Search

Background and objectives: This review aims to delve into the role of artificial intelligence in medicine. Ulcerative colitis (UC) is a chronic, inflammatory bowel disease (IBD) characterized by superficial mucosal inflammation, rectal bleeding, diarrhoea and abdominal pain. By identifying the challenges inherent in UC diagnosis, we seek to highlight the potential impact of artificial intelligence on enhancing both diagnosis and treatment methodologies for this condition. Method: A targeted, non-systematic review of literature relating to ulcerative colitis was undertaken. The PubMed and Scopus databases were searched to categorize a well-rounded understanding of the field of artificial intelligence and its developing role in the diagnosis and treatment of ulcerative colitis. Articles that were thought to be relevant were included. This paper only included articles published in English. Results: Artificial intelligence (AI) refers to computer algorithms capable of learning, problem solving and decision-making. Throughout our review, we highlighted the role and importance of artificial intelligence in modern medicine, emphasizing its role in diagnosis through AI-assisted endoscopies and histology analysis and its enhancements in the treatment of ulcerative colitis. Despite these advances, AI is still hindered due to its current lack of adaptability to real-world scenarios and its difficulty in widespread data availability, which hinders the growth of AI-led data analysis. Conclusions: When considering the potential of artificial intelligence, its ability to enhance patient care from a diagnostic and therapeutic perspective shows signs of promise. For the true utilization of artificial intelligence, some roadblocks must be addressed. The datasets available to AI may not truly reflect the real-world, which would prevent its impact in all clinical scenarios when dealing with a spectrum of patients with different backgrounds and presenting factors. Considering this, the shift in medical diagnostics and therapeutics is coinciding with evolving technology. With a continuous advancement in artificial intelligence programming and a perpetual surge in patient datasets, these networks can be further enhanced and supplemented with a greater cohort, enabling better outcomes and prediction models for the future of modern medicine. [ABSTRACT FROM AUTHOR]

A neural network model needs to be manually designed for ancient mural dynasty recognition, and this paper proposes an ancient mural dynasty recognition algorithm that is based on a neural architecture search (NAS). First, the structural edge information of mural images is extracted for use by the neural network model in recognizing mural missions. Second, an NAS algorithm that is based on contrast selection (CS) simplifies the architecture search to an incremental CS and then searches for the optimal network architecture on the mural dataset. Finally, the identified optimal network architecture is used for training and testing to complete the mural dynasty recognition task. The results show that the top accuracy of the proposed method on the mural dataset is 88.10%, the recall rate is 87.52%, and the precision rate is 87.69%. Each evaluation index used by the neural network model is superior to that of classical network models such as AlexNet and ResNet-50. Compared with NAS methods such as ASNG and MIGO, the accuracy of mural dynasty recognition is higher by an average of 4.27% when using the proposed method. The proposed method is verified on CIFAR-10, CIFAR-100, ImageNet16-120 and other datasets and achieves a good recognition accuracy in the NAS-bench-201 search space, which averages 93.26%, 70.73% and 45.34%, respectively, on the abovementioned datasets. [ABSTRACT FROM AUTHOR]

The health management of railway signal equipment in the high-speed railway is a key link between intelligent operation and maintenance. Accurately predicting the health state of compensation capacitors is of great significance to ensure the reliable work of track circuits. This paper proposes an improved deep neural network algorithm focusing on the problem of long-term accurate health forecasts for compensation capacitors. First, establishing a transmission state model for degradation mechanism mining, the difference function that can quantitatively evaluate features is defined by piecewise processing cab signaling receiving voltage. Introducing the degradation model, predictive driving under both model and data is implemented. Then, the convolutional neural networks and bidirectional long–short-term memory are combined and improved to construct a novel artificial intelligence combination strategy, while parameters are optimized based on the sparrow search algorithm. Finally, facing the conditional repair of compensation capacitors, we set a reasonable threshold for the occurrence of hidden dangers to complete fault warning. This novel and practical approach effectively explores the procedure of prognosis and health management, while the refined maintenance will better utilize current monitoring information, helping the intelligence and accuracy of safety control decision-making. [ABSTRACT FROM AUTHOR]

Patient-specific 3D models of the human mandible are finding increasing utility in medical fields such as oral and maxillofacial surgery, orthodontics, dentistry, and forensic sciences. The efficient creation of personalized 3D bone models poses a key challenge in these applications. Existing solutions often rely on 3D statistical models of human bone, offering advantages in rapid bone geometry adaptation and flexibility by capturing a range of anatomical variations, but also a disadvantage in terms of reduced precision in representing specific shapes. Considering this, the proposed parametric model allows for precise manipulation using morphometric parameters acquired from medical images. This paper highlights the significance of employing the parametric model in the creation of a personalized bone model, exemplified through a case study targeting mandibular prognathism reconstruction. A personalized model is described as 3D point cloud determined through the utilization of series of parametric functions, determined by the application of geometrical morphometrics, morphology properties, and artificial neural networks in the input dataset of human mandible samples. With 95.05% of the personalized model's surface area displaying deviations within −1.00–1.00 mm relative to the input polygonal model, and a maximum deviation of 2.52 mm, this research accentuates the benefits of the parametric approach, particularly in the preoperative planning of mandibular deformity surgeries. [ABSTRACT FROM AUTHOR]

Featured Application: The Deep Neural Network model employed in this work will help build a system for the pre-diagnosis of retinopathies that can lead to blindness. The main intention of this type of system is to support the work performed by ophthalmology specialists. Computer-based pre-diagnosis of diseases through medical imaging is a task worked on for many years. The so-called fundus images stand out since they do not have uniform illumination and are highly sensitive to noise. One of the diseases that can be pre-diagnosed through fundus images is age-related macular degeneration, which initially manifests as the appearance of lesions called drusen. Several ways of pre-diagnosing macular degeneration have been proposed, methods based entirely on the segmentation of drusen with prior image processing have been designed and applied, and methods based on image pre-processing and subsequent conversion to feature vectors, or patterns, to be classified by a Machine-Learning model have also been developed. Finally, in recent years, the use of Deep-Learning models, particularly Convolutional Networks, has been proposed and used in classification problems where the data are only images. The latter has allowed the so-called transfer learning, which consists of using the learning achieved in the solution of one problem to solve another. In this paper, we propose the use of transfer learning through the Xception Deep Convolutional Neural Network to detect age-related macular degeneration in fundus images. The performance of the Xception model was compared against six other state-of-the-art models with a dataset created from images available in public and private datasets, which were divided into training/validation and test; with the training/validation set, the training was made using 10-fold cross-validation. The results show that the Xception neural network obtained a validation accuracy that surpasses other models, such as the VGG-16 or VGG-19 networks, and had an accuracy higher than 80% in the test set. We consider that the contributions of this work include the use of a Convolutional Neural Network model for the detection of age-related macular degeneration through the classification of fundus images in those affected by AMD (drusen) and the images of healthy patients. The performance of this model is compared against other methods featured in the state-of-the-art approaches, and the best model is tested on a test set outside the training and validation set. [ABSTRACT FROM AUTHOR]

