Search

Convolutional Neural Networks (CNNs) are a kind of artificial neural network designed to extract features and find out patterns for tasks such as segmentation, recognizing objects, and drawing up classification. Within a CNNs architecture, pooling operations are used until the number of parameters and the computational complexity are reduced. Numerous papers have focused on investigating the impact of pooling on the performance of Convolutional Neural Networks (CNNs), leading to the development of various pooling models. Recently, a fuzzy pooling operation based on type-1 fuzzy sets was introduced to cope with the local imprecision of the feature maps. However, in fuzzy set theory, it is not always accurate to assume that the degree of non-membership of an element in a fuzzy set is simply the complement of the degree of membership. This is due to the potential existence of a hesitation degree, which implies a certain level of uncertainty. To overcome this limitation, intuitionistic fuzzy sets (IFS) were introduced to incorporate the concept of a degree of hesitation. In this paper, we introduce a novel pooling operation based on intuitionistic fuzzy sets to incorporate the degree of hesitation heretofore neglected by a fuzzy pooling operation based on classical fuzzy sets, and we investigate its performance in the context of image classification. Intuitionistic pooling is performed in four steps: bifuzzification (by the transformation of data through the use of membership and non-membership maps), first aggregation (through the transformation of the IFS into a standard fuzzy set, second aggregation (through the transformation and use of a sum operator), and the defuzzification of feature map neighborhoods by using a max operator. IFS pooling is used for the construction of an intuitionistic pooling layer that can be applied as a drop-in replacement for the current, fuzzy (type-1) and crisp, pooling layers of CNN architectures. Various experiments involving multiple datasets demonstrate that an IFS-based pooling can enhance the classification performance of a CNN. A benchmarking study reveals that this significantly outperforms even the most recent pooling models, especially in stochastic environments. [ABSTRACT FROM AUTHOR]

Deep learning, a crucial technique for achieving artificial intelligence (AI), has been successfully applied in many fields. The gradual application of the latest architectures of deep learning in the field of time series forecasting (TSF), such as Transformers, has shown excellent performance and results compared to traditional statistical methods. These applications are widely present in academia and in our daily lives, covering many areas including forecasting electricity consumption in power systems, meteorological rainfall, traffic flow, quantitative trading, risk control in finance, sales operations and price predictions for commercial companies, and pandemic prediction in the medical field. Deep learning-based TSF tasks stand out as one of the most valuable AI scenarios for research, playing an important role in explaining complex real-world phenomena. However, deep learning models still face challenges: they need to deal with the challenge of large-scale data in the information age, achieve longer forecasting ranges, reduce excessively high computational complexity, etc. Therefore, novel methods and more effective solutions are essential. In this paper, we review the latest developments in deep learning for TSF. We begin by introducing the recent development trends in the field of TSF and then propose a new taxonomy from the perspective of deep neural network models, comprehensively covering articles published over the past five years. We also organize commonly used experimental evaluation metrics and datasets. Finally, we point out current issues with the existing solutions and suggest promising future directions in the field of deep learning combined with TSF. This paper is the most comprehensive review related to TSF in recent years and will provide a detailed index for researchers in this field and those who are just starting out. [ABSTRACT FROM AUTHOR]

Recent research has revealed that subtle imperceptible perturbations can deceive well-trained neural network models, leading to inaccurate outcomes. These instances, known as adversarial examples, pose significant threats to the secure application of machine learning techniques in safety-critical systems. In this paper, we delve into the study of one-pixel attacks in deep neural networks, recently reported as a kind of adversarial examples. To identify such one-pixel attacks, most existing methodologies rely on the differential evolution method, which utilizes random selection from the current population to escape local optima. However, the differential evolution technique might waste search time and overlook good solutions if the number of iterations is insufficient. Hence, in this paper, we propose a gradient ascent with momentum approach to efficiently discover good solutions for the one-pixel attack problem. As our method takes a more direct route to the goal compared to existing methods relying on blind random walks, it can effectively identify one-pixel attacks. Our experiments conducted on popular CNNs demonstrate that, in comparison with existing methodologies, our technique can detect one-pixel attacks significantly faster. [ABSTRACT FROM AUTHOR]

