Convolutional neural networks, which automatically learn features from raw data to approximate functions, are being increasingly applied to the end-to-end analysis of electroencephalographic signals, especially for decoding brain states in brain-computer interfaces. Nevertheless, CNNs introduce a large number of trainable parameters, may require long training times, and lack in interpretability of learned features. The aim of this study is to propose a CNN design for P300 decoding with emphasis on its lightweight design while guaranteeing high performance, on (...) the effects of different training strategies, and on the use of post-hoc techniques to explain network decisions. The proposed design, named MS-EEGNet, learned temporal features in two different timescales in an efficient and optimized way, and was validated on three P300 datasets. The CNN was trained using different strategies and was compared with several state-of-the-art algorithms. Furthermore, variants of the baseline MS-EEGNet were analyzed to evaluate the impact of different hyper-parameters on performance. Lastly, saliency maps were used to derive representations of the relevant spatio-temporal features that drove CNN decisions. MS-EEGNet was the lightest CNN compared with the tested SOA CNNs, despite its multiple timescales, and significantly outperformed the SOA algorithms. Post-hoc hyper-parameter analysis confirmed the benefits of the innovative aspects of MS-EEGNet. Furthermore, MS-EEGNet did benefit from transfer learning, especially using a low number of training examples, suggesting that the proposed approach could be used in BCIs to accurately decode the P300 event while reducing calibration times. Representations derived from the saliency maps matched the P300 spatio-temporal distribution, further validating the proposed decoding approach. This study, by specifically addressing the aspects of lightweight design, transfer learning, and interpretability, can contribute to advance the development of deep learning algorithms for P300-based BCIs. (shrink)

Background: Detecting and classifying fish diseases is crucial for maintaining the health and sustainability of aquaculture systems. This study employs deep learning techniques, particularly Convolutional Neural Networks (CNNs), to automate the detection of various fish diseases using image data. Methods: The study utilizes a carefully curated dataset sourced from the Kaggle database, comprising images representing seven distinct types of fish diseases, along with images of healthy fish. Data preprocessing techniques, including resizing, rescaling, denoising, sharpening, and smoothing, are (...) applied to enhance image quality and facilitate accurate disease detection. Data augmentation is employed to increase the model's ability to generalize to unseen data. The CNN architecture is designed with cascading convolutional layers, ReLU activation functions, and pooling operations to extract high-level features associated with fish infections. The model architecture, implemented using the Keras Sequential API, includes convolutional layers, max pooling layers, and densely connected layers for classification. Results: Experimental results demonstrated promising performance across various disease categories, with high accuracy and balanced precision and recall values for most classes. The study also discussed the impact of climate change on fish disease incidence and underscores the importance of effective monitoring and management practices facilitated by technological innovations such as Big Data, IoT, sensors, and robotics in ensuring sustainable fisheries management. (shrink)

The investigation of visual categorization has recently been aided by the introduction of deep convolutional neural networks (CNNs), which achieve unprecedented accuracy in picture classification after extensive training. Even if the architecture of CNNs is inspired by the organization of the visual brain, the similarity between CNN and human visual processing remains unclear. Here, we investigated this issue by engaging humans and CNNs in a two‐class visual categorization task. To this end, pictures containing animals or vehicles were (...) modified to contain only low/high spatial frequency (HSF) information, or were scrambled in the phase of the spatial frequency spectrum. For all types of degradation, accuracy increased as degradation was reduced for both humans and CNNs; however, the thresholds for accurate categorization varied between humans and CNNs. More remarkable differences were observed for HSF information compared to the other two types of degradation, both in terms of overall accuracy and image‐level agreement between humans and CNNs. The difficulty with which the CNNs were shown to categorize high‐passed natural scenes was reduced by picture whitening, a procedure which is inspired by how visual systems process natural images. The results are discussed concerning the adaptation to regularities in the visual environment (scene statistics); if the visual characteristics of the environment are not learned by CNNs, their visual categorization may depend only on a subset of the visual information on which humans rely, for example, on low spatial frequency information. (shrink)

Convolutional neural networks (CNNs) are increasingly widely used in psychology and neuroscience to predict how human minds and brains respond to visual images. Typically, CNNs represent these images using thousands of features that are learned through extensive training on image datasets. This raises a question: How many of these features are really needed to model human behavior? Here, we attempt to estimate the number of dimensions in CNN representations that are required to capture human psychological representations in (...) two ways: (1) directly, using human similarity judgments and (2) indirectly, in the context of categorization. In both cases, we find that low-dimensional projections of CNN representations are sufficient to predict human behavior. We show that these low-dimensional representations can be easily interpreted, providing further insight into how people represent visual information. A series of control studies indicate that these findings are not due to the size of the dataset we used and may be due to a high level of redundancy in the features appearing in CNN representations. (shrink)

Augmented reality-based brain–computer interface (AR–BCI) has a low signal-to-noise ratio (SNR) and high real-time requirements. Classical machine learning algorithms that improve the recognition accuracy through multiple averaging significantly affect the information transfer rate (ITR) of the AR–SSVEP system. In this study, a fast recognition method based on a separable convolutional neural network (SepCNN) was developed for an AR-based P300 component (AR–P300). SepCNN achieved single extraction of AR–P300 features and improved the recognition speed. A nine-target AR–P300 single-stimulus paradigm was (...) designed to be administered with AR holographic glasses to verify the effectiveness of SepCNN. Compared with four classical algorithms, SepCNN significantly improved the average target recognition accuracy (81.1%) and information transmission rate (57.90 bits/min) of AR–P300 single extraction. SepCNN with single extraction also attained better results than classical algorithms with multiple averaging. (shrink)

Cultural similarities and differences in facial expressions have been a controversial issue in the field of facial communications. A key step in addressing the debate regarding the cultural dependency of emotional expression is to characterize the visual features of specific facial expressions in individual cultures. Here we developed an image analysis framework for this purpose using convolutional neural networks that through training learned visual features critical for classification. We analyzed photographs of facial expressions derived from two databases, (...) each developed in a different country, in which corresponding emotion labels were available. While the CNNs reached high rates of correct results that were far above chance after training with each database, they showed many misclassifications when they analyzed faces from the database that was not used for training. These results suggest that facial features useful for classifying facial expressions differed between the databases. The selectivity of computational units in the CNNs to action units of the face varied across the facial expressions. Importantly, the AU selectivity often differed drastically between the CNNs trained with the different databases. Similarity and dissimilarity of these tuning profiles partly explained the pattern of misclassifications, suggesting that the AUs are important for characterizing the facial features and differ between the two countries. The AU tuning profiles, especially those reduced by principal component analysis, are compact summaries useful for comparisons across different databases, and thus might advance our understanding of universality vs. specificity of facial expressions across cultures. (shrink)

