Search

• Five Machine Learning (ML) models compared for wave height time series prediction. • Complex ML models do not outperform simple AR in wave height time series prediction. • Comment to related papers: signal decomposition in test set series is WRONG. Significant Wave Height (SWH) is crucial in many aspect of ocean engineering. The accurate prediction of SWH has therefore been of immense practical value. Recently, Artificial Intelligence (AI) time series prediction methods have been widely used for single-point short-term SWH time-series forecasting, resulting in many AI-based models claiming to achieve good results. However, the extent to which these complex AI models can outperform traditional methods has largely been overlooked. This study compared five different models - AutoRegressive (AR), eXtreme Gradient Boosting (XGB), Artificial Neural Network (ANN), Long Short-Term Memory (LSTM), and WaveNet - for their performance on SWH time series prediction at 16 buoy locations. Surprisingly, the results suggest that the differences of performance among different models are negligible, indicating that all these AI models have only "learned" the linear auto-regression from the data. Additionally, we noticed that many recent studies used signal decomposition method for such time series prediction, and most of them decomposed the test sets, which is WRONG. [ABSTRACT FROM AUTHOR]

An instrument-free, user-friendly, and cost-effective PAD colorimetric sensor that can quantitative detection of H 2 O 2 has been realized by using bimetallic nickel–cobalt selenides as highly active peroxidase mimic and smartphone integrated with dark cavity as detector. Integrated with an ANN model and a self-compiled easy-to-use smartphone APP, the intelligent and on-site detection of H 2 O 2 was constructed, which exhibited an ultra-wide dynamic range. [Display omitted] • An effective paper-based colorimetric sensor was prepared based on nanozyme. • The optimized Ni 0.75 Co 0.25 Se exhibited excellent peoxidase-mimetic activities. • The on-site detection of H 2 O 2 was constructed by a self-compiled smartphone APP. • The machine learning-assisted sensor can detect H 2 O 2 over a wide dynamic range. Paper-based analytical devices (PADs) integrated with smartphones have shown great potential in various fields, but they also face challenges such as single signal reading, complex data processing and significant environmental impacting. In this study, a colorimetric PAD platform has been proposed using bimetallic nickel–cobalt selenides as highly active peroxidase mimic, smartphone with 3D-printing dark-cavity as a portable detector and an artificial neural network (ANN) model as multi-signal processing tool. Notably, the optimized nickel–cobalt selenides (Ni 0.75 Co 0.25 Se with Ni to Co ratio of 3/1) exhibit excellent peoxidase-mimetic activities and are capable of catalyzing the oxidation of four chromogenic reagents in the presence of H 2 O 2. Using a smartphone with image capture function as a friendly signal readout tool, the Ni 0.75 Co 0.25 Se based four channel colorimetric sensing paper is used for multi-signal quantitative analysis of H 2 O 2 by determining the Grey, red (R), green (G) and blue (B) channel values of the captured pictures. An intelligent on-site detection method for H 2 O 2 has been constructed by combining an ANN model and a self-programmed easy-to-use smartphone APP with a dynamic range of 5 μM to 2 M. Noteworthy, machine learning-assisted smartphone sensing devices based on nanozyme and 3D printing technology provide new insights and universal strategies for visual ultrasensitive detection in a variety of fields, including environments monitoring, biomedical diagnosis and safety screening. [ABSTRACT FROM AUTHOR]

[Display omitted] • Large datasets of U and UP are constructed with 1526 and 743 fuel samples. • The effect of C, H, and O atomic ratios on HHV is investigated by ternary plots. • HHV of any type of waste and fuel is estimated by artificial neural networks. • Hyperparameter optimization is carried out to obtain best performing ANN models. • Ultimate analysis data is observed to be sufficient for HHV estimation of fuels. Higher heating value (HHV) is one of the most important parameters in determining the quality of the fuels. In this study, comparatively large datasets of ultimate and proximate analysis are constructed to be used in HHV estimation of several classes of fuels, including char & fossil fuels, agricultural wastes, manure (chicken, cow, horse, sheep, llama, and pig), sludge (like paper, paper-mil, sewage, and pulp), micro/macro-algae's, wastes (RDF and MSW), treated woods, untreated woods, and others (non-fossil pyrolysis oils) between the HHV range of 4.22–55.55 MJ/kg. The relationships of carbon, hydrogen, and oxygen atomic ratios for fuel classes are illustrated by using ternary plots, and the effects of elemental composition on HHV was analyzed with the extensive dataset. Then, the ultimate (U) and ultimate & proximate (UP) datasets were utilized separately to estimate the HHV by using artificial neural networks (ANN). Hyperparameter optimization was carried out and the best performing ANNs were determined for each dataset, which yielded R2 values of 0.9719 and 0.9715, respectively. The results indicated that while ANNs trained by both datasets perform remarkably well, utilization of U dataset is sufficient for HHV estimation. Finally, the best performing ANN models for both U and UP datasets are given in a directly utilizable format enabling the accurate estimation of HHV of any fuel for optimization of fuel processing and waste management operations. [ABSTRACT FROM AUTHOR]

• A model to explore the multiphysics characteristic of semiconductors is presented. • The model determines the thermal and mechanical properties of complex patterns. • Results show a strong correlation between thermal and mechanical properties. • Dielectric bands asymmetrically affect thermal and mechanical behavior. • Machine learning can predict one property from another. As semiconductor performance improves through advanced package designs, it becomes important to consider both thermal and mechanical properties. Better understanding their relationship enhances system design and optimization. This study has introduced a numerical method that takes into account both thermal and mechanical fluxes to construct thermal and mechanical property maps for practical application in semiconductor engineering. Furthermore, this paper investigated the relationship between the two properties using the constructed property maps in commercially available semiconductor packages. Owing to the complexity of packaging design patterns, a coupled isoparametric mapping and machine learning (ML) method was introduced to investigate their effects. The model then determines and investigates the anisotropic equivalent thermal and mechanical properties of the commercialized semiconductor packages with complex pattern designs, according to the package materials, volume fractions of each material, and design patterns. This approach pursues more sophistication and practicality compared to simplified composite structure property evaluation models. Additionally, all processes in the algorithm are automated based on ML methods, making them practically applicable in the semiconductor industry. The study shows that there is a strong correlation between the thermal and mechanical characteristics in the complex package patterns. This relationship was able to form a fairly clear category based on the shape of the dielectric band because the dielectric band had significantly different effects on the thermal and mechanical fluxes. The study discussed the physical implications of the similarities and differences between the two behaviors and validated the results of the equivalent properties through finite element (FE) analysis. Finally, the study cross-validates the relationship by showing that information from one flux behavior can be used to predict the other based on the ML method. Based on the results, this paper can provide a better understanding of thermal and mechanical fluxes in semiconductor package patterns for package design and optimization. [ABSTRACT FROM AUTHOR]

In order to accurately estimate the period of X-ray pulsars to improve navigation performance, this paper proposes a pulsar period estimation method based on photon energy using reverse Hilbert coding and double Convolutional Neural Networks (CNNs) discrimination. This method uses photon energy information to perform epoch folding. It converts one-dimensional contour information into two-dimensional image signals through reverse Hilbert curve and recognizes contour image features through CNN models to determine the optimal period. According to the simulation results, the period estimation accuracy of this method is 0.5350 ns, which is 65.71% higher than the χ 2 epoch folding method. The contour phase accuracy is 0.0004767, which is 41.93% higher than the χ 2 epoch folding method. At the same time, the observation time and noise interference that may affect the accuracy of period estimation are also quantitatively analyzed. In addition, in order to simulate real navigation scenarios, this paper also conducts dynamic period estimation experiments on PSR B0531+21 pulsar in a specific period of time. The method proposed in this paper has the advantages of high precision, fast calculation speed, strong anti-interference ability and accurate dynamic period estimation, which can significantly improve the navigation performance of X-ray pulsars. • The proposed period estimation method uses photon energy information for contour weighted folding. • The proposed method uses reverse Hilbert curve to convert one-dimensional contour information into two-dimensional image information. • Convolutional Neural Network models are used to optimize pulsar period estimation. [Display omitted] [ABSTRACT FROM AUTHOR]

