Search

The recognition of food images is of great significance for nutrition monitoring, food retrieval and food recommendation. However, the accuracy of recognition had not been high enough due to the complex background of food images and the characteristics of small inter-class differences and large intra-class differences. To solve these problems, this paper proposed a food image recognition method based on transfer learning and ensemble learning. Firstly, generic image features were extracted by using the convolutional neural network models (VGG19, ResNet50, MobileNet V2, AlexNet) pre-trained on the ImageNet dataset. Secondly, the 4 pre-trained models were transferred to the food image dataset for model fine-tuning. Finally, different basic learner combination strategies were adopted to establish the ensemble model and classify feature information. In this paper, several kinds of experiments were performed to compare the results of food image recognition between single models and ensemble models on food-11 dataset. The experimental results demonstrated that the accuracy of the ensemble model was the highest, reaching 96.88%, which was superior to any base learner. Therefore, the convolutional neural network model based on transfer learning and ensemble learning has strong learning ability and generalization ability, and it is feasible and practical to apply the method to food image recognition. [ABSTRACT FROM AUTHOR]

Speech enhancement is crucial both for human and machine listening applications. Over the last decade, the use of deep learning for speech enhancement has resulted in tremendous improvement over the classical signal processing and machine learning methods. However, training a deep neural network is not only time-consuming; it also requires extensive computational resources and a large training dataset. Transfer learning, i.e. using a pretrained network for a new task, comes to the rescue by reducing the amount of training time, computational resources, and the required dataset, but the network still needs to be fine-tuned for the new task. This paper presents a novel method of speech denoising and dereverberation (SD&D) on an end-to-end frozen binaural anechoic speech separation network. The frozen network requires neither any architectural change nor any fine-tuning for the new task, as is usually required for transfer learning. The interaural cues of a source placed inside noisy and echoic surroundings are given as input to this pretrained network to extract the target speech from noise and reverberation. Although the pretrained model used in this paper has never seen noisy reverberant conditions during its training, it performs satisfactorily for zero-shot testing (ZST) under these conditions. It is because the pretrained model used here has been trained on the direct-path interaural cues of an active source and so it can recognize them even in the presence of echoes and noise. ZST on the same dataset on which the pretrained network was trained (homo-corpus) for the unseen class of interference, has shown considerable improvement over the weighted prediction error (WPE) algorithm in terms of four objective speech quality and intelligibility metrics. Also, the proposed model offers similar performance provided by a deep learning SD&D algorithm for this dataset under varying conditions of noise and reverberations. Similarly, ZST on a different dataset has provided an improvement in intelligibility and almost equivalent quality as provided by the WPE algorithm. [ABSTRACT FROM AUTHOR]

The meta-learning method proposed in this paper addresses the issue of small-sample regression in the application of engineering data analysis, which is a highly promising direction for research. By integrating traditional regression models with optimization-based data augmentation from meta-learning, the proposed deep neural network demonstrates excellent performance in optimizing glass fiber reinforced plastic (GFRP) for wrapping concrete short columns. When compared with traditional regression models, such as Support Vector Regression (SVR), Gaussian Process Regression (GPR), and Radial Basis Function Neural Networks (RBFNN), the meta-learning method proposed here performs better in modeling small data samples. The success of this approach illustrates the potential of deep learning in dealing with limited amounts of data, offering new opportunities in the field of material data analysis. [ABSTRACT FROM AUTHOR]

Network traffic prediction is an important network monitoring method, which is widely used in network resource optimization and anomaly detection. However, with the increasing scale of networks and the rapid development of 5-th generation mobile networks (5G), traditional traffic forecasting methods are no longer applicable. To solve this problem, this paper applies Long Short-Term Memory (LSTM) network, data augmentation, clustering algorithm, model compression, and other technologies, and proposes a Cluster-based Lightweight PREdiction Model (CLPREM), a method for real-time traffic prediction of 5G mobile networks. We have designed unique data processing and classification methods to make CLPREM more robust than traditional neural network models. To demonstrate the effectiveness of the method, we designed and conducted experiments in a variety of settings. Experimental results confirm that CLPREM can obtain higher accuracy than traditional prediction schemes with less time cost. To address the occasional anomaly prediction issue in CLPREM, we propose a preprocessing method that minimally impacts time overhead. This approach not only enhances the accuracy of CLPREM but also effectively resolves the real-time traffic prediction challenge in 5G mobile networks. [ABSTRACT FROM AUTHOR]

This paper presents a novel sound event detection (SED) system for rare events occurring in an open environment. Wavelet multiresolution analysis (MRA) is used to decompose the input audio clip of 30 seconds into five levels. Wavelet denoising is then applied on the third and fifth levels of MRA to filter out the background. Significant transitions, which may represent the onset of a rare event, are then estimated in these two levels by combining the peak-finding algorithm with the K-medoids clustering algorithm. The small portions of one-second duration, called 'chunks' are cropped from the input audio signal corresponding to the estimated locations of the significant transitions. Features from these chunks are extracted by the wavelet scattering network (WSN) and are given as input to a support vector machine (SVM) classifier, which classifies them. The proposed SED framework produces an error rate comparable to the SED systems based on convolutional neural network (CNN) architecture. Also, the proposed algorithm is computationally efficient and lightweight as compared to deep learning models, as it has no learnable parameter. It requires only a single epoch of training, which is 5, 10, 200, and 600 times lesser than the models based on CNNs and deep neural networks (DNNs), CNN with long short-term memory (LSTM) network, convolutional recurrent neural network (CRNN), and CNN respectively. The proposed model neither requires concatenation with previous frames for anomaly detection nor any additional training data creation needed for other comparative deep learning models. It needs to check almost 360 times fewer chunks for the presence of rare events than the other baseline systems used for comparison in this paper. All these characteristics make the proposed system suitable for real-time applications on resource-limited devices. [ABSTRACT FROM AUTHOR]