Interior permanent magnet synchronous machines (IPMSMs) driven with a square-wave control (i.e., six-step, block, or 120° control), known commonly as brushless direct current (BLDC) drives, are used widely due to their high power density and control simplicity. The advance firing (AF) angle is employed to achieve improved operation characteristics of the drive. The AF angle is, in general, applied to compensate for the commutation effects. In the case of an IPMSM, the AF angle can also be adjusted to exploit reluctance torque. In this paper, a detailed study was performed to understand its effect on the drive's performance in regard to reluctance torque. Furthermore, a multi-objective optimization of the machine's cross-section using neural network models was conducted to enhance performance at a constant AF angle. The reference and improved machine designs were evaluated in a system-level simulation, where the impact was considered of the commutation of currents. A significant improvement in the machine performance was achieved after optimizing the geometry and implementing a fixed AF angle of 10°. [ABSTRACT FROM AUTHOR]

Artificial Neural Networks (ANNs) have been used in a multitude of real-world applications given their predictive capabilities, and algorithms based on gradient descent, such as Backpropagation (BP) and variants, are usually considered for their optimisation. However, these algorithms have been shown to get stuck at local optima, and they require a cautious design of the architecture of the model. This paper proposes a novel memetic training method for simultaneously learning the ANNs structure and weights based on the Coral Reef Optimisation algorithms (CROs), a global-search metaheuristic based on corals' biology and coral reef formation. Three versions based on the original CRO combined with a Local Search procedure are developed: (1) the basic one, called Memetic CRO; (2) a statistically guided version called Memetic SCRO (M-SCRO) that adjusts the algorithm parameters based on the population fitness; (3) and, finally, an improved Dynamic Statistically-driven version called Memetic Dynamic SCRO (M-DSCRO). M-DSCRO is designed with the idea of improving the M-SCRO version in the evolutionary process, evaluating whether the fitness distribution of the population of ANNs is normal to automatically decide the statistic to be used for assigning the algorithm parameters. Furthermore, all algorithms are adapted to the design of ANNs by means of the most suitable operators. The performance of the different algorithms is evaluated with 40 classification datasets, showing that the proposed M-DSCRO algorithm outperforms the other two versions on most of the datasets. In the final analysis, M-DSCRO is compared against four state-of-the-art methods, demonstrating its superior efficacy in terms of overall accuracy and minority class performance. [ABSTRACT FROM AUTHOR]

Accurate quantification of uncertainty in solar photovoltaic (PV) generation forecasts is imperative for the efficient and reliable operation of the power grid. In this paper, a data-driven non-parametric probabilistic method based on the Naïve Bayes (NB) classification algorithm and Dempster–Shafer theory (DST) of evidence is proposed for day-ahead probabilistic PV power forecasting. This NB-DST method extends traditional deterministic solar PV forecasting methods by quantifying the uncertainty of their forecasts by estimating the cumulative distribution functions (CDFs) of their forecast errors and forecast variables. The statistical performance of this method is compared with the analog ensemble method and the persistence ensemble method under three different weather conditions using real-world data. The study results reveal that the proposed NB-DST method coupled with an artificial neural network model outperforms the other methods in that its estimated CDFs have lower spread, higher reliability, and sharper probabilistic forecasts with better accuracy. [ABSTRACT FROM AUTHOR]

Demand response management (DRM) plays a crucial role in the prospective development of smart grids. The precise estimation of electricity demand for individual houses is vital for optimizing the operation and planning of the power system. Accurate forecasting of the required components holds significance as it can substantially impact the final cost, mitigate risks, and support informed decision-making. In this paper, a forecasting approach employing neural networks for smart grid demand-side management is proposed. The study explores various enhanced artificial neural network (ANN) architectures for forecasting smart grid consumption. The performance of the ANN approach in predicting energy demands is evaluated through a comparison with three statistical models: a time series model, an auto-regressive model, and a hybrid model. Experimental results demonstrate the ability of the proposed neural network framework to deliver accurate and reliable energy demand forecasts. [ABSTRACT FROM AUTHOR]

Power quality improvement and Power quality disturbance (PQD) detection are two significant concerns that must be addressed to ensure an efficient power distribution within the utility grid. When the process to analyze PQD is migrated to real-time platforms, the possible occurrence of a phase mismatch can affect the algorithm's accuracy; this paper evaluates phase shifting as an additional stage in signal acquisition for detecting and classifying eight types of single power quality disturbances. According to their mathematical models, a set of disturbances was generated using an arbitrary waveform generator BK Precision 4064. The acquisition, detection, and classification stages were embedded into a BeagleBone Black. The detection stage was performed using multiresolution analysis. The feature vectors of the acquired signals were obtained from the combination of Shannon entropy and log-energy entropy. For classification purposes, four types of classifiers were trained: multilayer perceptron, K-nearest neighbors, probabilistic neural network, and decision tree. The results show that incorporating a phase-shifting stage as a preprocessing stage significantly improves the classification accuracy in all cases. [ABSTRACT FROM AUTHOR]

