solve. This paper illustrates a new approach to the RIS configuration problem, based on the use of artificial intelligence (AI) and deep learning (DL) algorithms. Concretely, a custom convolutional neural network (CNN) intended for edge computing is presented, and implementations on different representative edge devices are compared, including the use of commercial AI-oriented devices and a field-programmable gate array (FPGA) platform. This FPGA option provides the best performance, with × 20 performance increase over the closest FP32, GPU-accelerated option, and almost × 3 performance advantage when compared with the INT8-quantized, TPU-accelerated implementation. More noticeably, this is achieved even when high-level synthesis (HLS) tools are used and no custom accelerators are developed. At the same time, the inherent reconfigurability of FPGAs opens a new field for their use as enabler hardware in RIS applications. [ABSTRACT FROM AUTHOR]

For grid stability, operation, and planning, solar irradiance forecasting is crucial. In this paper, we provide a method for predicting the Global Horizontal Irradiance (GHI) mean values one hour in advance. Sky images are utilized for training the various forecasting models along with measured meteorological data in order to account for the short-term variability of solar irradiance, which is mostly caused by the presence of clouds in the sky. Additionally, deep learning models like the multilayer perceptron (MLP), convolutional neural networks (CNN), long short-term memory (LSTM), or their hybridized forms are widely used for deterministic solar irradiance forecasting. The implementation of probabilistic solar irradiance forecasting, which is gaining prominence in grid management since it offers information on the likelihood of different outcomes, is another task we carry out using quantile regression. The novelty of this paper lies in the combination of a hybrid deep learning model (CNN-LSTM) with quantile regression for the computation of prediction intervals at different confidence levels. The training of the different machine learning algorithms is performed over a year's worth of sky images and meteorological data from the years 2019 to 2020. The data were measured at the University of French Polynesia (17.5770° S, 149.6092° W), on the island of Tahiti, which has a tropical climate. Overall, the hybrid model (CNN-LSTM) is the best performing and most accurate in terms of deterministic and probabilistic metrics. In addition, it was found that the CNN, LSTM, and ANN show good results against persistence. [ABSTRACT FROM AUTHOR]

Automatic brain tumor detection is a challenging task as tumors vary in their position, mass, nature, and similarities found between brain lesions and normal tissues. The tumor detection is vital and urgent as it is related to the lifespan of the affected person. Medical experts commonly utilize advanced imaging practices such as magnetic resonance imaging (MRI), computed tomography (CT), and ultrasound images to decide the presence of abnormal tissues. It is a very time-consuming task to extract the tumor information from the enormous quantity of information produced by MRI volumetric data examination using a manual approach. In manual tumor detection, precise identification of tumor along with its details is a complex task. Henceforth, reliable and automatic detection systems are vital. In this paper, convolutional neural network based automated brain tumor recognition approach is proposed to analyze the MRI images and classify them into tumorous and non-tumorous classes. Various convolutional neutral network architectures like Alexnet, VGG-16, GooGLeNet, and RNN are explored and compared together. The paper focuses on the tuning of the hyperparameters for the two architectures namely Alexnet and VGG-16. Exploratory results on BRATS 2013, BRATS 2015, and OPEN I dataset with 621 images confirmed that the accuracy of 98.67% is achieved using CNN Alexnet for automatic detection of brain tumors while testing on 125 images. [ABSTRACT FROM AUTHOR]

In recent years, deep learning technology has significantly improved the performance of various computer vision tasks. Convolutional neural networks for edge detection tasks are usually composed of two parts: encoding and decoding. Encoding is mainly used for feature extraction and characterization; while decoding is mainly used to effectively integrate the local, detailed features extracted from encoding into global information. The research suggests that convolutional neural networks are a technical replication of biological neural networks in a simplified sense, and the model building of convolutional neural networks relies on the intricate connections and cellular functions of biological neural networks. For visual tasks, the visual "ventral stream" neural pathway plays an essential role. And inspired by the interactive feedback mechanism between cells and tissues in the ventral stream visual pathway, this paper proposes a novel convolutional neural network model for edge detection. We use Visual Geometry Group Net to simulate the visual signal perceptron retina, the relay lateral geniculate nucleus, and the ventral stream neural pathway, and based on the visual neural information transmission mechanism, we build a lateral interactive feedback coding network. Also by using the bottom-up feedback parsing and parallel processing of feature information in the Inferior Temporal layer, the feedforward information, and feedback information are integrated in a longitudinal feedback interactive manner in the decoding network. We conducted experiments on the publicly available datasets BSDS500, NYUD, Multicue-Boundary, and Multicue- Edge, achieving Score 0.824, 0.773, 0.839, and 0.892, respectively. The results show that our method achieves good performance and is highly competitive. [ABSTRACT FROM AUTHOR]