Banking and stock markets consider gold to be an important component of their economic and financial status. There are various factors that influence the gold price trend and its fluctuations. Accurate and reliable prediction of the gold price is an essential part of financial and portfolio management. Moreover, it could provide insights about potential buy and sell points in order to prevent financial damages and reduce the risk of investment. In this paper, different architectures of deep neural network (DNN) have been proposed based on long short-term memory (LSTM) and convolutional-based neural networks (CNN) as a hybrid model, along with automatic parameter tuning to increase the accuracy, coefficient of determination, of the forecasting results. An illustrative dataset from the closing gold prices for 44 years, from 1978 to 2021, is provided to demonstrate the effectiveness and feasibility of this method. The grid search technique finds the optimal set of DNNs' parameters. Furthermore, to assess the efficiency of DNN models, three statistical indices of RMSE, RMAE, and coefficient of determination (R2), were calculated for the test set. Results indicate that the proposed hybrid model (CNN-Bi-LSTM) outperforms other models in total bias, capturing extreme values and obtaining promising results. In this model, CNN is used to extract features of input dataset. Furthermore, Bi-LSTM uses CNN's outputs to predict the daily closing gold price. [ABSTRACT FROM AUTHOR]

Purpose: As agricultural technology continues to develop, the scale of planting and production of date fruit is increasing, which brings higher yields. However, the increasing yields also put a lot of pressure on the classification step afterward. Image recognition based on deep learning algorithms can help to identify and classify the date fruit species, even in natural light. Method: In this paper, a deep fusion model based on whale optimization and an artificial neural network for Arabian date classification is proposed. The dataset used in this study includes five classes of date fruit images (Barhi, Khalas, Meneifi, Naboot Saif, Sullaj). The process of designing each model can be divided into three phases. The first phase is feature extraction. The second phase is feature selection. The third phase is the training and testing phase. Finally, the best-performing model was selected and compared with the currently established models (Alexnet, Squeezenet, Googlenet, Resnet50). Results: The experimental results show that, after trying different combinations of optimization algorithms and classifiers, the highest test accuracy achieved by DeepDate was 95.9%. It takes less time to achieve a balance between classification accuracy and time consumption. In addition, the performance of DeepDate is better than that of many deep transfer learning models such as Alexnet, Squeezenet, Googlenet, VGG-19, NasNet, and Inception-V3. Conclusion: The proposed DeepDate improves the accuracy and efficiency of classifying date fruits and achieves better results in classification metrics such as accuracy and F1. DeepDate provides a promising classification solution for date fruit classification with higher accuracy. To further advance the industry, it is recommended that stakeholders invest in technology transfer programs to bring advanced image recognition and AI tools to smaller producers, enhancing sustainability and productivity across the sector. Collaborations between agricultural technologists and growers could also foster more tailored solutions that address specific regional challenges in date fruit production. [ABSTRACT FROM AUTHOR]

Even though deep learning shows impressive results in several applications, its use on problems with High Dimensions and Low Sample Size, such as diagnosing rare diseases, leads to overfitting. One solution often proposed is feature selection. In deep learning, along with feature selection, network sparsification is also used to improve the results when dealing with high dimensions low sample size data. However, most of the time, they are tackled as separate problems. This paper proposes a new approach that integrates feature selection, based on sparsification, into the training process of a deep neural network. This approach uses a constrained biobjective gradient descent method. It provides a set of Pareto optimal neural networks that make a trade-off between network sparsity and model accuracy. Results on both artificial and real datasets show that using a constrained biobjective gradient descent increases the network sparsity without degrading the classification performances. With the proposed approach, on an artificial dataset, the feature selection score reached 0.97 with a sparsity score of 0.92 with an accuracy of 0.9. For the same accuracy, none of the other methods reached a feature score above 0.20 and sparsity score of 0.35. Finally, statistical tests validate the results obtained on all datasets. [ABSTRACT FROM AUTHOR]

Deep learning has achieved immense success in computer vision and has the potential to help physicians analyze visual content for disease and other abnormalities. However, the current state of deep learning is very much a black box, making medical professionals skeptical about integrating these methods into clinical practice. Several methods have been proposed to shed some light on these black boxes, but there is no consensus on the opinion of medical doctors that will consume these explanations. This paper presents a study asking medical professionals about their opinion of current state-of-the-art explainable artificial intelligence methods when applied to a gastrointestinal disease detection use case. We compare two different categories of explanation methods, intrinsic and extrinsic, and gauge their opinion of the current value of these explanations. The results indicate that intrinsic explanations are preferred and that physicians see value in the explanations. Based on the feedback collected in our study, future explanations of medical deep neural networks can be tailored to the needs and expectations of doctors. Hopefully, this will contribute to solving the issue of black box medical systems and lead to successful implementation of this powerful technology in the clinic. [ABSTRACT FROM AUTHOR]