The credit risk assessment acts as an important part in daily affairs for financial institutions. But in the era of big data, the growing business volume makes it an urgent demand to develop digital ways of credit risk assessment. Currently, the machine learning is universally employed to establish various data-driven models for this purpose. However, machine learning models generally suffer from limited ability of feature representation and robustness, and cannot deal with more complex financial security scenarios. To deal with this issue, this work introduces ensemble learning to construct a stronger credit risk prediction model via integration of several basic machine learning models. Thus, an ensemble learning-enhanced smart prediction model for financial credit risk is proposed in this paper. Three classification-based machine learning models (support vector machine, artificial neural network and radial basis function) are selected as the basic classifiers, and "voting" strategy is utilized to integrate them into a novel strong classifier. A real-world financial credit dataset released by a Chinese commercial bank was selected as the experimental scenario. The obtained results show that the proposal has better prediction accuracy compared with basic machine learning models without ensemble learning. [ABSTRACT FROM AUTHOR]

Deep neural network has made surprising achievements in natural language processing, image pattern classification recognition, and other domains in the last few years. It is still tough to apply to hardware-constrained or mobile equipment because of the huge number of parameters, high storage as well as computing costs. In this paper, a new sparse iteration neural network architecture is proposed. First, the pruning method is used to compress the model size and make the network sparse. Then the architecture is iterated on the sparse network model, and the network performance is improved without adding additional parameters. Finally, the hybrid deep learning model was carried out on CV tasks and NLP tasks on ANN, CNN, and Transformer. Compared with the sparse network architecture, we finally found that the accuracy of the MINST, CIFAR10, PASCAL VOC 2012, and SQuAD datasets is improved by 0.47%, 0.64%, 3.75%, and 15.06%, respectively. [ABSTRACT FROM AUTHOR]

Photovoltaic (PV) panels are one of the popular green energy resources and PV panel parameter estimations are one of the popular research topics in PV panel technology. The PV panel parameters could be used for PV panel health monitoring and fault diagnosis. Recently, a PV panel parameters estimation method based in neural network and numerical current predictor methods has been developed. However, in order to further improve the estimation accuracies, a new approach of PV panel parameter estimation is proposed in this paper. The output current and voltage dynamic responses of a PV panel are measured, and the time series of the I–V vectors will be used as input to an artificial neural network (ANN)-based PV model parameter range classifier (MPRC). The MPRC is trained using an I–V dataset with large variations in PV model parameters. The results of MPRC are used to preset the initial particles' population for a particle swarm optimization (PSO) algorithm. The PSO algorithm is used to estimate the PV panel parameters and the results could be used for PV panel health monitoring and the derivation of maximum power point tracking (MMPT). Simulations results based on an experimental I–V dataset and an I–V dataset generated by simulation show that the proposed algorithms can achieve up to 3.5% accuracy and the speed of convergence was significantly improved as compared to a purely PSO approach. [ABSTRACT FROM AUTHOR]

In this paper, we study the post-hoc calibration of modern neural networks, a problem that has drawn a lot of attention in recent years. Despite the plethora of calibration methods proposed, there is no consensus yet on the inherent complexity of the task and, while some authors claim that simple functions solve the problem, others suggest that more expressive models are needed to capture misscalibration. As a first approach, we focus on the task of confidence scaling, specifically on post-hoc methods that generalize Temperature Scaling, which we refer to as the Adaptive Temperature Scaling family. We begin by demonstrating that while complex models like neural networks provide an advantage when there is ample data, they fail in scenarios where it is limited, notably common in fields like medical diagnosis. We then show how under this ideal data conditions the more expressive methods learn a relationship between the entropy of a prediction and its level of overconfidence, and based on this observation, we propose Entropy-based Temperature Scaling, a simple method that scales the confidence of a prediction according to this relationship. Results show that our method obtains state-of-the-art performance and is robust against data scarcity. Moreover, our proposed model enables a deeper understanding of the calibration process by the interpretation of the entropy as a measure of uncertainty in the network outputs. [ABSTRACT FROM AUTHOR]

In order to ensure flight safety, the requirement of foundation settlement of high-plateau airport is stricter than that of airport in plain area. In order to monitor the abnormal state of runway foundation in the process of use of a high-plateau airport and prevent and resolve the major risk of foundation settlement to flight safety. It takes a high-plateau airport in the southwest mountain area as an example, selecting two representative A and B sections for analysis. It takes the first 60 days' monitoring data as training samples, which shows nonlinear characteristics. The Long and Short Term Memory neural network (LSTM) prediction model and BP neural network model are constructed to predict the trend of foundation settlement after construction. In the process of building the LSTM model, the minimum root-mean-square error of test samples was selected as the fitness function, and the parameters of the LSTM model were modified by Genetic Algorithm (GA). And then the modified LSTM prediction model based on the early settlement of the foundation was constructed. The results shows that the modified LSTM model and BP model constructed in this paper are generally consistent with the field measured values in the prediction of airport foundation settlement of high-plateau, but the modified LSTM model is more sensitive to the abrupt change of data and has a more stable trend than the BP model. The predicted values of the modified LSTM model are all greater than those of the BP model, and the predicted values of the modified LSTM model are closer to the monitored values in the field than the predicted values of the BP model, and the relative error between the predicted values and the monitored values is less than 3%. The research can provide a reliable theoretical reference for the design, construction, operation management and later maintenance of high-plateau airport. [ABSTRACT FROM AUTHOR]

Deep neural networks are vulnerable to backdoor attacks. Previous backdoor attacks have mainly focused on images. Unlike images composed of regular pixels, 3D point clouds are composed of irregular three-dimensional XYZ coordinates, which are widely used in areas such as autonomous driving and 3D measurement. As many deep neural networks have been developed for processing 3D point clouds, these networks also face the risk of backdoor attacks. Nevertheless, backdoor attacks on 3D point clouds have rarely been investigated. This paper proposes a stealthy backdoor attack on point clouds in the physical world, aiming to generate trainable non-rigid deformations as backdoor patterns. Instead of directly adding backdoor patterns onto the point clouds, we deform the 3D space of the point clouds to a new space, ensuring that all point clouds have the same backdoor deformation. We use point cloud alignment to overcome the inconsistency of backdoor deformation caused by shifting and scaling in the physical world. We also propose a physical transformation layer to combat the physical transformations. Additionally, we propose mask contrast learning to eliminate pseudo backdoor patterns to make the network's backdoor property stealthier. Extensive experiments indicate that the proposed method can achieve better attack success rates and stealthiness. [ABSTRACT FROM AUTHOR]