Breast cancer is one of the most common causes of death in women. Early signs of breast cancer can be an abnormality depicted on breast images like breast ultrasonography. Unfortunately, ultrasound images contain a lot of noise, which greatly increases the difficulty for doctors to interpret them. In recent years, computer-aided diagnosis (CAD) has been widely used in medical images, reducing the workload of doctors and the probability of misdiagnosis. However, it still faces the following challenges in clinical practice: one is the lack of interpretability, and another is that the accuracy is not high enough. In this paper, we propose a classification model of breast ultrasound images that leverages tumor boundaries as prior knowledge and strengthens the model to guide classification. Furthermore, we employ the advantages of convolutional neural network (CNN) to extract local features and Transformer to extract global features to achieve information balance and complementarity between the two neural network models which increase the recognition performance of the model. Additionally, an explanation method is used to generate visual results, thereby improving the poor interpretability of deep learning models. Finally, we evaluate the model on the BUSI dataset and compare it with other CNN and Transformer models. Experimental results show that the proposed model obtains an accuracy of 0.9870 and an F1 score of 0.9872, achieving state-of-the-art performance. [ABSTRACT FROM AUTHOR]

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

With the rapid growth of the Internet, a wealth of movie resources are readily available on the major search engines. Still, it is unlikely that users will be able to find precisely the movies they are more interested in any time soon. Traditional recommendation algorithms, such as collaborative filtering recommendation algorithms only use the user's rating information of the movie, without using the attribute information of the user and the movie, which has the problem of inaccurate recommendations. In order to achieve personalized accurate movie recommendations, a movie recommendation algorithm based on a multi-feature attention mechanism with deep neural networks and convolutional neural networks is proposed. In order to make the predicted movie ratings more accurate, user attribute information and movie attribute information are added, user network and movie network are presented to learn user features and movie features, respectively, and a feature attention mechanism is proposed so that different parts contribute differently to movie ratings. Text features are also extracted using convolutional neural networks, in which an attention mechanism is added to make the extracted text features more accurate, and finally, personalized movie accurate recommendations are achieved. The experimental results verify the effectiveness of the algorithm. The user attribute features and movie attribute features have a good effect on the rating, the feature attention mechanism makes the features distinguish the degree of importance to the rating, and the convolutional neural network adding the attention mechanism makes the extracted text features more effective and achieves high accuracy in MSE, MAE, MAPE, R2, and RMSE indexes. [ABSTRACT FROM AUTHOR]

The COVID-19 pandemic highlighted the importance of health and education and also revealed the need for innovative solutions relative to the challenges confronting these disciplines. This includes the development of interactive learning tools and intelligent tutoring systems that can provide feedback to both teachers and students, as well as the use of data analytics to assess student progress and adjust teaching strategies accordingly. In healthcare, machine learning algorithms have been used to predict the likelihood of disease progression, identify at-risk patients, and personalize treatment plans. Thus, in [[19]], both machine learning models such as support vector machines, decision trees, and neural networks, together with logistic regression, were used to predict likely university dropout rates either at the beginning of the course of study or at the end of the first semester. [Extracted from the article]

Convolutional neural networks (CNNs) offer significant advantages when used in various image classification tasks and computer vision applications. CNNs are increasingly deployed in environments from edge and Internet of Things (IoT) devices to high-end computational infrastructures, such as supercomputers, cloud computing, and data centers. The growing amount of data and the growth in their model size and computational complexity, however, introduce major computational challenges. Such challenges present entry barriers for IoT and edge devices as well as increase the operational expenses of large-scale computing systems. Thus, it has become essential to optimize CNN algorithms. In this paper, we introduce the S-VELCRO compression algorithm, which exploits value locality to trim filters in CNN models utilized for specialized tasks. S-VELCRO uses structured compression, which can save costs and reduce overhead compared with unstructured compression. The algorithm runs in two steps: a preprocessing step identifies the filters with a high degree of value locality, and a compression step trims the selected filters. As a result, S-VELCRO reduces the computational load of the channel activation function and avoids the convolution computation of the corresponding trimmed filters. Compared with typical CNN compression algorithms that run heavy back-propagation training computations, S-VELCRO has significantly fewer computational requirements. Our experimental analysis shows that S-VELCRO achieves a compression-saving ratio between 6% and 30%, with no degradation in accuracy for ResNet-18, MobileNet-V2, and GoogLeNet when used for specialized tasks. [ABSTRACT FROM AUTHOR]