Autonomous spacecraft relative navigation via monocular images became a hot topic in the past few years and, recently, received a further push thanks to the constantly growing field of artificial neural networks and the publication of several spaceborne image datasets. Despite the proliferation of spacecraft relative-state initialization algorithms developed, most architectures adopt computationally expensive solutions relying on convolutional neural networks (CNNs) that provide accurate output at the cost of a high computational burden that seems unfeasible for current spaceborne hardware. The paper addresses this issue by proposing a novel pose initialization algorithm based on lightweight CNNs. Inspired by previous state-of-the-art algorithms, the developed architecture leverages a fast and accurate target detection CNN followed by a line segment detection CNN capable of running with low inference time on mobile devices. The line segments and their junctions are grouped into complex geometrical groups, reducing the solution search space, and subsequently, they are adopted to extract the final pose estimate. As a main outcome, the analyses demonstrate that the lightweight architecture developed scores high accuracy in the pose estimation task, with a mean estimation error of less than 10 cm in translation and 2.5°in rotation. The baseline algorithm scores a mean SLAB error of 0.04552 with a standard deviation of 0.22972 in the test dataset. Detailed analyses demonstrate that the uncertainties on the overall pose score are driven mainly by errors in the relative attitude, which gives the highest contribution to the pose error metric adopted. The analyses on the error distributions point out that the uncertainties on the estimated relative position are higher in the camera boresight axis direction. Concerning the relative attitude, the algorithm proposed has higher uncertainties in estimating directions of the target x and y axes due to ambiguities related to the target geometry. Notably, the target detection CNN trained in this work outperforms the previous top scores in the benchmark dataset. The performances of the proposed algorithm have been investigated further by analyzing the effects on the accuracy due to the relative distance and the presence of background in the images. Lastly, the paper delves into the possibility of adopting a sub-portion of the 2D-to-3D match matrix made by the most complex perceptual groups identified that positively affects the overall run-time, pointing out the performances in terms of accuracy of the estimates and providing a comparison of both the baseline and the reduced match matrix versions against state-of-the-art algorithms concerning relative position and attitude errors and solution availability, highlighting the high accuracy and solution availability of the proposed architectures. • New relative pose initialization algorithm based on the detection of line segments. • Detailed literature review and description of available spaceborne image datasets. • Improvement of state of the art in spacecraft detection using lightweight CNN. • Assessment of accuracy of the proposed architecture and error sources analyses. • Proven feasibility of the approach via comparison with other architectures. [ABSTRACT FROM AUTHOR]

Over the past years, several efforts have been made to reduce greenhouse gas emissions coming from the transport sector. Due to the highly efficient CO2-free combustion and low manufacturing costs, Hydrogen Internal Combustion engines (H2ICEs) are considered one of the most promising solutions for the future of medium and heavy duty vehicles. However, the combustion of an air-hydrogen mixture presents challenges related to the production of nitrogen oxides (NOx) and high knock tendency, mainly due to the chemical characteristics of the fuel. Although these problems can be mitigated by the use of a lean mixture, which is also useful to increase the combustion efficiency, the presence of excess air reduces exhaust temperatures and, consequently, the enthalpy content in the exhaust would be limited, leading to a reduced boosting capability. Therefore, a proper control of mixture preparation and combustion phasing is mandatory to limit NOx emissions, avoid abnormal combustions, and maximize efficiency without performance limitations. This paper focuses on the design of a dedicated control strategy for H2ICEs. Starting from a previously validated 1-D engine model operated with hydrogen, a 0-D Artificial Neural Network (ANN) - based engine model has been designed and calibrated. By using the obtained fast running ANN-based model, an innovative torque-based engine controller has been developed and both engine and controller models have been tested covering different torque profiles. The results show good accuracy within a range of ±5% on producing the requested torque by controlling the centre of combustion. [Display omitted] • Hydrogen represents an optimal solution for the abatement of CO2 emissions related to the transport sector. • Hydrogen combustion is prone to abnormal combustions and NOx emissions. • Dedicated control strategies are needed to achieve an efficient, clean and reliable H2 combustion. • Model in the Loop approach aimed at testing the proposed control strategy. • Artificial neural network – based fast running engine model enabled testing the control system in relevant running conditions. [ABSTRACT FROM AUTHOR]

• Thermomechanical problem of FGMs sphere with material uncertainties is analyzed. • The interval random uncertainty model is recommended for material parameters. • A data-driven ANN fast calculation for FGMs sphere uncertainties analysis is established. • The volume fraction distribution is optimized for the safety design of the FGMs sphere. Mechanical analysis and optimal design for functionally graded materials (FGMs) structures are significant. The present paper analyzes the parameter uncertainties problem for the thermomechanical response of the FGMs spherical shells with volume fraction power distribution. Here, the interval random uncertainty model is recommended to describe the uncertainties of each component of material parameters in FGMs, and a data-driven artificial neural network (ANN) fast calculation for FGMs spherical shells thermomechanical problems with uncertainties analysis is established and trained. The thermomechanical coupling response analysis and volume fraction optimization analysis of the FGMs spherical shell with material uncertainties are realized for zirconia-titanium FGMs, with the maximum normalized Von Mises stress as the structural safety index and the ANN as the fast calculation method. In addition, the Von Mises stress of the FGMs spherical shell and a ZrO 2 -Ti alloy double-layer spherical shell under different loads is compared. The results show that material parameter uncertainties, especially those in Young's modulus, thermal expansion coefficient, and uniaxial yield limit significantly affect structural safety. The structural safety index λ calculated based on the volume fraction optimization design of FGMs spherical shell is significantly lower than that of the ZrO 2 -Ti alloy double-layer. The ANN method greatly improves the computational efficiency for uncertain problems and maintains high accuracy, compared with the statistical analysis after many calculations by randomly selecting material parameters. This study provides a path for the safety design of FGMs structures with uncertain parameters. [ABSTRACT FROM AUTHOR]

• AI improves infectious waste management. • Ensemble model exceeds 97.81% accuracy. • Reinforcement learning optimizes classification. • Geometric augmentation boosts model robustness. • Study addresses urgent urban waste challenges. This research paper focuses on effective infectious municipal waste management in urban settings, highlighting a dearth of dedicated research in this domain. Unlike general or specific waste types, infectious waste poses distinct health and environmental risks. Leveraging advanced artificial intelligence techniques, we prioritize infectious waste categorization and optimization, integrating metaheuristics into optimization methods to create a robust dual-ensemble framework. Our model, the "Enhanced Artificial Intelligence for Infectious Municipal Waste Classification System," combines ensemble image segmentation methods and diverse convolutional neural network models. Innovative geometric image augmentation enhances model robustness, diversifies training data, and improves accuracy across waste types. A pivotal aspect is the integration of a reinforcement learning-differential evolution algorithm as a decision fusion strategy, optimizing classification by harmonizing outputs from ensemble methods and convolutional neural network models. Computational results, using a newly collected dataset, demonstrate our model's accuracy exceeding 96.54% while using the existing solid waste dataset we achieve the accuracy of 97.81%, outperforming advanced approaches by margins ranging from 2.02% to 8.80%. This research significantly advances sustainable waste management, showcasing artificial intelligence's transformative potential in addressing intricate waste challenges. It establishes a foundational framework prioritizing efficiency, effectiveness, and sustainability for future waste management solutions. Acknowledging the importance of diverse datasets, customization for urban contexts, and practical integration into existing infrastructures, our work contributes to the broader discourse on the role of artificial intelligence in evolving waste management practices. [ABSTRACT FROM AUTHOR]