Recent studies show that neural networks are vulnerable to backdoor attacks, in which compromised networks behave normally for clean inputs but make mistakes when a pre-defined trigger appears. Although prior studies have designed various invisible triggers to avoid causing visual anomalies, they cannot evade some trigger detectors. In this paper, we consider the stealthiness of backdoor attacks from input space and feature representation space. We propose a novel backdoor attack named sparse backdoor attack, and investigate the minimum required trigger to induce the well-trained networks to make incorrect results. A U-net-based generator is employed to create triggers for each clean image. Considering the stealthiness of the trigger, we restrict the elements of the trigger between −1 and 1. In the aspect of the feature representation domain, we adopt an entanglement cost function to minimize the gap between feature representations of benign and malicious inputs. The inseparability of benign and malicious feature representations contributes to the stealthiness of our attack against various model diagnosis-based defences. We validate the effectiveness and generalization of our method by conducting extensive experiments on multiple datasets and networks. [ABSTRACT FROM AUTHOR]

While tensor accelerated compilers have proven effective in deploying deep neural networks (DNN) on general-purpose hardware, optimizing for FPGA remains challenging due to the complex DNN architectures and the heterogeneous, semi-open compute units. This paper introduces the Automatic Kernel Generation for DNN on CPU-FPGA (AKGF) framework for efficient deployment of DNN on heterogeneous CPU-FPGA platforms. AKGF generates an intermediate representation (IR) of the DNN using TVM's Halide IR, annotates the operators of model layers in the IR to compute them on the corresponding hardware cores, and further optimizes the operator code for CPU and FPGA using ARM's function library and the polyhedral model to enhance model inference speed and power consumption. The experimental tests conducted on a CPU-FPGA board validate the effectiveness of AKGF, demonstrating significant acceleration ratios (up to 6.7x) compared to state-of-the-art accelerators while achieving a 2x power optimization. AKGF effectively leverages the computational capabilities of both CPU and FPGA for high-performance deployment of DNN on CPU-FPGA platforms. [ABSTRACT FROM AUTHOR]

Knowledge graph (KG) is introduced as side information into recommender systems, which can alleviate the sparsity and cold start problems in collaborative filtering. Existing studies mainly focus on modeling users' historical behavior data and KG-based propagation. However, they have the limitation of ignoring noise information during recommendation. We consider that noise exists in two parts (i.e. KG and user-item interaction data). In this paper, we propose Knowledge-aware Dual-Channel Graph Neural Networks (KDGNN) to improve the recommendation performance by reducing the noise in the recommendation process. Specifically, (1) for the noise in KG, we design a personalized gating mechanism, namely dual-channel balancing mechanism, to block the propagation of redundant information in KG. (2) For the noise in user-item interaction data, we integrate personalized and knowledge-aware signals to capture user preferences fully and use personalized knowledge-aware attention to denoise user-item interaction data. Compared with existing KG-based methods, we aim to propose a knowledge-aware recommendation method from a new perspective of denoising. We perform performance analysis on three real-world datasets, and experiment results demonstrate that KDGNN achieves strongly competitive performance compared with several compelling state-of-the-art baselines. [ABSTRACT FROM AUTHOR]

Existing research in metasurface design was based on trial-and-error high-intensity iterations and requires deep acoustic expertise from the researcher, which severely hampered the development of the metasurface field. Using deep learning enabled the fast and accurate design of hypersurfaces. Based on this, in this paper, an integrated learning approach was first utilized to construct a model of the forward mapping relationship between the hypersurface physical structure parameters and the acoustic field, which was intended to be used for data enhancement. Then a dual-feature fusion model (DFCNN) based on a convolutional neural network was proposed, in which the first feature was the high-dimensional nonlinear features extracted using a data-driven approach, and the second feature was the physical feature information of the acoustic field mined using the model. A convolutional neural network was used for feature fusion. A genetic algorithm was used for network parameter optimization. Finally, generalization ability verification was performed to prove the validity of the network model. The results showed that 90% of the integrated learning models had an error of less than 3 dB between the real and predicted sound field data, and 93% of the DFCNN models could achieve an error of less than 5 dB in the local sound field intensity. [ABSTRACT FROM AUTHOR]

We present a novel approach to identify galaxy clusters that are undergoing a merger using a deep learning approach. This paper uses massive galaxy clusters spanning 0 ≤ z ≤ 2 from The Three Hundred project, a suite of hydrodynamic resimulations of 324 large galaxy clusters. Mock, idealized Compton- y and X-ray maps were constructed for the sample, capturing them out to a radius of 2 R 200. The idealized nature of these maps mean they do not consider observational effects such as foreground or background astrophysical objects, any spatial resolution limits or restriction on X-ray energy bands. Half of the maps belong to a merging population as defined by a mass increase Δ M/M ≥ 0.75, and the other half serves as a controlled, relaxed population. We employ a convolutional neural network architecture and train the model to classify clusters into one of the groups. A best-performing model was able to correctly distinguish between the two populations with a balanced accuracy (BA) and recall of 0.77, ROC-AUC of 0.85, PR-AUC of 0.55, and F 1 score of 0.53. Using a multichannel model relative to a single-channel model, we obtain a 3 per cent improvement in BA score, and a 6 per cent improvement in F 1 score. We use a saliency interpretation approach to discern the regions most important to each classification decision. By analysing radially binned saliency values we find a preference to utilize regions out to larger distances for mergers with respect to non-mergers, greater than ∼1.2 R 200 and ∼0.7 R 200 for SZ and X-ray, respectively. [ABSTRACT FROM AUTHOR]

Gradient-based aerodynamic optimization methods involve complex gradient calculations with high computational costs. To address these problems, this paper proposes a rapid deep learning-based method for predicting the aerodynamic force gradients and establishes an aerodynamic optimization framework. A deep neural network is used to determine the latent mapping relationship between the near-wall flow field information and the aerodynamic force gradients, and the resulting gradient prediction model is integrated into an aerodynamic optimization platform. Combining grid deformation techniques with gradient-based optimization enables the aerodynamic optimization of airfoils. The deep neural network model can rapidly predict gradients that are basically consistent with those from the traditional discrete adjoint method, and decouples the gradient computation from the flow field solution process. The proposed method is validated through the aerodynamic optimization of the airfoil. Under various optimization objectives and initial conditions, the deep neural network model significantly improves the aerodynamic performance of the airfoil and substantially enhances the efficiency of optimization compared with traditional methods. [ABSTRACT FROM AUTHOR]

