Search

In this paper, we present a lightweight and effective change detection model, called TinyCD. This model has been designed to be faster and smaller than current state-of-the-art change detection models due to industrial needs. Despite being from 13 to 140 times smaller than the compared change detection models, and exposing at least a third of the computational complexity, our model outperforms the current state-of-the-art models by at least 1 % on both F1-score and IoU on the LEVIR-CD dataset, and more than 8 % on the WHU-CD dataset. To reach these results, TinyCD uses a Siamese U-Net architecture exploiting low-level features in a globally temporal and locally spatial way. In addition, it adopts a new strategy to mix features in the space-time domain both to merge the embeddings obtained from the Siamese backbones, and, coupled with an MLP block, it forms a novel space-semantic attention mechanism, the Mix and Attention Mask Block (MAMB). [ABSTRACT FROM AUTHOR]

In this paper, conductive polymer-based composites in order to have higher electrical conductivity have been constructed using different nanoparticles and numerically considered by different classification techniques. Due to non-conducting feature of polymer-based composites, their other positive advantages (e.g., light weight and stress corrosion) underneath non-conducting defect in which this paper has tried to overcome the faced challenges. For this purpose, carbon black (CB), carbon nanotube (CNT), and expanded graphite (EG) with different weight percentages are added to the epoxy resin as input factors and the electrical conductivity of the samples are measured as response factor. The analysis of input factors is performed and the Taguchi method, artificial neural networks (ANNs) and extreme learning machine (ELM) are designed and used for the prediction of the response factor. The predicted responses using the applied methods are compared with the experimental results. In order to increase the mechanical strength, ten layers of unidirectional carbon fiber are used. The simulation results show that the ANNs and ELM provide good compatible predictions with respect to actual experiment data. Besides, obtained experimental results prove that the highest electrical conductivity has been achieved using 10, 15, and 25 percent using the CNT, EG, and CB, respectively. As a novelty of this paper, the constructed sample composite reaches the acceptable electrical conductivity suggested by United Stated Department of Energy standard considered as material development. In particular, the findings of this research can be used to construct conductive electrodes particularly in oil and gas industries. [ABSTRACT FROM AUTHOR]

Cross-domain few-shot classification aims to recognize images in the new categories and domains that only contain few but unacquainted images. Considering the problems of fine-grained recognition in cross-domain few-shot classification including marginal overall-discrepancy in feature distribution and obvious fine-grained difference in dataset, this paper proposes a simple and effective attentive fine-grained recognition (AFGR) model. Specifically, the residual attention module is stacked into the feature encoder based on the residual network, which can linearly enhance different semantic feature information to help the metric function better locate the fine-grained feature information of the image. In addition, a bilinear metric function structure is proposed to learn and fuse different fine-grained image features, respectively, since the weights of bilinear measurement functions are not shared. Eventually, the final classification result is obtained by merging the recognition of bilinear metric function through posterior probability multiplication. In this paper, ablation experiments and comparative experiments are carried out with the typical few-shot dataset mini-ImageNet as the training domain and the CUB, Cars, Places and Plantae datasets as the test domain. The experimental results demonstrate that the proposed AFGR method is effective, with the highest increase in recognition accuracy 13.82% and 7.95% compared with the latest results under the experimental settings of 5-way1-shot and 5-way5-shot, respectively, which also proves the problems of fine-grained recognition in cross-domain small sample classification. [ABSTRACT FROM AUTHOR]

English expression, language characteristics and usage norms are quite special, which is quite different from Chinese. This has special requirements for auxiliary teaching tools that use computer technology for English text processing. Based on neural network algorithm, this paper combines the actual needs of English grammar error correction to construct an English grammar error correction model based on neural network. In data processing, after feature selection, logistic regression model is used to analyze the influence of different features on article error correction. The article error correction incorporating word vector features mainly explores how to effectively express the features in English grammar error correction. In addition, this paper proposes two methods to optimize the feature representation in article error correction. One is to directly use the word vector corresponding to the word as a feature, replacing the original One-hot encoding, and the other uses a clustering method to compress the article features. Finally, this paper designs experiments to study the performance of the model constructed in this paper. The results obtained show that the model constructed in this paper has a certain effect. [ABSTRACT FROM AUTHOR]

The operation of the mobile interactive autonomous learning system injects advanced management technology and scientific and reasonable management system for the effective management and arrangement of the school's teaching, enables students to conduct autonomous learning in their spare time, makes full use of students' fragmented time, and improves students' learning enthusiasm and efficiency. Based on the neural network algorithm, this paper constructs an English network learning interactive evaluation model, studies the influence of the flattening layer in the convolutional neural network structure on the structural complexity, and then proposes spatial pyramid weighted average pooling to optimize the traditional flattened layer. Moreover, this paper evaluates RSPP from three aspects: space complexity, training time-consuming, and accuracy. In addition, this paper designs two types of integrated convolutional neural networks, namely Bagging integration and snapshot integration. Finally, this paper evaluates the performance of the model through experiments and counts the experimental results. The research results show that the model constructed in this paper has a certain effect. [ABSTRACT FROM AUTHOR]

How to build a football match prediction model and use scientific methods to solve the prediction problem has become a key point in the application of artificial intelligence in the sports industry. In this paper, we choose a BP neural network model that is powerful in processing nonlinear data to perform research. According to the demand, this paper constructs a gray fuzzy prediction model based on neural network, a gray extreme learning machine prediction model, and a gray fuzzy extreme learning machine prediction combination model based on neural network. Moreover, this paper tests the neural network model by comparing actual results with predicted results. In addition, by predicting and analyzing the football league data, this article tests the three models in terms of match result prediction accuracy, data processing speed, data transmission accuracy, match analysis scores, etc., and uses statistical analysis methods to process data, and uses intuitive statistical graphs to obtain the processing results. The research results show that the gray fuzzy extreme learning machine prediction combination model based on neural network constructed in this paper can retain the advantages of a single model and effectively improve the prediction accuracy of the model and the performance of the system. [ABSTRACT FROM AUTHOR]

In order to overcome the shortcomings of the current English network learning system, based on the neural network algorithm, this paper constructs an intelligent English network learning system based on the improved algorithm. Moreover, by analyzing the coupling between recurrent neural networks by contrast methods, this paper infers the coupling between recurrent neural networks. Moreover, this paper studies the continuous attractors of the autoencoder neural network and studies the continuous attractors of different types of autoencoder models. On this basis, this paper expands the existing model, adds the module of the interaction between the external input and the visible layer and studies the conditions required for the continuous attractor of the autoencoder model. In addition, on the basis of actual needs, this paper constructs the basic structure of the model and integrates it into the improved algorithm proposed in this paper to realize English online intelligent learning. Finally, this paper designs experiments to analyze the practical effects of this model and analyzes the experimental results through mathematical statistics. The research results show that the English network learning system constructed in this paper is effective. [ABSTRACT FROM AUTHOR]