Background: Although convolutional neural networks (CNNs) achieve high diagnostic accuracy for detecting Alzheimer’s disease (AD) dementia based on magnetic resonance imaging (MRI) scans, they are not yet applied in clinical routine. One important reason for this is a lack of model comprehensibility. Recently developed visualization methods for deriving CNN relevance maps may help to fill this gap as they allow the visualization of key input image features that drive the decision of the model. We investigated whether models (...) with higher accuracy also rely more on discriminative brain regions predefined by prior knowledge. Methods: We trained a CNN for the detection of AD in N = 663 T1-weighted MRI scans of patients with dementia and amnestic mild cognitive impairment (MCI) and verified the accuracy of the models via cross-validation and in three independent samples including in total N = 1655 cases. We evaluated the association of relevance scores and hippocampus volume to validate the clinical utility of this approach. To improve model comprehensibility, we implemented an interactive visualization of 3D CNN relevance maps, thereby allowing intuitive model inspection. Results: Across the three independent datasets, group separation showed high accuracy for AD dementia versus controls (AUC ≥ 0.91) and moderate accuracy for amnestic MCI versus controls (AUC ≈ 0.74). Relevance maps indicated that hippocampal atrophy was considered the most informative factor for AD detection, with additional contributions from atrophy in other cortical and subcortical regions. Relevance scores within the hippocampus were highly correlated with hippocampal volumes (Pearson’s r ≈ −0.86, p < 0.001). Conclusion: The relevance maps highlighted atrophy in regions that we had hypothesized a priori. This strengthens the comprehensibility of the CNN models, which were trained in a purely data-driven manner based on the scans and diagnosis labels. The high hippocampus relevance scores as well as the high performance achieved in independent samples support the validity of the CNN models in the detection of AD-related MRI abnormalities. The presented data-driven and hypothesis-free CNN modeling approach might provide a useful tool to automatically derive discriminative features for complex diagnostic tasks where clear clinical criteria are still missing, for instance for the differential diagnosis between various types of dementia. (shrink)

Electroencephalography is the measurement of neuronal activity in different areas of the brain through the use of electrodes. As EEG signal technology has matured over the years, it has been applied in various methods to EEG emotion recognition, most significantly including the use of convolutional neural network. However, these methods are still not ideal, and shortcomings have been found in the results of some models of EEG feature extraction and classification. In this study, two CNN models were selected (...) for the extraction and classification of preprocessed data, namely, common spatial patterns- CNN and wavelet transform- CNN. Using the CSP-CNN, we first used the common space model to reduce dimensionality and then applied the CNN directly to extract and classify the features of the EEG; while, with the WT-CNN model, we used the wavelet transform to extract EEG features, thereafter applying the CNN for classification. The EEG classification results of these two classification models were subsequently analyzed and compared, with the average classification accuracy of the CSP-CNN model found to be 80.56%, and the average classification accuracy of the WT-CNN model measured to 86.90%. Thus, the findings of this study show that the average classification accuracy of the WT-CNN model was 6.34% higher than that of the CSP-CNN. (shrink)

The purpose is to improve the teaching and learning efficiency of college Innovation and Entrepreneurship Education. Firstly, from the perspective of aesthetic education, this work designs the teacher and student sides of the Computer-aided Instruction system. Secondly, the CAI model is implemented based on the weight sharing and local perception of the Convolutional Neural Network. Finally, the performance of the CNN-based CAI model is tested. Meanwhile, it analyses students’ IEE experience under the proposed CAI model through a case (...) study of Music Majors from Xi’an Conservatory of Music. The experimental data show that the CNN-based CAI model can respond quickly and stably when users access different functional modules, such as webpage browsing. The proposed CAI model increases students’ entrepreneurial interest, skills, and knowledge by 55.62, 57.32, and 72.12%, respectively. Students’ entrepreneurial practice ability has been improved by over 50.00%; such an increase in entrepreneurial practice ability has also shown individual differences. Thus, the proposed Music Majors-oriented IEE-infiltrated CAI model based on CNN improves students’ entrepreneurial practice ability and reflects the positive experience of Music Majors on IEE. The finding provides references for the step-by-step identification of the CNN-based CAI model and has certain guiding significance for analyzing the effect of college IEE. (shrink)

This study decodes consumers' preference levels using a convolutional neural network in neuromarketing. The classification accuracy in neuromarketing is a critical factor in evaluating the intentions of the consumers. Functional near-infrared spectroscopy is utilized as a neuroimaging modality to measure the cerebral hemodynamic responses. In this study, a specific decoding structure, called CNN-based fNIRS-data analysis, was designed to achieve a high classification accuracy. Compared to other methods, the automated characteristics, constant training of the dataset, and learning efficiency of (...) the proposed method are the main advantages. The experimental procedure required eight healthy participants to view commercial advertisement videos of different durations. The cerebral hemodynamic responses of the participants were measured. To compare the preference classification performances, CNN was utilized to extract the most common features, including the mean, peak, variance, kurtosis, and skewness. Considering three video durations, the average classification accuracies of 15, 30, and 60 s videos were 84.3, 87.9, and 86.4%, respectively. Among them, the classification accuracy of 87.9% for 30 s videos was the highest. The average classification accuracies of three preferences in females and males were 86.2 and 86.3%, respectively, showing no difference in each group. By comparing the classification performances in three different combinations between two groups, male participants were observed to have targeted preferences for commercial advertising, and the classification performance 88.4% between “like” vs. “dislike” out of three categories was the highest. Finally, pairwise classification performance are shown as follows: For female, 86.1%, 87.4%, 85.2%, and for male 85.7, 88.4, 85.1%, respectively. (shrink)

The purpose of crowd counting is to estimate the number of pedestrians in crowd images. Crowd counting or density estimation is an extremely challenging task in computer vision, due to large scale variations and dense scene. Current methods solve these issues by compounding multi-scale Convolutional Neural Network with different receptive fields. In this paper, a novel end-to-end architecture based on Multi-Scale Adversarial Convolutional Neural Network (MSA-CNN) is proposed to generate crowd density and estimate the amount of (...) crowd. Firstly, a multi-scale network is used to extract the globally relevant features in the crowd image, and then fractionally-strided convolutional layers are designed for up-sampling the output to recover the loss of crucial details caused by the earlier max pooling layers. An adversarial loss is directly employed to shrink the estimated value into the realistic subspace to reduce the blurring effect of density estimation. Joint training is performed in an end-to-end fashion using a combination of Adversarial loss and Euclidean loss. The two losses are integrated via a joint training scheme to improve density estimation performance.We conduct some extensive experiments on available datasets to show the significant improvements and supremacy of the proposed approach over the available state-of-the-art approaches. (shrink)

The brain-computer interface of steady-state visual evoked potential is one of the fundamental ways of human-computer communication. The main challenge is that there may be a nonlinear relationship between different SSVEP in other states. For improving the performance of SSVEP BCI, a novel CNN algorithm model is proposed in this study. Based on the discrete Fourier transform to calculate the signal's power spectral density, we perform zero-padding in the signal's time domain to improve its performance on the PSD and make (...) it more refined. In this way, the frequency point interval in the PSD of the SSVEP is consistent with the minimum gap between the stimulation frequency. Combining the nonlinear transformation capabilities of CNN in deep learning, a zero-padding frequency domain convolutional neural network model is proposed. Extensive experiments based on the SSVEP dataset validate the effectiveness of our method. The study verifies that the proposed ZPFDCNN method can improve the effectiveness of the SSVEP-based high-speed BCI ITR. It has massive potential in the application of BCI. (shrink)