Learning in neural networks with locally-tuned neuron models such as radial Basis Function (RBF) networks is often seen as instable, in particular when multi-layered architectures are used. Furthermore, universal approximation theorems for single-layered RBF networks are very well established; therefore, deeper architectures are theoretically not required. Consequently, RBFs are mostly used in a single-layered manner. However, deep neural networks have proven their effectiveness on many different tasks. In this paper, we show that deeper RBF architectures with multiple radial basis function layers can be designed together with efficient learning schemes. We introduce an initialization scheme for deep RBF networks based on k-means clustering and covariance estimation. We further show how to make use of convolutions to speed up the calculation of the Mahalanobis distance in a partially connected way, which is similar to the convolutional neural networks (CNNs). Finally, we evaluate our approach on image classification as well as speech emotion recognition tasks. Our results show that deep RBF networks perform very well, with comparable results to other deep neural network types, such as CNNs. [ABSTRACT FROM AUTHOR]

Finding the most interesting areas of an image is the aim of saliency detection. Conventional methods based on low-level features rely on biological cues like texture and color. These methods, however, have trouble with processing complicated or low-contrast images. In this paper, we introduce a deep neural network-based saliency detection method. First, using semantic segmentation, we construct a pixel-level model that gives each pixel a saliency value depending on its semantic category. Next, we create a region feature model by combining both hand-crafted and deep features, which extracts and fuses the local and global information of each superpixel region. Third, we combine the results from the previous two steps, along with the over-segmented superpixel images and the original images, to construct a multi-level feature model. We feed the model into a deep convolutional network, which generates the final saliency map by learning to integrate the macro and micro information based on the pixels and superpixels. We assess our method on five benchmark datasets and contrast it against 14 state-of-the-art saliency detection algorithms. According to the experimental results, our method performs better than the other methods in terms of F-measure, precision, recall, and runtime. Additionally, we analyze the limitations of our method and propose potential future developments. [ABSTRACT FROM AUTHOR]

Purpose: Fused Filament Fabrication (FFF) is one of the growing technologies in additive manufacturing, that can be used in a number of applications. In this method, process parameters can be customized and their simultaneous variation has conflicting impacts on various properties of printed parts such as dimensional accuracy (DA) and surface finish. These properties could be improved by optimizing the values of these parameters. Design/methodology/approach: In this paper, four process parameters, namely, print speed, build orientation, raster width, and layer height which are referred to as "input variables" were investigated. The conflicting influence of their simultaneous variations on the DA of printed parts was investigated and predicated. To achieve this goal, a hybrid Genetic Algorithm – Artificial Neural Network (GA-ANN) model, was developed in C#.net, and three geometries, namely, U-shape, cube and cylinder were selected. To investigate the DA of printed parts, samples were printed with a central through hole. Design of Experiments (DoE), specifically the Rotational Central Composite Design method was adopted to establish the number of parts to be printed (30 for each selected geometry) and also the value of each input process parameter. The dimensions of printed parts were accurately measured by a shadowgraph and were used as an input data set for the training phase of the developed ANN to predict the behavior of process parameters. Then the predicted values were used as input to the Desirability Function tool which resulted in a mathematical model that optimizes the input process variables for selected geometries. The mean square error of 0.0528 was achieved, which is indicative of the accuracy of the developed model. Findings: The results showed that print speed is the most dominant input variable compared to others, and by increasing its value, considerable variations resulted in DA. The inaccuracy increased, especially with parts of circular cross section. In addition, if there is no need to print parts in vertical position, the build orientation should be set at 0° to achieve the highest DA. Finally, optimized values of raster width and layer height improved the DA especially when the print speed was set at a high value. Originality/value: By using ANN, it is possible to investigate the impact of simultaneous variations of FFF machines' input process parameters on the DA of printed parts. By their optimization, parts of highly accurate dimensions could be printed. These findings will be of significant value to those industries that need to produce parts of high DA on FFF machines. [ABSTRACT FROM AUTHOR]

This paper presents a new accurate method to compute the mechanical response of pavement structures using an Artificial Neural Network (ANN) model coupled with Multi-Layer Elastic Analysis (MLEA). The ANN model is used to improve the numerical integration of the response function used in the MLEA method. It requires four inputs: total pavement thickness, the diameter of the contact area, radial distance, and depth of the response point; and it was trained on one million hypothetical pavement structures. The developed method has been validated by a comparative analysis against boundary conditions, finite element analysis, and available MLEA solutions using various hypothetical pavement structures. The results demonstrate that the developed solution gives excellent response in the vicinity of the pavement surface together with a significant improvement in computational efficiency. [ABSTRACT FROM AUTHOR]

This paper presents a novel discrete memristor model that incorporates exponential and absolute value functions. A discrete coupled memristor neural network model is constructed based on this memristor design. The periodic and chaotic regions of the discrete neural network model are determined using bifurcation and Lyapunov exponent spectrum. Furthermore, by varying the initial values of the discrete memristive neural network, we observe the coexistence of chaos and periodic attractors, as well as periodic attractors. Additionally, an application to color image encryption based on the discrete system model is given. Security analysis is conducted in the aspects of key space, histogram analysis, correlation analysis, sensitivity analysis, Peak Signal-to-Noise Ratio (PSNR), and information entropy analysis. The analysis results show that the algorithm has a key space size of 2 2 5 8 , and the information entropy of baboon graph is 7.9993, which is very close to the ideal value of 8. It shows that the image encryption algorithm is feasible and effective. Finally, the implementation of the discrete memristive neural network model is realized using Field Programmable Gate Array (FPGA). The experimental implementation is conducted using the Verilog language on the Vivado 2018.3 platform, and the obtained results align with the numerical simulation results obtained through MATLAB. [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]