Buried pipeline is threatened from the soil displacement due to earthquake and other causes, which leads to the formation of unexpected external forces such as bending moment. The problem can be worse with the appearance of defects, resulting in the reduction in pipe capacity. The paper focuses on the overall problem of defected pipe crossing the strike-slip fault. A full-scaled FE model can be very complicated with the large-scale and micro-scale levels corresponding to the strike-slip fault and defect on pipe problems, respectively. To ease this difficulty, the macro and micro problems are solved separately with two types of FE models and their corresponding databases. To be specific, one FE model is used for predicting external moment due to strike-slip fault and the other is for predicting the moment capacity of defected pipe. Data-driven models are consequently developed with artificial neural network (ANN) for each database generated from these types of models: ANN1 evaluating moment capacity of defected pipe (R2 is 0.9943 on test set) and ANN2 predicting both moment and axial force appeared in pipe due to strike-slip fault (R-squares are 0.9883 and 0.9929 on test set, respectively). Consequently, the stress–strength analysis for the overall problem is solved. Accounting for the unavoidable uncertainty of the models, the paper proposed an approach which assumes that the actual distribution of residual of a model is equivalent to this of the test set. The distributions of residuals on test set of these ANNs are tested to be normally distributed and generated by the conventional Monte Carlo simulation. To the end, the deterministic problem leads to the failure probability. The proposed framework has been investigated, and the final results on this selective parametric study are reasonable. [ABSTRACT FROM AUTHOR]

This paper presents an estimation of the sound source location using deep neural networks in order to provide auditory perception of a humanoid robot. Estimation of a moving sound source is crucial for a humanoid robot to improve functionality in some environments where the robot's camera cannot operate. It plays an important role, especially in a recovery scenario with no visual contact. In this study, the data of the sound source around the robot were recorded by four microphones placed on the humanoid robot's head. A wheeled robot was used to obtain the sound source with odometry. Recorded sound dataset and collected odometry dataset were used as input data and target data, respectively. The discrete wavelet transform (DWT) was applied for pre-processing of the input data. After pre-processing, the obtained matrices were applied as inputs of the proposed convolutional neural network (CNN), long short-term memory (LSTM), bidirectional long-short-term memory (biLSTM), and multilayer perceptron (MLP) networks to estimate the sound source location around the humanoid robot. As a result of all tests for the estimation models created by proposed networks, the R 2 metrics of the biLSTM structure were obtained as approximately 0.97. This study showed experimentally that humanoid robots can sense the position of sound source in the environment with sufficient accuracy like many living creatures. [ABSTRACT FROM AUTHOR]

Spiking neural networks (SNNs) are mimicking computationally powerful biologically inspired models in which neurons communicate through sequences of spikes, regarded here as sparse binary sequences of zeros and ones. In neuroscience it is conjectured that time encoding, where the information is carried by the temporal position of spikes, is playing a crucial role at least in some parts of the brain where estimation of the spiking rate with a large latency cannot take place. Motivated by the efficiency of temporal coding, compared with the widely used rate coding, the goal of this paper is to develop and train an energy-efficient time-coded deep spiking neural network system. To ensure that the similarity among input stimuli is translated into a correlation of the spike sequences, we introduce correlative temporal encoding and extended correlative temporal encoding techniques to map analog input information into input spike patterns. Importantly, we propose an implementation where all multiplications in the system are replaced with at most a few additions. As a more efficient alternative to both rate-coded SNNs and artificial neural networks, such system represents a preferable solution for the implementation of neuromorphic hardware. We consider data classification tasks where input spike patterns are presented to a feed-forward architecture with leaky-integrate-and-fire neurons. The SNN is trained by backpropagation through time with the objective to match sequences of output spikes with those of specifically designed target spike patterns, each corresponding to exactly one class. During inference the target spike pattern with the smallest van Rossum distance from the output spike pattern determines the class. Extensive simulations indicate that the proposed system achieves a classification accuracy at par with that of state-of-the-art machine learning models. [ABSTRACT FROM AUTHOR]

In recent years, remote data collection and remote monitoring technologies based on artificial neural networks have been increasingly used in various industries. In order to in-depth study whether the data collection system based on artificial neural network theory can analyze the characteristics of different strokes in swimming events, this paper uses simulation comparison method, data integration method, and step-by-step construction method to collect samples, analyze the data collection system, and streamline the algorithm. And integrate and create a data collection system that can analyze the characteristics of swimming styles. After constructing the system, select the image frequency 450 ms once, and set the signal frequency to 2.5 KHZ. Set the waveforms to sawtooth wave and sine wave, respectively; the voltage range of sine wave is − 6 to 8 V, and the sampling frequency is 250. The voltage range of the sawtooth wave is − 8 to 6 V, and the sampling frequency is 45 KHZ. Experiments show that the system basically works normally during the sampling process. To further study the stability of the system, this test is in a swimming pool with a one-story building with a relative humidity of 85%. It is set to send 110 data frames from the coordinator segment to the normal segment every 2.5 s. The acquisition success rate is 88% when there is interference and 96% when there is no interference, which is much higher than that when there is interference. Therefore, a retransmission mechanism must be used when designing the software for common segment points to ensure reliable data transmission. In general, the data acquisition system we designed basically meets the design standards. It is basically realized that starting from the artificial neural network, a data acquisition system that can analyze swimming styles is designed. [ABSTRACT FROM AUTHOR]

Accurate travel time prediction allows passengers to schedule their journeys efficiently. However, cyclical factors (time intervals of the day, weather conditions, and holidays), unpredictable factors (incidents, abnormal weather), and other complicated factors (dynamic traffic conditions, dwell times, and variation in travel demand) make accurate bus travel time prediction complicated. This paper aims to achieve accurate travel time prediction. To do so, we propose a clustering method that identifies travel time paradigms of different route links and clusters them based on their similarity using the nonnegative matrix factorization algorithm. Additionally, we propose a deep learning model based on CNN with spatial–temporal attention and gating mechanisms to select the most relevant features and capture their dependencies and correlations. For each defined cluster, we train a separate model to predict the travel time at various time intervals over the day. As a result, the travel times of all journey links from related prediction models are aggregated to predict the total journey time. Extensive experiments using data collected from four different bus lines in Beijing show that our method outperforms the compared baselines. [ABSTRACT FROM AUTHOR]