Pulmonary diseases are life-threatening diseases commonly observed worldwide, and timely diagnosis of these diseases is essential. Meanwhile, increased use of Convolution Neural Networks has promoted the advancement of computer-assisted clinical recommendation systems for diagnosing diseases using chest radiographs. The texture and shape of the tissues in the diagnostic images are essential aspects of prognosis. Therefore, in the latest studies, the vast set of images with a larger resolution is paired with deep learning techniques to enhance the performance of the disease diagnosis in chest radiographs. Moreover, pulmonary diseases have irregular and different sizes; therefore, several studies sought to add new components to existing deep learning techniques for acquiring multi-scale imaging features from diagnostic chest X-rays. However, most of the attempts do not consider the computation overhead and lose the spatial details in an effort to capture the larger receptive field for obtaining the discriminative features from high-resolution chest X-rays. In this paper, we propose an explainable and lightweight Multi-Scale Chest X-ray Network (MS-CheXNet) to predict abnormal diseases from the diagnostic chest X-rays. The MS-CheXNet consists of four following main subnetworks: (1) Multi-Scale Dilation Layer (MSDL), which includes multiple and stacked dilation convolution channels that consider the larger receptive field and captures the variable sizes of pulmonary diseases by obtaining more discriminative spatial features from the input chest X-rays; (2) Depthwise Separable Convolution Neural Network (DS-CNN) is used to learn imaging features by adjusting lesser parameters compared to the conventional CNN, making the overall network lightweight and computationally inexpensive, making it suitable for mobile vision tasks; (3) a fully connected Deep Neural Network module is used for predicting abnormalities from the chest X-rays; and (4) Gradient-weighted Class Activation Mapping (Grad-CAM) technique is employed to check the decision models' transparency and understand their ability to arrive at a decision by visualizing the discriminative image regions and localizing the chest diseases. The proposed work is compared with existing disease prediction models on chest X-rays and state-of-the-art deep learning strategies to assess the effectiveness of the proposed model. The proposed model is tested with a publicly available Open-I Dataset and data collected from a private hospital. After the comprehensive assessment, it is observed that the performance of the designed approach showcased a 7% to 18% increase in accuracy compared to the existing method. [ABSTRACT FROM AUTHOR]

Person re-identification has become an essential application within computer vision due to its ability to match the same person over non-overlapping cameras. However, it is a challenging task because of the broad view of cameras with a large number of pedestrians appearing with various poses. As a result, various approaches of supervised model learning have been utilized to locate and identify a person based on the given input. Nevertheless, several of these approaches perform worse than expected in retrieving the right person in real-time over multiple CCTVs/camera views. This is due to inaccurate segmentation of the person, leading to incorrect classification. This paper proposes an efficient and real-time person re-identification system, named ReID-DeePNet system. It is based on fusing the matching scores generated by two different deep learning models, convolutional neural network and deep belief network, to extract discriminative feature representations from the pedestrian image. Initially, a segmentation procedure was developed based on merging the advantages of the Mask R-CNN and GrabCut algorithm to tackle the adverse effects caused by background clutter. Afterward, the two different deep learning models extracted discriminative feature representations from the pedestrian segmented image, and their matching scores were fused to make the final decision. Several extensive experiments were conducted, using three large-scale and challenging person re-identification datasets: Market-1501, CUHK03, and P-DESTRE. The ReID-DeePNet system achieved new state-of-the-art Rank-1 and mAP values on these three challenging ReID datasets. [ABSTRACT FROM AUTHOR]

The fine identification of vehicle color can assist in criminal investigation or intelligent traffic management law enforcement. Since almost all vehicle-color datasets that are used to train models are collected in good weather, the existing vehicle-color recognition algorithms typically show poor performance for outdoor visual tasks. In this paper we construct a new R a i n V e h i c l e C o l o r -24 dataset by rain-image rendering using P S technology and a S y R a G A N algorithm based on the V e h i c l e C o l o r -24 dataset. The dataset contains a total of 40,300 rain images with 125 different rain patterns, which can be used to train deep neural networks for specific vehicle-color recognition tasks. Experiments show that the vehicle-color recognition algorithms trained on the new dataset R a i n V e h i c l e C o l o r -24 improve accuracy to around 72 % and 90 % on rainy and sunny days, respectively. The code is available at humingdi2005@github.com. [ABSTRACT FROM AUTHOR]

