Search

The traditional method for transformer moisture diagnosis is to establish empirical equations between feature parameters extracted from frequency domain spectroscopy (FDS) and the transformer’s moisture content. However, the established empirical equation may not be applicable to a novel testing environment, resulting in an unreliable evaluation result. In this regard, it is acknowledged that FDS combined with machine learning is more suitable for estimating moisture content in a variety of test environments. Nonetheless, the accuracy of the estimation results obtained using the existing method is limited by the algorithm’s inability to generalize. To address this issue, we propose an AdaBoost algorithm-enhanced back-propagation neural network (BP_AdaBoost). This study creates a database by extracting feature parameters from the FDS that characterize the insulation states of the prepared samples. Then, using the BP_AdaBoost algorithm and the newly constructed database, the moisture estimation models are trained. Finally, the results of the estimation are discussed in terms of laboratory and field transformers. By comparing the proposed BP_AdaBoost algorithm to other intelligence algorithms, it is demonstrated that it not only performs better in generalization, but also maintains a high level of accuracy. [ABSTRACT FROM AUTHOR]

In the petroleum and coal industries, digital image technology and acoustic emission technology are employed to study rock properties, but both exhibit flaws during data processing. Digital image technology is vulnerable to interference from fractures and scaling, leading to potential loss of image data; while acoustic emission technology is not hindered by these issues, noise from rock destruction can interfere with the electrical signals, causing errors. The monitoring errors of these techniques can undermine the effectiveness of rock damage analysis. To address this issue, this paper focuses on the restoration of image data acquired through digital image technology, leveraging deep learning techniques, and using soft and hard rocks made of similar materials as research subjects, an improved Incremental Transformer image algorithm is employed to repair distorted or missing strain nephograms during uniaxial compression experiments. The concrete implementation entails using a comprehensive training set of strain nephograms derived from digital image technology, fabricating masks for absent image segments, and predicting strain nephograms with full strain detail. Additionally, we adopt deep separable convolutional networks to optimize the algorithm's operational efficiency. Based on this, the analysis of rock damage is conducted using the repaired strain nephograms, achieving a closer correlation with the actual physical processes of rock damage compared to conventional digital image technology and acoustic emission techniques. The improved incremental Transformer algorithm presented in this paper will contribute to enhancing the efficiency of digital image technology in the realm of rock damage, saving time and money, and offering an innovative approach to traditional rock damage analysis. [ABSTRACT FROM AUTHOR]

Train wheels are crucial components for ensuring the safety of trains. The accurate and fast identification of wheel tread defects is necessary for the timely maintenance of wheels, which is essential for achieving the premise of conditional repair. Image-based detection methods are commonly used for detecting tread defects, but they still have issues with the misdetection of water stains and the leaking of small defects. In this paper, we address the challenges posed by the detection of wheel tread defects by proposing improvements to the YOLOv8 model. Firstly, the impact of water stains on tread defect detection is avoided by optimising the structure of the detection layer. Secondly, an improved SPPCSPC module is introduced to enhance the detection of small targets. Finally, the SIoU loss function is used to accelerate the convergence speed of the network, which ensures defect recognition accuracy with high operational efficiency. Validation was performed on the constructed tread defect dataset. The results demonstrate that the enhanced YOLOv8 model in this paper outperforms the original network and significantly improves the tread defect detection indexes. The average precision, accuracy, and recall reached 96.95%, 96.30%, and 95.31%. [ABSTRACT FROM AUTHOR]

This study aims to present a comparative analysis of the Bayesian regularization backpropagation and Levenberg–Marquardt training algorithms in neural networks for the metrics prediction of damaged archaeological artifacts, of which the state of conservation is often fragmented due to different reasons, such as ritual, use wear, or post-depositional processes. The archaeological artifacts, specifically laminar blanks (so-called blades), come from different sites located in the Southern Levant that belong to the Pre-Pottery B Neolithic (PPNB) (10,100/9500–400 cal B.P.). This paper shows the entire procedure of the analysis, from its normalization of the dataset to its comparative analysis and overfitting problem resolution. [ABSTRACT FROM AUTHOR]

Photocatalysts have made great contributions to the degradation of pollutants to achieve environmental purification. The traditional method of developing new photocatalysts is to design and perform a large number of experiments to continuously try to obtain efficient photocatalysts that can degrade pollutants, which is time-consuming, costly, and does not necessarily achieve the best performance of the photocatalyst. The rapid development of photocatalysis has been accelerated by the rapid development of artificial intelligence. Intelligent algorithms can be utilized to design photocatalysts and predict photocatalytic performance, resulting in a reduction in development time and the cost of new catalysts. In this paper, the intelligent algorithms for photocatalyst design and photocatalytic performance prediction are reviewed, especially the artificial neural network model and the model optimized by an intelligent algorithm. A detailed discussion is given on the advantages and disadvantages of the neural network model, as well as its application in photocatalysis optimized by intelligent algorithms. The use of intelligent algorithms in photocatalysis is challenging and long term due to the lack of suitable neural network models for predicting the photocatalytic performance of photocatalysts. The prediction of photocatalytic performance of photocatalysts can be aided by the combination of various intelligent optimization algorithms and neural network models, but it is only useful in the early stages. Intelligent algorithms can be used to design photocatalysts and predict their photocatalytic performance, which is a promising technology. [ABSTRACT FROM AUTHOR]