Deep learning-based surrogate modeling is becoming a promising approach for learning and simulating dynamical systems. However, deep-learning methods find it very challenging to learn stiff dynamics. In this paper, we develop DAE-PINN, the first effective physics-informed deep-learning framework for learning and simulating the solution trajectories of nonlinear differential-algebraic equations (DAE). DAEs are used to model complex engineering systems, e.g., power networks, and present a "form" of infinite stiffness, which makes learning their solution trajectories challenging. Our DAE-PINN bases its effectiveness on the synergy between implicit Runge–Kutta time-stepping schemes (designed specifically for solving DAEs) and physics-informed neural networks (PINN) (deep neural networks that we train to satisfy the dynamics of the underlying problem). Furthermore, our framework (i) enforces the neural network to satisfy the DAEs as (approximate) hard constraints using a penalty-based method and (ii) enables simulating DAEs for long-time horizons. We showcase the effectiveness and accuracy of DAE-PINN by learning the solution trajectories of a three-bus power network. [ABSTRACT FROM AUTHOR]

Active learning helps software developers reduce the labeling cost when building high-quality machine learning models. A core component of active learning is the acquisition function that determines which data should be selected to annotate.State-of-the-art (SOTA) acquisition functions focus on clean performance (e.g. accuracy) but disregard robustness (an important quality property), leading to fragile models with negligible robustness (less than 0.20%). In this paper, we first propose to integrate adversarial training into active learning (adversarial-robust active learning, ARAL) to produce robust models. Our empirical study on 11 acquisition functions and 15105 trained deep neural networks (DNNs) shows that ARAL can produce models with robustness ranging from 2.35% to 63.85%. Our study also reveals, however, that the acquisition functions that perform well on accuracy are worse than random sampling when it comes to robustness. Via examining the reasons behind this, we devise the density-based robust sampling with entropy (DRE) to target both clean performance and robustness. The core idea of DRE is to maintain a balance between selected data and the entire set based on the entropy density distribution. DRE outperforms SOTA functions in terms of robustness by up to 24.40%, while remaining competitive on accuracy. Additionally, the in-depth evaluation shows that DRE is applicable as a test selection metric for model retraining and stands out from all compared functions by up to 8.21% robustness. [ABSTRACT FROM AUTHOR]

The explosive growth of geospatial data is increasing requirements for automatic and efficient data learning abilities. Many deep learning methods have been widely applied for geospatial data understanding tasks, such as road networks and geospatial object detection. However, the demands for more accurate learning of high-level features require the use of deeper neural networks. To further improve the learning efficiency of deep neural networks, in this paper, we propose an improved convolutional neural network named EDense. First, we use its dense connectivity to integrate a CNN with an extreme learning machine. Then, we expand the kernels in the convolutional layers to increase the width of the network model. Furthermore, we propose one-feature EDense (OF-EDense), which is a simplified version of EDense, to fit conditions in which the number of parameters is strictly limited. Finally, the experimental results fully demonstrate the strong learning ability and high learning efficiency of EDense. [ABSTRACT FROM AUTHOR]

The application of Deep Neural Networks (DNNs) to a broad variety of tasks demands methods for coping with the complex and opaque nature of these architectures. When a gold standard is available, performance assessment treats the DNN as a black box and computes standard metrics based on the comparison of the predictions with the ground truth. A deeper understanding of performances requires going beyond such evaluation metrics to diagnose the model behavior and the prediction errors. This goal can be pursued in two complementary ways. On one side, model interpretation techniques "open the box" and assess the relationship between the input, the inner layers and the output, so as to identify the architecture modules most likely to cause the performance loss. On the other hand, black-box error diagnosis techniques study the correlation between the model response and some properties of the input not used for training, so as to identify the features of the inputs that make the model fail. Both approaches give hints on how to improve the architecture and/or the training process. This paper focuses on the application of DNNs to computer vision (CV) tasks and presents a survey of the tools that support the black-box performance diagnosis paradigm. It illustrates the features and gaps of the current proposals, discusses the relevant research directions and provides a brief overview of the diagnosis tools in sectors other than CV. [ABSTRACT FROM AUTHOR]

In machine learning models, one of the most popular models is artificial neural networks. The activation function is one of the important parameters of neural networks. In this paper, the sigmoid function is used as an activation function with a fractional derivative approach to minimize the convergence error in backpropagation and to maximize the generalization performance of neural networks. The proportional Caputo definition is considered a fractional derivative. We evaluated three neural network models on the usage of the proportional Caputo derivative. The results show that the proportional Caputo derivative approach has higher classification accuracy than traditional derivative models in backpropagation for neural networks with and without L2 regularization. [ABSTRACT FROM AUTHOR]

Deep learning techniques, in particular generative models, have taken on great importance in medical image analysis. This paper surveys fundamental deep learning concepts related to medical image generation. It provides concise overviews of studies which use some of the latest state-of-the-art models from last years applied to medical images of different injured body areas or organs that have a disease associated with (e.g., brain tumor and COVID-19 lungs pneumonia). The motivation for this study is to offer a comprehensive overview of artificial neural networks (NNs) and deep generative models in medical imaging, so more groups and authors that are not familiar with deep learning take into consideration its use in medicine works. We review the use of generative models, such as generative adversarial networks and variational autoencoders, as techniques to achieve semantic segmentation, data augmentation, and better classification algorithms, among other purposes. In addition, a collection of widely used public medical datasets containing magnetic resonance (MR) images, computed tomography (CT) scans, and common pictures is presented. Finally, we feature a summary of the current state of generative models in medical image including key features, current challenges, and future research paths. [ABSTRACT FROM AUTHOR]

Demand forecasting is a scientific and methodical assessment of future demand for a critical product.The effective Demand Forecast Model (DFM) enables pharmaceutical companies to be successful in the global market. The purpose of this research paper is to validate various shallow and deep neural network methods for demand forecasting, with the aim of recommending sales and marketing strategies based on the trend/seasonal effects of eight different groups of pharmaceutical products with different characteristics. The root mean squared error (RMSE) is used as the predictive accuracy of DFMs. This study also found that the mean RMSE value of the shallow neural network-based DFMs was 6.27 for all drug categories, which was lower than deep neural network models. According to the findings, DFMs based on shallow neural networks can effectively estimate future demand for pharmaceutical products. [ABSTRACT FROM AUTHOR]