The forecasting of tourist arrival depends on the accurate modeling of prevalent data patterns found in tourist arrival, especially for daily tourist arrival, where tourist arrival changes are more complex and highly nonlinear. In this paper, a new multiscale mode learning-based tourist arrival forecasting model is proposed to exploit different multiscale data features in tourist arrival movement. Two popular Mode Decomposition models (MD) and the Convolutional Neural Network (CNN) model are introduced to model the multiscale data features in the tourist arrival data The data patterns at different scales are extracted using these two different MD models which dynamically decompose tourist arrival into the distinctive intrinsic mode function (IMF) data components. The convolutional neural network uses the deep network to further model the multiscale data structure of tourist arrivals, with the reduced dimensionality of key multiscale data features and finer modeling of nonlinearity in tourist arrival. Our empirical results using daily tourist arrival data show that the MD-CNN tourist arrival forecasting model significantly improves the forecasting reliability and accuracy. [ABSTRACT FROM AUTHOR]

In light of the increasing level of correlation and dependence between the crude oil markets and the external influencing factors in the related financial markets, we propose a new multivariate empirical decomposition convolutional neural network model to incorporate the external influence of financial markets such as stock market and exchange market in a multiscale setting into the modeling of crude oil market risk movement. We propose a multivariate empirical model decomposition to analyze the finer details of interdependence among risk movement of different markets across different time horizons or scales. We also introduce the convolutional neural network to construct a new nonlinear ensemble algorithm to reduce the estimation bias and improve the forecasting accuracy. We used the major crude oil price data, stock market index, and the euro/United States dollar exchange rate data to evaluate the performance of the multivariate empirical model decomposition convolutional neural network model. The combination of both the multivariate empirical model decomposition and the convolutional neural network model in this paper has produced the risk forecasts with significantly improved risk forecasting accuracy. [ABSTRACT FROM AUTHOR]

The rapid and accurate damage assessment of buildings plays a critical role in disaster response. Based on pairs of pre- and post-disaster remote sensing images, effective building damage level assessment can be conducted. However, most existing methods are based on Convolutional Neural Network, which has limited ability to learn the global context. An attention mechanism helps ameliorate this problem. Hierarchical Transformer has powerful potential in the remote sensing field with strong global modeling capability. In this paper, we propose a novel two-stage damage assessment framework called SDAFormer, which embeds a symmetric hierarchical Transformer into a siamese U-Net-like network. In the first stage, the pre-disaster image is fed into a segmentation network for building localization. In the second stage, a two-branch damage classification network is established based on weights shared from the first stage. Then, pre- and post-disaster images are delivered to the network separately for damage assessment. Moreover, a spatial fusion module is designed to improve feature representation capability by building pixel-level correlation, which establishes spatial information in Swin Transformer blocks. The proposed framework achieves significant improvement on the large-scale building damage assessment dataset—xBD. [ABSTRACT FROM AUTHOR]

Offshore wind energy is increasingly being realized at deeper ocean depths where jacket foundations are now the greatest choice for dealing with the hostile environment. The structural stability of these undersea constructions is critical. This paper states a methodology to detect and classify damage in a jacket-type support structure for offshore wind turbines. Because of the existence of unknown external disturbances (wind and waves), standard structural health monitoring technologies, such as guided waves, cannot be used directly in this application. Therefore, using vibration-response-only accelerometer measurements, a methodology based on two in-cascade Siamese convolutional neural networks is proposed. The first Siamese network detects the damage (discerns whether the structure is healthy or damaged). Then, in case damage is detected, a second Siamese network determines the damage diagnosis (classifies the type of damage). The main results and claims of the proposed methodology are the following ones: (i) It is solely dependent on accelerometer sensor output vibration data, (ii) it detects damage and classifies the type of damage, (iii) it operates in all wind turbine regions of operation, (iv) it requires less data to train since it is built on Siamese convolutional neural networks, which can learn from very little data compared to standard machine/deep learning algorithms, (v) it is validated in a scaled-down experimental laboratory setup, and (vi) its feasibility is demonstrated as all computed metrics (accuracy, precision, recall, and F1 score) for the obtained results remain above 96%. [ABSTRACT FROM AUTHOR]