A brain tumor is an abnormal mass or growth of a cell that leads to certain death, and this is still a challenging task in clinical practice. Early and correct diagnosis of this type of cancer is very important for the treatment process. For this reason, this study aimed to develop computer-aided systems for the diagnosis of brain tumors. In this research, we proposed three different end-to-end deep learning approaches for analyzing effects of local and deep features for brain MRI (...) images anomaly detection. The first proposed system is Directional Bit-Planes Deep Autoencoder which extracts and learns local and direction features. The DBP-DAE by decomposition of a local binary pattern into eight bit-planes extracts are directional and inherent local-structure features from the input image and learns robust feature for classification purposes. The second one is a Dilated Separable Residual Convolutional Network which extracts high and low-level features. The main advantage of this approach is that it is robust and shows stable results regardless to size of image database and to solve overfitting problems. To explore the effects of mixture of local and deep extracted feature on accuracy of classification of brain anomaly, a multibranch convolutional neural network approach is proposed. This approach is designed according to combination of DBP-DAE and DSRCN in an end-to-end manner. Extensive experiments conducted based on brain tumor in MRI image public access databases and achieves significant results compared to state-of-the-art algorithms. In addition, we discussed the effectiveness and applicability of CNNs with a variety of different features and architectures for brain abnormalities such as Alzheimer’s. (shrink)

In the age of big data, machine learning models are globally used to execute default risk prediction. Imbalanced datasets and redundant features are two main problems that can reduce the performance of machine learning models. To address these issues, this study conducts an analysis from the viewpoint of different balance ratios as well as the selection order of feature selection. Accordingly, we first use data rebalancing and feature selection to obtain 32 derived datasets with varying ratios of balance and feature (...) combinations for each dataset. Second, we propose a comprehensive metric model based on multimachine learning algorithms to select the best-derived dataset with the optimal balance ratio and feature combination. Finally, the convolutional neural network is trained on the selected derived dataset to evaluate the performance of our approach in terms of type-II error, accuracy, G-mean, and AUC. There are two contributions in this study. First, the optimal balance ratio is found through the classification accuracy, which changes the deficiency of the existing research that samples are imbalanced or the balance ratio is 1 : 1 and ensures the accuracy of the classification model. Second, a comprehensive metric model based on the machine learning algorithm is proposed, which can simultaneously find the best balance ratio and the optimal feature selection. The experimental results show that our method can noticeably improve the performance of CNN, and CNN outperforms the other four commonly used machine learning models in the task of default risk prediction on four benchmark datasets. (shrink)

This research aims to analyze the influencing factors of migrant children’s education integration based on the convolutional neural network algorithm. The attention mechanism, LSTM, and GRU are introduced based on the CNN algorithm, to establish an ALGCNN model for text classification. Film and television review data set, Stanford sentiment data set, and news opinion data set are used to analyze the classification accuracy, loss value, Hamming loss, precision, recall, and micro-F1 of the ALGCNN model. Then, on the big (...) data platform, data in the Comprehensive Management System of Floating Population and Rental Housing, Student Status Information Management System, and Student Information Management System of Beijing city are taken as samples. The ALGCNN model is used to classify and compare related data. It is found that in the MR, STT, and MPQA data sets, the classification accuracy and loss value of the ALGCNN model are better than other algorithms. HL is the lowest, the Pre is second only to the BERT algorithm, and the Re and F1 are both higher than other algorithms. From 2015 to 2019, the number of migrant children in different grades of elementary school shows a gradual increase. Among migrant children, the number of migrant children from other counties in this province is evidently higher than the number of migrant children from other provinces. Among children of migrant workers, the number of immigrants from other counties in this province is also notably higher than the number of immigrants from other provinces. With the gradual increase in the years, the proportion of township-level expenses shows a gradual decrease, whereas the proportion of district and county-level expenses shows a gradual increase. Moreover, the accuracy of the ALGCNN model in migrant children and local children data classification is 98.6 and 98.9%, respectively. The proportion of migrant children in the first and second grades of a primary school in Beijing city is obviously higher than that of local children. The average final score of local children was greatly higher than that of migrant children, whereas the scores of migrant children’s listening methods, learning skills, and learning environment adaptability are lower, which shows that an effective text classification model is established based on the CNN algorithm. In short, the children’s education costs, listening methods, learning skills, and learning environment adaptability are the main factors affecting migrant children’s educational integration, and this work provides a reference for the analysis of migrant children’s educational integration. (shrink)

A sector is a basic unit of airspace whose operation is managed by air traffic controllers. The operation complexity of a sector plays an important role in air traffic management system, such as airspace reconfiguration, air traffic flow management, and allocation of air traffic controller resources. Therefore, accurate evaluation of the sector operation complexity is crucial. Considering there are numerous factors that can influence SOC, researchers have proposed several machine learning methods recently to evaluate SOC by mining the relationship between (...) factors and complexity. However, existing studies rely on hand-crafted factors, which are computationally difficult, specialized background required, and may limit the evaluation performance of the model. To overcome these problems, this paper for the first time proposes an end-to-end SOC learning framework based on deep convolutional neural network specifically for free of hand-crafted factors environment. A new data representation, i.e., multichannel traffic scenario image, is proposed to represent the overall air traffic scenario. A MTSI is generated by splitting the airspace into a two-dimension grid map and filled with navigation information. Motivated by the applications of deep learning network, the specific CNN model is introduced to automatically extract high-level traffic features from MTSIs and learn the SOC pattern. Thus, the model input is determined by combining multiple image channels composed of air traffic information, which are used to describe the traffic scenario. The model output is SOC levels for the target sector. The experimental results using a real dataset from the Guangzhou airspace sector in China show that our model can effectively extract traffic complexity information from MTSIs and achieve promising performance than traditional machine learning methods. In practice, our work can be flexibly and conveniently applied to SOC evaluation without the additional calculation of hand-crafted factors. (shrink)

Through the analysis of facial feature extraction technology, this paper designs a lightweight convolutional neural network. The LW-CNN model adopts a separable convolution structure, which can propose more accurate features with fewer parameters and can extract 3D feature points of a human face. In order to enhance the accuracy of feature extraction, a face detection method based on the inverted triangle structure is used to detect the face frame of the images in the training set before the model (...) extracts the features. Aiming at the problem that the feature extraction algorithm based on the difference criterion cannot effectively extract the discriminative information, the Generalized Multiple Maximum Dispersion Difference Criterion and the corresponding feature extraction algorithm are proposed. The algorithm uses the difference criterion instead of the entropy criterion to avoid the “small sample” problem, and the use of QR decomposition can extract more effective discriminative features for facial recognition, while also reducing the computational complexity of feature extraction. Compared with traditional feature extraction methods, GMMSD avoids the problem of “small samples” and does not require preprocessing steps on the samples; it uses QR decomposition to extract features from the original samples and retains the distribution characteristics of the original samples. According to different change matrices, GMMSD can evolve into different feature extraction algorithms, which shows the generalized characteristics of GMMSD. Experiments show that GMMSD can effectively extract facial identification features and improve the accuracy of facial recognition. (shrink)