In this paper, we propose a method to approximate the solutions to nonlinear ordinary differential equations (ODE) using a deep learning feedforward artificial neural networks (ANNs). The efficiency of the proposed—unsupervised type machine learning—method is shown by solving two boundary value problems (BVPs) from quantum mechanics and nanofluid mechanics. The proposed mean-squared loss function is the sum of two terms: the first term satisfies the differential equation, while the second term satisfies the initial or boundary conditions. The total loss function is minimized by using general type of quasi-Newton optimization methods to get a desired network output. The approximation capability of the proposed method is verified for two sets of boundary value problems: first, a second-order nonlinear ODE and, second, a system of coupled nonlinear third-order ODEs. Point-wise comparison of our approximation shows a strong agreement with the available exact solutions and/or Runge–Kutta-based numerical solutions. We remark that the proposed algorithm minimizes the overall learnable network hyperparameters in a given initial or boundary value problems. More importantly, for the coupled system of third-order nonlinear ordinary differential equations, the proposed method does not need any adjustment with the initial/boundary conditions. Also, the current method does not require any special type of computational mesh. A straightforward minimization of total loss function yields a highly accurate results even with less number of epochs. Therefore, the proposed framework offers an attractive setting for the fluid mechanics community who are interested in studying heat and mass transfer problems. [ABSTRACT FROM AUTHOR]

As a compact and effective learning model, the random vector functional link neural network (RVFL) has been confirmed with universal approximation capabilities. It has gained considerable attention in various fields. However, the randomly generated parameters in RVFL often lead to the loss of valid information and data redundancy, which severely degrades the model performance in practice. This paper first proposes an efficient network parameters learning approach for the original RVFL with pseudoinverse learner (RVFL-PL). Instead of taking the random feature mapping directly, RVFL-PL adopts a non-iterative manner to obtain influential enhancement nodes implanted with valuable information from input data, which realizes to improve the quality of the enhancement nodes and ease the problem caused by the randomly assigned parameters in the standard RVFL. Since the network parameters are optimized analytically, this improved variant can maintain the efficiency of the standard RVFL. Further, the RVFL-PL is extended to a multilayered structure (mRVFL-PL) to obtain high-level representations from the input data. The results of comprehensive experiments on some benchmarks indicate the performance improvement of the proposed method compared to other corresponding methods. [ABSTRACT FROM AUTHOR]

Process fault detection and diagnosis (FDD) is a predominant task to ensure product quality and process reliability in modern industrial systems. Those traditional FDD techniques are largely based on diagnostic experience. These methods have met significant challenges with immense expansion of plant scale and large numbers of process variables. Recently, deep learning has become the newest trends in process control. The upsurge of deep neural networks (DNNs) in leaning highly discriminative features from complicated process data has provided practitioners with effective process monitoring tools. This paper is to present a review and full developing route of deep learning-based FDD in complex process industries. Firstly, the nature of traditional data projection-based and machine learning-based FDD methods is discussed in process FDD. Secondly, the characteristics of deep learning and their applications in process FDD are illustrated. Thirdly, these typical deep learning techniques, e.g., transfer learning, generative adversarial network, capsule network, graph neural network, are presented for process FDD. These DNNs will effectively solve these problems of fault detection, fault classification, and fault isolation in process. Finally, the developing route of DNN-based process FDD techniques is highlighted for future work. [ABSTRACT FROM AUTHOR]

Oxygen content in the flue gas system of power plants is an essential factor affecting boiler efficiency. Accurate oxygen content measurement is vital in evaluating boiler combustion efficiency. The device measuring oxygen content in flue gases at an oil refinery uses a Zirconia oxygen analyzer. This sensor utilization without sensor redundancy makes the oxygen content measurement conducted manually. Workers' manual measurement is risky because it is a high-risk work area. In addition, the oxygen content in flue gas also indicates boiler combustion efficiency and the amount of other harmful gases produced by the boiler. This paper proposes a soft sensor using artificial neural networks (ANN) and extreme gradient boosting (XGBoost) to predict oxygen content. The dataset used is collected from the historical data of the distributed control system of an oil refinery system boiler. The experimental results show that the one hidden layer ANN model achieves an MAE of 0.0715 and RMSE of 0.0935, while the XGBoost model with hyperparameter tuning and seven features achieves an MAE of 0.0452 and RMSE of 0.0642. The results suggest that the XGBoost model with hyperparameter tuning and seven features outperforms the one hidden layer ANN model. The use of the seven features of the XGBoost model is the result of optimization between computational complexity and system performance. [ABSTRACT FROM AUTHOR]

The proposed paper presents the analysis, design, implementation and evaluation of an ultra-short-term frequency trading system for the foreign exchange (FOREX) market, which features all stages of the trading process (Pretrade Analysis, Trend Forecasting, Transaction Execution) substantially exploiting artificial intelligence techniques. Our goal is to simulate the judgment and decision making of the human expert (technical analyst or broker) with a system that responds in a timely manner to changes in market conditions, thus allowing the optimization of ultra-short-term transactions. We designed and implemented a series of technical indicator simulators, which are fed to a novel artificial neural network architecture, to eventually generate the trend forecasting signal. We also designed and implemented a series of customizable ultra-short-term automated trading machines, which receive as inputs the generated forecasting signals and perform real-time virtual transactions. A comparative analysis of the results of both automated trading machines and each machine is carried out for a comprehensive variety of trend forecasting sources. [ABSTRACT FROM AUTHOR]

The objective of this work is to compare the efficiency of three computational intelligence techniques: Artificial Neural Networks (ANNs), Support Vector Machines (SVMs) and Adaptive Neuro-Fuzzy Inference System (ANFIS) to model the dynamic adsorption of organic pollutants on activated carbon. A comparison study was enhanced using five models: ANN with conventional transfer functions, ANN with new transfer function called "SPOCU", SVM, SVM hybrid with Dragonfly optimisation algorithm (SVM-DA) and ANFIS. A set of data points, collected from scientific papers containing the dynamic adsorption kinetics of adsorption on activated carbon, was used in the modelling process. The studied parameters were molar mass, initial concentration, flow rate, bed height, BET surface area, time and concentration of non-dimensional effluents. Overall, the developed model was able to accurately estimate 11,763 experimental data points gathered from the literature. The performance of the optimised models has been evaluated using different metrics between the experimental and the predicted data. Results show that SVM-DA model can estimate accurately the dynamic adsorption of organic pollutants on activated carbon against the other tested models. Also a graphical user interface is developed in this paper in order to keep the traceability of the estimated results. [ABSTRACT FROM AUTHOR]

Due to the noises captured in ultrasound device and image reconstruction process, the edges of thyroid nodule are usually not distinctive and it is very difficult for existing approaches to well segment them in ultrasound images. While deep neural networks like U-Net have been successfully applied in many medical image segmentation tasks, their segmentation performances on ultrasound images are still not satisfactory. To address this issue, we propose in this paper a boundary field regression branch to provide useful boundary information to help improve the segmentation performance of existing networks. Without requirement of additional labeling costs, our approach firstly generates boundary field heatmap from available segmentation masks, which are then used as a supervision to train the regression branch. As a general architecture, our branch can be integrated with all encoder-decoder like segmentation networks. A dataset consisting of 3169 images from 2004 patients is used for experiments. We integrate our branch with U-Net, Attention U-Net, U-Net++ and DeepLabv3+; consistent improvements of Dice metrics were observed. The memory and computation costs required by adding our branch are marginal as well. [ABSTRACT FROM AUTHOR]