The accidental leakage of gaseous hydrogen from hydrogen refueling station facilities has the potential to result in a large fire and explosion catastrophe. The ability to forecast the spatiotemporal evolution of hydrogen plumes in real-time is crucial for monitoring the distribution of plume concentrations and mitigating the risk of fire and explosion. The utilization of deep learning has been extensively employed in a diverse range of spatiotemporal forecasting tasks. However, these approaches encounter limitations in accurately quantifying uncertainty when predicting spatiotemporal concentrations and plume boundaries. This research paper introduces a novel model called DPSTNN_H 2 Evolution, which is a deep probabilistic spatial-temporal neural network designed for forecasting the spatiotemporal evolution of hydrogen plumes. The benchmark dataset is constructed by the implementation of numerical simulations pertaining to the inadvertent leak of hydrogen within a hydrogen refueling station. The findings of the study indicate that incorporating quantified uncertainty information might enhance the precision of plume boundaries and the resilience of plume concentrations when predicting the spatiotemporal development of hydrogen. By employing Monte Carlo sampling with a sample size of m = 100 and a dropout rate of p = 0.1 , the model demonstrates the ability to provide real-time inference for 10 instances of plumes, while maintaining a high level of accuracy with R2 = 0.9829. In comparison to the current state-of-the-art model, the proposed model demonstrates superior accuracy and robustness in forecasting the spatiotemporal evolution of hydrogen plumes. In general, our proposed model has the potential to serve as a dependable option for the development of a digital twin for emergency management of hydrogen refueling stations. • Probabilistic spatial-temporal neural network model for hydrogen plume evolutions is proposed. • Normalized uncertainty contours and uncertainty intervals to improve accuracy and robustness. • Numerical experiment of hydrogen leakage and dispersion in refueling station are conducted. • Optimal hyper-parameters of the proposed model are determined • Comparison between the proposed model with point-estimation based model is conducted [ABSTRACT FROM AUTHOR]

The efficient approximation of parametric PDEs is of tremendous importance in science and engineering. In this paper, we show how one can train Galerkin discretizations to efficiently learn quantities of interest of solutions to a parametric PDE. The central component in our approach is an efficient neural-network-weighted Minimal-Residual formulation, which, after training, provides Galerkin-based approximations in standard discrete spaces that have accurate quantities of interest, regardless of the coarseness of the discrete space. [ABSTRACT FROM AUTHOR]

Accurate three-dimensional (3D) measurement for large field of view (FOV) is currently a significant research field. Accordingly, system calibration is crucial to ensure accuracy. However typical calibration methods often involve the use of large calibration objects, which is not only expensive but also difficult to achieve sufficient accuracy. A novel method based on a dual-brand deep neural network (DNN) is proposed for the system calibration. Taking advantage of the concept of "divide and conquer", the FOV is divided into sub-regions with a part of overlapping regions by a small calibration object, which forms a large calibration object covering the whole FOV. Then the sub-regions are fused into a global framework and further optimized by the proposed dual-brand DNN. The proposed method reduces the need for calibration objects while improving the calibration accuracy and generalization ability in large FOV. A series of experiments have been designed to prove the effectiveness and robustness of the proposed method. • A high-accuracy calibration method of a 3D measurement system with large field-of-view is proposed. The highlights of the paper are: • A high-accuracy calibration method for large field-of-view is proposed. • The large field-of-view is divided into multiple sub-regions. • Sub-regions are unified to a uniform coordinate system by self-constraint. • A dual-branch DNN is optimized using the multi-objective loss function. [ABSTRACT FROM AUTHOR]

Precision Agriculture (PA) has revolutionized crop management by leveraging information technology, satellite positioning data, and remote sensing. One crucial component in PA applications is the Normalized Difference Vegetation Index (NDVI), which offers valuable insights into crop vigor and health. However, discontinuity of optical satellite acquisitions related to cloud cover and the huge load of the required processing time pose challenges to real-time applications. NDVI prediction emerges as an innovative solution to address these limitations. It allows for proactive decision-making by providing accurate estimates, enabling farmers and land managers to plan essential agronomic activities such as irrigation, fertilization, and pest control, based on anticipated future conditions. This study introduces an Artificial Neural Network (ANN) model incorporating NDVI, Normalized Difference Water Index (NDWI), temperatures, and precipitation as predictive variables. The model employs a novel time series slicing algorithm, Boosting Adaptive Time Series Slicer (BATS), to enhance the input training dataset's variability, presenting the model with a broader range of examples. A 2-Bidirectional Long Short-Term Memory (LSTM) forecasting model was developed to predict future NDVI values over short and medium-term horizons. The study area used to train, test and validate the ANN corresponds to a diverse landscape of cultivated corn fields located in Piemonte (NW-Italy). Results showed that NDVI future estimates were accurate; considering three time horizons for predictions (5, 10, and 15 days) RMSE values resulted to be 0.028, 0.038 and 0.050, respectively. Additionally, ablation tests proved that the most important variable for enhancing the model's accuracy is the NDWI, and the most useful timesteps are the four most recent ones. To preliminary investigate the capability of the ANN to operate over a wider and different area it was applied over the entire Europe, using the LUCAS dataset as reference map to locate corn fields. Results show RMSE of 0.062, 0.083 and 0.105 for the 5, 10 and 15 days forecasting horizons, respectively. The methodology proposed in this paper can be a possible alternative to more ordinary approaches for NDVI forecasting that nowadays appears to be a fundamental step for a proactive precision agriculture where crop management can be significantly improved. Future developments should explore the use of sequence-to-sequence ANNs to predict the development of multiple spectral indices over multiple crop types simultaneously. [ABSTRACT FROM AUTHOR]

This paper introduces an innovative approach for generating re-entry trajectories for a reusable winged spacecraft. This approach utilizes Fourier series parametrized control profiles. The Fourier coefficients are derived through a combination of the Improved Search Space Reduction (ISSR) technique and Sequential Quadratic Programming (SQP) optimization methods, which effectively limit the maximum heat rate experienced by the spacecraft. These re-entry trajectories and control profiles are then used to train artificial neural networks, enabling the controller to provide optimal control inputs based on the spacecraft's current altitude and velocity. To validate this methodology, Hardware-in-loop (HIL) simulations are conducted, integrating the designed neural network-based controller with a Texas Instruments TI Delfino TMSF28335 controller and a real-time simulator, the OPAL-RT OP4510. The results of the HIL simulation demonstrate that the generated re-entry trajectory accurately adheres to heat rate and terminal constraints. Additionally, the Fourier series parametrization of control profiles is applied to a high lift-to-drag ratio CAV-H vehicle, showcasing the method's versatility. Furthermore, resilience of proposed method to uncertainties in aerodynamic coefficients and atmospheric density is also demonstrated. The results show that the proposed method is generic and exhibits robustness to uncertainties. [ABSTRACT FROM AUTHOR]