Functional near-infrared spectroscopy has attracted increasing attention in the field of brain–computer interfaces owing to their advantages such as non-invasiveness, user safety, affordability, and portability. However, fNIRS signals are highly subject-specific and have low test-retest reliability. Therefore, individual calibration sessions need to be employed before each use of fNIRS-based BCI to achieve a sufficiently high performance for practical BCI applications. In this study, we propose a novel deep convolutional neural network -based approach for implementing a subject-independent fNIRS-based BCI. (...) A total of 18 participants performed the fNIRS-based BCI experiments, where the main goal of the experiments was to distinguish a mental arithmetic task from an idle state task. Leave-one-subject-out cross-validation was employed to evaluate the average classification accuracy of the proposed subject-independent fNIRS-based BCI. As a result, the average classification accuracy of the proposed method was reported to be 71.20 ± 8.74%, which was higher than the threshold accuracy for effective BCI communication as well as that obtained using conventional shrinkage linear discriminant analysis. To achieve a classification accuracy comparable to that of the proposed subject-independent fNIRS-based BCI, 24 training trials were necessary for the traditional subject-dependent fNIRS-based BCI. It is expected that our CNN-based approach would reduce the necessity of long-term individual calibration sessions, thereby enhancing the practicality of fNIRS-based BCIs significantly. (shrink)

Timely detection and efficient recognition of fault are challenging for the bogie of high-speed train, owing to the fact that different types of fault signals have similar characteristics in the same frequency range. Notice that convolutional neural networks are powerful in extracting high-level local features and that recurrent neural networks are capable of learning long-term context dependencies in vibration signals. In this paper, by combining CNN and RNN, a so-called convolutional recurrent neural network (...) is proposed to diagnose various faults of the HST bogie, where the capabilities of CNN and RNN are inherited simultaneously. Within the novel architecture, the proposed CRNN first filters out the features from the original data through convolutional layers. Then, four recurrent layers with simple recurrent cell are used to model the context information in the extracted features. By comparing the performance of the presented CRNN with CNN, RNN, and ensemble learning, experimental results show that CRNN achieves not only the best performance with accuracy of 97.8% but also the least time spent in training model. (shrink)

The interference of the complex background and less information of the small targets are two major problems in vehicle attribute recognition. In this paper, two cascaded networks of vehicle attribute recognition are established to solve the two problems. For vehicle targets with normal size, the multitask cascaded convolution neural network MC-CNN-NT uses the improved Faster R-CNN as the location subnetwork. The vehicle targets in the complex background are extracted by the location subnetwork to the classification subnetwork CNN for (...) the classification. The implementation of this task decomposition strategy effectively eliminates the interference of the complex background in target detection. For vehicle targets with small size, the multitask cascaded convolution neural network MC-CNN-ST applies the network compression strategy and the multilayer feature fusion strategy to extract the feature maps. These strategies enrich the location information and semantic information of the feature maps. In order to optimize the nonlinear mapping ability and the hard-to-detect samples mining ability of the networks, the activation function and the loss function in the two cascaded networks are improved. The experimental results show that MC-CNN-NT for the normal targets and MC-CNN-ST for the small targets achieve the state-of-the-art performance compared with other attribute recognition networks. (shrink)

In order to better assess the mental health status, combining online text data and considering the problems of lexicon sparsity and small lexicon size in feature statistics of word frequency of the traditional linguistic inquiry and word count dictionary, and combining the advantages of constructive neural network convolutional neural network in contextual semantic extraction, a CNN-based mental health assessment method is proposed and evaluated with the measurement indicators in CLPsych2017. The results showed that the results obtained from (...) the mental health assessment by CNN were superior in all indicators, in which F1 = 0.51 and ACC = 0.69. Meanwhile, ACC evaluated by FastText, CNN, and CNN + Word2Vec were 0.66, 0.67, 0.67, and F1 were 0.37, 0.47, and 0.49, respectively, which indicates the use of CNN in mental health assessment has feasibility. (shrink)

The purpose is to minimize the substantial losses caused by public health emergencies to people’s health and daily life and the national economy. The tuberculosis data from June 2017 to 2019 in a city are collected. The Structural Equation Model is constructed to determine the relationship between hidden and explicit variables by determining the relevant indicators and parameter estimation. The prediction model based on Artificial Neural Network and Convolutional Neural Network is constructed. The method’s effectiveness is verified (...) by comparing the prediction model’s loss value and accuracy in training and testing. Meanwhile, 50 pieces of actual cases are tested, and the warning level is determined according to the T-value. The results show that comparing and analyzing ANN, CNN, and the hybrid network of ANN and CNN, the hybrid network’s accuracy is higher than the other two algorithms, 89.1 and 90.1%. Also, the hybrid network has sound prediction effects and accuracy when predicting actual cases. Therefore, the early warning method based on ANN in deep learning has better performance in public health emergencies’ early warning, which is significant for improving early warning capabilities. (shrink)

The representations of deep convolutional neural networks (CNNs) are formed from generalizing similarities and abstracting from differences in the manner of the empiricist theory of abstraction (Buckner, Synthese 195:5339–5372, 2018). The empiricist theory of abstraction is well understood to entail infinite regress and circularity in content constitution (Husserl, Logical Investigations. Routledge, 2001). This paper argues these entailments hold a fortiori for deep CNNs. Two theses result: deep CNNs require supplementation by Quine’s “apparatus of identity and quantification” in (...) order to (1) achieve concepts, and (2) represent objects, as opposed to “half-entities” corresponding to similarity amalgams (Quine, Quintessence, Cambridge, 2004, p. 107). Similarity amalgams are also called “approximate meaning[s]” (Marcus & Davis, Rebooting AI, Pantheon, 2019, p. 132). Although Husserl inferred the “complete abandonment of the empiricist theory of abstraction” (a fortiori deep CNNs) due to the infinite regress and circularity arguments examined in this paper, I argue that the statistical learning of deep CNNs may be incorporated into a Fodorian hybrid account that supports Quine’s “sortal predicates, negation, plurals, identity, pronouns, and quantifiers” which are representationally necessary to overcome the regress/circularity in content constitution and achieve objective (as opposed to similarity-subjective) representation (Burge, Origins of Objectivity. Oxford, 2010, p. 238). I base myself initially on Yoshimi’s (New Frontiers in Psychology, 2011) attempt to explain Husserlian phenomenology with neural networks but depart from him due to the arguments and consequently propose a two-system view which converges with Weiskopf’s proposal (“Observational Concepts.” The Conceptual Mind. MIT, 2015. 223–248). (shrink)