Many different kind of fluids in a wide variety of industries exist, such as two-phase and three-phase. Various combinations of them can be expected and gas-oil-water is one of the most common flows. Measuring the volume fraction of phases without separation is vital in many aspects, one of which is financial issues. Many methods are utilized to ascertain the volumetric proportion of each phase. Sensors based on measuring capacity are so popular because this kind of sensor operates seamlessly and autonomously without necessitating any form of segregation or disruption for measuring in the process. Besides, at the present moment, Artificial intelligence (AI) can be nominated as the most useful tool in several fields, and metering is no exception. Also, three main type of regimes can be found which are annular, stratified, and homogeneous. In this paper, volume fractions in a gas-oil-water three-phase homogeneous regime are measured. To accomplish this objective, an Artificial Neural Network (ANN) and a capacitance-based sensor are utilized. To train the presented network, an optimized sensor was implemented in the COMSOL Multiphysics software and after doing a lot of simulations, 231 different data are produced. Among all obtained results, 70 percent of them (161 data) are awarded to the train data, and the rest of them (70 data) are considered for the test data. This investigation proposes a new intelligent metering system based on the Multilayer Perceptron network (MLP) that can estimate a three-phase water-oil-gas fluid's water volume fraction precisely with a very low error. The obtained Mean Absolute Error (MAE) is equal to 1.66. This dedicates the presented predicting method's considerable accuracy. Moreover, this study was confined to homogeneous regime and cannot measure void fractions of other fluid types and this can be considered for future works. Besides, temperature and pressure changes which highly temper relative permittivity and density of the liquid inside the pipe can be considered for another future idea. [ABSTRACT FROM AUTHOR]

Based on the integrated model of Super-SBM model, spatial Durbin model (SDM) and Grey neural network model, this paper analyzes the panel data of various provinces in China from multiple angles and dimensions. It was found that there were significant differences in eco-efficiency between organic rice production and conventional rice production. The response of organic rice to climate change, the spatial distribution of ecological and economic benefits and the impact on carbon emission were analyzed. The results showed that organic rice planting not only had higher economic benefits, but also showed a rising trend of ecological benefits and a positive feedback effect. This finding highlights the importance of organic rice farming in reducing carbon emissions. Organic rice farming effectively reduces greenhouse gas emissions, especially carbon dioxide and methane, by improving soil management and reducing the use of fertilizers and pesticides. This has important implications for mitigating climate change and promoting soil health and biodiversity. With the acceleration of urbanization, the increase of organic rice planting area shows the trend of organic rice gradually replacing traditional rice cultivation, further highlighting the potential of organic agriculture in emission reduction, environmental protection and sustainable agricultural production. To this end, it is recommended that the Government implement a diversified support strategy to encourage technological innovation, provide guidance and training, and raise public awareness and demand for organic products. At the same time, private sector participation is stimulated to support the development of organic rice cultivation through a public-private partnership model. Through these measures, further promote organic rice cultivation, achieve the dual goals of economic benefits and environmental benefits, and effectively promote the realization of double carbon emission reduction targets. [ABSTRACT FROM AUTHOR]

In order to further improve the accuracy of the video-based behavior recognition method, an effective behavior recognition method in the video session using convolutional neural network is proposed. Specifically, by adding the target detection phase before the behavior recognition algorithm, the body region in the video can be accurately extracted to reduce the interference of redundant and unnecessary background noises, and at the same time, the inappropriate images can be replaced, which has reached the role of balance background trade-off, and finally, the neural network can learn the human behavior information with emphasis. By adding fragmentation and stochastic sampling, the long-time time-domain modeling of the whole video session can be established, so that the model can obtain video-level expression ability. Finally, the improved loss function is used for behavior recognition to solve the problem of classification difficulty and possible sample imbalance. In addition, we conducted the hyperparametric experiment, the ablation experiment and the contrast experiment on different open source and benchmark datasets. Compared with other commonly used behavior recognition algorithms, the experimental results verify the effectiveness of the proposed method. In addition, the related deep learning-based methods used in behavior recognition are reviewed at the beginning of this paper, and the challenges in behavior recognition and future research directions are prospected at the end of this paper, which will undoubtedly play a double role in the work of later researchers. [ABSTRACT FROM AUTHOR]

Click-through rate (CTR) prediction is a term used to predict the probability of a user clicking on an ad or item and has become a popular research area in advertising. As the volume of Internet data increases, the labor costs of traditional feature engineering continue to rise. To reduce the dependence on feature interactions, this paper proposes a fusion model that combines explicit and implicit feature interactions, called the Two-Tower Multi-Head Attention Neural Network (TMH) approach. The model integrates multiple components such as multi-head attention, residual network, and deep neural networks into an end-to-end model that automatically obtains vector-level combinations of explicit and implicit features to predict click-through rates through higher-order explicit and implicit interactions. We evaluated the effectiveness of TMH in CTR prediction through numerous experiments using three real datasets. The results demonstrate that our proposed method not only outperforms existing prediction methods but also offers good interpretability. [ABSTRACT FROM AUTHOR]

Coal pillar retention plays a crucial role in ensuring safety and minimizing ground deformation in coal mining operations. However, accurately and efficiently determining the optimal size of protective pillars, reducing coal pillar pressure, and addressing challenges such as limited access to retention parameters, lengthy observation times, and high labor costs are challenges that must be addressed. In this paper, we presented a methodology using Huainan mine as a case study to address these challenges. The solution involves deriving the formula for coal pillar retention parameters based on the Three Regulations definition and requirements. The total least squares algorithm was integrated with surface observation station data and the MATLAB software platform to automate the coal pillar retention solution. Furthermore, a linear regression model of coal pillar retention-related parameters was established using the geological mining condition data. The proposed ELM neural network model was optimized using a genetic algorithm and combined with the linear regression model to establish a predictive model. The results demonstrated that the proposed machine learning algorithm attains the requisite level of accuracy for industrial production. [ABSTRACT FROM AUTHOR]