The paper studies the effectiveness of machine learning techniques in predicting the microhardness of composite materials manufactured from a mixture of iron-copper (Fe-Cu) nanopowders and hydroxyapatite (HA) particles. It is shown that the different proportion of Fe-Cu and HA powders and the polymer fraction in the composite significantly affect its hardness. A surrogate model based on the artificial neural network (ANN) and the analytical model, is proposed to quantitatively evaluate the microhardness, depending on the powder/polymer ratio. The ANN models show the probability distribution of indentation values after microhardness testing, which is the input data for the analytical model to compute the hardness. This approach can reduce the time and cost of the material research and minimizes the reliance on expensive materials and experimental equipment. [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]

Interpreting a seemingly simple function word like "or," "behind," or "more" can require logical, numerical, and relational reasoning. How are such words learned by children? Prior acquisition theories have often relied on positing a foundation of innate knowledge. Yet recent neural‐network‐based visual question answering models apparently can learn to use function words as part of answering questions about complex visual scenes. In this paper, we study what these models learn about function words, in the hope of better understanding how the meanings of these words can be learned by both models and children. We show that recurrent models trained on visually grounded language learn gradient semantics for function words requiring spatial and numerical reasoning. Furthermore, we find that these models can learn the meanings of logical connectives and and or without any prior knowledge of logical reasoning as well as early evidence that they are sensitive to alternative expressions when interpreting language. Finally, we show that word learning difficulty is dependent on the frequency of models' input. Our findings offer proof‐of‐concept evidence that it is possible to learn the nuanced interpretations of function words in a visually grounded context by using non‐symbolic general statistical learning algorithms, without any prior knowledge of linguistic meaning. [ABSTRACT FROM AUTHOR]

Purpose: This study aims to elucidate the machining properties of low-cost expanded clay-reinforced syntactic foams by using different neural network models for the first time in the literature. The main goal of this endeavor is to create a casting machining-neural network modeling flow-line for real-time foam manufacturing in the industry. Design/methodology/approach: Samples were manufactured via an industry-based die-casting technology. For the slot milling tests performed with different cutting speeds, depth of cut and lubrication conditions, a 3-axis computer numerical control (CNC) machine was used and the force data were collected through a digital dynamometer. These signals were used as input parameters in neural network modelings. Findings: Among the algorithms, the scaled-conjugated-gradient (SCG) methodology was the weakest average results, whereas the Levenberg–Marquard (LM) approach was highly successful in foreseeing the cutting forces. As for the input variables, an increase in the depth of cut entailed the cutting forces, and this circumstance was more obvious at the higher cutting speeds. Research limitations/implications: The effect of milling parameters on the cutting forces of low-cost clay-filled metallic syntactics was examined, and the correct detection of these impacts is considerably prominent in this paper. On the other side, tool life and wear analyses can be studied in future investigations. Practical implications: It was indicated that the milling forces of the clay-added AA7075 syntactic foams, depending on the cutting parameters, can be anticipated through artificial neural network modeling. Social implications: It is hoped that analyzing the influence of the cutting parameters using neural network models on the slot milling forces of metallic syntactic foams (MSFs) will be notably useful for research and development (R&D) researchers and design engineers. Originality/value: This work is the first investigation that focuses on the estimation of slot milling forces of the expanded clay-added AA7075 syntactic foams by using different artificial neural network modeling approaches. [ABSTRACT FROM AUTHOR]

In this paper, we propose a method for efficient target classification based on the spatial features of the point cloud generated by using a high-resolution radar sensor. The frequency-modulated continuous wave radar sensor can estimate the distance and velocity of a target. In addition, the azimuth and elevation angle of the target can be estimated by using a multiple-input and multiple-output antenna system. Using the estimated distance, velocity, and angle, the 3D point cloud of target can be generated. From the generated point cloud, we extract the point cloud for each individual target using the density-based spatial clustering of application with noise method and a camera mounted on the radar sensor. Then, we define the convex hull boundaries that enclose these point clouds in both 3D and 2D spaces obtained by orthogonally projecting onto the x y , y z , and z x planes. Using the vertices of convex hull, we calculate the volume of the targets and the areas in 2D spaces. Several feature points, including the calculated spatial information, are numerized and configured into feature vectors. We design an uncomplicated deep neural network classifier based on minimal input information to achieve fast and efficient classification performance. As a result, the proposed method achieved an average accuracy of 97.1%, and the time required for training was reduced compared to the method using only point cloud data and the convolutional neural network-based method. [ABSTRACT FROM AUTHOR]

Water bodies can offer local microclimates that have the potential to attenuate the effects of urban heat islands by reducing local temperature. This capability is shaded when the river is channelized. In such cases, the river temperature rises during hot periods, leading to negative impacts on the water quality. The main aim of this paper is to develop a local simple model to predict the temperature of the Dâmbovița River at its exit from Bucharest City, the capital of Romania. The location is chosen based on the historical critical impacts, in terms of extreme heatwaves that took place during hot summers, as well as future possible risks due to climate change. The water temperature prediction model is based on an artificial neural network that uses the Levenberg–Marquardt algorithm, due to its stability and rapid convergence capabilities. The model forecasts, with an accuracy of ±1 °C, the water temperature in an ungauged, downstream location, as a function of measured air and upstream water temperatures. The proposed model represents a first attempt to provide water managers in Bucharest City with a useful tool that will allow them to take timely measures to counteract the unwanted effects that can be generated by high water temperatures. [ABSTRACT FROM AUTHOR]

This paper introduces an innovative electrocardiogram (ECG ) denoising technique based on stationary wavelet transform ( S W T) and wavelet/total variation (WATV). In this technique, we also use two different artificial neural networks ( ANNs ) to determine two ideal thresholds, t h r 1 and t h r 2 . The latter is used for the soft thresholding of a noisy details coefficient, c d b 2 , to obtain a denoised coefficient, c d d 2 . The threshold t h r 1 is used for the soft thresholding of a noisy details coefficient, c d b 1 , yielding a denoised coefficient, c d d 1. The coefficient c d b 1 and a noisy approximation coefficient, c a b 1 , are obtained by applying SWT to the noisy ECG signal. The coefficient c d b 2 and another noisy approximation coefficient, c a b 2 , are obtained by applying SWT to c a b 1 . In this proposed ECG denoising system, we also apply a WATV-based denoising technique to c a b 2 to obtain a denoised approximation coefficient, c a d 2 . This WATV-based denoising technique requires the estimation of the level of the noise corrupting the clean ECG signal. This noise is additive Gaussian white noise (AGWN) and its level is denoted as σ , which is estimated from c d b 1 . After that, the inverse of SWT ( S W T - 1 ) is applied to c d d 2 and c a d 2 to obtain a denoised approximation coefficient, c a d 1 . Subsequently, we apply S W T - 1 to c d d 1 and c a d 1 to finally obtain the denoised ECG signal. The performance of this proposed ECG denoising technique is proven by the results obtained after computing the signal-to-noise ratio ( SNR ), the peak SNR ( PSNR ), the mean square error ( MSE ), the mean absolute error ( MAE ) and the cross-correlation ( CC ). [ABSTRACT FROM AUTHOR]