Naturalistic stimuli, including movie, music, and speech, have been increasingly applied in the research of neuroimaging. Relative to a resting-state or single-task state, naturalistic stimuli can evoke more intense brain activities and have been proved to possess higher test–retest reliability, suggesting greater potential to study adaptive human brain function. In the current research, naturalistic functional magnetic resonance imaging (N-fMRI) has been a powerful tool to record brain states under naturalistic stimuli, and many efforts have been devoted to study the high-level (...) semantic features from spatial or temporal representations via N-fMRI. However, integrating both spatial and temporal characteristics of brain activities for better interpreting the patterns under naturalistic stimuli is still underexplored. In this work, a novel hybrid learning framework that comprehensively investigates both the spatial (via Predictive Model) and the temporal [via convolutional neural network (CNN) model] characteristics of the brain is proposed. Specifically, to focus on certain relevant regions from the whole brain, regions of significance (ROS), which contain common spatial activation characteristics across individuals, are selected via the Predictive Model. Further, voxels of significance (VOS), whose signals contain significant temporal characteristics under naturalistic stimuli, are interpreted via one-dimensional CNN (1D-CNN) model. In this article, our proposed framework is applied onto the N-fMRI data during naturalistic classical/pop/speech audios stimuli. The promising performance is achieved via the Predictive Model to differentiate the different audio categories. Especially for distinguishing the classic and speech audios, the accuracy of classification is up to 92%. Moreover, spatial ROS and VOS are effectively obtained. Besides, temporal characteristics of the high-level semantic features are investigated on the frequency domain via convolution kernels of 1D-CNN model, and we effectively bridge the “semantic gap” between high-level semantic features of N-fMRI and low-level acoustic features of naturalistic audios in the frequency domain. Our results provide novel insights on characterizing spatiotemporal patterns of brain activities via N-fMRI and effectively explore the high-level semantic features under naturalistic stimuli, which will further benefit the understanding of the brain working mechanism and the advance of naturalistic stimuli clinical application. (shrink)

Most binaural speech source localization models perform poorly in unprecedentedly noisy and reverberant situations. Here, this issue is approached by modelling a multiscale dilated convolutional neural network. The time-related crosscorrelation function and energy-related interaural level differences are preprocessed in separate branches of dilated convolutional network. The multiscale dilated CNN can encode discriminative representations for CCF and ILD, respectively. After encoding, the individual interaural representations are fused to map source direction. Furthermore, in order to improve the parameter adaptation, (...) a novel semiadaptive entropy is proposed to train the network under directional constraints. Experimental results show the proposed method can adaptively locate speech sources in simulated noisy and reverberant environments. (shrink)

With the rapid growth of informatics systems’ technology in this modern age, the Internet of Things (IoT) has become more valuable and vital to everyday life in many ways. IoT applications are now more popular than they used to be due to the availability of many gadgets that work as IoT enablers, including smartwatches, smartphones, security cameras, and smart sensors. However, the insecure nature of IoT devices has led to several difficulties, one of which is distributed denial-of-service (DDoS) attacks. IoT (...) systems have several security limitations due to their disreputability characteristics, like dynamic communication between IoT devices. The dynamic communications resulted from the limited resources of these devices, such as their data storage and processing units. Recently, many attempts have been made to develop intelligent models to protect IoT networks against DDoS attacks. The main ongoing research issue is developing a model capable of protecting the network from DDoS attacks that is sensitive to various classes of DDoS and can recognize legitimate traffic to avoid false alarms. Subsequently, this study proposes combining three deep learning algorithms, namely recurrent neural network (RNN), long short-term memory (LSTM)-RNN, and convolutional neural network (CNN), to build a bidirectional CNN-BiLSTM DDoS detection model. The RNN, CNN, LSTM, and CNN-BiLSTM are implemented and tested to determine the most effective model against DDoS attacks that can accurately detect and distinguish DDoS from legitimate traffic. The intrusion detection evaluation dataset (CICIDS2017) is used to provide more realistic detection. The CICIDS2017 dataset includes benign and up-to-date examples of typical attacks, closely matching real-world data of Packet Capture. The four models are tested and assessed using Confusion Metrix against four commonly used criteria: accuracy, precision, recall, and F-measure. The performance of the models is quite effective as they obtain an accuracy rate of around 99.00%, except for the CNN model, which achieves an accuracy of 98.82%. The CNN-BiLSTM achieves the best accuracy of 99.76% and precision of 98.90%. (shrink)

Deep neural networks (DNNs) have been playing a significant role in acoustic modeling. Convolutional neural networks (CNNs) are the advanced version of DNNs that achieve 4–12% relative gain in the word error rate (WER) over DNNs. Existence of spectral variations and local correlations in speech signal makes CNNs more capable of speech recognition. Recently, it has been demonstrated that bidirectional long short-term memory (BLSTM) produces higher recognition rate in acoustic modeling because they are adequate to (...) reinforce higher-level representations of acoustic data. Spatial and temporal properties of the speech signal are essential for high recognition rate, so the concept of combining two different networks came into mind. In this paper, a hybrid architecture of CNN-BLSTM is proposed to appropriately use these properties and to improve the continuous speech recognition task. Further, we explore different methods like weight sharing, the appropriate number of hidden units, and ideal pooling strategy for CNN to achieve a high recognition rate. Specifically, the focus is also on how many BLSTM layers are effective. This paper also attempts to overcome another shortcoming of CNN, i.e. speaker-adapted features, which are not possible to be directly modeled in CNN. Next, various non-linearities with or without dropout are analyzed for speech tasks. Experiments indicate that proposed hybrid architecture with speaker-adapted features and maxout non-linearity with dropout idea shows 5.8% and 10% relative decrease in WER over the CNN and DNN systems, respectively. (shrink)

How to automatically detect intracranial aneurysms from Three-Dimension Time of Flight Magnetic Resonance Angiography images is a typical 3D image classification problem. Currently, the commonly used method is the Maximum Intensity Projection- based way. It transfers 3D classification into 2D case by projecting the 3D patch into 2D planes along different directions on the basis of voxel’s intensity. After then, the 2D Convolutional Neural Network is established to do classification. It has been shown that the MIP-based method can (...) reduce the demands for the samples and increase the computation efficiency. Meanwhile, the accuracy is comparable with that of 3D image classification. Inspired by the strategy of MIP, we want to further reduce the demands for samples and accelerate the training by transferring the 2D image classification into 1D case, i.e., we want to generate the 1D vectors from the MIP images and then establish a 1D CNN to do intracranial aneurysm detection and classification for 3D TOF MRA image. Specifically, our method first extracts a series of patches as the Region of Interests along the blood vessels from the original 3D TOF MRA 3D image. The corresponding MIP images of each ROI will be obtained through maximum intensity projecting. Then, we generate a series of 1D vectors by accumulating each MIP image along different directions. Meanwhile, a 1D CNN is established to detect aneurysms, in which, the input is the obtained 1D vectors and the output is the binary classification result denoting whether there are intracranial aneurysms in the considered patch. Generally, compared with 2D- and 3D-CNN, the 1D CNN-based way greatly accelerates the training and shows stronger robustness in the case of fewer samples. The efficiency of the proposed method outperforms the 2D CNN about 10 times in CPU training. Yet, their accuracies are close. (shrink)

For unmanned aerial vehicle, object detection at different scales is an important component for the visual recognition. Recent advances in convolutional neural networks have demonstrated that attention mechanism remarkably enhances multiscale representation of CNNs. However, most existing multiscale feature representation methods simply employ several attention blocks in the attention mechanism to adaptively recalibrate the feature response, which overlooks the context information at a multiscale level. To solve this problem, a multiscale feature filtering network is proposed in this (...) paper for image recognition system in the UAV. A novel building block, namely, multiscale feature filtering module, is proposed for ResNet-like backbones and it allows feature-selective learning for multiscale context information across multiparallel branches. These branches employ multiple atrous convolutions at different scales, respectively, and further adaptively generate channel-wise feature responses by emphasizing channel-wise dependencies. Experimental results on CIFAR100 and Tiny ImageNet datasets reflect that the MFFNet achieves very competitive results in comparison with previous baseline models. Further ablation experiments verify that the MFFNet can achieve consistent performance gains in image classification and object detection tasks. (shrink)