Long short-term memory (LSTM) has been effectively used to represent sequential data in recent years. However, LSTM still struggles with capturing the long-term temporal dependencies. In this paper, we propose an hourglass-shaped LSTM that is able to capture long-term temporal correlations by reducing the feature resolutions without data loss. We have used skip connections in non-adjacent layers to avoid gradient decay. In addition, an attention process is incorporated into skip connections to emphasize the essential spectral features and spectral regions. The proposed LSTM model is applied to speech enhancement and recognition applications. The proposed LSTM model uses no future information, resulting in a causal system suitable for real-time processing. The combined spectral feature sets are used to train the LSTM model for improved performance. Using the proposed model, the ideal ratio mask (IRM) is estimated as a training objective. The experimental evaluations using short-time objective intelligibility (STOI) and perceptual evaluation of speech quality (PESQ) have demonstrated that the proposed model with robust feature representation obtained higher speech intelligibility and perceptual quality. With the TIMIT, LibriSpeech, and VoiceBank datasets, the proposed model improved STOI by 16.21%, 16.41%, and 18.33% over noisy speech, whereas PESQ is improved by 31.1%, 32.9%, and 32%. In seen and unseen noisy situations, the proposed model outperformed existing deep neural networks (DNNs), including baseline LSTM, feedforward neural network (FDNN), convolutional neural network (CNN), and generative adversarial network (GAN). With the Kaldi toolkit for automated speech recognition (ASR), the proposed model significantly reduced the word error rates (WERs) and reached an average WER of 15.13% in noisy backgrounds. [ABSTRACT FROM AUTHOR]

The deep neural network is used to establish a neural network model to solve the problems of low accuracy and poor accuracy of traditional algorithms in screening differentially expressed genes and function prediction during the walnut endocarp hardening stage. The paper walnut is used as the research object to analyze the biological information of paper walnut. The changes of lignin deposition during endocarp hardening from 50 days to 90 days are observed by microscope. Then, the Convolutional Neural Network (CNN) and Long and Short-term Memory (LSTM) network model are adopted to construct an expression gene screening and function prediction model. Then, the transcriptome and proteome sequencing and biological information of walnut endocarp samples at 50, 57, 78, and 90 days after flowering are analyzed and taken as the training data set of the CNN + LSTM model. The experimental results demonstrate that the endocarp of paper walnut began to harden at 57 days, and the endocarp tissue on the hardened inner side also began to stain. This indicates that the endocarp hardened laterally from outside to inside. The screening and prediction results show that the CNN + LSTM model's highest accuracy can reach 0.9264. The Accuracy, Precision, Recall, and F1-score of the CNN + LSTM model are better than the traditional machine learning algorithm. Moreover, the Receiver Operating Curve (ROC) area enclosed by the CNN + LSTM model and coordinate axis is the largest, and the Area Under Curve (AUC) value is 0.9796. The comparison of ROC and AUC proves that the CNN + LSTM model is better than the traditional algorithm for screening differentially expressed genes and function prediction in the walnut endocarp hardening stage. Using deep learning to predict expressed genes' function accurately can reduce the breeding cost and significantly improve the yield and quality of crops. This research provides scientific guidance for the scientific breeding of paper walnut. [ABSTRACT FROM AUTHOR]

The 3D point clouds are increasingly being used in various application including safety-critical fields. It has recently been demonstrated that deep neural networks can successfully process 3D point clouds. However, these deep networks can be misclassified via 3D adversarial attacks intentionality designed to perturb some point cloud's features. These misclassifications may be due to the network's overreliance on features with unnecessary information in training sets. As such, identifying the features used by deep classifiers and removing features with unnecessary information from the training data can improve network's robustness against adversarial attacks. In this paper, the LPF-Defense framework is proposed to discard this unnecessary information from the training data by suppressing the high-frequency content in the training phase. Our analysis shows that adversarial perturbations are found in the high-frequency contents of adversarial point clouds. Experiments showed that the proposed defense method achieves the state-of-the-art defense performance against six adversarial attacks on PointNet, PointNet++, and DGCNN models. The findings are practically supported by an expansive evaluation of synthetic (ModelNet40 and ShapeNet) and real datasets (ScanObjectNN). In particular, improvements are achieved with an average increase of classification accuracy by 3.8% on Drop100 attack and 4.26% on Drop200 attack compared to the state-of-the-art methods. The method also improves models' accuracy on the original dataset compared to other available methods. (To facilitate research in this area, an open-source implementation of the method and data is released at https://github.com/kimianoorbakhsh/LPF-Defense.). [ABSTRACT FROM AUTHOR]

Introduction: Postoperative complications affect up to 15% of surgical patients constituting a major part of the overall disease burden in a modern healthcare system. While several surgical risk calculators have been developed, none have so far been shown to decrease the associated mortality and morbidity. Combining deep neural networks and genomics with the already established clinical predictors may hold promise for improvement. Methods: The UK Biobank was utilized to build linear and deep learning models for the prediction of surgery relevant outcomes. An initial GWAS for the relevant outcomes was initially conducted to select the Single Nucleotide Polymorphisms for inclusion in the models. Model performance was assessed with Receiver Operator Characteristics of the Area Under the Curve and optimum precision and recall. Feature importance was assessed with SHapley Additive exPlanations. Results: Models were generated for atrial fibrillation, venous thromboembolism and pneumonia as genetics only, clinical features only and a combined model. For venous thromboembolism, the ROC-AUCs were 60.1% [59.6%-60.4%], 63.4% [63.2%-63.4%] and 66.6% [66.2%-66.9%] for the linear models and 51.5% [49.4%-53.4%], 63.2% [61.2%-65.0%] and 62.6% [60.7%-64.5%] for the deep learning SNP, clinical and combined models, respectively. For atrial fibrillation, the ROC-AUCs were 60.3% [60.0%-60.4%], 78.7% [78.7%-78.7%] and 80.0% [79.9%-80.0%] for the linear models and 59.4% [58.2%-60.9%], 78.8% [77.8%-79.8%] and 79.8% [78.8%-80.9%] for the deep learning SNP, clinical and combined models, respectively. For pneumonia, the ROC-AUCs were 50.1% [49.6%-50.6%], 69.2% [69.1%-69.2%] and 68.4% [68.0%-68.5%] for the linear models and 51.0% [49.7%-52.4%], 69.7% [.5%-70.8%] and 69.7% [68.6%-70.8%] for the deep learning SNP, clinical and combined models, respectively. Conclusion: In this report we presented linear and deep learning predictive models for surgery relevant outcomes. Overall, predictability was similar between linear and deep learning models and inclusion of genetics seemed to improve accuracy. [ABSTRACT FROM AUTHOR]