With the increasing complexity of building structures and interior materials, the danger of indoor fires has become more severe. It is effective to improve the accuracy and timeliness of fire-sensing devices in order to reduce the harm caused by fires. This paper focuses on the temporal characteristics of sensor information, creatively introducing second-order exponential smoothing into the information fusion algorithm. The RNN structure is used to fit the formula and adaptively trained with various types of fire data. Experimental results show that the proposed algorithm achieves an accuracy of 98% in fire recognition, significantly improving the accuracy of fire recognition. To avoid the issue of imbalanced positive and negative samples, this paper comprehensively evaluates parameters such as F1-score and Matthews correlation coefficient (MCC). The achieved scores are 0.97 and 0.95, respectively, indicating the algorithm's good performance in detecting the presence or absence of fire. Furthermore, the proposed algorithm is tested for its alarm time. The experimental results show that the proposed algorithm can timely identify various types of fires and can give an alarm earlier than traditional fire alarms. [ABSTRACT FROM AUTHOR]

This paper proposes a robust identification and control-based on a neural network method for a Twin Rotor Multivariable System (TRMS) using a recursive adaptive training algorithm. The algorithm is based on a recursive least squares approach with an additional steepest descent stage. An Adaline neural network is used for modeling the system, and a robust structure is selected based on a linear auto-regressive structure with exogenous inputs (ARX) related to the estimation error. The identification is performed online and the system is controlled under a polynomial structure by pole placement with a dead-beat strategy. The method is evaluated in terms of estimation and tracking error in the presence of external additive disturbances, parametric disturbances, and sinusoidal reference signals. The Root-Mean Square Error (RMSE) is used to evaluate the estimation performance and the Integral-Time Absolute Error (ITAE) is used to evaluate the tracking performance. As a result, a novel robust controller based on a neural network is designed where the best results are obtained for a training recursive least squares algorithm with an additional steepest descent stage. [ABSTRACT FROM AUTHOR]

Hybrid approaches combining machine learning with traditional inverse problem solution methods represent a promising direction for the further development of inverse modeling algorithms. The paper proposes an approach to emission source identification from measurement data for advection–diffusion–reaction models. The approach combines general-type source identification and post-processing refinement: first, emission source identification by measurement data is carried out by a sensitivity operator-based algorithm, and then refinement is done by incorporating a priori information about unknown sources. A general-type distributed emission source identified at the first stage is transformed into a localized source consisting of multiple point-wise sources. The second, refinement stage consists of two steps: point-wise source localization and emission rate estimation. Emission source localization is carried out using deep learning with convolutional neural networks. Training samples are generated using a sensitivity operator obtained at the source identification stage. The algorithm was tested in regional remote sensing emission source identification scenarios for the Lake Baikal region and was able to refine the emission source reconstruction results. Hence, the aggregates used in traditional inverse problem solution algorithms can be successfully applied within machine learning frameworks to produce hybrid algorithms. [ABSTRACT FROM AUTHOR]

With the improvement of digital image display technology, the "secondary imaging" caused by digital cameras is also gradually popularized, and the quality of the recaptured image formed by this imaging is also getting higher and higher, and this kind of high-quality fake image has caused great threat to digital images security. We propose a neural network-based recaptured image identification algorithm and use the difference between two types of images to build the identification algorithm in the frequency domain. The algorithm uses filtering to obtain the feature images which are the high-frequency and low-frequency filtering images, in order to further distinguish the image differences, the direction of the filtered image obtained from high-frequency images, each direction of the filtered image contains high-frequency information at different angles, and the low-frequency image is downsampled. At the same time, the low-frequency image is downsampled to obtain a multi-scale filtered image. The algorithm extracts the features from previous images as the feature values for classification, and finally uses neural networks for classification to obtain the classification results, and these prove that the algorithm presented is able to differentiate the recaptured images effectively in this paper. [ABSTRACT FROM AUTHOR]

Finding all the roots of a nonlinear equation is an important and difficult task that arises naturally in numerous scientific and engineering applications. Sequential iterative algorithms frequently use a deflating strategy to compute all the roots of the nonlinear equation, as rounding errors have the potential to produce inaccurate results. On the other hand, simultaneous iterative parallel techniques require an accurate initial estimation of the roots to converge effectively. In this paper, we propose a new class of global neural network-based root-finding algorithms for locating real and complex polynomial roots, which exploits the ability of machine learning techniques to learn from data and make accurate predictions. The approximations computed by the neural network are used to initialize two efficient fractional Caputo-inverse simultaneous algorithms of convergence orders ς + 2 and 2 ς + 4 , respectively. The results of our numerical experiments on selected engineering applications show that the new inverse parallel fractional schemes have the potential to outperform other state-of-the-art nonlinear root-finding methods in terms of both accuracy and elapsed solution time. [ABSTRACT FROM AUTHOR]

Multimedia data is crucial in the military, medical, forensics, social, etc., to transmit a large amount of data. Security of this sensitive information is the primary issue. This paper uses Latin square and machine learning techniques such as neural networks and genetic algorithm to design an image encryption algorithm. A new neural network-based pseudorandom number generator is proposed to generate a chaotic sequence for various applications. Encryption key images are designed using Latin squares in the finite field. Further, the Latin squares are XOR with the input matrix to get the encrypted images. The proposed algorithm is iterated a finite number of times to generate a cipher image population. Randomly two parents are chosen from the generated population, and row and column arrangements produce offspring. A genetic algorithm is the optimization technique used for the best encrypted image search. The pixel correlation value serves as a fitness function. Finally, the least correlated cipher image is obtained from the genetic algorithm applied to the parent and offspring of the population generated from the encryption algorithm. The simulation results from the proposed image encryption model surpass many communication channel attacks and perform better when compared to existing image security algorithms. [ABSTRACT FROM AUTHOR]