Point-of-interest (POI) recommendation is the prevalent personalized service in location-based social networks (LBSNs). A single use of matrix factorization (MF) or deep neural networks cannot effectively capture the complex structure of user–POI interactions. In addition, to alleviate the data-sparsity problem, current methods primarily introduce the auxiliary information of users and POIs. Auxiliary information is often judged to be equally valued, which will dissipate some of the valuable information. Hence, we propose a novel POI recommendation method fusing auxiliary attribute information based on the neural matrix factorization, integrating the convolutional neural network and attention mechanism (NueMF-CAA). First, the k-means and term frequency–inverse document frequency (TF-IDF) algorithms are used to mine the auxiliary attribute information of users and POIs from user check-in data to alleviate the data-sparsity problem. A convolutional neural network and an attention mechanism are applied to learn the expression of auxiliary attribute information and distinguish the importance of auxiliary attribute information, respectively. Then, the auxiliary attribute information feature vectors of users and POIs are concatenated with their respective latent feature vectors to obtain the complete latent feature vectors of users and POIs. Meanwhile, generalized matrix factorization (GMF) and multilayer perceptron (MLP) are used to learn the linear and nonlinear interactions between users and POIs, respectively, and the last hidden layer is connected to integrate the two parts to alleviate the implicit feedback problem and make the recommendation results more interpretable. Experiments on two real-world datasets, the Foursquare dataset and the Weibo dataset, demonstrate that the proposed method significantly improves the evaluation metrics—hit ratio (HR) and normalized discounted cumulative gain (NDCG). [ABSTRACT FROM AUTHOR]

In the single pruning algorithm, channel pruning or filter pruning is used to compress the deep convolution neural network, and there are still many redundant parameters in the compressed model. Directly pruning the filter will largely cause the loss of key information and affect the accuracy of model classification. To solve these problems, a parallel pruning algorithm combined with image enhancement is proposed. Firstly, in order to improve the generalization ability of the model, a data enhancement method of random erasure is introduced. Secondly, according to the trained batch normalization layer scaling factor, the channels with small contribution are cut off, the model is initially thinned, and then the filters are pruned. By calculating the geometric median of the filters, redundant filters similar to them are found and pruned, and their similarity is measured by calculating the distance between filters. Pruning was done using VGG19 and DenseNet40 on cifar10 and cifar100 data sets. The experimental results show that this algorithm can improve the accuracy of the model, and at the same time, it can compress the calculation and parameters of the model to a certain extent. Finally, this method is applied in practice, and combined with transfer learning, traffic objects are classified and detected on the mobile phone. [ABSTRACT FROM AUTHOR]

The prediction of stock price movement is a popular area of research in academic and industrial fields due to the dynamic, highly sensitive, nonlinear and chaotic nature of stock prices. In this paper, we constructed a convolutional neural network model based on a deep factorization machine and attention mechanism (FA-CNN) to improve the prediction accuracy of stock price movement via enhanced feature learning. Unlike most previous studies, which focus only on the temporal features of financial time series data, our model also extracts intraday interactions among input features. Further, in data representation, we used the sub-industry index as supplementary information for the current state of the stock, since there exists stock price co-movement between individual stocks and their industry index. The experiments were carried on the individual stocks in three industries. The results showed that the additional inputs of (a) the intraday interactions among input features and (b) the sub-industry index information effectively improved the prediction accuracy. The highest prediction accuracy of the proposed FA-CNN model is 64.81%. It is 7.38% higher than that of traditional LSTM, and 3.71% higher than that of the model without sub-industry index as additional input features. [ABSTRACT FROM AUTHOR]

The images in high resolution contain more useful information than the images in low resolution. Thus, high-resolution digital images are preferred over low-resolution images. Image super-resolution is one of the principal techniques for generating high-resolution images. The major advantages of super-resolution methods are that they are economical, independent of the image capture devices, and can be statically used. In this paper, a single-image super-resolution network model based on convolutional neural networks is proposed by combining conventional autoencoder and residual neural network approaches. A convolutional neural network-based dictionary method is used to train low-resolution input images for high-resolution images. In addition, a linear refined unit thresholds the convolutional neural network output to provide a better low-resolution image dictionary. Autoencoders aid in the removal of noise from images and the enhancement of their quality. Secondly, the residual neural network model processes it further to create a high-resolution image. The experimental results demonstrate the outstanding performance of our proposed method compared to other traditional methods. The proposed method produces clearer and more detailed high-resolution images, as they are important in real-life applications. Moreover, it has the advantage of combining convolutional neural network-based dictionary learning, autoencoder image enhancement, and noise removal. Furthermore, residual neural network training with improved preprocessing creates an efficient and versatile single-image super-resolution network. [ABSTRACT FROM AUTHOR]