Predicting the moment-rotation response parameters of semirigid steel connections can be challenging given the many components contributing to the connection's elastic and plastic deformations. This is the case for the popular flush endplate beam-to-column connections (FEPCs). The literature has highlighted the limitations of current analytical, mechanical, and traditional empirical models in providing accurate predictions of the FEPCs' moment-rotation response. Considering this limitation, machine-learning methods have gained wide attention recently in structural engineering applications to address problems associated with complex structural deformation and damage phenomena. To that end, the superior nonlinearity of artificial neural networks (ANN) is employed herein to predict the response characteristics of FEPCs. A large data set of about 200 specimens, collected from past experimental programs, is utilized to train the ANN for predicting the bilinear response of FEPCs including strain hardening. The paper describes the deduction of the response parameters from test data using data fitting, the determination of significant geometric, material, and layout features, the ANN architecture and algorithms, and the accuracy metrics of the new model. The Shapley algorithm is used to explain the inner workings of the model. A computer tool as well as a descriptive guide to the mathematical construction of the ANN are provided to aid with model implementation in practice. [ABSTRACT FROM AUTHOR]

Quantum neural networks are neural network models based on the principles of quantum mechanics, a combination of the advantages of classical neural networks and quantum information, using quantum bits instead of neurons in classical neural networks and quantum gates instead of activation functions in classical neural networks. Immune algorithms are a class of algorithms based on the theory of artificial immune systems, which implement functions similar to the biological immune system in terms of antigen recognition, cell differentiation, memory and self-regulation, using a population search strategy and iterative computation to eventually obtain the optimal solution to the problem with a higher probability. Quantum neural networks, one of the most important approaches in the field of quantum machine learning, can be implemented by means of variational quantum circuits. However, the classification training accuracy of variational quantum algorithms is not very high. In this paper, we propose a variational shadow quantum neural network based on the immune optimisation algorithm to classify data in order to improve the training accuracy and also the training speed. Experiments show that the immune optimisation algorithm-based variational shadow quantum neural network can not only improve the training accuracy, but also the training speed. [ABSTRACT FROM AUTHOR]

Artificial neural network is considered to be one of the effective ways to enable soft robots to achieve high-performance control due to their significant advantages, such as massively parallel processing and distributed storage of information, adaptivity, and fault tolerance. Artificial neural networks are composed of microelectronic components connected together, of which the most basic units are artificial neural synaptic units, such as atomic switches, memristors, and synaptic transistors. This paper first introduces the research status of soft robots and artificial neural synapses, predicts the demand of soft robots for artificial neural synapses, summarizes the difficulties and problems that may be encountered in the application of artificial neural synapses to soft robots, and finally points out the importance and feasibility of artificial neural synapses in the research and development of soft robots. [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]

This paper proposes a hybrid forecasting model combining auto-regressive integrated moving average (ARIMA) and artificial neural network (ANN) techniques to improve the software fault forecasting and hence improvising the reliability of software. Software reliability forecasting plays a critical role in software development and maintenance, as it helps to identify potential errors and improve the overall performance of software systems. The proposed model leverages the strengths of both ARIMA and ANN, allowing for more accurate predictions and better handling of complex and dynamic software systems. The effectiveness of the hybrid model is evaluated using real-world software data, demonstrating its superiority over traditional forecasting methods. This research contributes to the development of more robust and reliable software systems, which are essential in today's rapidly evolving technological landscape. [ABSTRACT FROM AUTHOR]

This paper proposes a method for simultaneous evaluation of the assembly process complexity together with the performance of the future product. It allows for product design optimization, considering different aspects of the future design at the early stage of the development process. The proposed method, embodied in a fully automated framework, substitutes the traditional sequential development process with a more efficient and rapid combined procedure, which addresses multiple design aspects simultaneously. Design for assembly (DFA) rules, used as quantitative metrics of the ease-of-assembly of the whole product and individual assembly operations, are automatically evaluated together with performance metrics, estimated based on finite element (FE) simulations. The direct solution to this optimization problem might be inefficient or impossible since it requires the recurrent evaluation of computationally expensive discrete and continuous functions with unknown behavior that represent the optimization objectives and constraints. For that reason, the proposed framework employs regression models based on the Gaussian process and artificial neural networks, thus achieving the optimal design of a product as a result of metamodel-based design optimization (MBDO). The suggested approach is demonstrated in the optimization of a gearbox assembly, considering its mechanical performance and assembly process. Comparing the results of the metamodel-based and direct design optimization shows that MBDO allows finding a better solution using a three times smaller computational budget. In addition, analysis of the results obtained using stationary sampling data sets of different sizes highlighted the limitations of the employed sampling procedure. [ABSTRACT FROM AUTHOR]

Recent research has shown the vulnerability of deep networks to adversarial perturbations. Adversarial training and its variants have been shown to be effective defense algorithms against adversarial attacks, enhancing the defense abilities of deep neural networks by training them to fit adversarial examples. However, the significant computational burden of generating strong adversarial examples has rendered the process time-consuming, presenting a challenge for efficient training. In this paper, we propose adversarial training with robust area (ATRA), a highly efficient variant of adversarial training. We experimentally find that certain pixels in the image play a crucial role in improving robust accuracy, which we refer to the collection of discrete pixels as the high-robust area. Based on the robust area of the input instance, ATRA generates adversarial examples by applying an adaptive perturbation. Furthermore, we investigate the transferability of the high-robust area during the attack iteration process and experimentally demonstrate its effectiveness. Therefore, ATRA has the advantage of reducing the additional cost of generating strong adversarial examples while maintaining model robustness. Our experimental results on MNIST, CIFAR10, and TinyImageNet show that our method outperforms current state-of-the-art baselines with significantly less additional training time required, especially on MNIST where our method requires 18 × less training time. Furthermore, our method also achieves good performance under different adversarial attacks such as FGSM, CW, and AutoAttack. [ABSTRACT FROM AUTHOR]