Simple Summary: Melanoma is the most dangerous type of skin cancer worldwide. Early detection of melanoma is crucial for better outcomes, but this often can be challenging. This research explores the use of artificial intelligence (AI) techniques combined with non-invasive imaging methods to improve melanoma detection. The authors aim to evaluate the current state of AI-based techniques using tools including dermoscopy, optical coherence tomography (OCT), and reflectance confocal microscopy (RCM). The findings demonstrate that several AI algorithms perform as well as or better than dermatologists in detecting melanoma, particularly in the analysis of dermoscopy images. This research highlights the potential of AI to enhance diagnostic accuracy, leading to improved patient outcomes. Further studies are needed to address limitations and ensure the reliability and effectiveness of AI-based techniques. Background: Melanoma, the deadliest form of skin cancer, poses a significant public health challenge worldwide. Early detection is crucial for improved patient outcomes. Non-invasive skin imaging techniques allow for improved diagnostic accuracy; however, their use is often limited due to the need for skilled practitioners trained to interpret images in a standardized fashion. Recent innovations in artificial intelligence (AI)-based techniques for skin lesion image interpretation show potential for the use of AI in the early detection of melanoma. Objective: The aim of this study was to evaluate the current state of AI-based techniques used in combination with non-invasive diagnostic imaging modalities including reflectance confocal microscopy (RCM), optical coherence tomography (OCT), and dermoscopy. We also aimed to determine whether the application of AI-based techniques can lead to improved diagnostic accuracy of melanoma. Methods: A systematic search was conducted via the Medline/PubMed, Cochrane, and Embase databases for eligible publications between 2018 and 2022. Screening methods adhered to the 2020 version of the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. Included studies utilized AI-based algorithms for melanoma detection and directly addressed the review objectives. Results: We retrieved 40 papers amongst the three databases. All studies directly comparing the performance of AI-based techniques with dermatologists reported the superior or equivalent performance of AI-based techniques in improving the detection of melanoma. In studies directly comparing algorithm performance on dermoscopy images to dermatologists, AI-based algorithms achieved a higher ROC (>80%) in the detection of melanoma. In these comparative studies using dermoscopic images, the mean algorithm sensitivity was 83.01% and the mean algorithm specificity was 85.58%. Studies evaluating machine learning in conjunction with OCT boasted accuracy of 95%, while studies evaluating RCM reported a mean accuracy rate of 82.72%. Conclusions: Our results demonstrate the robust potential of AI-based techniques to improve diagnostic accuracy and patient outcomes through the early identification of melanoma. Further studies are needed to assess the generalizability of these AI-based techniques across different populations and skin types, improve standardization in image processing, and further compare the performance of AI-based techniques with board-certified dermatologists to evaluate clinical applicability. [ABSTRACT FROM AUTHOR]

There is a trend to deploy neural network on edge devices in recent years. While the mainstream of research often concerns with single edge device processing and edge-cloud two-layer neural network collaborative computing, in this paper, we propose partitioning multi-layer edge network for neural network collaborative computing. With the proposed method, sub-models of neural network are deployed on multi-layer edge devices along the communication path from end users to cloud. Firstly, we propose an optimal path selection method to form a neural network collaborative computing path with lowest communication overhead. Secondly, we establish a time-delay optimization mathematical model to evaluate the effects of different partitioning solutions. To find the optimal partition solution, an ordered elitist genetic algorithm (OEGA) is proposed. The experimental results show that, compared with traditional cloud computing, single-device edge computing and edge-cloud collaborative computing, the proposed multi-layer edge network collaborative computing has a smaller runtime delay with limited bandwidth resources, and because of the pipeline computing characteristics, the proposed method has a better response speed when processing large number of requests. Meanwhile, the OEGA algorithm has better performance than conventional methods, and the optimized partitioning method outperforms other methods like random and evenly partition. [ABSTRACT FROM AUTHOR]

As a novel neural network learning framework, Twin Extreme Learning Machine (TELM) has received extensive attention and research in the field of machine learning. However, TELM is affected by noise or outliers in practical applications so that its generalization performance is reduced compared to robust learning algorithms. In this paper, we propose two novel distance metric optimization-driven robust twin extreme learning machine learning frameworks for pattern classification, namely, CWTELM and FCWTELM. By introducing the robust Welsch loss function and capped L 2 , p -distance metric, our methods reduce the effect of outliers and improve the generalization performance of the model compared to TELM. In addition, two efficient iterative algorithms are designed to solve the challenges brought by the non-convex optimization problems CWTELM and FCWTELM, and we theoretically guarantee their convergence, local optimality, and computational complexity. Then, the proposed algorithms are compared with five other classical algorithms under different noise and different datasets, and the statistical detection analysis is implemented. Finally, we conclude that our algorithm has excellent robustness and classification performance. [ABSTRACT FROM AUTHOR]

• Distinct DG Output Modes Validation: The simulation validates distinct DG output modes, impacting prediction. • Mode-Based State Estimation: The paper proposes an innovative mode-based state estimation using IPSO-DBSCAN clustering, overcoming k-means limitations. • Enhanced Data Recovery using DBSCAN: Enhanced data recovery employs DBSCAN with improved secondary clustering, guided by similarity and homogeneity, outperforming traditional methods. • BiGRU-PF State Estimation: BiGRU-PF enhances state estimation accuracy and robustness in distribution networks by detecting DG output modes, addressing k-means limitations, and improving data recovery. This paper proposes a new forecasting-aided state estimation (FASE) method for distribution systems that mitigates issues with uncertain distributed generation (DG) and lost measurements. We utilize an Improved Particle Swarm Optimization (IPSO)-optimized Density-Based Spatial Clustering of Applications with Noise (DBSCAN) for examination of historical DG output data. Based on identified DG output modes, it facilitates precise state prediction and data reconstruction,. The proposed method employs a Bidirectional Gated Recurrent Unit (BiGRU) neural network for state prediction and a particle filter (PF) for final state filtering. The method verification is provided through Python simulations of the Distribution Transformer Unit (DTU)7k distribution network system, demonstrating improved accuracy and robustness against sudden load change and bad data in measurements. [ABSTRACT FROM AUTHOR]