Social media platforms serve as communication tools where users freely share information regardless of its accuracy. Propaganda on these platforms refers to the dissemination of biased or deceptive information aimed at influencing public opinion, encompassing various forms such as political campaigns, fake news, and conspiracy theories. This study introduces a Hybrid Feature Engineering Approach for Propaganda Identification (HAPI), designed to detect propaganda in text-based content like news articles and social media posts. HAPI combines conventional feature engineering methods with machine learning techniques to achieve high accuracy in propaganda detection. This study is conducted on data collected from Twitter via its API, and an annotation scheme is proposed to categorize tweets into binary classes (propaganda and non-propaganda). Hybrid feature engineering entails the amalgamation of various features, including Term Frequency-Inverse Document Frequency (TF-IDF), Bag of Words (BoW), Sentimental features, and tweet length, among others. Multiple Machine Learning classifiers undergo training and evaluation utilizing the proposed methodology, leveraging a selection of 40 pertinent features identified through the hybrid feature selection technique. All the selected algorithms including Multinomial Naive Bayes (MNB), Support Vector Machine (SVM), Decision Tree (DT), and Logistic Regression (LR) achieved promising results. The SVM-based HaPi (SVM-HaPi) exhibits superior performance among traditional algorithms, achieving precision, recall, F-Measure, and overall accuracy of 0.69, 0.69, 0.69, and 69.2%, respectively. Furthermore, the proposed approach is compared to well-known existing approaches where it overperformed most of the studies on several evaluation metrics. This research contributes to the development of a comprehensive system tailored for propaganda identification in textual content. Nonetheless, the purview of propaganda detection transcends textual data alone. Deep learning algorithms like Artificial Neural Networks (ANN) offer the capability to manage multimodal data, incorporating text, images, audio, and video, thereby considering not only the content itself but also its presentation and contextual nuances during dissemination. [ABSTRACT FROM AUTHOR]

Accurate Origin-Destination (OD) prediction is significant for effective traffic monitor, which can support operation decision in traffic planning and management field. The enclosed expressway network system like toll gates system in China can collect mounts of trip records which can be gathered for OD prediction. The paper develops a novel neural network, which is named Expressway OD Prediction Neural Network (EODPNN) for toll data-based prediction. The network consists of the following three modules: The Feature Extension Module, the Memory Module, and the Prediction Module. In the process, the attributes data which can reflect the city attribute such as GDP, population, and the number of vehicles are considered to embeded into the notwork to increase the accuracy of the model. For the applicability improvment of the model, we categorize the cities in multiple classes based on their economy and population scales in this paper, which can provide a higher accurate prediction of OD by EODPNN. The results shows that, comparing to the traditional model like ARIMA and SVM, or typical neural networks like Bidirectional Long Short-term Memory, the EODPNN delivers a better prediction performance. The method proposed in this paper has been fully verified and has a potential to transplant to the other OD data-based management systems for a more accurate and flexible prediction. [ABSTRACT FROM AUTHOR]

As the industry gradually enters the stage of unmanned and intelligent, factories in the future need to realize intelligent monitoring and diagnosis and maintenance of parts and components. In order to achieve this goal, it is first necessary to accurately identify and classify the parts in the factory. However, the existing literature rarely studies the classification and identification of parts of the entire factory. Due to the lack of existing data samples, this paper studies the identification and classification of small samples of industrial machine parts. In order to solve this problem, this paper establishes a convolutional neural network model based on the InceptionNet-V3 pretrained model through migration learning. Through experimental design, the influence of data expansion, learning rate and optimizer algorithm on the model effectiveness is studied, and the optimal model was finally determined, and the test accuracy rate reaches 99.74%. By comparing with the accuracy of other classifiers, the experimental results prove that the convolutional neural network model based on transfer learning can effectively solve the problem of recognition and classification of industrial machine parts with small samples and the idea of transfer learning can also be further promoted. [ABSTRACT FROM AUTHOR]

I-nteract is a cyber-physical system that enables real-time interaction with both virtual and real artifacts to design 3D models for additive manufacturing by leveraging mixed-reality technologies. This paper presents novel advances in the development of the interaction platform to generate 3D models using both constructive solid geometry and artificial intelligence. In specific, by taking advantage of the generative capabilities of deep neural networks, the system has been automated to generate 3D models inferred from a single 2D image captured by the user. Furthermore, a novel generative neural architecture, SliceGen, has been proposed and integrated with the system to overcome the limitation of single-type genus 3D model generation imposed by differentiable-rendering-based deep neural architectures. The system also enables the user to adjust the dimensions of the 3D models with respect to their physical workspace. The effectiveness of the system is demonstrated by generating 3D models of furniture (e.g., chairs and tables) and fitting them into the physical space in a mixed reality environment. The presented developmental advances provide a novel and immersive form of interaction to facilitate the inclusion of a consumer into the design process for personal fabrication. [ABSTRACT FROM AUTHOR]