Controlled de-orbiting is crucial for a low earth orbiting (LEO) satellite or capsule intending to land in a desired location and to prevent damage to people and property on the ground caused by debris. Drag modulation is one possible mechanism to control de-orbiting, exploiting atmospheric drag variation to reduce the necessary orbital energy from the initial conditions to the re-entry interface. In this context, this paper proposes a novel targeted de-orbiting Artificial Neural Network (ANN) and drag-based guidance algorithm for a LEO artificial satellite. It relies on the combination of empirical and analytical relations with Deep Neural Networks (DNNs) to estimate the main parameters of the optimal control law in real time. The training set is composed of several optimal control solutions generated with a previously developed optimal control algorithm, exploiting the formulation in equinoctial modified orbital parameters to manage the large time scale of the problem and the computational cost. An innovative procedure for the training set generation led to the achievement of general results with a limited number of samples. The successful outcome of the guidance algorithm on over 1000 cases demonstrates its robustness and generalization of results. To conclude, a Linear Quadratic Regulator (LQR) feedback control is applied to one case to deal with a more realistic and uncertain density model. • Analytical optimal guidance for a satellite de-orbiting from Low Earth Orbit. • A novel approach based on Deep Neural Networks. • Prediction of the key parameters of the optimal control law in real time. • A Monte Carlo analysis showed the algorithm's robustness and generalization. • Successful feedback control thanks to a Linear Quadratic Regulator (LQR). [ABSTRACT FROM AUTHOR]

While deep neural networks have shown impressive results in automatic speaker recognition and related tasks, it is dissatisfactory how little is understood about what exactly is responsible for these results. Part of the success has been attributed in prior work to their capability to model supra-segmental temporal information (SST), i.e., learn rhythmic-prosodic characteristics of speech in addition to spectral features. In this paper, we (i) present and apply a novel test to quantify to what extent the performance of state-of-the-art neural networks for speaker recognition can be explained by modeling SST; and (ii) present several means to force respective nets to focus more on SST and evaluate their merits. We find that a variety of CNN- and RNN-based neural network architectures for speaker recognition do not model SST to any sufficient degree, even when forced. The results provide a highly relevant basis for impactful future research into better exploitation of the full speech signal and give insights into the inner workings of such networks, enhancing explainability of deep learning for speech technologies. • Literature explains speaker recognition in neural nets by modeling of voice dynmaics. • Diagnostic: We quantify how well deep learning models actually capture dynamics. • Observation: State-of-the-art deep nets do not model speaker prosody but ignore it. • Interpretation as "cheating": Achieving high without putting in due effort. • Outlook: Increasing task difficulty biases models towards prosody, but not enough. [ABSTRACT FROM AUTHOR]

The extensive spread of fake news on social networks is carried out by a diverse range of users, encompassing private individuals, newspapers, and organizations. With widely accessible image and video editing tools, malicious users can easily create manipulated media. They can then distribute this content through multiple fake profiles, aiming to maximize its social impact. To tackle this problem effectively, it is crucial to possess the ability to analyze shared media to identify the originators of fake news. To this end, multimedia forensics research has advanced tools that examine traces in media, revealing valuable insights into its origins. While combining these tools has proven to be highly efficient in creating profiles of image and video creators, it is important to note that most of these tools are not specifically designed to function effectively in the complex environment of content exchange on social networks. In this paper, we introduce the problem of establishing associations between images and their source profiles as a means to tackle the spread of disinformation on social platforms. To this end, we assembled SocialNews , an extensive image dataset comprising more than 12,000 images sourced from 21 user profiles across Facebook, Instagram, and Twitter, and we propose three increasingly realistic and challenging experimental scenarios. We present two simple yet effective techniques as benchmarks, one based on statistical analysis of Discrete Cosine Transform (DCT) coefficients and one employing a neural network model based on ResNet, and we compare their performance against the state of the art. Experimental results show that the proposed approaches exhibit superior performance in accurately classifying the originating user profiles. • We introduce SocialNews, a novel dataset for disinformation detection online. • Images were sourced primarily from social profiles of news agencies around the world. • The goal is to automatically identify the profile of the user that shared an image. • We introduce two benchmarks methods: a DCT-based one and a ResNet-based one. • Experiments show that the proposed benchmark methods outperform the state of the art. [ABSTRACT FROM AUTHOR]

With the rapidly evolving geo-political landscape and unceasing advancements in technology, sustainable energy security is a very important topic. Research indicates that electrochemical energy systems are quite promising to solve many of energy conversion, storage, and conservation challenges while offering high efficiencies and low pollution. The paper provides an overview of electrochemical energy devices and the various optimization techniques used to evaluate them. The optimization techniques include linear regression, factorial design, the Taguchi method, artificial neural networks, filters, and a combination of such methods to improve these systems. To support the growing interest in research, the bulk of this study focuses on a review of the most promising and highly researched electrochemical energy devices, such as fuel cells, batteries, and supercapacitors. The paper also provides modest commentary on hydrogen production technologies, electrochemical reactors, and membrane separation technologies, amongst other technologies. Building on a previous paper by the authors of this paper on artificial intelligence in hybrid renewable energy systems with fuel cells, this work provides a comparative review of optimization techniques for supercapacitors by highlighting key findings based on model accuracy. A summary of the advantages and disadvantages of the different major optimization techniques is presented. The paper concludes that a combination of optimization techniques is used to overcome the drawbacks of individual techniques, with adaptive filters being the most widely studied. This paper presents studies on the Design of Experiments (DoE) with the goal of building a better understanding of the relationships that exist between different operating variables in various electrochemical devices. • The electrochemical systems can be optimized for better performance with high accuracy. • The optimization techniques used are either model-based or data-driven. • Linear regression and artificial neural networks are the most common techniques studied. • Hybrid models could be applied to enhance systems' accuracy and minimize errors. [ABSTRACT FROM AUTHOR]

Large deep learning models are impressive, but they struggle when real-time data is not available. Few-shot class-incremental learning (FSCIL) poses a significant challenge for deep neural networks to learn new tasks from just a few labeled samples without forgetting the previously learned ones. This setup can easily leads to catastrophic forgetting and overfitting problems, severely affecting model performance. Studying FSCIL helps overcome deep learning model limitations on data volume and acquisition time, while improving practicality and adaptability of machine learning models. This paper provides a comprehensive survey on FSCIL. Unlike previous surveys, we aim to synthesize few-shot learning and incremental learning, focusing on introducing FSCIL from two perspectives, while reviewing over 30 theoretical research studies and more than 20 applied research studies. From the theoretical perspective, we provide a novel categorization approach that divides the field into five subcategories, including traditional machine learning methods, meta learning-based methods, feature and feature space-based methods, replay-based methods, and dynamic network structure-based methods. We also evaluate the performance of recent theoretical research on benchmark datasets of FSCIL. From the application perspective, FSCIL has achieved impressive achievements in various fields of computer vision such as image classification, object detection, and image segmentation, as well as in natural language processing and graph. We summarize the important applications. Finally, we point out potential future research directions, including applications, problem setups, and theory development. Overall, this paper offers a comprehensive analysis of the latest advances in FSCIL from a methodological, performance, and application perspective. • In-depth survey on FSCIL methods, applications, performance. • Categorizing FSCIL into five subcategories for clear analysis. • Evaluating FSCIL research on benchmarks for strengths, weaknesses. • FSCIL applications in computer vision, NLP, and graph. [ABSTRACT FROM AUTHOR]

Deep neural networks have achieved outstanding performance in computer vision tasks. Convolutional Neural Networks (CNNs) typically operate in the spatial domain with raw images, but in practice, images are usually stored and transmitted in their compressed representation where JPEG is one of the most widely used encoder. Also, these networks are computationally intensive and slow. This paper proposes performing the learning and inference processes in the compressed domain in order to reduce the computational complexity and improve the speed of popular CNNs. For this purpose, a novel graph-based frequency channel selection method is proposed to identify and select the most important frequency channels. The computational complexity is reduced by retaining the important frequency components and discarding the insignificant ones as well as eliminating the unnecessary layers of the network. Experimental results show that the modified ResNet-50 operating in the compressed domain is up to 70% faster than the spatial-based traditional ResNet-50 while resulting in similar classification accuracy. Moreover, this paper proposes a preprocessing step with partial encoding to improve the resilience to distortions caused by low-quality encoded images. Finally, we show that training a network with highly compressed data can achieve a good classification accuracy with up to 93% reduction in the storage requirements of the training data. [ABSTRACT FROM AUTHOR]