Over the past decade, Convolutional Neural Networks (CNNs) have been extensively deployed in security-critical areas; however, the security of CNN models is threatened by adversarial attacks. Decision-based adversarial attacks, wherein an attacker relies solely on the final output label of the target model to craft adversarial examples, are the most challenging yet practical adversarial attacks. However, existing decision-based adversarial attacks generally suffer from poor query efficiency or low attack success rate, especially for targeted attacks. To address these issues, we propose a query-efficient Adversarial Direction-guided Decision-based Attack (ADDA), which exploits the advantages of transfer-based priors and the benefits of a single query. The transfer-based priors provided by the gradients of multiple different surrogate models can be utilized to suggest the most promising search directions for generating adversarial examples. The query consumption during the ADDA attack is mainly derived from a single query evaluation of the candidate adversarial samples, which significantly saves the number of queries. Experimental results on several ImageNet classifiers, including l ∞ and l 2 threat models, demonstrate that our proposed approach overwhelmingly outperforms existing state-of-the-art decision-based attacks in terms of both query efficiency and attack success rate. We show case studies of ADDA against a real-world API in which it is successfully able to fool the Google Cloud Vision API after only a few queries. [ABSTRACT FROM AUTHOR]

Due to industrial demands to handle increasing amounts of training data, lower the cost of computing one model at a time, and lessen the ecological effects of intensive computing resource consumption, the job of speeding the training of deep neural networks becomes exceedingly challenging. Adaptive Online Importance Sampling and IDS are two brand-new methods for accelerating training that are presented in this research. On the one hand, Adaptive Online Importance Sampling accelerates neural network training by lowering the number of forward and backward steps depending on how poorly a model can identify a given data sample. On the other hand, Intellectual Data Selection accelerates training by removing semantic redundancies from the training dataset and subsequently lowering the number of training steps. The study reports average 1.9x training acceleration for ResNet50, ResNet18, MobileNet v2 and YOLO v5 on a variety of datasets: CIFAR-100, CIFAR-10, ImageNet 2012 and MS COCO 2017, where training data are reduced by up to five times. Application of Adaptive Online Importance Sampling to ResNet50 training on ImageNet 2012 results in 2.37 times quicker convergence to 71.7% top-1 accuracy, which is within 5% of the baseline. Total training time for the same number of epochs as the baseline is reduced by 1.82 times, with an accuracy drop of 2.45 p.p. The amount of time required to apply Intellectual Data Selection to ResNet50 training on ImageNet 2012 is decreased by 1.27 times with a corresponding decline in accuracy of 1.12 p.p. Applying both methods to ResNet50 training on ImageNet 2012 results in 2.31 speedup with an accuracy drop of 3.5 p.p. [ABSTRACT FROM AUTHOR]

A common issue with X-ray examinations (XE) is the erroneous quality classification of the XE, implying that the process needs to be repeated, thus delaying the diagnostic assessment of the XE and increasing the amount of radiation the patient receives. The authors propose a system for automatic quality classification of XE based on convolutional neural networks (CNN) that would simplify this process and significantly decrease erroneous quality classification. The data used for CNN training consist of 4000 knee images obtained via radiography procedure (KXE) in total, with 2000 KXE labeled as acceptable and 2000 as unacceptable. Additionally, half of the KXE belonging to each label are right knees and left knees. Due to the sensitivity to image orientation of some CNNs, three approaches are discussed: (1) Left-right-knee (LRK) classifies XE based just on their label, without taking into consideration their orientation; (2) Orientation discriminator (OD) for the left knee (LK) and right knee (RK) analyses images based on their orientation and inserts them into two separate models regarding orientation; (3) Orientation discriminator combined with knee XRs flipped to the left or right (OD-LFK)/OD-RFK trains the models with all images being horizontally flipped to the same orientation and uses the aforementioned OD to determine whether the image needs to be flipped or not. All the approaches are tested with five CNNs (AlexNet, ResNet50, ResNet101, ResNet152, and Xception), with grid search and k-fold cross-validation. The best results are achieved using the OD-RFK hybrid approach with the Xception network architecture as the classifier and ResNet152 as the OD, with an average AUC of 0.97 (±0.01). [ABSTRACT FROM AUTHOR]