The most predominant kind of disease that is normal among ladies is breast cancer. It is one of the significant reasons among ladies, regardless of huge endeavors to stay away from it through screening developers. An automatic detection system for disease helps doctors to identify and provide accurate results, thereby minimizing the death rate. Computer-aided diagnosis has minimum intervention of humans and produces more accurate results than humans. It will be a difficult and long task that depends on the expertise (...) of pathologists. Deep learning methods proved to give better outcomes when correlated with ML and extricate the best highlights of the images. The main objective of this paper is to propose a deep learning technique in combination with a convolution neural network and long short-term memory with a random forest algorithm to diagnose breast cancer. Here, CNN is used for feature extraction, and LSTM is used for extracted feature detection. The experimental results show that the proposed system accomplishes 100% of accuracy, a sensitivity of 99%, recall of 99%, and an F1-score of 98% compared to other traditional models. As the system achieved correct results, it can help doctors to investigate breast cancer easily. (shrink)

Abstract: In modern agriculture, ensuring the quality of crops plays a vital role in enhancing production and minimizing waste. This research focuses on the classification of lemon plants into two categories: good quality and bad quality, using deep learning techniques. We employ convolutional neural networks (CNN) to develop a classification model that can accurately predict plant quality based on images. Through a structured pipeline involving data collection, preprocessing, model design, and evaluation, we demonstrate the effectiveness of CNNs (...) in performing quality assessments. This paper discusses the experimental results in applying deep learning to agricultural tasks. (shrink)

State-of-the-art facial expression methods outperform human beings, especially, thanks to the success of convolutional neural networks. However, most of the existing works focus mainly on analyzing an adult’s face and ignore the important problems: how can we recognize facial expression from a baby’s face image and how difficult is it? In this paper, we first introduce a new face image database, named BabyExp, which contains 12,000 images from babies younger than two years old, and each image is (...) with one of three facial expressions. To the best of our knowledge, the proposed dataset is the first baby face dataset for analyzing a baby’s face image, which is complementary to the existing adult face datasets and can shed some light on exploring baby face analysis. We also propose a feature guided CNN method with a new loss function, called distance loss, to optimize interclass distance. In order to facilitate further research, we provide the benchmark of expression recognition on the BabyExp dataset. Experimental results show that the proposed network achieves the recognition accuracy of 87.90% on BabyExp. (shrink)

Bioassessment is the process of using living organisms to assess the ecological health of a particular ecosystem. It typically relies on identifying specific organisms that are sensitive to changes in environmental conditions. Benthic macroinvertebrates are widely used for examining the ecological status of freshwaters. However, a time-consuming process of species identification that requires high expertise represents one of the key obstacles to more precise bioassessment of aquatic ecosystems. Partial automation of this process using deep learning-based image classification is the goal (...) of an ongoing project AIAQUAMI we are participating in. One of the project goals is to develop software support for image classification with visualization and reporting. For that purpose, we developed desktop and web applications that we open-sourced as Imagelytics Suite. Both desktop and web applications rely on a convolutional neural network (CNN) to classify images and the Grad-CAM algorithm to produce heatmaps of the image areas that mostly influenced the network decision. Along with the source code of the applications, we also open-sourced scripts that can be used to train CNN on an arbitrary dataset and produce required metadata, so it can be used with Imagelytics applications. In this article, we presented technical details regarding the design of the applications and the training method that will enable their general use for image classification tasks. As a part of the evaluation, we will show a use case related to species identification of non-biting midges (Diptera: Chironomidae). (shrink)

Adaptive optics are techniques used for processing the spatial resolution of astronomical images taken from large ground-based telescopes. In this work, computational results are presented for a modified curvature sensor, the tomographic pupil image wavefront sensor, which measures the turbulence of the atmosphere, expressed in terms of an expansion over Zernike polynomials. Convolutional neural networks are presented as an alternative to the TPI-WFS reconstruction. This technique is a machine learning model of the family of artificial neural (...) networks, which are widely known for its performance as modeling and prediction technique in complex systems. Results obtained from the reconstruction of the networks are compared with the TPI-WFS reconstruction by estimating errors and optical measurements. The reconstructed wavefronts from both techniques are compared for wavefronts of 153 Zernike modes. For this case, a detailed comparison and grid search to find the most suitable neural network is performed, searching between multi-layer perceptron, CNN and recurrent networks topologies. In general, the best network was a CNN trained for TPI-WFS reconstruction, achieving better performance than the reconstruction software from TPI-WFS in most of the turbulent profiles, but the most significant improvements were found for higher turbulent profiles that have the lowest r0 values. (shrink)

Artificial intelligence techniques in general and convolutional neural networks in particular have attained successful results in medical image analysis and classification. A deep CNN architecture has been proposed in this paper for the diagnosis of COVID-19 based on the chest X-ray image classification. Due to the nonavailability of sufficient-size and good-quality chest X-ray image dataset, an effective and accurate CNN classification was a challenge. To deal with these complexities such as the availability of a very-small-sized and imbalanced (...) dataset with image-quality issues, the dataset has been preprocessed in different phases using different techniques to achieve an effective training dataset for the proposed CNN model to attain its best performance. The preprocessing stages of the datasets performed in this study include dataset balancing, medical experts’ image analysis, and data augmentation. The experimental results have shown the overall accuracy as high as 99.5% which demonstrates the good capability of the proposed CNN model in the current application domain. The CNN model has been tested in two scenarios. In the first scenario, the model has been tested using the 100 X-ray images of the original processed dataset which achieved an accuracy of 100%. In the second scenario, the model has been tested using an independent dataset of COVID-19 X-ray images. The performance in this test scenario was as high as 99.5%. To further prove that the proposed model outperforms other models, a comparative analysis has been done with some of the machine learning algorithms. The proposed model has outperformed all the models generally and specifically when the model testing was done using an independent testing set. (shrink)

Abstract : Background: Vegetable agriculture is very important to human continued existence and remains a key driver of many economies worldwide, especially in underdeveloped and developing economies. Objectives: There is an increasing demand for food and cash crops, due to the increasing in world population and the challenges enforced by climate modifications, there is an urgent need to increase plant production while reducing costs. Methods: In this paper, Lemon classification approach is presented with a dataset that contains approximately 2,000 images (...) belong to 3 species at a few developing phases. Convolutional Neural Network (CNN) algorithms, a deep learning technique extensively applied to image recognition was used, for this task. The results: found that CNN-driven lemon classification applications when used in farming automation have the latent to enhance crop harvest and improve output and productivity when designed properly. The trained model achieved an accuracy of 99.48% on a held-out test set, demonstrating the feasibility of this approach. (shrink)