Threshold-based methods are prevalent across numerous domains, with specific relevance to image binarization, which traditionally employs global and local threshold algorithms. This paper presents a novel approach to image binarization, where the capacity of neural networks is utilized not just for determining optimal thresholds, but also for combining multiple global thresholds sourced from existing binarization techniques. The primary objective of our method is to develop a robust binarization strategy capable of managing a wide array of image conditions. By integrating the strengths of various thresholding techniques, our approach aims to establish a significant connection between traditional thresholding methods and those underpinned by deep learning. [ABSTRACT FROM AUTHOR]

Orbit determination (OD) for spacecraft with unknown maneuver is always a challenging task. This paper proposes a novel framework for efficiently solving continuously maneuvering spacecraft OD problems by merging the Long Short-Term Memory (LSTM) neural network and the filter algorithms. A polynomial-representation fitted the unknown continuous maneuver is first proposed. Rather than directly output the estimated maneuver, the LSTM is trained to detect the unknown maneuver and then estimate the coefficients of the polynomial-representation. Then a fusion is designed to combine the prediction of the LSTM and the estimation of the filter for a more accurate estimation. The proposed LSTM-based framework is successfully applied to solve a Low-Earth-orbit OD problem and a Middle-Earth-orbit OD problem. The continuously maneuvering target is well tracked and the unknown maneuver is accurately estimated. Numerical simulations show that the LSTM trained based on one training dataset can also be applied to other scenarios that share some common features with the training dataset. • A framework for solving maneuvering spacecraft OD problems is proposed. • A polynomial-representation is used to fit the unknown maneuver. • A fusion strategy is designed to combine the predictions of the LSTM and estimations of the filter. [ABSTRACT FROM AUTHOR]

CRC-aided successive cancellation list (CA-SCL) decoding is a powerful algorithm that dramatically improves the error performance of polar codes. Path selection is a major issue that affects the decoding latency of SCL decoders. Generally, path selection is implemented using a metric sorter, which causes its latency to increase as the list grows. In this paper, intelligent path selection (IPS) is proposed as an alternative to the traditional metric sorter. First, we found that in the path selection, only the most reliable paths need to be selected, and it is not necessary to completely sort all paths. Second, based on a neural network model, an intelligent path selection scheme is proposed, including a fully connected network construction, a threshold and a post-processing unit. Simulation results show that the proposed path-selection method can achieve comparable performance gain to the existing methods under SCL/CA-SCL decoding. Compared with the conventional methods, IPS has lower latency for medium and large list sizes. For the proposed hardware structure, IPS's time complexity is O (k log 2 (L)) where k is the number of hidden layers of the network and L is the list size. [ABSTRACT FROM AUTHOR]

Effective recognition of tags in the dynamic measurement system would significantly improve the reading performance of the tag group, but the blurred outline and appearance of tag images captured in motion seriously limit the effectiveness of the existing tag group recognition. Thus, this paper proposes passive tag group recognition in the dynamic environment based on motion blur estimation and improved YOLOv2. Firstly, blur angles are estimated with a Gabor filter, and blur lengths are estimated through nonlinear modelling of a Generalized Regression Neural Network (GRNN). Secondly, tag recognition based on YOLOv2 improved by a Gaussian algorithm is proposed. The features of the tag group are analyzed by the Gaussian algorithm, the region of interest of the dynamic tag is effectively framed, and the tag foreground is extracted; Secondly, the data set of tag groups are trained by the end-to-end YOLOv2 algorithm for secondary screening and recognition, and finally the specific locations of tags are framed to meet the effective identification of tag groups in different scenes. A considerable number of experiments illustrate that the fusion algorithm can significantly improve recognition accuracy. Combined with the reading distance, the research presented in this paper can more accurately optimize the three-dimensional structure of the tag group, improve the reading performance of the tag group, and avoid the interference and collision of tags in the communication channel. Compared with the previous template matching algorithm, the tag group recognition ability put forward in this paper is improved by at least 13.9%, and its reading performance is improved by at least 6.2% as shown in many experiments. [ABSTRACT FROM AUTHOR]

This paper investigates the stochastic optimization problem focusing on developing scalable parallel algorithms for deep learning tasks. Our solution involves a reformation of the objective function for stochastic optimization in neural network models, along with a novel parallel computing strategy, coined the weighted aggregating stochastic gradient descent (WASGD). Following a theoretical analysis on the characteristics of the new objective function, WASGD introduces a decentralized weighted aggregating scheme based on the performance of local workers. Without any center variable, the new method automatically gauges the importance of local workers and accepts them by their contributions. Furthermore, we have developed an enhanced version of the method, WASGD+, by (1) implementing a designed sample order and (2) upgrading the weight evaluation function. To validate the new method, we benchmark our pipeline against several popular algorithms including the state-of-the-art deep neural network classifier training techniques (e.g., elastic averaging SGD). Comprehensive validation studies have been conducted on four classic datasets: CIFAR-100, CIFAR-10, Fashion-MNIST, and MNIST. Subsequent results have firmly validated the superiority of the WASGD scheme in accelerating the training of deep architecture. Better still, the enhanced version, WASGD+, is shown to be a significant improvement over its prototype. [ABSTRACT FROM AUTHOR]

In today's shopping platform, some enterprises can use all commercial means to obtain users' personal information. How to protect the privacy of consumers has become an important issue. This paper discusses the shortcomings of the traditional neural network algorithm, and puts forward some countermeasures to improve it. Based on the basic principle of standard neural network, a new improved algorithm is developed according to the needs of this paper. The basic principle of the algorithm is based on the added momentum method. This paper mainly uses data models to collect and organize user data through user behavior patterns, so as to prove that the record of target user data cannot predict the possibility of user transportation and consumption, so as to better promote the improvement of transactions and services through these data models. [ABSTRACT FROM AUTHOR]