The risk of death incurred by breast cancer is rising exponentially, especially among women. This made the early breast cancer detection a crucial problem. In this paper, we propose a computer-aided diagnosis (CAD) system, called CADNet157, for mammography breast cancer based on transfer learning and fine-tuning of well-known deep learning models. Firstly, we applied hand-crafted features-based learning model using four extractors (local binary pattern, gray-level co-occurrence matrix, and Gabor) with four selected machine learning classifiers (K-nearest neighbors, support vector machine, random forests, and artificial neural networks). Then, we performed some modifications on the Basic CNN model and fine-tuned three pre-trained deep learning models: VGGNet16, InceptionResNetV2, and ResNet152. Finally, we conducted a set of experiments using two benchmark datasets: Digital Database for Screening Mammography (DDSM) and INbreast. The results of the conducted experiments showed that for the hand-crafted features based CAD system, we achieved an area under the ROC curve (AUC) of 95.28% for DDSM using random forest and 98.10% for INbreast using support vector machine with the histogram of oriented gradients extractor. On the other hand, CADNet157 model (i.e., fine-tuned ResNet152) was the best performing deep model with an AUC of 98.90% (sensitivity: 97.72%, specificity: 100%), and 98.10% (sensitivity: 100%, specificity: 96.15%) for, respectively, DDSM and INbreast. The CADNet157 model overcomes the limitations of traditional CAD systems by providing an early detection of breast cancer and reducing the risk of false diagnosis. [ABSTRACT FROM AUTHOR]

Despite the enormous performance of deep neural networks (DNNs), recent studies have shown their vulnerability to adversarial examples (AEs), i.e., carefully perturbed inputs designed to fool the targeted DNN. Currently, the literature is rich with many effective attacks to craft such AEs. Meanwhile, many defense strategies have been developed to mitigate this vulnerability. However, these latter showed their effectiveness against specific attacks and does not generalize well to different attacks. In this paper, we propose a framework for defending DNN classifier against adversarial samples. The proposed method is based on a two-stage framework involving a separate detector and a denoising block. The detector aims to detect AEs by characterizing them through the use of natural scene statistic (NSS), where we demonstrate that these statistical features are altered by the presence of adversarial perturbations. The denoiser is based on block matching 3D (BM3D) filter fed by an optimum threshold value estimated by a convolutional neural network (CNN) to project back the samples detected as AEs into their data manifold. We conducted a complete evaluation on three standard datasets, namely MNIST, CIFAR-10 and Tiny-ImageNet. The experimental results show that the proposed defense method outperforms the state-of-the-art defense techniques by improving the robustness against a set of attacks under black-box, gray-box and white-box settings. The source code is available at: https://github.com/kherchouche-anouar/2DAE. [ABSTRACT FROM AUTHOR]

Age estimation from face images can be profitably employed in several applications, ranging from digital signage to social robotics, from business intelligence to access control. Only in recent years, the advent of deep learning allowed for the design of extremely accurate methods based on convolutional neural networks (CNNs) that achieve a remarkable performance in various face analysis tasks. However, these networks are not always applicable in real scenarios, due to both time and resource constraints that the most accurate approaches often do not meet. Moreover, in case of age estimation, there is the lack of a large and reliably annotated dataset for training deep neural networks. Within this context, we propose in this paper an effective training procedure of CNNs for age estimation based on knowledge distillation, able to allow smaller and simpler "student" models to be trained to match the predictions of a larger "teacher" model. We experimentally show that such student models are able to almost reach the performance of the teacher, obtaining high accuracy over the LFW+, LAP 2016 and Adience datasets, but being up to 15 times faster. Furthermore, we evaluate the performance of the student models in the presence of image corruptions, and we demonstrate that some of them are even more resilient to these corruptions than the teacher model. [ABSTRACT FROM AUTHOR]

In this paper, a new fine-grained image classification (FGIC) network with feature relationship enhancement of multiple stages is established. After the engaging of scene text in FGIC and retrieval, basic architecture of local, global, text feature encoders and classifier have been approved. This method retains these portions and expands them into a five-module architecture. In specific, positional encoding is incorporated to both local and textual feature encoders such that complementary information carried could engage in feature representation. In local and textual feature encoders, intra-modal semantic relation reasoning is introduced for FGIC by a proposed General Feature Relation Enhancement (GFRE) module. GFRE is a feature reasoning module applicable to any two inputs of same modality or distinct modalities. GFRE adopts Graph Attention which represents and infers relationships among graph data. Moreover, latest multi-modal reasoning module is improved by a proposed Multi-Head Multi-Modal Joint Semantic Reasoning module consisted of cross-modal GFREs by multi-head fusion. Experimental results on multiple datasets verify the effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

The application of clustering in generating random subspace has improved the accuracy and diversity of ensemble classification methods. If clusters are not balanced (unequal size of clusters) and not strong (unequal number of data from each class in each cluster), the results will deviate from classes with more samples in each cluster and thereby will be biased. The current paper presents a novel strong balance-constrained clustering or hard-strong clustering. This method creates diverse strong balanced data clusters to train different base classifiers and an artificial neural network with more than one hidden layer, in which the final decision is made for the data class through majority voting. By implementing the proposed method on 16 datasets, two objectives are followed: enhancing the performance of ensemble classifier and deep learning-based method (data mining objective), and adopting appropriate policies for budget, time, and energy assignment to various business domains by decision-makers (business objective). Based on the evaluation and comparison of the results, the proposed method is faster than other balancing methods. Furthermore, the accuracy of the proposed ensemble method has proved acceptable improvement than other ensemble classification methods. [ABSTRACT FROM AUTHOR]

Adversarial examples can attack multiple unknown convolutional neural networks (CNNs) due to adversarial transferability, which reveals the vulnerability of CNNs and facilitates the development of adversarial attacks. However, most of the existing adversarial attack methods possess a limited transferability on vision transformers (ViTs). In this paper, we propose a partial blocks search attack (PBSA) method to generate adversarial examples on ViTs, which significantly enhance transferability. Instead of directly employing the same strategy for all encoder blocks on ViTs, we divide encoder blocks into two categories by introducing the block weight score and exploit distinct strategies to process them. In addition, we optimize the generation of perturbations by regularizing the self-attention feature maps and creating an ensemble of partial blocks. Finally, perturbations are adjusted by an adaptive weight to disturb the most effective pixels of original images. Extensive experiments on the ImageNet dataset are conducted to demonstrate the validity and effectiveness of the proposed PBSA. The experimental results reveal the superiority of the proposed PBSA to state-of-the-art attack methods on both ViTs and CNNs. Furthermore, PBSA can be flexibly combined with existing methods, which significantly enhances the transferability of adversarial examples. [ABSTRACT FROM AUTHOR]