In the human-computer interaction, electroencephalogram access for automatic emotion recognition is an effective way for robot brains to perceive human behavior. In order to improve the accuracy of the emotion recognition, a method of EEG access for emotion recognition based on a deep hybrid network was proposed in this paper. Firstly, the collected EEG was decomposed into four frequency band signals, and the multiscale sample entropy features of each frequency band were extracted. Secondly, the constructed 3D MSE feature matrices were (...) fed into a deep hybrid network for autonomous learning. The deep hybrid network was composed of a continuous convolutional neural network and hidden Markov models. Lastly, HMMs trained with multiple observation sequences were used to replace the artificial neural network classifier in the CNN, and the emotion recognition task was completed by HMM classifiers. The proposed method was applied to the DEAP dataset for emotion recognition experiments, and the average accuracy could achieve 79.77% on arousal, 83.09% on valence, and 81.83% on dominance. Compared with the latest related methods, the accuracy was improved by 0.99% on valence and 14.58% on dominance, which verified the effectiveness of the proposed method. (shrink)

Through the analysis of emotional tendency in online public opinion, governments and enterprises can stabilize people’s emotion more effectively and maintain social stability. The problem studied in this paper is how to analyze the emotional tendency of online public opinion efficiently, and finally, this paper chooses deep learning algorithm to perform fast analysis of emotional tendency of online public opinion. This paper briefly introduced the structure of the basic model used for emotional tendency analysis of online public opinion and the (...) convolutional neural network model used for text emotion classification. Then, the CNN model was improved by long short-term memory. A simulation experiment was carried out on MATLAB for the improved text emotion classification model to verify the influence of activation function type on the improved model and the performance difference between the improved model and support vector machine and traditional CNN models. The results showed that the improved classification model that adopted the sigmoid activation function had higher accuracy and was less affected by language than the relu and tanh activation functions; the improved classification model had the highest accuracy, recall rate, and F-value in classifying emotional tendency of web texts, followed by the traditional CNN model and the SVM model. (shrink)

As the stock market is an important part of the national economy, more and more investors have begun to pay attention to the methods to improve the return on investment and effectively avoid certain risks. Many factors affect the trend of the stock market, and the relevant information has the nature of time series. This paper proposes a composite model CNN-BiSLSTM to predict the closing price of the stock. Bidirectional special long short-term memory improved on bidirectional long short-term memory adds (...) 1 − tanh function in the output gate which makes the model better predict the stock price. The model extracts advanced features that influence stock price through convolutional neural network, and predicts the stock closing price through BiSLSTM after the data processed by CNN. To verify the effectiveness of the model, the historical data of the Shenzhen Component Index from July 1, 1991, to October 30, 2020, are used to train and test the CNN-BiSLSTM. CNN-BiSLSTM is compared with multilayer perceptron, recurrent neural network, long short-term memory, BiLSTM, CNN-LSTM, and CNN-BiLSTM. The experimental results show that the mean absolute error, root-mean-squared error, and R-square evaluation indicators of the CNN-BiSLSTM are all optimal. Therefore, CNN-BiSLSTM can accurately predict the closing price of the Shenzhen Component Index of the next trading day, which can be used as a reference for the majority of investors to effectively avoid certain risks. (shrink)

In face recognition systems, highly robust facial feature representation and good classification algorithm performance can affect the effect of face recognition under unrestricted conditions. To explore the anti-interference performance of convolutional neural network reconstructed by deep learning framework in face image feature extraction and recognition, in the paper, first, the inception structure in the GoogleNet network and the residual error in the ResNet network structure are combined to construct a new deep reconstruction network algorithm, with the random gradient (...) descent and triplet loss functions as the model optimizer and classifier, respectively, and it is applied to the face recognition in Labeled Faces in the Wild face database. Then, the portrait pyramid segmentation and local feature point segmentation are applied to extract the features of face images, and the matching of face feature points is achieved using Euclidean distance and joint Bayesian method. Finally, Matlab software is used to simulate the algorithm proposed in this paper and compare it with other algorithms. The results show that the proposed algorithm has the best face recognition effect when the learning rate is 0.0004, the attenuation coefficient is 0.0001, the training method is SGD, and dropout is 0.1, and the algorithm proposed in this paper has the largest mean average precision compared to other CNN algorithms. The correct rate of face feature matching of the algorithm proposed in this paper is 84.72%, which is higher than LetNet-5, VGG-16, and VGG-19 algorithms, the correct rates of which are 6.94%, 2.5%, and 1.11%, respectively, but lower than GoogleNet, AlexNet, and ResNet algorithms. At the same time, the algorithm proposed in this paper has a faster matching time and a higher correct matching rate than the joint Bayesian method, indicating that the deep reconstruction network algorithm proposed in this paper can be used in face image recognition, FE, and matching, and it has strong anti-interference. (shrink)

Aiming at the problem of radar target recognition of High-Resolution Range Profile under low signal-to-noise ratio conditions, a recognition method based on the Constrained Naive Least-Squares Generative Adversarial Network, Short-time Fourier Transform, and Convolutional Neural Network is proposed. Combining the Least-Squares Generative Adversarial Network with the Wasserstein Generative Adversarial Network with Gradient Penalty, the CN-LSGAN is presented and applied to the HRRP denoise. The frequency domain and phase features of HRRP are gained by STFT in order to facilitate (...) feature learning and also match the input data format of the CNN. These experimental results show that the CN-LSGAN has better data augmentation performance and can effectively avoid the model collapse compared to the generative adversarial network and LSGAN. Also, the method has better recognition performance than the one-dimensional CNN method and the Long Short-Term Memory network method. (shrink)

Computational visual perception, also known as computer vision, is a field of artificial intelligence that enables computers to process digital images and videos in a similar way as biological vision does. It involves methods to be developed to replicate the capabilities of biological vision. The computer vision’s goal is to surpass the capabilities of biological vision in extracting useful information from visual data. The massive data generated today is one of the driving factors for the tremendous growth of computer vision. (...) This survey incorporates an overview of existing applications of deep learning in computational visual perception. The survey explores various deep learning techniques adapted to solve computer vision problems using deep convolutional neural networks and deep generative adversarial networks. The pitfalls of deep learning and their solutions are briefly discussed. The solutions discussed were dropout and augmentation. The results show that there is a significant improvement in the accuracy using dropout and data augmentation. Deep convolutional neural networks’ applications, namely, image classification, localization and detection, document analysis, and speech recognition, are discussed in detail. In-depth analysis of deep generative adversarial network applications, namely, image-to-image translation, image denoising, face aging, and facial attribute editing, is done. The deep generative adversarial network is unsupervised learning, but adding a certain number of labels in practical applications can improve its generating ability. However, it is challenging to acquire many data labels, but a small number of data labels can be acquired. Therefore, combining semisupervised learning and generative adversarial networks is one of the future directions. This article surveys the recent developments in this direction and provides a critical review of the related significant aspects, investigates the current opportunities and future challenges in all the emerging domains, and discusses the current opportunities in many emerging fields such as handwriting recognition, semantic mapping, webcam-based eye trackers, lumen center detection, query-by-string word, intermittently closed and open lakes and lagoons, and landslides. (shrink)