This paper presents a method of high-capacity and transparent watermarking based on the usage of deep neural networks with the adjustable subsquares properties algorithm to encode the data of a watermark in high-quality video using the H.265/HEVC (High-Efficiency Video Coding) codec. The aim of the article is to present a method of embedding a watermark in a video with HEVC codec compression by making changes in a video in a way that is not noticeable to the naked eye. The method presented here is characterised by focusing on ensuring the accuracy of the original image in relation to the watermarked image, providing the transparency of the embedded watermark, while ensuring its survival after compression by the HEVC codec. The article includes a presentation of the practical results of watermark embedding with a built-in variation mechanism of its capacity and resistance, thanks to the adjustable subsquares properties algorithm. The obtained PSNR (peak signal-to-noise ratio) results are at the level of 40 dB or better. There is the possibility of the complete recovery of a watermark from a single frame compressed in the CRF (constant rate factor) range of up to 16, resulting in a BER (bit error rate) equal to 0 for the received watermark. [ABSTRACT FROM AUTHOR]

Depression has gradually become the most common mental disorder in the world. The accuracy of its diagnosis may be affected by many factors, while the primary diagnosis seems to be difficult to define. Finding a way to identify depression by satisfying both objective and effective conditions is an urgent issue. In this paper, a strategy for predicting depression based on spatiotemporal features is proposed, and is expected to be used in the auxiliary diagnosis of depression. Firstly, electroencephalogram (EEG) signals were denoised through the filter to obtain the power spectra of the three corresponding frequency ranges, Theta, Alpha and Beta. Using orthogonal projection, the spatial positions of the electrodes were mapped to the brainpower spectrum, thereby obtaining three brain maps with spatial information. Then, the three brain maps were superimposed on a new brain map with frequency domain and spatial characteristics. A Convolutional Neural Network (CNN) and Gated Recurrent Unit (GRU) were applied to extract the sequential feature. The proposed strategy was validated with a public EEG dataset, achieving an accuracy of 89.63% and an accuracy of 88.56% with the private dataset. The network had less complexity with only six layers. The results show that our strategy is credible, less complex and useful in predicting depression using EEG signals. [ABSTRACT FROM AUTHOR]

In order to improve the accuracy of visual SLAM algorithms in a dynamic scene, instance segmentation is widely used to eliminate dynamic feature points. However, the existing segmentation technology has low accuracy, especially for the contour of the object, and the amount of calculation of instance segmentation is large, limiting the speed of visual SLAM based on instance segmentation. Therefore, this paper proposes a contour optimization hybrid dilated convolutional neural network (CO-HDC) algorithm, which can perform a lightweight calculation on the basis of improving the accuracy of contour segmentation. Firstly, a hybrid dilated convolutional neural network (HDC) is used to increase the receptive field, which is defined as the size of the region in the input that produces the feature. Secondly, the contour quality evaluation (CQE) algorithm is proposed to enhance the contour, retaining the highest quality contour and solving the problem of distinguishing dynamic feature points from static feature points at the contour. Finally, in order to match the mapping speed of visual SLAM, the Beetle Antennae Search Douglas–Peucker (BAS-DP) algorithm is proposed to lighten the contour extraction. The experimental results have demonstrated that the proposed visual SLAM based on the CO-HDC algorithm performs well in the field of pose estimation and map construction on the TUM dataset. Compared with ORB-SLAM2, the Root Mean Squared Error (Rmse) of the proposed method in absolute trajectory error is about 30 times smaller and is only 0.02 m. [ABSTRACT FROM AUTHOR]

In the modern era, lack of adequate training data requires lexicon-based models. The lexicon scoring model was extensively deployed as an effective and convenient substitute by the majority of practitioners and researchers. Usually, the entire sentiment of the document is portrayed by leading polarity (i.e., negative or positive) among the indicators. The efficiency of the conventional lexicons is however quite imperfect when employed to novel issues. This paper intends to propose a new "Intelligent Senti-net based lexicon generation method," which guarantees the classification of sentiments in social media. The proposed sentiment classification model is performed through certain steps (i) pre-processing (ii) keyword extraction (iii) holoentropy-based lexicon construction (iv) feature extraction (semantic similarity) (v) classification (vi) feedback process and (vii) sentiment classification from Int SentiNet. For classification purposes, neural network (NN) is used. To make the classification more accurate, the training of NN is carried out using a new Improved Sealion (SLnO) algorithm named Self-Improved SLnO via optimizing the weights. In the end, simulation is done to validate the enhancement of the presented scheme over traditional schemes. [ABSTRACT FROM AUTHOR]

Multi‐label classification algorithms deal with classification problems where a single datapoint can be classified (or labelled) with more than one class (or label) at the same time. Early multi‐label approaches like binary relevance consider each label individually and train individual binary classifier models for each label. State‐of‐the‐art algorithms like RAkEL, classifier chains, calibrated label ranking, IBLR‐ML+, and BPMLL also consider the associations between labels for improved performance. Like most machine learning algorithms, however, these approaches require careful hyper‐parameter tuning, a computationally expensive optimisation problem. There is a scarcity of multi‐label classification algorithms that require minimal hyper‐parameter tuning. This paper addresses this gap in the literature by proposing CascadeML, a multi‐label classification method based on the existing cascaded neural network architecture, which also takes label associations into consideration. CascadeML grows a neural network architecture incrementally (deep as well as wide) in a two‐phase process as it learns network weights using an adaptive first‐order gradient descent algorithm. This omits the requirement of preselecting the number of hidden layers, nodes, activation functions, and learning rate. The performance of the CascadeML algorithm was evaluated using 13 multi‐label datasets and compared with nine existing multi‐label algorithms. The results show that CascadeML achieved the best average rank over the datasets, performed better than BPMLL (one of the earliest well known multi‐label specific neural network algorithms), and was similar to the state‐of‐the‐art classifier chains and RAkEL algorithms. [ABSTRACT FROM AUTHOR]