This paper presents a novel deep-learning (DL)-based approach for classifying digitally modulated signals, which involves the use of capsule networks (CAPs) together with the cyclic cumulant (CC) features of the signals. These were blindly estimated using cyclostationary signal processing (CSP) and were then input into the CAP for training and classification. The classification performance and the generalization abilities of the proposed approach were tested using two distinct datasets that contained the same types of digitally modulated signals, but had distinct generation parameters. The results showed that the classification of digitally modulated signals using CAPs and CCs proposed in the paper outperformed alternative approaches for classifying digitally modulated signals that included conventional classifiers that employed CSP-based techniques, as well as alternative DL-based classifiers that used convolutional neural networks (CNNs) or residual networks (RESNETs) with the in-phase/quadrature (I/Q) data used for training and classification. [ABSTRACT FROM AUTHOR]

Convolutional neural networks (CNN) have demonstrated state-of-the-art classification results in image categorization, but have received comparatively little attention for classification of one-dimensional physiological signals. We design a deep CNN architecture for automated sleep stage classiffication of human sleep EEG and EOG signals. The CNN proposed in this paper amply outperforms recent work that uses a different CNN architecture over a single-EEG-channel version of the same dataset. We show that the performance gains achieved by our network rely mainly on network depth, and not on the use of several signal channels. Performance of our approach is on par with human expert inter-scorer agreement. By examining the internal activation levels of our CNN, we find that it spontaneously discovers signal features such as sleep spindles and slow waves that figure prominently in sleep stage categorization as performed by human experts. [ABSTRACT FROM AUTHOR]

This paper focuses on the training of a deep neural network regarding danger sign detection and recognition in a substation. It involved applying the concepts of neural networks and computer vision to achieve results similar to traffic sign and number plate detection systems. The input data were captured in three distinct formats, i.e. grayscale, RGB, and YCbCr, which have been used as a base for comparison in this paper. The efficiency of the neural network was tested on a unique data set involving danger signs present in industrial and processing facilities. The data set was unique, consisting of four distinct symbols. The trained data were selected so that they would not facilitate overfitting and also would not be under fitted. The accuracy of the model varied with the input type and was tested with two distinct classifiers, CNN and SVM, and the results were compared. The model was designed to be fast and accurate, and it can be implemented on mobile devices. [ABSTRACT FROM AUTHOR]

Steganography is the set of techniques aiming to hide information in messages as images. Recently, stenographic techniques have been combined with polyglot attacks to deliver exploits in Web browsers. Machine learning approaches have been proposed in previous works as a solution for detecting stenography in images, but the specifics of hiding exploit code have not been systematically addressed to date. This paper proposes the use of deep learning methods for such detection, accounting for the specifics of the situation in which the images and the malicious content are delivered using Spatial and Frequency Domain Steganography algorithms. The methods were evaluated by using benchmark image databases with collections of JavaScript exploits, for different density levels and steganographic techniques in images. A convolutional neural network was built to classify the infected images with a validation accuracy around 98.61% and a validation AUC score of 99.75%. [ABSTRACT FROM AUTHOR]

The paper proposes a novel block-wise prediction paradigm based on Convolutional Neural Networks (CNNs) for lossless video coding. A deep neural network model which follows a multi-resolution design is employed for block-wise prediction. Several contributions are proposed to improve neural network training. A first contribution proposes a novel loss function formulation for an efficient network training based on a new approach for patch selection. Another contribution consists in replacing all HEVC-based angular intra-prediction modes with a CNN-based intra-prediction method, where each angular prediction mode is complemented by a CNN-based prediction mode using a specifically trained model. Another contribution consists in an efficient adaptation of the CNN-based intra-prediction residual for lossless video coding. Experimental results on standard test sequences show that the proposed coding system outperforms the HEVC standard with an average bitrate improvement of around 5%. To our knowledge, the paper is the first to replace all the traditional HEVC-based angular intra-prediction modes with an intra-prediction method based on modern Machine Learning techniques for lossless video coding applications. [ABSTRACT FROM AUTHOR]