This paper introduces a developed method of an artificial neural networks (ANN) architecture for estimating the residual strength of clay soil. To implement this purpose, a database of input soil parameters is built, including liquid limit, plasticity index, A-line value, clay fraction, massive minerals, mica, kaolinite, and smectite, in which the output is the residual friction angle. The ANN model was developed by extensively analyzing a number of hidden layers and number of neurons in every layer, incorporating a statistical investigation of the model performance. The obtained results indicate that the ANN model is an outperformed and promising method based on various well-known indicators such as correlation coefficient, mean absolute error, and root mean square error. The achieved ANN model also gives higher estimation accuracy than those results in the literature. Finally, partial dependence plot 2-D was used for sensitivity analysis within the ANN algorithm to investigate the effect of coupled input variables on the estimated residual friction angle of the soil. It was found that A-line value, clay fraction, and massive minerals are the most important input parameters influencing the residual friction angle. [ABSTRACT FROM AUTHOR]

In the previous works on heat stress detection, various state-of-the-art machine learning techniques had been used to detect stress patterns from electroencephalographic (EEG) signals. Since the handcrafted feature engineering-based approaches pose certain limitations and are sensitive to transform the nonlinearities of EEG, deep learning techniques have drawn attention in the domain of EEG-based applications. Moreover, existing approaches for stress detection consider the whole frequency band (delta to gamma) which conceals the redundant and lossy information that increased the false detection rate. Also, these approaches were implemented only to identify the stress in binary classes and confined their application to identifying the level of stress. Therefore, a multi-scale channel-wise convolution-based multi-level heat stress assessment has been proposed in this paper. The novel contributions of this work are (1) designing a multi-scale convolutional neural network (MS-CNN) for extracting precise information from individual frequency bands of EEG, (2) use of sparse connectivity to reduce the redundant information and increase the performance with less trainable parameters, and (3) multi-level heat stress assessment for precise identification of the severity of stress. The proposed approaches were evaluated on pre-recorded data of 10 rats in a simulated laboratory environment. The high accuracy of approximately 96–97% and 90–92% has been achieved for binary and multi-level stress detection. There is approximately a 6 to 50% reduction in the trainable parameters with a 2% improvement of accuracy achieved on adopting channel-wise convolution over MS-CNN and deep convolutional neural network (DCNN). This demonstrates the effectiveness of the adopted multiscale feature extraction and sparse connectivity to improve the performance with a less complex model. [ABSTRACT FROM AUTHOR]

Advances in deep neural networks have led to significant improvement of object detection accuracy. However, object detection in crowded scenarios is a challenging task for neural networks since extremely overlapped objects provide fewer visible cues for a model to learn from. Further complicating the detection of overlapping objects is the fact that most object detectors produce multiple redundant detections for single objects, which are indistinguishable from detections of separate overlapped objects. Most existing works use some variant of non-maximum suppression to prune duplicate candidate bounding boxes based on their confidence scores and the amount of overlap between predicted bounding boxes. These methods are unaware of how much overlap there actually is between the objects in the image, and are therefore inclined to merge detections for highly overlapped objects. In this paper, we propose an overlap aware box selection solution that uses a predicted overlap map to help it decide which highly overlapping bounding boxes are associated with actual overlapping objects and should not be pruned. We show our solution outperforms the state-of-the-art set-NMS bounding box selection algorithm for both the crowdHuman dataset and a sports dataset. [ABSTRACT FROM AUTHOR]

Diabetic Retinopathy (DR), one of the most progressive sight-threatening diseases caused by the long-term diabetic condition, can lead to vision impairment and blindness later. Early diagnosis and timely treatment help control and avert DR from its progression. However, manual grading is exceptionally challenging and arduous due to the complex anatomical features in the retina. Therefore, developing an automated diagnostic method for screening DR is obligatory. This paper proposes a deep learning-enabled optimized feature selection approach to classify the stage of DR severity in the fundus image. At first, a pre-processing phase eradicates the noise and improves the contrast in the retinal fundus image. Then, blood vessel segmentation is performed using the Coherence Enhancing Energy Based Regularized Level Set Evolution method in the green channel fundus image. Subsequently, the optic disk is segmented with Canny Anisotropic Diffusion filter and morphological transformations. Next, the candidate lesion region is detected using an Attention-based Fusion Network (AFU-Net). Then, shape and texture features are extracted, and then, the optimal subset of features is selected using the Improved Harris Hawk Optimization algorithm. Finally, a deep Convolutional Neural Network classifies the DR stages, and the model weight is updated using the same algorithm. The proposed method achieved superior performance in two benchmark public datasets compared with the existing state-of-the-art methods using F1-score, accuracy, sensitivity, and specificity measures. [ABSTRACT FROM AUTHOR]

Object tracking has achieved impressive performance in computer vision. However, there are many challenges due to complex scenarios in reality. The mainstream trackers mostly locate the object in form of two branches, which limits the ability of trackers to fully mine similarity between template and search region. In this paper, we propose a multi-branch and multi-scale perception object tracking framework based on Siamese Convolutional Neural Networks (MultiBSP), in which the multi-branch tracking framework is established based on the idea of relation mining, and a tower-structured relation network is designed for each branch to learn the non-linear relation function between template and search region. By branch combination, multiple branches can verify their predictions with each other, which is beneficial to robust tracking. Besides, in order to sense the scale and aspect ratio of object in advance, a multi-scale perception module is designed by utilizing the dilated convolutions in five scales, which contributes to the ability of tracker to deal with scale variation. In addition, we propose an information enhancement module that focuses on important features and suppresses unnecessary ones along spatial and channel dimensions. Extensive experiments on six visual tracking benchmarks including OTB100, VOT2018, VOT2019, UAV123, GOT-10k, and LaSOT demonstrate that our MultiBSP can achieve robust tracking and have state-of-the-art performance. Finally, ablation experiments verify the effectiveness of each module and the tracking stability is proved by qualitative and quantitative analyses. [ABSTRACT FROM AUTHOR]