The choice of crossover and mutation strategies plays a crucial role in the searchability, convergence efficiency and precision of genetic algorithms. In this paper, a novel improved genetic algorithm is proposed by improving the crossover and mutation operation of the simple genetic algorithm, and it is verified by 15 test functions. The qualitative results show that, compared with three other mainstream swarm intelligence optimization algorithms, the algorithm can not only improve the global search ability, convergence efficiency and precision, but also increase the success rate of convergence to the optimal value under the same experimental conditions. The quantitative results show that the algorithm performs superiorly in 13 of the 15 tested functions. The Wilcoxon rank-sum test was used for statistical evaluation, showing the significant advantage of the algorithm at 95% confidence intervals. Finally, the algorithm is applied to neural network adversarial attacks. The applied results show that the method does not need the structure and parameter information inside the neural network model, and it can obtain the adversarial samples with high confidence in a brief time just by the classification and confidence information output from the neural network. [ABSTRACT FROM AUTHOR]

This study develops a "Skill Talent Ecological Evaluation Model" across cultivation, potential energy, kinetic energy, innovation, and service and support ecologies. AHP-entropy determines indicator weights, Hopfield neural network assesses talent ecology levels, and the PVAR model analyzes digital transformation effects. Findings reveal: Cultivation ecology rates A, potential ecology rates B+, kinetic ecology rates B-, service and support ecology rates B-, and innovation ecology rates C. Digital transformation spurs skill demand, impacting talent and economic contributions. Kinetic ecology sees increased demand, potentially impacting traditional industries positively. Innovation ecology necessitates continuous skill learning. Service and support ecology witnesses growth in digital entrepreneurship, requiring policy incentives and incubation center support. [ABSTRACT FROM AUTHOR]

Global warming, caused by greenhouse gas emissions, is a major challenge for all human societies. To ensure that ambitious carbon neutrality and sustainable economic development goals are met, regional human activities and their impacts on carbon emissions must be studied. Guizhou Province is a typical karst area in China that predominantly uses fossil fuels. In this study, a backpropagation (BP) neural network and extreme learning machine (ELM) model, which is advantageous due to its nonlinear processing, were used to predict carbon emissions from 2020 to 2040 in Guizhou Province. The carbon emissions were calculated using conversion and inventory compilation methods with energy consumption data and the results showed an "S" growth trend. Twelve influencing factors were selected, however, five with larger correlations were screened out using a grey correlation analysis method. A prediction model for carbon emissions from Guizhou Province was established. The prediction performance of a whale optimization algorithm (WOA)-ELM model was found to be higher than the BP neural network and ELM models. Baseline, high-speed, and low-carbon scenarios were analyzed and the size and time of peak carbon emissions in Liaoning Province from 2020 to 2040 were predicted using the WOA-ELM model. [ABSTRACT FROM AUTHOR]

Medical image segmentation is a critical application that plays a significant role in clinical research. Despite the fact that many deep neural networks have achieved quite high accuracy in the field of medical image segmentation, there is still a scarcity of annotated labels, making it difficult to train a robust and generalized model. Few-shot learning has the potential to predict new classes that are unseen in training with a few annotations. In this study, a novel few-shot semantic segmentation framework named prototype-based generative adversarial network (PG-Net) is proposed for medical image segmentation without annotations. The proposed PG-Net consists of two subnetworks: the prototype-based segmentation network (P-Net) and the guided evaluation network (G-Net). On one hand, the P-Net as a generator focuses on extracting multi-scale features and local spatial information in order to produce refined predictions with discriminative context between foreground and background. On the other hand, the G-Net as a discriminator, which employs an attention mechanism, further distills the relation knowledge between support and query, and contributes to P-Net producing segmentation masks of query with more similar distributions as support. Hence, the PG-Net can enhance segmentation quality by an adversarial training strategy. Compared to the state-of-the-art (SOTA) few-shot segmentation methods, comparative experiments demonstrate that the proposed PG-Net provides noticeably more robust and prominent generalization ability on different medical image modality datasets, including an abdominal Computed Tomography (CT) dataset and an abdominal Magnetic Resonance Imaging (MRI) dataset. [ABSTRACT FROM AUTHOR]

In the field of soil mechanics, especially in transportation and environmental geotechnics, the use of machine learning (ML) techniques has emerged as a powerful tool for predicting and understanding the compressive strength behavior of soils especially graded ones. This is to overcome the sophisticated equipment, laboratory space and cost needs utilized in multiple experiments on the treatment of soils for environmental geotechnics systems. This present study explores the application of machine learning (ML) techniques, namely Genetic Programming (GP), Artificial Neural Networks (ANN), Evolutionary Polynomial Regression (EPR), and the Response Surface Methodology in predicting the unconfined compressive strength (UCS) of soil-lime mixtures. This was for purposes of subgrade and landfill liner design and construction. By utilizing input variables such as Gravel, Sand, Silt, Clay, and Lime contents (G, S, M, C, L), the models forecasted the strength values after 7 and 28 days of curing. The accuracy of the developed models was compared, revealing that both ANN and EPR achieved a similar level of accuracy for UCS after 7 days, while the GP model performed slightly lower. The complexity of the formula required for predicting UCS after 28 days resulted in decreased accuracy. The ANN and EPR models achieved accuracies of 85% and 82%, with R2 of 0.947 and 0.923, and average error of 0.15 and 0.18, respectively, while the GP model exhibited a lower accuracy of 66.0%. Conversely, the RSM produced models for the UCS with predicted R2 of more than 98% and 99%, for the 7- and 28- day curing regimes, respectively. The RSM also produced adequate precision in modelling UCS of more than 14% against the standard 7%. All input factors were found to have almost equal importance, except for the lime content (L), which had an average influence. This shows the importance of soil gradation in the design and construction of subgrade and landfill liners. This research further demonstrates the potential of ML techniques for predicting the strength of lime reconstituted G-S-M-C graded soils and provides valuable insights for engineering applications in exact and sustainable subgrade and liner designs, construction and performance monitoring and rehabilitation of the constructed civil engineering infrastructure. [ABSTRACT FROM AUTHOR]