The exploration of the performance of elite athletes by cognitive neuroscience as a research method has become an emerging field of study in recent years. In the research of cognitive abilities and athletic performance of elite athletes, the tasks of an experiment are usually performed by athletics task of closed skills rather than open skills. Thus, little has been conducted to explore the cognitive abilities and athletic performance of elite athletes with open skills. This study is novel as it attempts at predicting how table tennis athletes perform by collecting their dynamic brain waves when executing specific plays of table tennis, and then putting the data of dynamic brain waves to deep neural network algorithms. The method of this study begins with the collection of data on the dynamic brain waves of table tennis athletes and then converts the time domain data into frequency domain data before improving the accuracy of categorization using a hybrid convolutional neural networks (CNN) framework of deep learning. The findings hereof were that the algorithm of hybrid deep neural networks proposed herein was able to predict the sports performance of athletes from their dynamic brain waves with an accuracy up to 96.70%. This study contributes to the literature in cognitive neuroscience on dynamic brain waves in open skills and creates a novel hybrid deep CNN classification model for identifying dynamic brain waves associated with good elite sports performance. [ABSTRACT FROM AUTHOR]

Researchers are interested in Facial Emotion Recognition (FER) because it could be useful in many ways and has promising applications. The main task of FER is to identify and recognize the original facial expressions of users from digital inputs. Feature extraction and emotion recognition make up the majority of the traditional FER. Deep Neural Networks, specifically Convolutional Neural Network (CNN), are popular and highly used in FER due to their inherent image feature extraction process. This work presents a novel method dubbed as EfficientNet-XGBoost that is based on Transfer Learning (TL) technique. EfficientNet-XGBoost is basically a cascading of the EfficientNet and the XGBoost techniques along with certain enhancements by experimentation that reflects the novelty of the work. To ensure faster learning of the network and to overcome the vanishing gradient problem, our model incorporates fully connected layers of global average pooling, dropout and dense. EfficientNet is fine-tuned by replacing the upper dense layer(s) and cascading the XGBoost classifier making it suitable for FER. Feature map visualization is carried out that reveals the reduction in the size of feature vectors. The proposed method is well-validated on benchmark datasets such as CK+, KDEF, JAFFE, and FER2013. To overcome the issue of data imbalance, in some of the datasets namely CK+ and FER2013, we augmented data artificially through geometric transformation techniques. The proposed method is implemented individually on these datasets and corresponding results are recorded for performance analysis. The performance is computed with the help of several metrics like precision, recall and F1 measure. Comparative analysis with competent schemes are carried out on the same sample data sets separately. Irrespective of the nature of the datasets, the proposed scheme outperforms the rest with overall rates of accuracy being 100%, 98% and 98% for the first three datasets respectively. However, for the FER2013 datasets, efficiency is less promisingly observed in support of the proposed work. [ABSTRACT FROM AUTHOR]

Peer-to-Peer (P2P) lending transactions take place by the lenders choosing a borrower and lending money. It is important to predict whether a borrower can repay because the lenders must bear the credit risk when the borrower defaults, but it is difficult to design feature extractors with very complex information about borrowers and loan products. In this paper, we present an architecture of deep convolutional neural network (CNN) for predicting the repayment in P2P social lending to extract features automatically and improve the performance. CNN is a deep learning model for classifying complex data, which extracts discriminative features automatically by convolution operation on lending data. We classify the borrower's loan status by capturing the robust features and learning the patterns. Experimental results with 5-fold cross-validation show that our method automatically extracts complex features and is effective in repayment prediction on Lending Club data. In comparison with other machine learning methods, the standard CNN has achieved the highest performance with 75.86%. Exploiting various CNN models such as Inception, ResNet, and Inception-ResNet results in the state-of-the-art performance of 77.78%. We also demonstrate that the features extracted by our model are better performed by projecting the samples into the feature space. [ABSTRACT FROM AUTHOR]

Binary neural networks (BNNs) are an extremely promising method for reducing deep neural networks' complexity and power consumption significantly. Binarization techniques, however, suffer from ineligible performance degradation compared to their full-precision counterparts. Prior work mainly focused on strategies for sign function approximation during the forward and backward phases to reduce the quantization error during the binarization process. In this work, we propose a bimodal-distributed binarization method (BD-BNN). The newly proposed technique aims to impose a bimodal distribution of the network weights by kurtosis regularization. The proposed method consists of a teacher–trainer training scheme termed weight distribution mimicking (WDM), which efficiently imitates the full-precision network weight distribution to their binary counterpart. Preserving this distribution during binarization-aware training creates robust and informative binary feature maps and thus it can significantly reduce the generalization error of the BNN. Extensive evaluations on CIFAR-10 and ImageNet demonstrate that our newly proposed BD-BNN outperforms current state-of-the-art schemes. [ABSTRACT FROM AUTHOR]