Local failure of rail track commonly grow from surface defects. Hence, timely detection of surface defects helps to identify potential hazards on the track and reduce the occurrence of railroad accidents. Since track surface defects are scattered and diverse, and different service life leads to different types of defects, it is crucial to detect surface defects in real time, with efficiency, reliability and robustness. To this end, a pixel-level defects segmentation method is proposed. In this paper, features are tessellated together at the Channel level to form denser features, allowing additional information on surface defects textures to be propagated among high-resolution layers. Dropout is performed on the weak correlations learned during the convolution, so that the convolution blocks can share a uniform weight matrix, reducing computation redundancy and model complexity. Firstly, the track datasets of different ages are categorized into four sets, then, the samples are normalized to grey scale by pre-processing, and fed into the proposed network for training. An evaluation of the proposed model on defective samples was performed to demonstrate the performance of the method, with an Accuracy of 97.47%, a Loss of 0.0061 and an Average Frame Rate of 0.033s. The results of different networks tested on the same dataset show that the proposed model exhibits strong stability, adaptability and robustness. In addition, the proposed model is assessed on two different datasets with distinct challenges, with Mean Intersection over Union yielding 2.13% and 3.77% boosts respectively. [ABSTRACT FROM AUTHOR]

This paper proposes a momentum algorithm based on Borges difference and an adaptive momentum (Adam) algorithm based on Borges difference to update parameters, which can adjust the momentum information more flexibly. The Borges difference is proposed from the definition of Borges derivative to be combined with the gradient algorithm in convolutional neural networks. The proposed momentum algorithm based on Borges difference and Adam algorithm based on Borges difference can be adjusted more flexibly in order to speed up the convergence. The parameter optimization algorithm with the Borges difference presents a better performance compared with the integer-order momentum algorithm and integer-order Adam algorithm, with the proposed nonlinear adjustment method for the parameter tuning of convolutional neural networks. By analyzing experimental results of Fashion-MNIST dataset and CIFAR-10 dataset, the optimization algorithms based on Borges difference proposed in this paper gain better effects on the optimization model compared with the corresponding ones based on the integer-order difference, and can speed up the convergence speed and recognition accuracy of the image recognition. [ABSTRACT FROM AUTHOR]

Computer images consist of huge data and thus require more memory space. The compressed image requires less memory space and less transmission time. Imaging and video coding technology in recent years has evolved steadily. However, the image data growth rate is far above the compression ratio growth, considering image and video acquisition systems' popularization. It is generally accepted, in particular, that further improvement in coding efficiency within the conventional hybrid coding system is increasingly challenging. A new and exciting image compression solution is also offered by the deep convolution neural network (CNN), which in recent years has resumed the neural network and achieved significant success both in artificial intelligent fields and in signal processing. In this paper we include a systematic, detailed and current analysis of image compression techniques based on the neural network. Images are applied to the evolution and growth of compression methods based on neural networks. In particular, the end-to-end frames based on neural networks are reviewed, revealing fascinating explorations of frameworks/standards for next-generation image coding. The most important studies are highlighted and future trends even envisaged in relation to image coding topics using neural networks. [ABSTRACT FROM AUTHOR]

In this paper we aim to analyze the influence of Deep Learning (DL) and Neural Networks (NN), on financial forecasting, as a result we have extensively examined research papers and real life implementations of these sophisticated computer models that forecast patterns and movements in financial markets, in the same way we will explore and compare the development of financial forecasting techniques starting from classical methods to the adoption of deep learning models, like Convolutional Neural Network (CNN), Recurrent Neural Networks (RNN) and Long Short Term Memory (LSTM). To be more specific, in this article we delve into the abilities of these models to capture non-linear patterns in financial data such as stock market asset prices. We highlight how they excel in some situations compared to classical methods used for predicting the future of a financial asset. We emphasize how these models outperform conventional techniques for projecting the future of a financial asset in some circumstances, we also address the challenges and barriers associated with using these models to forecasting of financial outcomes, some challenges include overfitting, the need for high quality data, and the requirement for large databases. By examining and combining insights from multiple sources, our goal is to present a global perspective on the current state of neural networks and deep learning used for predicting future changes in the financial sector, we aim to identify areas where these models demonstrate some kind of performance while also showing areas that necessitate more research and development. [ABSTRACT FROM AUTHOR]