The increase in debt levels of families in different parts of the world has drawn the attention of organizations dedicated to the prevention of financial risk and has highlighted the need to develop early detection methods for over-indebtedness. In this paper, we propose a hybrid model of the adaptive neural fuzzy inference system (ANFIS) and Probit model for the prediction of household over-indebtedness. The proposed model is compared with Probit, artificial neural networks (ANN), classification and regression trees (CART), random forest (RF) and support vector machine (SVM) models. The most relevant parameters for the performance of each model are optimized, and we address data balance problems through the synthetic minority over-sampling technique (SMOTE). We use data obtained from the Financial Household Survey of the Central Bank of Chile. The results show that the proposed model performs significantly better than the reference models in terms of the correct classification of indebted individuals. Consequently, this model provides an innovative understanding of household over-indebtedness, which can be useful for different governmental entities focused on preventing excessive indebtedness and maintaining financial stability. [ABSTRACT FROM AUTHOR]

Fused deposition modeling (FDM) has shown to be a highly beneficial process for product development. However, one of the great challenges in using FDM is maintaining the surface quality of the produced part. Poor texture quality can be regarded as a defect. It is not part of the geometric prototype but results from the fabrication process. Poor input parameters typically cause these defects by the user. This paper presents the integration between an artificial neural network (ANN) and symbiotic organism search, known as ANN–SOS, to model and minimize the surface roughness (Ra) of the FDM process. The FDM input parameters considered were layer height, print speed, print temperature, and outer shell speed. The experimental data were collected using the central composite design response surface method. Then, the surface roughness model was established using an ANN. After validating the model's accuracy, it was combined with symbiotic organism search (SOS) to determine the optimal parameter settings for the minimum surface roughness value. The results illustrate that ANN–SOS with a 4-8-8-1 network structure would be the best model for surface roughness prediction. It was observed that decreasing the layer thickness, printing speed, print temperature, and outer shell speed of the FDM input parameters for ANN–SOS resulted in minimum surface roughness of approximately 2.011 µm, which was 12.36% better than the RSM method. [ABSTRACT FROM AUTHOR]

Pedestrian Attribute Recognition (PAR) can provide valuable clues for several innovative surveillance applications. It is also a difficult task because inference of the multiple attributes at a far distance is challenging in real complex scenarios. Most existing methods improve the PAR with visual attention mechanisms or body-part detection modules, which increase the complexity of networks and require manual annotations of the human body. Also, uneven data distribution, leading to a decline in recall values, is still underestimated. This paper presents a novel multi-label optimization algorithm to mitigate these issues, named Multi-label Contrastive Focal Loss (MCFL). Specifically, we first propose a multi-label focal loss to emphasize the error-prone and minority attributes with a separated re-weighting scheme. And then, we introduce a multi-label contrastive learning strategy based on the multi-label divergences to help the deep network to distinguish the hard fine-grained attributes. We conduct extensive experiments on seven PAR benchmarks, and results indicate that the proposed MCFL with the native ResNet-50 backbone surpasses the state-of-the-art comparison methods in mean accuracy and recall. [ABSTRACT FROM AUTHOR]

Artificial neural network (ANN) is one of the technologies used for emerging real-world problems. Activation functions (AF) are used in deep learning architectures to make decisions in the hidden and output layers. An AF influences the dynamics of training and performance of an ANN. This paper proposes a novel AF called E-Tanh by extending the Tanh AF for ANN models. When used in three shallow ANN models with 2, 4, and 6 hidden layers with the Modified National Institute of Standards and Technology database (MNIST), it gave a maximum accuracy of 99.5% for handwritten digits classification than the results produced by the existing AFs. The proposed AF E-Tanh outperformed other existing and well-known AFs ReLU, Sigmoid, Tanh, Swish, and E-Swish. In deep ANNs with 5–50 hidden layers, the proposed AF's prediction accuracy of up to 25 hidden layers was higher than the existing AFs on the MNIST database. When used in shallow CNN for the CIFAR10 database, it outperformed other AFs. When used in wide residual network, it performed poorly in classifying images in CIFAR10 and CIFAR100 database but performed competitively with all other AFs in CNN models on the MNIST dataset. [ABSTRACT FROM AUTHOR]

Recently, many studies have been carried out on model compression to handle the high computational cost and high memory footprint brought by the implementation of deep neural networks. In this paper, model compression of convolutional neural networks is constructed as a multiobjective optimization problem with two conflicting objectives, reducing the model size and improving the performance. A novel structured pruning method called Conventional-based and Evolutionary Approaches Guided Multiobjective Pruning (CEA-MOP) is proposed to address this problem, where the power of conventional pruning methods is effectively exploited for the evolutionary process. A delicate balance in pruning rate and model accuracy has been automated achieved by a multiobjective optimization evolutionary model. First, an ensemble framework integrates pruning metrics to establish a codebook for further evolutionary operations. Then, an efficient coding method is developed to shorten the length of chromosome, thus ensuring its superior scalability. Finally, sensitivity analysis is automatically carried out to determine the upper bound of pruning rate for each layer. Notably, on CIFAR-10, CEA-MOP reduces more than 50% FLOPs on ResNet-110 and improves the relative accuracy. Moreover, on ImageNet, CEA-MOP reduces more than 50% FLOPs on ResNet-101 with negligible top-1 accuracy drop. [ABSTRACT FROM AUTHOR]

Crime forecasting has been one of the most complex challenges in law enforcement today, especially when an analysis tends to evaluate inferable and expanded crime rates, although a few methodologies for subsequent equivalents have been embraced before. In this work, we use a strategy for a time series model and machine testing systems for crime estimation. The paper centers on determining the quantity of crimes. Considering various experimental analyses, this investigation additionally features results obtained from a neural system that could be a significant alternative to machine learning and ordinary stochastic techniques. In this paper, we applied various techniques to forecast the number of possible crimes in the next 5 years. First, we used the existing machine learning techniques to predict the number of crimes. Second, we proposed two approaches, a modified autoregressive integrated moving average model and a modified artificial neural network model. The prime objective of this work is to compare the applicability of a univariate time series model against that of a variate time series model for crime forecasting. More than two million datasets are trained and tested. After rigorous experimental results and analysis are generated, the paper concludes that using a variate time series model yields better forecasting results than the predicted values from existing techniques. These results show that the proposed method outperforms existing methods. [ABSTRACT FROM AUTHOR]

Credit rating is an important part of bank credit risk management. Since the traditional radial basis function network model is more susceptible to outliers and cannot effectively process the classification data, it is very sensitive in terms of the initial center and class width of the selected model. This paper mainly studies the application of the radial basis function neural network model combined with the optimal segmentation algorithm in the personal loan credit rating model of banks or other financial institutions. The optimal segmentation algorithm is improved and applied to the training of RBF neural network parameters in this paper to increase the center and width of the class, and the center and width of the RBF network model are further improved. Finally, the adaptive selection of the number of hidden nodes is realized by using the differential objective function of the class to adjust dynamically the structure of the radial basis function network model, which is used to establish the credit rating model. The experimental results show that the improved model has higher precision when dealing with non-numeric data, and the robustness of the improved model has been improved. [ABSTRACT FROM AUTHOR]