Brain cancers caused by malignant brain tumors are one of the most fatal cancer types with a low survival rate mostly due to the difficulties in early detection. Medical professionals therefore use various invasive and non-invasive methods for detecting and treating brain tumors at the earlier stages thus enabling early treatment. The main non-invasive methods for brain tumor diagnosis and assessment are brain imaging like computed tomography (CT), positron emission tomography (PET) and magnetic resonance imaging (MRI) scans. In this paper, the focus is on detection and segmentation of brain tumors from 2D and 3D brain MRIs. For this purpose, a complete automated system with a web application user interface is described which detects and segments brain tumors with more than 90% accuracy and Dice scores. The user can upload brain MRIs or can access brain images from hospital databases to check presence or absence of brain tumor, to check the existence of brain tumor from brain MRI features and to extract the tumor region precisely from the brain MRI using deep neural networks like CNN, U-Net and U-Net++. The web application also provides an option for entering feedbacks on the results of the detection and segmentation to allow healthcare professionals to add more precise information on the results that can be used to train the model for better future predictions and segmentations. [ABSTRACT FROM AUTHOR]

Deep neural networks (DNNs) detect patterns in data and have shown versatility and strong performance in many computer vision applications. However, DNNs alone are susceptible to obvious mistakes that violate simple, common sense concepts and are limited in their ability to use explicit knowledge to guide their search and decision making. While overall DNN performance metrics may be good, these obvious errors, coupled with a lack of explainability, have prevented widespread adoption for crucial tasks such as medical image analysis. The purpose of this paper is to introduce SimpleMind, an open-source software environment for Cognitive AI focused on medical image understanding. It allows creation of a knowledge base that describes expected characteristics and relationships between image objects in an intuitive human-readable form. The knowledge base can then be applied to an input image to recognize and understand its content. SimpleMind brings thinking to DNNs by: (1) providing methods for reasoning with the knowledge base about image content, such as spatial inferencing and conditional reasoning to check DNN outputs; (2) applying process knowledge, in the form of general-purpose software agents, that are dynamically chained together to accomplish image preprocessing, DNN prediction, and result post-processing, and (3) performing automatic co-optimization of all knowledge base parameters to adapt agents to specific problems. SimpleMind enables reasoning on multiple detected objects to ensure consistency, providing cross-checking between DNN outputs. This machine reasoning improves the reliability and trustworthiness of DNNs through an interpretable model and explainable decisions. Proof-of-principle example applications are provided that demonstrate how SimpleMind supports and improves deep neural networks by embedding them within a Cognitive AI environment. [ABSTRACT FROM AUTHOR]

Awarding joint or sole custody is of crucial importance for the lives of both the child and the parents. This paper first models the factors explaining a court's decision to grant child custody and later tests the predictive capacity of the proposed model. We conducted an empirical study using data from 1,884 court rulings, identifying and labeling factual elements, legal principles, and other relevant information. We developed a neural network model that includes eight factual findings, such as the relationship between the parents and their economic resources, the child's opinion, and the psychological report on the type of custody. We performed a temporal validation using cases later in time than those in the training sample for prediction. Our system predicted the court's decisions with an accuracy exceeding 85%. We obtained easy-to-apply decision rules with the decision tree technique. The paper contributes by identifying the factors that best predict joint custody, which is useful for parents, lawyers, and prosecutors. Parents would do well to know these findings before venturing into a courtroom. [ABSTRACT FROM AUTHOR]

The outbreak of a novel coronavirus pneumonia (COVID-19), wherein more than 200 million people have been infected and millions have died, poses a great threat to achieving the United Nations 2030 sustainable development goal (SDGs). Based on the Baidu index of 'novel coronavirus', this paper analyses the spatial and temporal characteristics of and factors that influenced the attention network for COVID-19 from January 9, 2020, to April 15, 2020. The study found that (1) Temporally, the attention in the new coronavirus network showed an upward trend from January 9 to January 29, with the largest increase from January 23 to January 29 and a peak on January 29, and then a slow downward trend. The level of attention in the new coronavirus network was basically flat when comparing January 22 and March 4. (2) Spatially, first, from the perspective of regional differences, the network attention in the eastern and central regions decreased in turn. The network users in the eastern region exhibited the highest attention to the new coronavirus, especially in Guangdong, Shandong, Jiangsu and other provinces and cities. The network attention in Tibet, Xinjiang, Qinghai and Ningxia in the western region was the lowest in terms of the national network attention. Second, from the perspective of interprovincial differences, the attention in the new coronavirus network was highly consistent with the Hu Huanyong line of China's population boundary. The east of the Hu Huanyong line is densely populated, and the network showed high concern, mostly ranking at the third to fifth levels. (3) The number of Internet users in the information technology field, the population, and the culture and age characteristics of individuals are important factors that influence the novel coronavirus attention network. [ABSTRACT FROM AUTHOR]

The vibration generated by tractor field operations will seriously affect the comfort and health of the driver. The low frequency vibration generated by the engine and ground excitation is similar to the natural frequency of human organs. Long term operation in this environment will resonate with the organs and affect drivers' health. To investigate this possibility, in this paper we carried out a collection experiment of human physiological indicators relevant to vibration fatigue. Four physiological signals of surface electromyography, skin electricity, skin temperature, and photoplethysmography signal were collected while the subjects experienced vibration. Several features of physiological signals as well as the law of signal features changing with fatigue are studied. The test results show that with the increase of human fatigue, the overall physiological parameters show the following trends: The median frequency of the human body surface electromyography and the slope of skin surface temperature decreases, the value of skin conductivity and the mean value of the photoplethysmography signal increases. Furthermore, this paper proposes a vibration comfort evaluation method based on multiple physiological parameters of the human body. An artificial neural network model is trained with test samples, and the prediction accuracy rate reaches 88.9%. Finally, the vibration conditions are changed by the shock-absorbing suspension of a tractor, verifying the effectiveness of the physiological signal changing with the vibration of the human body. The established prediction model can also be used to objectively reflect the discomfort of the human body under different working conditions and provide a basis for structural design optimization. [ABSTRACT FROM AUTHOR]