Content-based image retrieval (CBIR) is a technique used to retrieve image from an image database. However, the CBIR process suffers from less accuracy to retrieve many images from an extensive image database and prove the privacy of images. The aim of this article is to address the issues of accuracy utilizing deep learning techniques such as the CNN method. Also, it provides the necessary privacy for images using fully homomorphic encryption methods by Cheon–Kim–Kim–Song (CKKS). The system has been proposed, namely (...) RCNN_CKKS, which includes two parts. The first part (offline processing) extracts automated high-level features based on a flatting layer in a convolutional neural network (CNN) and then stores these features in a new dataset. In the second part (online processing), the client sends the encrypted image to the server, which depends on the CNN model trained to extract features of the sent image. Next, the extracted features are compared with the stored features using a Hamming distance method to retrieve all similar images. Finally, the server encrypts all retrieved images and sends them to the client. Deep-learning results on plain images were 97.87% for classification and 98.94% for retriever images. At the same time, the NIST test was used to check the security of CKKS when applied to Canadian Institute for Advanced Research (CIFAR-10) dataset. Through these results, researchers conclude that deep learning is an effective method for image retrieval and that a CKKS method is appropriate for image privacy protection. (shrink)

For product packaging, the visual elements in it can further enhance the appeal of the package to customers. This article briefly introduces visual elements and packaging design and made an example analysis with the gift packaging design of Squirrel Design Studio. In the case study, the packaging design of the studio’s mirror, storage bag, and puzzle was rated by hierarchical analysis and questionnaires, and the packaging design was analyzed based on the rating results. A convolutional neural network (CNN) (...) was also used to evaluate packages in batches. The results showed that the CNN could make a batch evaluation of gift packaging design accurately; the three gift packaging designs were based on the studio’s logo, making the ratings similar; in addition, the packaging design patterns were composed of different geometric shapes to show the studio’s innovative design theme, and the squirrel silhouette and text description were used to strengthen the impression of the studio among customers. (shrink)

The performance of deep Neural Networks (NNs) in the text (ChatGPT) and image (DALL‐E2) domains has attracted worldwide attention. Convolutional NNs (CNNs), Large Language Models (LLMs), Denoising Diffusion Probabilistic Models (DDPMs)/Noise Conditional Score Networks (NCSNs), and Graph NNs (GNNs) have impacted computer vision, language editing and translation, automated conversation, image generation, and social network management. Proteins can be viewed as texts written with the alphabet of amino acids, as images, or as graphs of interacting residues. Each (...) of these perspectives suggests the use of tools from a different area of deep learning for protein structural biology. Here, I review how CNNs, LLMs, DDPMs/NCSNs, and GNNs have led to major advances in protein structure prediction, inverse folding, protein design, and small molecule design. This review is primarily intended as a deep learning primer for practicing experimental structural biologists. However, extensive references to the deep learning literature should also make it relevant to readers who have a background in machine learning, physics or statistics, and an interest in protein structural biology. (shrink)

The car-sharing system is a popular rental model for cars in shared use. It has become particularly attractive due to its flexibility; that is, the car can be rented and returned anywhere within one of the authorized parking slots. The main objective of this research work is to predict the car usage in parking stations and to investigate the factors that help to improve the prediction. Thus, new strategies can be designed to make more cars on the road and fewer (...) in the parking stations. To achieve that, various machine learning models, namely vector autoregression, support vector regression, eXtreme gradient boosting, k-nearest neighbors, and deep learning models specifically long short-time memory, gated recurrent unit, convolutional neural network, CNN-LSTM, and multilayer perceptron, were performed on different kinds of features. These features include the past usage levels, Chongqing’s environmental conditions, and temporal information. After comparing the obtained results using different metrics, we found that CNN-LSTM outperformed other methods to predict the future car usage. Meanwhile, the model using all the different feature categories results in the most precise prediction than any of the models using one feature category at a time. (shrink)

In this paper, we report on an experiment with The Walking Dead (TWD), which is a narrative-driven adventure game where players have to survive in a post-apocalyptic world filled with zombies. We used OpenFace software to extract action unit (AU) intensities of facial expressions characteristic of decision-making processes and then we implemented a simple convolution neural network (CNN) to see which AUs are predictive of decision-making. Our results provide evidence that the pre-decision variations in action units 17 (chin raiser), (...) 23 (lip tightener), and 25 (parting of lips) are predictive of decision-making processes. Furthermore, when combined, their predictive power increased up to 0.81 accuracy on the test set; we offer speculations about why it is that these particular three AUs were found to be connected to decision-making. Our results also suggest that machine learning methods in combination with video games may be used to accurately and automatically identify complex decision-making processes using AU intensity alone. Finally, our study offers a new method to test specific hypotheses about the relationships between higher-order cognitive processes and behavior, which relies on both narrative video games and easily accessible software, like OpenFace. (shrink)

Rheumatoid arthritis is a progressive systemic autoimmune disease characterized by inflammation of the joints and surrounding tissues, which seriously affects the life of patients. The Sharp/van der Heijde method has been widely used in clinical evaluation for the RA disease. However, this manual method is time-consuming and laborious. Even if two radiologists evaluate a specific location, their subjective evaluation may lead to low inter-rater reliability. Here, we developed an efficient model powered by deep convolutional neural networks to (...) solve these problems and automated the overall scoring on hand X-rays. The depthwise separable convolution technique is used based on ResNet-50 due to the high resolution of hand X-rays. An inverted residual block is introduced to devise a ResNet-Dwise50 model to enhance the efficiency of the model. The model was trained and tested using bilateral posteroanterior images of 3818 patients. The experiment results show the ResNet-Dwise50 model achieved an MAE of 14.90 and RMSE of 22.01 while ensuring high efficiency. There was no statistical difference between the average scores given by two experienced radiologists and predicted scores from our model. (shrink)

Abstract. This study investigates the application of convolutional neural networks (CNNs) to the task of classifying male and female eyes. Using a dataset of eye images, the research explores the potential of deep learning to accurately distinguish between the genders based solely on eye features. The proposed CNN model achieved 94% accuracy on the training set and 91% on the validation set. The study addresses the challenges and limitations in feature extraction from eye images and compares the (...) proposed model with traditional machine learning approaches. The results demonstrate the model's robustness, providing significant insights into gender recognition through partial facial analysis. (shrink)

Ship-type identification in a maritime context can be critical to the authorities to control the activities being carried out. Although Automatic Identification Systems has been mandatory for certain vessels, if a vessel does not have them voluntarily or not, it can lead to a whole set of problems, which is why the use of tracking alternatives such as radar is fully complementary for a vessel monitoring systems. However, radars provide positions, but not what they are detecting. Having systems capable of (...) adding categorical information to radar detections of vessels makes it possible to increase control of the activities being carried out, improve safety in maritime traffic, and optimize on-site inspection resources on the part of the authorities. This paper addresses the binary classification problem (fishing ships versus all other vessels) using unbalanced data from real vessel trajectories. It is performed from a deep learning approach comparing two of the main trends, Convolutional Neural Networks and Long Short-Term Memory. In this paper, it is proposed the weighted cross-entropy methodology and compared with classical data balancing strategies. Both networks show high performance when applying weighted cross-entropy compared with the classical machine learning approaches and classical balancing techniques. This work is shown to be a novel approach to the international problem of identifying fishing ships without context. (shrink)