Due to the characteristics of time-varying traffic and nonlinearity, the short-term traffic flow data are difficult to predict accurately. The purpose of this paper is to improve the short-term traffic flow prediction accuracy through the proposed improved wavelet neural network prediction model and provide basic data and decision support for the intelligent traffic management system. In view of the extremely strong nonlinear processing power, self-organization, self-adaptation and learning ability of wavelet neural network (WNN), this paper uses it as the basic prediction model and uses the particle swarm optimization algorithm for the slow convergence rate and local optimal problem of WNN prediction algorithm. With the advantages of fast convergence, high robustness and strong global search ability, an improved particle swarm optimization algorithm is proposed to optimize the wavelet neural network prediction model. The improved wavelet neural network is used to predict short-term traffic flow. The experimental results show that the proposed algorithm is more efficient than the WNN and PSO–WNN algorithms alone. The prediction results are more stable and more accurate. Compared with the traditional wavelet neural network, the error is reduced by 14.994%. [ABSTRACT FROM AUTHOR]

The monitoring of physical activities and recognition of motion disorders belong to important diagnostical tools in neurology and rehabilitation. The goal of the present paper is in the contribution to this topic by (1) analysis of accelerometric signals recorded by wearable sensors located at specific body positions and by (2) implementation of deep learning methods to classify signal features. This paper uses the general methodology to analysis of accelerometric signals acquired during cycling at different routes followed by the global positioning system. The experimental dataset includes 850 observations that were recorded by a mobile device in the spine area (L3 verterbra) for cycling routes with the different slope. The proposed methodology includes the use of deep learning convolutional neural networks with five layers applied to signal values transformed into the frequency domain without specification of any signal features. The accuracy of discrimination between different motion patterns for the uphill and downhill cycling and recognition of 4 classes associated with different route slopes was 96.6% with the loss criterion of 0.275 for sigmoidal activation functions. These results were compared with those evaluated for selected sets of features estimated for each observation and classified by the support vector machine, Bayesian methods, and the two-layer neural network. The best cross-validation error of 0.361 was achieved for the two-layer neural network model with the sigmoidal and softmax transfer functions. Our methodology suggests that deep learning neural networks are efficient in the assessment of motion activities for automated data processing and have a wide range of applications, including rehabilitation, early diagnosis of neurological problems, and possible use in engineering as well. [ABSTRACT FROM AUTHOR]

Signature verification has been one of the major researched areas in the field of computer vision. Many financial and legal organizations use signature verification as an access control and authentication. Signature images are not rich in texture; however, they have much vital geometrical information. Through this work, we have proposed a signature verification methodology that is simple yet effective. The technique presented in this paper harnesses the geometrical features of a signature image like center, isolated points, connected components, etc. and, with the power of artificial neural network classifier, classifies the signature image based on their geometrical features. Publicly available dataset MCYT, BHSig260 (contains the image of two regional languages Bengali and Hindi) has been used in this paper to test the effectiveness of the proposed method. We have received a lower equal error rate on MCYT 100 dataset and higher accuracy on the BHSig260 dataset. [ABSTRACT FROM AUTHOR]

The introduction of logistics theory and logistics technology has made the government and enterprises gradually realize that the development of logistics has an important strategic role, which can effectively solve the changing needs of users, optimize resource allocation, improve the investment environment, and enhance the overall strength and overall competitiveness of the regional economy. This paper carries out matrix–vector multiplication operations and weight update operations, designs a perceptron neural network model, and realizes a simulation platform based on MLP neural network. Moreover, on the basis of the standard MLP neural network, this paper proposes to use the deep learning training mechanism to improve the MLP neural network, which provides effective technical support for the improvement of the prediction model. In addition, through the fusion of deep learning and MLP neural network, an MLP neural network with three hidden layers is determined. Finally, this paper builds a model based on the MLP neural network algorithm, selects the RBF kernel function as the kernel function of the model by referring to the relevant literature, and uses PSO to optimize the combination of parameters. It can be seen from the result of the evaluation index that each evaluation index is relatively small. The result shows that the prediction is accurate, and the empirical result shows the feasibility of the model to predict the demand for industrial logistics in Shanxi Province. [ABSTRACT FROM AUTHOR]

Source localization with a network of low-cost motes with limited processing, memory, and energy resources is considered in this paper. The state-of-the-art methods are mostly based on complicated signal processing approaches in which motes send their (processed) data to a fusion center (FC) wherein the source is localized. These methods are resource-demanding and mostly do not meet the limitations of motes and network. In this paper, we consider distributed detection where each mote performs a binary hypothesis test to detect locally the existence of a desired source and sends its (potentially erroneous) decision to FC during just one bit (1 indicates source existence and 0 otherwise). Hence, both processing and bandwidth constraints are met. We propose to use an artificial neural network (ANN) to correct erroneous local decisions. After error correction, the region affected by the source is specified by nodes with decision 1. Moreover, we propose to localize the source by deep learning in FC which converts the network of decisions 1 and 0 to a black and white image with white pixels in the locations of motes with decision 1. The proposed schemes of error correction by ANN (ECANN) and source localization with deep learning (SoLDeL) were evaluated in a fire detection application. We showed that SoLDeL performs appropriately and scales well into large networks. Moreover, the applicability of ECANN in delineation of farm management zones was illustrated. [ABSTRACT FROM AUTHOR]

The purpose of smart city is to enhance the optimal utilization of scarce resources and improve the resident's quality of live. The smart cities employed Internet of Things (IoT) to create a sustainable urban life. The IoT devices such as sensors, actuators, and smartphones in the smart cities generate data. The data generated from the smart cities are subjected to analytics to gain insight and discover new knowledge for improving the efficiency and effectiveness of the smart cities. Recently, the application of deep learning in smart cities has gained a tremendous attention from the research community. However, despite raise in popularity and achievements made by deep learning in solving problems in smart cities, no survey has been dedicated mainly on the application of deep learning in smart cities to show recent progress and direction for future development. To bridge this gap, this paper proposes to conduct a dedicated survey on the applications of deep learning in smart cities. In this paper, recent progress, new taxonomies, challenges and opportunities for future research opportunities on the application of deep learning in smart cities have been unveiled. The paper can provide opportunities for experts in the research community to propose a novel approach for developing the research area. On the other hand, new researchers interested in the research area can use the paper as an entry point. [ABSTRACT FROM AUTHOR]