Schedule maintenance activities for hydrogen fuel cell vehicles are aimed to keep them in better condition in long-term operation. In this paper, we develop a reinforcement learning based schedule maintenance strategy, which is used to comprehensively consider the balance between safety and maintenance cost, so as to find the optimal maintenance strategy. A multi-level framework is established with remaining useful life of key components, fault tree analysis, and logistics cost model to generate an exploration environment that can express the operational stability, the failure rate of components, and the cost of repair and storage. The trained agent combines a deep neural network to explore the optimal strategy under the dynamic reliability of key components. Finite steps are the constraints. Safety rates, maintenance cost, and episode of operation are incorporated into a multi-objective reward function. The hydrogen supply circuit of fuel cell vehicle is simulated via Python. The trained agent is compared with traditional time-based schedule maintenance strategy and corrective maintenance strategy. The results show that the reinforcement learning based schedule maintenance agent has optimized the total reward, cost control and accident rate by 77%, 59% and 5%, respectively, compared with the traditional time-based schedule maintenance strategy. In the safe operation management of fuel cell vehicles, efficient and stable decision-making ability has been achieved. • An adaptive maintenance strategy of deep reinforcement learning is proposed. • An exploration environment of FCV is established. • The deep Q network is proposed to solve the maintenance problem. • The efficient and stable decision-making ability is much better than time-based scheduled maintenance strategy. [ABSTRACT FROM AUTHOR]

In recent studies, artificial intelligence models have been developed for the prediction of nitrogen oxide emissions from thermal power plants. This research utilizes an artificial intelligence prediction model with more coal input features than boiler features, including volatility, ash content, sulfur content, fixed carbon, total moisture, calorific value, grinding rate, fuel ratio, coal feeding rate, boiler efficiency, total air volume, and excess air volume. The paper delves into the importance analysis of input features for artificial intelligence models. Moreover, feature importance analysis is not only a prerequisite for predicting nitrogen oxide emissions but also a study providing insights into model performance. An artificial neural networks (ANN) regression model is employed to predict nitrogen oxide emissions, and the results demonstrate that the number of feature importance significantly impacts model performance. The best model performance is achieved with eight specific input features. Finally, after the training and validation processes, the ANN model yields the optimal coefficient of determination (R2) value. • Development of an artificial intelligence prediction model for nitrogen oxide emissions from thermal power plants. • A comprehensive set of input features is utilized for emissions prediction. • Importance analysis of input features significantly impacts model performance. • Optimal model performance was achieved with eight specific input features. • The robust coefficient of determination (R2) value demonstrates the accuracy of the ANN model. [ABSTRACT FROM AUTHOR]

Despite significant progress has been made towards crop yield prediction with remote sensing, there exist knowledge gaps on (1) the impacts of temporal resolution of imaging frequencies on yield prediction, (2) transferability of the models among different genotypes and test sites, and (3) translation of these research developments to crop breeding that benefit farmers. Existing research predominantly provides an on-site perspective, frequently missing the complexities of real-world applications. The objectives of this paper are to investigate the transferability and generalization capabilities of yield prediction models for crop breeding across test sites located in North and South Americas. Toward that goal, we tested different machine learning techniques including Random Forest Regressor (RF), Gradient Boosting Regression (GB), and Deep Neural Networks (DNN) for soybean yield prediction with experiments conducted in different climate and growth conditions. A novel transfer learning approach was proposed for genotype selection and categorizing soybean yield for screening high-yield varieties. Furthermore, we studied the effect of temporal resolution on yield prediction, focusing on the critical development stages and optimal aerial survey frequencies for precise yield prediction using large 31,404 sample data. Results demonstrated that the combined dataset of Argentina and United States representing different climate regimes provided the highest performance with an R2 of 0.76 using RF and GB algorithms. The classification approach was proven to be most useful for crop breeding as demonstrated by accurately identifying the high-yielding genotypes. Increasing temporal sampling of key phenological stages significantly improved yield prediction. Although transfer learning yielded promising outcomes across trials within Argentina the efficacy of transferring models from Argentina to the United States was limited, attributed to significant seasonal and climate variations. This study pioneered the use of transfer learning for model adaptability in real-world breeding scenarios, training and transferring models within the South and North Americas, providing actionable insights and strategies for the breeding community, aiming to facilitate improved decision-making for agricultural productivity. [ABSTRACT FROM AUTHOR]

To improve convergence speed of deep neural network trained by gradient descent methods (GDMs), this paper proposed a novel fractional order gradient descent optimizer (FOAdam) based on Caputo operator and Adam algorithm, and analyzed the impact of fractional order on convergence performance using optimization theory and simulation. Furthermore, to address the trade-off between convergence speed and precision under fixed-order conditions, a fractional order scheduler (FOS) was designed based on the Connections Cloud Model (CCM). Numerical experiments conducted on MNIST and CIFAR-10 datasets showed that FOS-FOAdam outperformed other mainstream GDMs in terms of convergence speed and precision. Finally, FOS-FOAdam was applied in recognizing and classifying image datasets of cuttings and cores at the logging site, demonstrating good prospects for practical engineering applications. [ABSTRACT FROM AUTHOR]

Despite the wide variety of methods developed for synthetic image attribution, most of them can only attribute images generated by models or architectures included in the training set and do not work with unknown architectures, hindering their applicability in real-world scenarios. In this paper, we propose a verification framework that relies on a Siamese Network to address the problem of open-set attribution of synthetic images to the architecture that generated them. We consider two different settings. In the first setting, the system determines whether two images have been produced by the same generative architecture or not. In the second setting, the system verifies a claim about the architecture used to generate a synthetic image, utilizing one or multiple reference images generated by the claimed architecture. The main strength of the proposed system is its ability to operate in both closed and open-set scenarios so that the input images, either the query and reference images, can belong to the architectures considered during training or not. Experimental evaluations encompassing various generative architectures such as GANs, diffusion models, and transformers, focusing on synthetic face image generation, confirm the excellent performance of our method in both closed and open-set settings, as well as its strong generalization capabilities. • New verification framework for open-set architecture attribution of synthetic images. • Tested with several types of generative architectures in closed and open set scenarios. • Generalization tests prove that the system can verify unknown models of the architecture. • Outperforms state-of-the-art methods for open-set architecture attribution with rejection. [ABSTRACT FROM AUTHOR]

Artificial Intelligence has found wide application, but also poses risks due to unintentional or malicious tampering during deployment. Regular checks are therefore necessary to detect and prevent such risks. Fragile watermarking is a technique used to identify tampering in AI models. However, previous methods have faced challenges including risks of omission, additional information transmission, and inability to locate tampering precisely. In this paper, we propose a method for detecting tampered parameters and bits, which can be used to detect, locate, and restore parameters that have been tampered with. We also propose an adaptive embedding method that maximizes information capacity while maintaining model accuracy. Our approach was tested on multiple neural networks subjected to attacks that modified weight parameters, and our results demonstrate that our method achieved great recovery performance when the modification rate was below 20%. Furthermore, for models where watermarking significantly affected accuracy, we utilized an adaptive bit technique to recover more than 15% of the accuracy loss of the model. • Fragile watermarking for rigorous neural network integrity detection. • Watermarking ensures 100% tampering detection, precise location, and recovery. • Watermarking fragility by combining Mutual- and Self-neural net parameters. • Incorporates watermarking with neural net feature, maintaining watermarked models' performance via gradient descent. • Bit-level training controls step size with carefully set hyperparameters. [ABSTRACT FROM AUTHOR]