Deformable linear objects (DLOs), such as rods, cables, and ropes, play important roles in daily life. However, manipulation of DLOs is challenging as large geometrically nonlinear deformations may occur during the manipulation process. This problem is made even more difficult as the different deformation modes (e.g., stretching, bending, and twisting) may result in elastic instabilities during manipulation. In this paper, we formulate a physics-guided data-driven method to solve a challenging manipulation task—accurately deploying a DLO (an elastic rod) onto a rigid substrate along various prescribed patterns. Our framework combines machine learning, scaling analysis, and physical simulations to develop a physics-based neural controller for deployment. We explore the complex interplay between the gravitational and elastic energies of the manipulated DLO and obtain a control method for DLO deployment that is robust against friction and material properties. Out of the numerous geometrical and material properties of the rod and substrate, we show that only three non-dimensional parameters are needed to describe the deployment process with physical analysis. Therefore, the essence of the controlling law for the manipulation task can be constructed with a low-dimensional model, drastically increasing the computation speed. The effectiveness of our optimal control scheme is shown through a comprehensive robotic case study comparing against a heuristic control method for deploying rods for a wide variety of patterns. In addition to this, we also showcase the practicality of our control scheme by having a robot accomplish challenging high-level tasks such as mimicking human handwriting, cable placement, and tying knots. [ABSTRACT FROM AUTHOR]

In this paper, the fixed-time and preassigned-time synchronization issues of fully quaternion-valued fuzzy memristive neural networks are studied based on the dynamic event-triggered control mechanism. Initially, the fuzzy rules are defined within the quaternion domain and the relevant properties are established through rigorous analysis. Subsequently, to conserve resources and enhance the efficiency of the controller, a kind of dynamic event-triggered control mechanism is introduced for the fuzzy memristive neural networks. Based on the non-separation analysis, fixed-time and preassigned-time synchronization criteria are presented and the Zeno phenomenon under the event-triggered mechanism is excluded successfully. Finally, the effectiveness of the theoretical results is verified through numerical simulations. [ABSTRACT FROM AUTHOR]

Spiking neural networks (SNNs) are gaining increasing attention for their biological plausibility and potential for improved computational efficiency. To match the high spatial-temporal dynamics in SNNs, neuromorphic chips are highly desired to execute SNNs in hardware-based neuron and synapse circuits directly. This paper presents a large-scale neuromorphic chip named Darwin3 with a novel instruction set architecture, which comprises 10 primary instructions and a few extended instructions. It supports flexible neuron model programming and local learning rule designs. The Darwin3 chip architecture is designed in a mesh of computing nodes with an innovative routing algorithm. We used a compression mechanism to represent synaptic connections, significantly reducing memory usage. The Darwin3 chip supports up to 2.35 million neurons, making it the largest of its kind on the neuron scale. The experimental results showed that the code density was improved by up to 28.3× in Darwin3, and that the neuron core fan-in and fan-out were improved by up to 4096× and 3072× by connection compression compared to the physical memory depth. Our Darwin3 chip also provided memory saving between 6.8× and 200.8× when mapping convolutional spiking neural networks onto the chip, demonstrating state-of-the-art performance in accuracy and latency compared to other neuromorphic chips. [ABSTRACT FROM AUTHOR]

Brain-inspired computing, drawing inspiration from the fundamental structure and information-processing mechanisms of the human brain, has gained significant momentum in recent years. It has emerged as a research paradigm centered on brain–computer dual-driven and multi-network integration. One noteworthy instance of this paradigm is the hybrid neural network (HNN), which integrates computer-science-oriented artificial neural networks (ANNs) with neuroscience-oriented spiking neural networks (SNNs). HNNs exhibit distinct advantages in various intelligent tasks, including perception, cognition and learning. This paper presents a comprehensive review of HNNs with an emphasis on their origin, concepts, biological perspective, construction framework and supporting systems. Furthermore, insights and suggestions for potential research directions are provided aiming to propel the advancement of the HNN paradigm. [ABSTRACT FROM AUTHOR]

Purpose: The macular ganglion cell layer (mGCL) is a strong potential biomarker of axonal degeneration in multiple sclerosis (MS). For this reason, this study aims to develop a computer‐aided method to facilitate diagnosis and prognosis in MS. Methods: This paper combines a cross‐sectional study of 72 MS patients and 30 healthy control subjects for diagnosis and a 10‐year longitudinal study of the same MS patients for the prediction of disability progression, during which the mGCL was measured using optical coherence tomography (OCT). Deep neural networks were used as an automatic classifier. Results: For MS diagnosis, greatest accuracy (90.3%) was achieved using 17 features as inputs. The neural network architecture comprised the input layer, two hidden layers and the output layer with softmax activation. For the prediction of disability progression 8 years later, accuracy of 81.9% was achieved with a neural network comprising two hidden layers and 400 epochs. Conclusion: We present evidence that by applying deep learning techniques to clinical and mGCL thickness data it is possible to identify MS and predict the course of the disease. This approach potentially constitutes a non‐invasive, low‐cost, easy‐to‐implement and effective method. [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]

Intelligent rice disease recognition methods based on deep neural networks can predict the degree of disease on the basis of, for example, the number of disease spots on an image, so that preventive measures can be taken. Currently, intelligent recognition methods for rice diseases suffer from the disadvantages of poor versatility and low accuracy. This paper uses eight common image classification networks to classify and identify four rice diseases. ResNet50 was selected as the feature extraction network and an enhanced feature fusion and target adaptive network (EFFTAN), referred to as EFFTAN, is proposed. The EFFTAN was used to detect four rice spot diseases in the rice leaf disease image samples dataset; the mean average precision of the final detection was 95.3%, and effective detection was also achieved for the dense spot features. [ABSTRACT FROM AUTHOR]