This paper presents machine learning valley-filling (MLVF) to enhance plug-in electric vehicle (PEV) charging at the local power level while minimizing the effects of uncontrolled PEV charging. This study investigated whether a neural network algorithm could learn to identify when to begin charging a PEV by distinguishing low and high demand sections in the forecasted baseload. The results indicate that a neural network algorithm can indeed identify low and high demand sections in the forecasted baseload and learn when to begin charging electric vehicles to decrease demand loads. MLVF achieved a microaveraged F1 score, an indicator of a classifier's overall accuracy, of 92.84% of selecting the correct timeslot to initiate charging. [ABSTRACT FROM AUTHOR]

For measuring the efficiency of workflow scheduling, determining makespan and execution cost is essential. As estimating makespan and cost is difficult in a Cloud environment, designing an efficient computation of workflow scheduling remains a challenge. The Cloud resources are scaled up and down in accordance with user demand by following a scheduling policy. The scalability of the work environment is achieved through the virtualization process. Based on system experience, this paper proposes the priority-based backfilling backpropagation neural network (PBF-NN) hybrid scheduling algorithm for measuring makespan and execution cost accurately. The backfill algorithm is used to schedule tasks to the available resources. The percentage of migration is reduced when this algorithm is used compared to the First Come First Serve algorithm. Then, the Berger model is used to measure the fairness of resource allocation. The system decides task reallocation based on the fairness value. The backpropagation neural network handles the virtual machine placement process with necessary training and testing. The proposed algorithm dynamically allocates the tasks and reduces the utilization of resources. We use an experimental study to illustrate how the proposed system enables higher efficiency in cost, makespan, and performance. [ABSTRACT FROM AUTHOR]

Efficient control of the process of jigging ore of small and fine grain allows avoiding the loss of valuable material in production residual. Due to the multi-dimensionality and multiconnectivity of this enrichment process, classical control methods do not allow achieving the maximum technological indicators of enrichment. This paper proposes investigating intelligent algorithms for controlling the jigging process, which determine the key variables - the level of the natural «bed» and the ripple frequency of the jigging machine. Algorithms are developed using fuzzy logic, neural and hybrid networks. The adequacy of intelligent algorithms was evaluated using the following criteria: correlation of expert and model values (R); Root Mean Square Error (RMSE); Mean absolute percentage error (MAPE). To assess the adequacy of the obtained algorithms, a test sample of input variables, different from the training one, was compiled. As a consequence, we determined an algorithm that gives a minimal discrepancy between the calculated and experimental data. [ABSTRACT FROM AUTHOR]

Abstract In the last 20 years, and in particular in the last decade, the availability of propagation data for GNSS has increased substantially. In this sense, the ionosphere has been sounded with a large number of receivers that provide an enormous amount of ionospheric data. Moreover, the maturity of the models has also been increased in the same period of time. As an example, IGS has ionospheric maps from GNSS data back to 1998, which would allow for the correlation of these data with other quantities relevant for the user and space weather (such as Solar Flux and Kp). These large datasets would account for almost half a billion points to be analyzed. With the advent and explosion of Big Data algorithms to analyze large databases and find correlations with different kinds of data, and the availability of open source code libraries (for example, the TensorFlow libraries from Google that are used in this paper), the possibility of merging these two worlds has been widely opened. In this paper, a proof of concept for a single frequency correction algorithm based in GNSS GIM vTEC and Fully Connected Neural Networks is provided. Different Neural Network architectures have been tested, including shallow (one hidden layer) and deep (up to five hidden layers) Neural Network models. The error in training data of such models ranges from 50% to 1% depending on the architecture used. Moreover, it is shown that by adjusting a Neural Network with data from 2005 to 2009 but tested with data from 2016 to 2017, Neural Network models could be suitable for the forecast of vTEC for single frequency users. The results indicate that this kind of model can be used in combination with the Galileo Signal-in-Space (SiS) NeQuick G parameters. This combination provides a broadcast model with equivalent performances to NeQuick G and better than GPS ICA for the years 2016 and 2017, showing a 3D position Root Mean Squared (RMS) error of approximately 2 m. [ABSTRACT FROM AUTHOR]

In this paper, by incorporating the neural network into an adaptive dynamic surface control (DSC) framework, a neural adaptive DSC algorithm is developed for a class of uncertain nonlinear system to ensure the asymptotic output tracking. Neural network is used to approximate the unknown nonlinear term in the system such that the requirements for known nonlinear term in control laws design procedure are released. In order to eliminate the boundary layer effects, which are caused by the linear filters at each step in the DSC procedure, the nonlinear filters with the compensation term are designed skillfully. The proposed neural adaptive DSC algorithm not only avoids the inherent problem of "explosion of complexity" in the backstepping procedure, but also has its own advantages: (1) releasing the requirements for known nonlinear term in control laws design procedure; (2) holding the asymptotic output tracking performance. Some simulations are shown to demonstrate the effectiveness and advantages of the proposed controller. [ABSTRACT FROM AUTHOR]

In this paper, a hybrid weight design and optimization mechanism is proposed to ensure a better application effect in the multi-level weighted evaluation/optimization process of intelligent neural network (NN) guidance algorithm. According to different target tracking scenarios, the tracking index are divided into different periods, a single period score is given according to a linear-nonlinear hybrid scoring mechanism. Furthermore, in a single index, the internal scores of different time periods are weighted and fused for the second time to obtain the index overall score. Finally, the third weighted fusion of the multi-index scores is used to obtain the comprehensive score of the algorithm. Design the algorithm parameter evaluation case sets, repeat the above compound weighting, obtain the case with the highest comprehensive score. Finally, the algorithm is optimized by the highest score case. In the hybrid weight design mechanism, the objective grey correlation first defines the weight range, then the subjective expert decision method with local extreme expert elimination and standard deviation global test for double optimization finally ensures the weight reliability of the hierarchical evaluation optimization. The evaluation optimization experiment using fuzzy NN radar seeker verifies the effectiveness of the method. [ABSTRACT FROM AUTHOR]