Deep learning methods have gained considerable interest in the numerical solution of various partial differential equations (PDEs). One particular focus is physics-informed neural networks (PINN), which integrate physical principles into neural networks. This transforms the process of solving PDEs into optimization problems for neural networks. To address a collection of advection-diffusion equations (ADE) in a range of difficult circumstances, this paper proposes a novel network structure. This architecture integrates the solver, a multi-scale deep neural networks (MscaleDNN) utilized in the PINN method, with a hard constraint technique known as HCPINN. This method introduces a revised formulation of the desired solution for ADE by utilizing a loss function that incorporates the residuals of the governing equation and penalizes any deviations from the specified boundary and initial constraints. By surpassing the boundary constraints automatically, this method improves the accuracy and efficiency of the PINN technique. To address the "spectral bias" phenomenon in neural networks, a subnetwork structure of MscaleDNN and a Fourier-induced activation function are incorporated into the HCPINN, resulting in a hybrid approach called SFHCPINN. The effectiveness of SFHCPINN is demonstrated through various numerical experiments involving ADE in different dimensions. The numerical results indicate that SFHCPINN outperforms both standard PINN and its subnetwork version with Fourier feature embedding. It achieves remarkable accuracy and efficiency while effectively handling complex boundary conditions and high-frequency scenarios in ADE. [ABSTRACT FROM AUTHOR]

• A graph neural network is proposed for learning multi-satellite scheduling policy. • It analyzes the differential impact of various constraints in scheduling. • It models the multi-satellite scheduling problem as a heterogeneous graph. • It designs a variant transformer to learn various relations within graph. • It designs a two-stage model to learn a multi-satellite scheduling policy. In this paper, we investigate the multi-satellite scheduling (MSS) problem, a combinatorial optimization problem (COP) that aims to enhance satellite utilization. Numerous scholars have conducted in-depth studies on this matter. Handcrafted policies are commonly employed in various algorithms. Despite the use of graphical representations, designing policies manually becomes increasingly difficult, particularly as the number of satellites and tasks grows. Consequently, we propose a novel approach for automatically summarizing graph structures and learning policies for MSS problem. The proposed approach is developed based on graph neural network, Transformer, and sequence to sequence framework. First, MSS problem is modeled as a heterogeneous graph following various constraints. Next, the encoder, which is based on GNN and Transformer, is designed to summarize crucial information from the aforementioned graph. Finally, a two-stage decoder is proposed taking into account dynamic information in stepwise solution generation. Since obtaining optimal solutions in practical applications is challenging, we train the model using reinforcement learning. The results of the experiment demonstrate that our proposed method performs effectively in various scenarios. The quality of the solutions generated through this method transcends that of conventional construction methods. Additionally, the method generates solutions quickly, which are comparable in quality to those produced by meta-heuristic algorithms. [ABSTRACT FROM AUTHOR]

This paper aims to study the feasibility of municipal sewage sludge utilization as an energy source in a polygeneration system. This system offers distinctive benefits such as contribution to the principled removal of sewage sludge, simultaneous utilization of raw and digested sludge in different parts of the system, and production of renewable hydrogen from bio-waste. 4E (energy, exergy, exergoeconomic, and environmental) analyses, are performed to understand the system performance comprehensively. Then, parametric studies are examined the impact of changing the values of main parameters on the system operation. Afterward, a multi-objective optimization based on a genetic algorithm is carried out to achieve optimal values, considering a trade-off between the exergy efficiency and the total cost rate. Meanwhile, this work harnesses the potential of artificial neural networks to expedite complex and time-consuming optimization processes. According to the results, the gasifier exhibits the highest rate of exergy destruction, and the primary cost of consumption is attributed to its heat supply. The multi-objective optimization findings show that the optimum point has an exergy efficiency of 38.26 % and a total cost rate of 58.17 M$/year. The hydrogen production rate, energy efficiency, and net power generation rate for the optimal case are determined as 1692 kg/h, 35.24 %, and 4269 kW, respectively. Also, the unit cost of hydrogen in the optimal case is obtained 1.49 $/kg which offers a cost-effective solution for hydrogen production. [Display omitted] • 4E analysis and optimization performed on a bio-waste driven polygeneration system. • Plant optimized using artificial neural network and multi-objective genetic algorithm. • The feasibility of integrating a membrane for hydrogen separation investigated. • The optimum exergy efficiency and total cost rate obtained 38.26 % and 58.17 M$/year. • Hydrogen and electricity cost of 1.49 $/kg and 0.0145 $/kWh achieved for optimal case. [ABSTRACT FROM AUTHOR]

The establishment of a prediction model for the hydrogen absorption state of a solid-state hydrogen storage device is crucial for its practical application. In this paper, a solid-state hydrogen storage device filled with AB 2 hydrogen storage alloy is investigated. The experimental data are obtained by controlling the hydrogen absorption temperature and hydrogen absorption rate respectively. The Broyden-Fletcher-Goldfarb-Shanno algorithm (BFGS) is used to fit the solid-state hydrogen storage device experimental data based on the Richards model, and Linear Regression, Gradient Descent and Artificial Neural Network algorithms are used to predict the parameters of the Richards model. It is confirmed that the Linear Regression model has the best prediction effect after verified by the test set, with coefficients of determination R2 ≥ 0.96. This study provides an effective way to predict the hydrogen absorption state of solid-state hydrogen storage devices quickly. • The effects of temperature and rate on hydrogen absorption process of solid-state hydrogen storage device are studied. • Richards model is used to fit the hydrogen absorption curve shaped as an S-type. • The prediction model of hydrogen absorption process of the device is established. • Three machine learning algorithms are applied to establish the prediction model. [ABSTRACT FROM AUTHOR]

• A Digital Cultural Heritage dataset of synthetic vaults exported as point cloud, based on shape grammar discussion. • A vaults synthetic dataset creation method for automatically generating training data when real 3D objects are insufficient. • A Deep Learning system able to segment and distinguish types of architectural vaults according to standard classifications. Historical heritage is demanding robust pipelines for preserving, enhancing, and disseminating its prominent value. Semantic segmentation of 3D Point Clouds has gained increasing attention over the years, since it might assist in automati-cally recognizing historical architectural elements, thus facilitating large dataset management. Nonetheless, semantic segmentation is particularly challenging in Cultural Heritage (CH) domain, due to the shapes complexity and the limited repeatability of elements across different architectures, which strengthens the difficulty to define common patterns within the same class of elements. Besides, as Deep Neural Networks demand an appreciably amount of labelled data to be trained, the lack of available annotated heritage point clouds prevent the research in this direction. To tackle these issues, in this paper it is proposed a Deep Learning system able to recognize historical building elements by lever-aging synthetic point cloud. The generation of the 3D models, vaults, is based on a procedural modeling approach that follows the ideal shapes, according to the rules of descriptive geometry for the main types of vaults. The approach has been applied to a newly synthetic dataset which is publicly available. This dataset comprises 6 labelled points clouds, derived from a comprehensive on-tological taxonomy in order to describe an univocal and robust architectural hierarchy: barrel vaults, groined vaults, mirror vaults, barrel vaults with clois-ter heads and lunettes, barrel vaults with lunettes, sail vaults. The experiments yield high accuracy, demonstrating the effectiveness and suitability of the pro-posed approach. [ABSTRACT FROM AUTHOR]