Image processing is the set of techniques used to adapt and extract the necessary information for a specific application. In the case of aerial vehicles, these techniques are widely used to define the elements of the environment, the device is immersed and based on these, to make decision and plan a new path or define new missions. This paper outlines the development of two Convolutional Neural Networks (CNN) designed to identify and localize trees within images. The development process involved utilizing a dataset comprising 280 images, of which 168 were processed and allocated for training. This augmentation increased the dataset in a ratio of 1:4, enhancing the network's learning capacity. Out of the 280 images used, the remaining 112 were dedicated for validation purposes. The classification network was designed with 10 layers featured two mutually exclusive and categorized outputs with and without tree; and 13 layers to the regression network include 4 independent outputs corresponding to the location and size of the tree. The outcomes suggest that the proposed networks promise for such applications, however, due to the limitations of the data used for training, the network presented problems of overtraining for the classification CNN and encountered issues and errors for the localization. [ABSTRACT FROM AUTHOR]

Modern machine degradation trend evaluation relies on the unsupervised model-based estimation of a health index (HI) from asset measurement data. This minimizes the need for timely human evaluation and avoids assumptions on the degradation shape. However, the comparability of multiple HI curves over time generated by unsupervised methods suffers from a scaling mismatch (non-coherent HIs) caused by the slightly different asset initial conditions and distinct HI model training. In this paper, we propose a novel self-supervised approach to obtain HI curves without suffering from the scale mismatch. Our approach uses an unsupervised autoencoder based on a convolutional neural network (CNN) to detect initial faults and autonomously label measurement samples. The resulting self-labeled data is used to train a 1D-CNN health predictor, effectively eliminating the scaling mismatch problem. On the basis of a bearing test-to-failure experiment, we show that our self-supervised scheme offers a promising solution for the non-coherent HI problem. In addition, we observed that our method indicates the gradual wear affecting the bearing prior to the independent analysis of a human expert. [ABSTRACT FROM AUTHOR]

Drowsy driving is a major cause of road accidents worldwide, necessitating the development of effective drowsiness detection systems. Each year, there are more accidents and fatalities than ever before for a variety of causes. For instance, there were 22,952 fatalities and 79,545 injuries as a result of nearly 66,500 vehicle accidents in the last 10 years. In this paper, we propose a novel approach for detecting drowsiness based on behavioral cues captured by a digital camera and utilizing the multi-task cascaded convolutional neural network (MTCNN) deep learning algorithm. A high-resolution camera records visual indications like closed or open eye movement to base the technique on the driver's behavior. In order to measure a car user's weariness in the present frame of reference, eyes landmarks are evaluated, which results in the identification of a fresh constraint known as "eyes aspect ratio." A picture with a frame rate of 60 frames per second (f/s) and a resolution of 4,320 eyeballs was used. The accuracy of sleepiness detection was more than 99.9% in excellent lighting and higher than 99.8% in poor lighting, according to testing data. The current study did better in terms of sleepiness detection accuracy than a lot of earlier investigations. [ABSTRACT FROM AUTHOR]

The accuracy and reliability requirements in aerospace manufacturing processes are some of the most demanding in industry. One of the first steps is detection and precise measurement using artificial vision models to accurately process the part. However, these systems require complex adjustments and do not work correctly in uncontrolled scenarios, but require manual supervision, which reduces the autonomy of automated machinery. To solve these problems, this paper proposes a convolutional neural network for the detection and measurement of drills and other fixation elements in an uncontrolled industrial manufacturing environment. In addition, a fine-tuning algorithm is applied to the results obtained from the network, and a new metric is defined to evaluate the quality of detection. The efficiency and robustness of the proposed method were verified in a real production environment, with 99.7% precision, 97.6% recall and an overall quality factor of 96.0%. The reduction in operator intervention went from 13.3% to 0.6%. The presented work will allow the competitiveness of aircraft component manufacturing processes to increase, and working environments will be safer and more efficient. [ABSTRACT FROM AUTHOR]