Sustainability is the major issue of small and medium sized enterprises (SMEs) all across the globe. Although SMEs contribute to GDP of any country their negative contribution to environment is also significant. Prior studies on SMEs' sustainability mainly classified into three categories—the correlation between environmental and social practices with economic performance, sustainable supply chain performance measurement, and empirical research on sustainability practices. There is no study that objectively derives the sustainable structure of SMEs through optimal combination of sustainability practices (inputs) and performance (outputs). Therefore, the main objective of this paper is to generate optimal structure of sustainable SMEs by combining neural network and particle swarm algorithm while considering Multi-Objective framework. The study uses data from 54 SMEs of Normandy in France and 30 SMEs of Midlands in the UK. The data was gathered through questionnaire survey. As we do not have the explicit expression of our objective functions, we train a neural network on our databases in order to enable the generation of value of the different objectives for any profile. We design and run a multi-objective version of particle swarm optimization (MPSO) to generate efficient companies' structures. The weighted sum method is then used for different weights. The comparison of observed data and the results of the PSO analysis facilitates to derive improvement measures for each individual SME. [ABSTRACT FROM AUTHOR]

In this paper, a deep reinforcement learning-based robust control strategy for quadrotor helicopters is proposed. The quadrotor is controlled by a learned neural network which directly maps the system states to control commands in an end-to-end style. The learning algorithm is developed based on the deterministic policy gradient algorithm. By introducing an integral compensator to the actor-critic structure, the tracking accuracy and robustness have been greatly enhanced. Moreover, a two-phase learning protocol which includes both offline and online learning phase is proposed for practical implementation. An offline policy is first learned based on a simplified quadrotor model. Then, the policy is online optimized in actual flight. The proposed approach is evaluated in the flight simulator. The results demonstrate that the offline learned policy is highly robust to model errors and external disturbances. It also shows that the online learning could significantly improve the control performance. [ABSTRACT FROM AUTHOR]

This paper presents a machine learning based model for control of local bioaerosol concentration via a forced corner flow with optimal energy efficiency in an indoor environment. A recirculation zone determined by the inlet flow rate traps particles partially with one or more vortices around the corner. The profile of the recirculation zone is then determined mathematically by the minimum net mass flux principle with a grid search technique. Subsequently, the variation of the recirculation zone profile is then learned through a neural network (NN), in which data is collected from the simulation by the Eulerian–Lagrangian scheme. Moreover, a model predictive control (MPC) algorithm is implemented to achieve an optimal profile of the recirculation zone with optimal energy consumption, based on the linearized NN model. Finally, the proposed NN-MPC is implemented for simulation of removing the local bioaerosol from an indoor corner through a flow-rate-controllable airflow from ventilation outlet located on the ceiling. • A recirculation zone trapping particles is defined by minimum net mass flux law. • Relationship between recirculation zone and inlet flow rate is trained by NN. • Energy consumption of input is optimized to fit long-term continuous process. • The proposed NN-MPC reduces particle concentration with energy efficiency. [ABSTRACT FROM AUTHOR]

In this paper, we apply the Monte Carlo neural network (MCNN), a type of neural network optimized by Monte Carlo algorithm, to electricity load forecast. Meanwhile, deep MCNNs with one, two and three hidden layers are designed. Results have demonstrated that three-layer MCNN improves 70.35% accuracy for 7-week electricity load forecast, compared with traditional neural network. And five-layer MCNN improves 17.24% accuracy for 7-week forecast. This proves that MCNN has great potential in electricity load forecast. [ABSTRACT FROM AUTHOR]

An improved algorithm with feature selection and neural network classification is proposed in this paper to investigate the fault diagnosis problem of rotating machinery. The feature vectors are constructed by extracting the time- and frequency-domain characteristics of the overall machine under multiple operating conditions. To strengthen the fault diagnostic ability, an improved sensitive feature selection algorithm is proposed by improving the distance evaluation (DE) method and reconstructing a low-dimensional sensitive feature sample with selectively chosen parameters from multidimensional feature vectors. The recursive least square backpropagation (RLS-BP) neural network algorithm is used for fault diagnosis by classifying the feature vectors of normal signal and faulty signals. The effectiveness of the proposed method is verified via hardware experiments using wind turbine drivetrain diagnostics simulator (WTDDS) by comparing with conventional feature vector construction methods and neural network algorithm. [ABSTRACT FROM AUTHOR]

In this paper, we consider a wireless-powered network with co-channel interference where the transmitters control their transmit power and receivers harvest wireless energy using a time switching policy. Considering the interference channels among multiple nodes, we jointly optimize the transmit power and energy harvesting time to maximize the energy efficiency of the network. To solve this non-convex optimization problem, we first design an iterative algorithm based on a typical optimization technique, and then, propose a learning algorithm based on a neural network with a proper loss function. Simulation results show that the proposed learning algorithm can achieve a near-optimal energy efficiency with reducing the computational complexity, compared to an iterative algorithm with a suboptimal performance. [ABSTRACT FROM AUTHOR]

This paper examines the problem of predictive gear scheduling for fuel consumption minimization in connected/automated heavy trucks. The literature highlights the fuel economy benefits of such predictive scheduling, but there is a need to optimize such scheduling online, in real time. To address this need, we begin by using dynamic programming (DP) to schedule gear shifting offline, in a manner that achieves a globally optimal Pareto tradeoff between the conflicting objectives of minimizing fuel consumption and shift frequency. The computational cost of DP is unfavorable for online implementation, but we present two algorithms addressing this challenge. Both algorithms rely on the fact that in the Pareto limit where fuel consumption minimization is the sole objective, DP furnishes a simple static shift map. Our first algorithm trains a recurrent neural network to prune the shift schedule generated by this map. The second algorithm performs this pruning in a direct manner tailored to reduce the schedule's rain flow count. We simulate these algorithms for different drive cycles. Both algorithms achieve a reasonable tradeoff between fuel consumption and gear shift frequency. However, the rain flow count algorithm is both more effective in approaching the DP-based Pareto front and more computationally efficient. [ABSTRACT FROM AUTHOR]