Due to the ubiquity of graph-structured data, Graph Neural Network (GNN) have been widely used in different tasks and domains and good results have been achieved in tasks such as node classification and link prediction. However, there are still many challenges in representation learning of heterogeneous networks. Existing graph neural network models are partly based on homogeneous graphs, which do not take into account the rich semantic information of nodes and edges due to their different types; And partly based on heterogeneous graphs, which require predefined meta-structures (include meta-paths and meta-graphs) and do not take into account the different effects of different meta-structures on node representation. In this paper, we propose the MS-GAN model, which consists of four parts: graph structure learner, graph structure expander, graph structure filter and graph structure parser. The graph structure learner automatically generates a graph structure consisting of useful meta-paths by selecting and combining the sub-adjacent matrices in the original graph using a 1 × 1 convolution. The graph structure expander further generates a graph structure containing meta-graphs by Hadamard product based on the previous step. The graph structure filterer filters out graph structures that are more effective for downstream classification tasks based on diversity. The graph structure parser assigns different weights to graph structures consisting of different meta-structures by a semantic hierarchical attention. Finally, through experiments on four datasets and meta-structure visualization analysis, it is shown that MS-GAN can automatically generate useful meta-structures and assign different weights to different meta-structures. • Semi-supervised learning based graph neural network. • Automatically generate meta-structures. • Assign weights to meta-structures. [ABSTRACT FROM AUTHOR]

Recent years have witnessed increasing interest in adversarial attacks on images, while adversarial video attacks have seldom been explored. In this paper, we propose a sparse adversarial attack strategy on videos (DeepSAVA). Our model aims to add a small human-imperceptible perturbation to the key frame of the input video to fool the classifiers. To carry out an effective attack that mirrors real-world scenarios, our algorithm integrates spatial transformation perturbations into the frame. Instead of using the l p norm to gauge the disparity between the perturbed frame and the original frame, we employ the structural similarity index (SSIM), which has been established as a more suitable metric for quantifying image alterations resulting from spatial perturbations. We employ a unified optimisation framework to combine spatial transformation with additive perturbation, thereby attaining a more potent attack. We design an effective and novel optimisation scheme that alternatively utilises Bayesian Optimisation (BO) to identify the most critical frame in a video and stochastic gradient descent (SGD) based optimisation to produce both additive and spatial-transformed perturbations. Doing so enables DeepSAVA to perform a very sparse attack on videos for maintaining human imperceptibility while still achieving state-of-the-art performance in terms of both attack success rate and adversarial transferability. Furthermore, built upon the strong perturbations produced by DeepSAVA, we design a novel adversarial training framework to improve the robustness of video classification models. Our intensive experiments on various types of deep neural networks and video datasets confirm the superiority of DeepSAVA in terms of attacking performance and efficiency. When compared to the baseline techniques, DeepSAVA exhibits the highest level of performance in generating adversarial videos for three distinct video classifiers. Remarkably, it achieves an impressive fooling rate ranging from 99.5% to 100% for the I3D model, with the perturbation of just a single frame. Additionally, DeepSAVA demonstrates favourable transferability across various time series models. The proposed adversarial training strategy is also empirically demonstrated with better performance on training robust video classifiers compared with the state-of-the-art adversarial training with projected gradient descent (PGD) adversary. • Sparse attacks on video models: perturb fewer frames to gain high fooling rate. • Combining additive and spatial perturbations to enhance attacking performance. • Using SSIM instead of l p -norm to maintain the human perception. • Applying Bayesian Optimisation to identify the most critical frame to perturb. • A new adversarial training method based on combination of diverse perturbations. [ABSTRACT FROM AUTHOR]

We study how the topology of feature embedding space changes as it passes through the layers of a well-trained deep neural network (DNN) through Betti numbers. Motivated by existing studies using simplicial complexes on shallow fully connected networks (FCN), we present an extended analysis using Cubical homology instead, with a variety of popular deep architectures and real image datasets. We demonstrate that as depth increases, a topologically complicated dataset is transformed into a simple one, resulting in Betti numbers attaining their lowest possible value. The rate of decay in topological complexity (as a metric) helps quantify the impact of architectural choices on the generalization ability. Interestingly from a representation learning perspective, we highlight several invariances such as topological invariance of (1) an architecture on similar datasets; (2) embedding space of a dataset for architectures of variable depth; (3) embedding space to input resolution/size, and (4) data sub-sampling. In order to further demonstrate the link between expressivity & the generalization capability of a network, we consider the task of ranking pre-trained models for downstream classification task (transfer learning). Compared to existing approaches, the proposed metric has a better correlation to the actually achievable accuracy via fine-tuning the pre-trained model. • This paper categorizes the change in topological complexity through Betti-Numbers. • Attempts to characterize the learning ability of the DNNs through topological transformation of feature space. • Attempts to use the topological complexity of feature space for the task of ranking pre-trained models. [ABSTRACT FROM AUTHOR]

Recently, leveraging deep neural networks for automated colorectal polyp segmentation has emerged as a hot topic due to the favored advantages in evading the limitations of visual inspection, e.g., overwork and subjectivity. However, most existing methods do not pay enough attention to the uncertain areas of colonoscopy images and often provide unsatisfactory segmentation performance. In this paper, we propose a novel boundary uncertainty aware network (BUNet) for precise and robust colorectal polyp segmentation. Specifically, considering that polyps vary greatly in size and shape, we first adopt a pyramid vision transformer encoder to learn multi-scale feature representations. Then, a simple yet effective boundary exploration module (BEM) is proposed to explore boundary cues from the low-level features. To make the network focus on the ambiguous area where the prediction score is biased to neither the foreground nor the background, we further introduce a boundary uncertainty aware module (BUM) that explores error-prone regions from the high-level features with the assistance of boundary cues provided by the BEM. Through the top-down hybrid deep supervision, our BUNet implements coarse-to-fine polyp segmentation and finally localizes polyp regions precisely. Extensive experiments on five public datasets show that BUNet is superior to thirteen competing methods in terms of both effectiveness and generalization ability. • A boundary uncertainty aware network is proposed for accurate polyp segmentation. • A boundary exploration module is proposed to explore boundary cues of polyps. • A boundary uncertainty aware module is proposed to seek error-prone regions. • The proposed network achieves high performance on six public datasets. [ABSTRACT FROM AUTHOR]

Neural network ensembling is a common and robust way to increase model efficiency. In this paper, we propose a new neural network ensemble algorithm based on Audibert's empirical star algorithm. We provide optimal theoretical minimax bound on the excess squared risk. Additionally, we empirically study this algorithm on regression and classification tasks and compare it to most popular ensembling methods. [ABSTRACT FROM AUTHOR]

Deep neural networks are highly vulnerable to adversarial samples. Most existing adversarial defense methods do not consider the distribution of adversarial samples. We argue that very few adversarial samples in the natural sample set prevent the deep neural networks from learning a complete and effective representation of the adversarial samples. This causes the spatial structures between the natural and the adversarial samples to be vastly different from that of the input space, thus making the models vulnerable to adversarial attacks. Based on this viewpoint, this paper proposes an effective deep-learning adversarial defense method, which incorporates information about the spatial structures of the natural and the adversarial samples in the embedding space during the training process. This proposed approach improves the deep learning model's generalization to new adversarial samples and achieves the purpose of defending against adversarial attacks. Four deep neural networks with different scales are used and experimentally verified on four typical publicly available image data. The experimental results show that our method effectively improves the defense ability of deep learning models against adversarial attacks. • Development of an effective adversarial training method using spatial structure constraints in embedding space. • Spatial structure information of the natural and adversarial samples can help improve the adversarial robustness of DNNs. • The spatial structure constrain can be extended to adversarial training of semi-supervised and unsupervised learning. [ABSTRACT FROM AUTHOR]