Accurate forecasting of taxi demand has facilitated the rational allocation of urban public transport resources, reduced congestion in urban transport networks, and shortened passenger waiting time. However, virtual station discovery and modelling of the demand when forecasting through graph convolutional neural networks remains challenging. In this study, the virtual station discovery problem was addressed by using a two-stage clustering approach, which considers the geographical and load characteristics of taxi demand. Furthermore, a fusion model combining non-negative matrix decomposition and a graph convolutional neural network was proposed in order to extract the features of the nodes for dimension reduction and adaptive adjacency matrix computation. By the construction of a local processing structure, further extraction of the local characteristics of the demand was achieved. The experimental results show that the method in this study outperforms state-of-the-art methods in terms of the root mean square error and average absolute value error. Therefore, the model proposed in this study is able to achieve accurate forecasting of taxi demand. [ABSTRACT FROM AUTHOR]

Sentiment analysis of news headlines is an important factor that investors consider when making investing decisions. We claim that the sentiment analysis of financial news headlines impacts stock market values. Hence financial news headline data are collected along with the stock market investment data for a period of time. Using Valence Aware Dictionary and Sentiment Reasoning (VADER) for sentiment analysis, the correlation between the stock market values and sentiments in news headlines is established. In our experiments, the data on stock market prices are collected from Yahoo Finance and Kaggle. Financial news headlines are collected from the Wall Street Journal, Washington Post, and Business-Standard website. To cope with such a massive volume of data and extract useful information, various embedding methods, such as Bag-of-words (BoW) and Term Frequency-Inverse Document Frequency (TF-IDF), are employed. These are then fed into machine learning models such as Naive Bayes and XGBoost as well as deep learning models such as Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM). Various natural language processing, andmachine and deep learning algorithms are considered in our study to achieve the desired outcomes and to attain superior accuracy than the current state-of-the-art. Our experimental study has shown that CNN (80.86%) and LSTM (84%) are the best performing models in relation to machine learning models, such as Support Vector Machine (SVM) (50.3%), Random Forest (67.93%), and Naive Bayes (59.79%). Moreover, two novel methods, BERT and RoBERTa, were applied with the expectation of better performance than all the other models, and they did exceptionally well by achieving an accuracy of 90% and 88%, respectively. [ABSTRACT FROM AUTHOR]

Cassava is a crucial food and nutrition security crop cultivated by small-scale farmers and it can survive in a brutal environment. It is a significant source of carbohydrates in African countries. Sometimes, Cassava crops can be infected by leaf diseases, affecting the overall production and reducing farmers' income. The existing Cassava disease research encounters several challenges, such as poor detection rate, higher processing time, and poor accuracy. This research provides a comprehensive learning strategy for real-time Cassava leaf disease identification based on enhanced CNN models (ECNN). The existing Standard CNN model utilizes extensive data processing features, increasing the computational overhead. A depth-wise separable convolution layer is utilized to resolve CNN issues in the proposed ECNN model. This feature minimizes the feature count and computational overhead. The proposed ECNN model utilizes a distinct block processing feature to process the imbalanced images. To resolve the color segregation issue, the proposed ECNN model uses a Gamma correction feature. To decrease the variable selection process and increase the computational efficiency, the proposed ECNN model uses global average election polling with batch normalization. An experimental analysis is performed over an online Cassava image dataset containing 6256 images of Cassava leaves with five disease classes. The dataset classes are as follows: class 0: "Cassava Bacterial Blight (CBB)"; class 1: "Cassava Brown Streak Disease (CBSD)"; class 2: "Cassava Green Mottle (CGM)"; class 3: "Cassava Mosaic Disease (CMD)"; and class 4: "Healthy". Various performance measuring parameters, i.e., precision, recall, measure, and accuracy, are calculated for existing Standard CNN and the proposed ECNN model. The proposed ECNN classifier significantly outperforms and achieves 99.3% accuracy for the balanced dataset. The test findings prove that applying a balanced database of images improves classification performance. [ABSTRACT FROM AUTHOR]