Neural networks that are embedded with prior knowledge of the distribution of the original signal in applications of compressed sensing have attracted increasing attention. However, the maximal probability of the desired output by a neural network cannot guarantee that the statistical distribution of the recovered signal is consistent with the statistical distribution of the original signal. In this paper, we combine neural networks with information geometry to study the recovery of sparse signals that satisfy a certain distribution. We construct the geodesic distance between the distribution of the original signal and distribution of the recovered signal as the input for the neural network. Experiments show that the proposed method has a better reconstruction quality compared with existing algorithms. [ABSTRACT FROM AUTHOR]

Abstract In this paper, a data-driven online entry guidance framework is proposed. Based on the proposed framework, a novel neural network based online predictive guidance algorithm for high lifting vehicles is developed, which combines the benefits of the existing predictive guidance and the neural network predictor. By introducing the neural network predictor, the proposed algorithm can effectively overcome the long-standing contradiction between guidance accuracy and real-time guidance of existing numerical predictive guidance methods. Take the augmented predictor–corrector guidance algorithm as guidance pattern, a large number of sample trajectory data can be generated by performing full envelop trajectory simulations with different perturbation terms. Based on the sample data, the mapping relationship between the real-time flight states of high lifting vehicles and guidance commands is approximated by multi-layer feedforward neural network. By substituting the off-line trained neural network predictor for the trajectory integrations of each guidance cycle in the augmented algorithm, the proposed algorithm can successfully realize the online precision guidance for high lifting vehicles. The simulation results for nominal and dispersed cases show that the proposed algorithm has better performance on real-time capability and robustness than the existing numerical predictive guidance methods, and it is suitable for engineering practice. [ABSTRACT FROM AUTHOR]

Stochastic computation has recently been proposed for implementing artificial neural networks with reduced hardware and power consumption, but at a decreased accuracy and processing speed. Most existing implementations are based on pre-training such that the weights are predetermined for neurons at different layers, thus these implementations lack the ability to update the values of the network parameters. In this paper, a stochastic computational multi-layer perceptron (SC-MLP) is proposed by implementing the backward propagation algorithm for updating the layer weights. Using extended stochastic logic (ESL), a reconfigurable stochastic computational activation unit (SCAU) is designed to implement different types of activation functions such as the $tanh$ and the rectifier function. A triple modular redundancy (TMR) technique is employed for reducing the random fluctuations in stochastic computation. A probability estimator (PE) and a divider based on the TMR and a binary search algorithm are further proposed with progressive precision for reducing the required stochastic sequence length. Therefore, the latency and energy consumption of the SC-MLP are significantly reduced. The simulation results show that the proposed design is capable of implementing both the training and inference processes. For the classification of nonlinearly separable patterns, at a slight loss of accuracy by 1.32-1.34 percent, the proposed design requires only 28.5-30.1 percent of the area and 18.9-23.9 percent of the energy consumption incurred by a design using floating point arithmetic. Compared to a fixed-point implementation, the SC-MLP consumes a smaller area (40.7-45.5 percent) and a lower energy consumption (38.0-51.0 percent) with a similar processing speed and a slight drop of accuracy by 0.15-0.33 percent. The area and the energy consumption of the proposed design is from 80.7-87.1 percent and from 71.9-93.1 percent, respectively, of a binarized neural network (BNN), with a similar accuracy. [ABSTRACT FROM AUTHOR]

This paper discusses the possibility of recognizing and predicting user activities in the IoT (Internet of Things) based smart environment. The activity recognition is usually done through two steps: activity pattern clustering and activity type decision. Although many related works have been suggested, they had some limited performance because they focused only on one part between the two steps. This paper tries to find the best combination of a pattern clustering method and an activity decision algorithm among various existing works. For the first step, in order to classify so varied and complex user activities, we use a relevant and efficient unsupervised learning method called the K-pattern clustering algorithm. In the second step, the training of smart environment for recognizing and predicting user activities inside his/her personal space is done by utilizing the artificial neural network based on the Allen's temporal relations. The experimental results show that our combined method provides the higher recognition accuracy for various activities, as compared with other data mining classification algorithms. Furthermore, it is more appropriate for a dynamic environment like an IoT based smart home. [ABSTRACT FROM AUTHOR]

Partial discharge (PD) recognition is an important tool for online monitoring of gas insulated switchgear (GIS) and diagnosing existing defects. At present, there are two different types of data patterns used for analysis and evaluation of PD signals: phase resolved partial discharge (PRPD) mode and time resolved partial discharge (TRPD) mode. Using different types of data patterns separately can lead to inconsistent or even conflicted recognition results, but the two types of data patterns having complementary information between each other can be used together for data fusion. Dempster-Shafer (DS) evidence theory is introduced to address the problem of evidence conflict and low fusion efficiency. First, two sub-networks for PD recognition are established and compared employing the back propagation neural network (BPNN) learning algorithm under the two modes respectively. Secondly, to minimize (with possible elimination of) the possibility of misclassification, a new fusion decision-making system for PD recognition is proposed on the basis of fusing the results from the sub-networks. Finally, extensive field experiments on two artificial defects are conducted in order to evaluate the performance of the proposed method in this paper. The classification results reveal that the proposed method significantly outperforms the ways of using only single type of data patterns. The method proposed in this paper reduces the uncertainty and effectively improves the credibility of diagnosis. [ABSTRACT FROM AUTHOR]