Hydrogen purification from steam methane reforming (SMR) by pressure swing adsorption (PSA) technology is a common method to obtain high-purity hydrogen. The breakthrough time can well reflect the adsorption dynamics and help PSA cycle design. In order to avoid time-consuming and labor-intensive breakthrough curve experiments, it is very necessary to develop a fast and accurate surrogate model. In this study, a genetic algorithm (GA) and artificial neural network (ANN) are combined to predict and optimize breakthrough times of adsorbates in activated carbon/zeolite layered beds. Using the Latin hypercube sampling strategy, training data sets of GA-optimized ANN (GA-ANN) obtains from the physical model of adsorption, heat and mass transfer model. The genetic algorithm (GA) optimizes the weights and biases of ANN for better performance. The ANN topology has 4 input variables (superficial velocity, activated carbon height, adsorption pressure and feed temperature) and 3 output variables (breakthrough times of CH 4 , CO and CO 2). The number of neurons in the hidden layer for the GA-ANN model was optimized as 7 to predict and optimize the maximum breakthrough time of SMR with a four-component (H 2 /CH 4 /CO/CO 2) system. The sensitivity analysis displays that relative importance to the breakthrough time is in the order of superficial velocity (40.88%) > adsorption pressure (24.55%) > activated carbon height (21.04%) > feed temperature (13.53%). To obtain high-purity hydrogen, the GA-ANN model combined with multi-objective GA optimization is used to maximize the breakthrough times of CH 4 and CO. The GA-ANN surrogate model proposed in this paper can not only accurately and quickly achieve the purpose of predicting the system breakthrough time with a high correlation coefficient (R = 0.9937) but also obtains the optimal operating conditions of PSA hydrogen purification. • A rigorous heat and mass transfer model of multi-component adsorption is established. • Artificial neural network (ANN) is well-trained by Latin hypercube sampling method. • Genetic algorithm (GA) optimizes the weights and biases of ANN for better performance. • Superficial velocity has the highest relative importance value on breakthrough time. • GA-optimized ANN model and GA combined for maximal breakthrough time of impurities. [ABSTRACT FROM AUTHOR]

The widespread risks of leakages in the hydrogen industry chain require a method that can quickly predict the consequences of accidents, especially in the hydrogen refueling station (HRS). This paper presents a surrogate model based on physics-informed neural network (PINN) that can predict the distribution of hydrogen concentration after a leakage. The proposed Physics-informed Convolutional Long Short-Term Memory Network (PI-ConvLSTM) model improves the concentration prediction results at the gas cloud boundary by adding a physical constraint term to the loss function of the ConvLSTM model. The concentration distributions after hydrogen leakage at HRS simulated by FLACS are used as the training samples, and the concentration data are converted into grayscale maps for training. The hydrogen concentration prediction method with the proposed surrogate model as the core achieves fast prediction of the gas cloud concentration distribution with acceptable accuracy. It is observed that the method can greatly reduce the prediction time of the consequences of hydrogen leak accidents with the surrogate model already trained. It can provide real-time risk warning and consequence prediction for hydrogen refueling station leakage accidents. • The hydrogen leak consequences data of HRS is generated using CFD. • ConvLSTM-based surrogate model can predict hydrogen concentration in HRS. • Physics-informed loss function improves accuracy of cloud boundary prediction. • Proposed surrogate model greatly reduces the prediction time compared to CFD. [ABSTRACT FROM AUTHOR]

Supervised learning in deep neural networks is commonly performed using error backpropagation. However, the sequential propagation of errors during the backward pass limits its scalability and applicability to low-powered neuromorphic hardware. Therefore, there is growing interest in finding local alternatives to backpropagation. Recently proposed methods based on forward-mode automatic differentiation suffer from high variance in large deep neural networks, which affects convergence. In this paper, we propose the Forward Direct Feedback Alignment algorithm that combines Activity-Perturbed Forward Gradients with Direct Feedback Alignment and momentum. We provide both theoretical proofs and empirical evidence that our proposed method achieves lower variance than forward gradient techniques. In this way, our approach enables faster convergence and better performance when compared to other local alternatives to backpropagation and opens a new perspective for the development of online learning algorithms compatible with neuromorphic systems. • Forward Gradient methods suffer from high variance that hinders convergence. • Activity-Perturbed Forward Gradients can be used to learn derivatives as direct feedback connections. • Feedback learning acts as a momentum that reduces the gradient variance closer to backpropagation. • Feedback learning reduces the biasness of Direct Feedback Alignment. • Feedback learning enables learning in convolutional layers. [ABSTRACT FROM AUTHOR]

Sharpness aware minimization (SAM) optimizer has been extensively explored as it can generalize better for training deep neural networks via introducing extra perturbation steps to flatten the landscape of deep learning models. Integrating SAM with adaptive learning rate and momentum acceleration, dubbed AdaSAM, has already been explored empirically to train large-scale deep neural networks without theoretical guarantee due to the triple difficulties in analyzing the coupled perturbation step, adaptive learning rate and momentum step. In this paper, we try to analyze the convergence rate of AdaSAM in the stochastic non-convex setting. We theoretically show that AdaSAM admits a O (1 / b T) convergence rate, which achieves linear speedup property with respect to mini-batch size b. Specifically, to decouple the stochastic gradient steps with the adaptive learning rate and perturbed gradient, we introduce the delayed second-order momentum term to decompose them to make them independent while taking an expectation during the analysis. Then we bound them by showing the adaptive learning rate has a limited range, which makes our analysis feasible. To the best of our knowledge, we are the first to provide the non-trivial convergence rate of SAM with an adaptive learning rate and momentum acceleration. At last, we conduct several experiments on several NLP tasks and the synthetic task, which show that AdaSAM could achieve superior performance compared with SGD, AMSGrad, and SAM optimizers. • Adaptive SAM with momentum acceleration ensures automatic learning rate adjustment. • Adaptive SAM shows linear speedup, converging at O (1 / b T). • Delaying 2nd-order momentum separates grad from adaptive rate & perturbed gradients. [ABSTRACT FROM AUTHOR]

This paper examines the issue of almost periodic quasi-projective synchronization of delayed fractional-order quaternion-valued neural networks. First, using a direct method rather than decomposing the fractional quaternion-valued system into four equivalent fractional real-valued systems, using Banach's fixed point theorem, according to the basic properties of fractional calculus and some inequality methods, we obtain that there is a unique almost periodic solution for this class of neural network with some sufficient conditions. Next, by constructing a suitable Lyapunov functional, using the characteristic of the Mittag-Leffler function and the scaling idea of the inequality, the adequate conditions for the quasi-projective synchronization of the established model are derived, and the upper bound of the systematic error is estimated. Finally, further use Matlab is used to carry out two numerical simulations to prove the results of theoretical analysis. [ABSTRACT FROM AUTHOR]

Currently, through proposing discontinuous control strategies with the signum function and discussing separately short-term memory (STM) and long-term memory (LTM) of competitive artificial neural networks (ANNs), the fixed-time (FXT) synchronization of competitive ANNs has been explored. Note that the method of separate analysis usually leads to complicated theoretical derivation and synchronization conditions, and the signum function inevitably causes the chattering to reduce the performance of the control schemes. To try to solve these challenging problems, the FXT synchronization issue is concerned in this paper for competitive ANNs by establishing a theorem of FXT stability with switching type and developing continuous control schemes based on a kind of saturation functions. Firstly, different from the traditional method of studying separately STM and LTM of competitive ANNs, the models of STM and LTM are compressed into a high-dimensional system so as to reduce the complexity of theoretical analysis. Additionally, as an important theoretical preliminary, a FXT stability theorem with switching differential conditions is established and some high-precision estimates for the convergence time are explicitly presented by means of several special functions. To achieve FXT synchronization of the addressed competitive ANNs, a type of continuous pure power-law control scheme is developed via introducing the saturation function instead of the signum function, and some synchronization criteria are further derived by the established FXT stability theorem. These theoretical results are further illustrated lastly via a numerical example and are applied to image encryption. [ABSTRACT FROM AUTHOR]