Mechanical cues such as stresses and strains are now recognized as essential regulators in many biological processes like cell division, gene expression or morphogenesis. Studying the interplay between these mechanical cues and biological responses requires experimental tools to measure these cues. In the context of large scale tissues, this can be achieved by segmenting individual cells to extract their shapes and deformations which in turn inform on their mechanical environment. Historically, this has been done by segmentation methods which are well known to be time consuming and error prone. In this context however, one doesn't necessarily require a cell-level description and a coarse-grained approach can be more efficient while using tools different from segmentation. The advent of machine learning and deep neural networks has revolutionized the field of image analysis in recent years, including in biomedical research. With the democratization of these techniques, more and more researchers are trying to apply them to their own biological systems. In this paper, we tackle a problem of cell shape measurement thanks to a large annotated dataset. We develop simple Convolutional Neural Networks (CNNs) which we thoroughly optimize in terms of architecture and complexity to question construction rules usually applied. We find that increasing the complexity of the networks rapidly no longer yields improvements in performance and that the number of kernels in each convolutional layer is the most important parameter to achieve good results. In addition, we compare our step-by-step approach with transfer learning and find that our simple, optimized CNNs give better predictions, are faster in training and analysis and don't require more technical knowledge to be implemented. Overall, we offer a roadmap to develop optimized models and argue that we should limit the complexity of such models. We conclude by illustrating this strategy on a similar problem and dataset. [ABSTRACT FROM AUTHOR]

The prediction of energy consumption is of great significance to the stability of the regional energy supply. In previous research on energy consumption forecasting, researchers have constantly proposed improved neural network prediction models or improved machine learning models to predict time series data. Combining the well-performing machine learning model and neural network model in energy consumption prediction, we propose a hybrid model architecture of GRU-MMattention-LightGBM with feature selection based on Prophet decomposition. During the prediction process, first, the prophet features are extracted from the original time series. We select the best LightGBM model in the training set and save the best parameters. Then, the Prophet feature is input to GRU-MMattention for training. Finally, MLP is used to learn the final prediction weight between LightGBM and GRU-MMattention. After the prediction weights are learned, the final prediction result is determined. The innovation of this paper lies in that we propose a structure to learn the internal correlation between features based on Prophet feature extraction combined with the gating and attention mechanism. The structure also has the characteristics of a strong anti-noise ability of the LightGBM method, which can reduce the impact of the energy consumption mutation point on the overall prediction effect of the model. In addition, we propose a simple method to select the hyperparameters of the time window length using ACF and PACF diagrams. The MAPE of the GRU-MMattention-LightGBM model is 1.69%, and the relative error is 8.66% less than that of the GRU structure and 2.02% less than that of the LightGBM prediction. Compared with a single method, the prediction accuracy and stability of this hybrid architecture are significantly improved. [ABSTRACT FROM AUTHOR]

Past research on the process of extinguishing a fire typically used a traditional linear water jet falling point model and the results ignored external factors, such as environmental conditions and the status of the fire engine, even though the water jet falling point location prediction was often associated with these parameters and showed a nonlinear relationship. This paper constructed a BP (Back Propagation) neural network model. The fire gun nozzle characteristics were included as model inputs, and the water discharge point coordinates were the model outputs; thus, the model could precisely predict the water discharge point with small error and high precision to determine an accurate firing position and allow for the timely adjustment of the spray gun. To improve the slow convergence and local optimality problems of the BP neural network (BPNN), this paper further used a genetic algorithm to optimize the BPNN (GA-BPNN). The BPNN can be used to optimize the weights in the network to train them for global optimization. A genetic algorithm was introduced into the neural network approach, and the water jet landing prediction model was further improved. The simulation results showed that the prediction accuracy of the GA-BP model was better than that of the BPNN alone. The established model can accurately predict the location of the water jet, making the prediction results more useful for firefighters. [ABSTRACT FROM AUTHOR]

Classifying bank accounts by using transaction data is encouraging in cracking down on illegal financial activities. However, few research simultaneously use heterogenous features, which are embedded in the time series data. In this paper, a two route convolution neural network TRHD-CNN model, fed with two types of heterogeneous feature matrices, is proposed for classifying the bank accounts. TRHD-CNN adopts divide and conquer strategy to extract characteristics from two types of data source independently. The strategy is proved able in mining complementary classification characteristics. We firstly transfer the original log data into a directed and dynamic transaction network. On the basis of that, two feature generation methods are devised for extracting information from local topological structure and time series transaction respectively. A DirectedWalk method is developed in this paper to learning the network vector of vertices used for embedding the neighbor relationship of bank account. The extensive experimental results, conducted on a real bank transaction dataset that contains illegal pyramid selling accounts, show the significant advantage of TRHD-CNN over the existing methods. TRHD-CNN can provide recall scores up to 5.15% higher than competing methods. In addition, the two-route architecture of TRHD-CNN is easy to extend to multi-route scenarios and other fields. [ABSTRACT FROM AUTHOR]

Accurate analysis of the strength of steel-fiber-reinforced concrete (SFRC) is important for ensuring construction quality and safety. Cube compression and splitting tensile tests of steel fiber with different varieties, lengths, and dosages were performed, and the effects of different varieties, lengths, and dosages on the compressive and splitting properties of secondary concrete were obtained. It was determined that the compression and splitting strengths of concrete could be effectively improved by the addition of end-hooked and milled steel fibers. The compressive and splitting strengths of concrete can be enhanced by increasing the fiber length and content. However, concrete also exhibits obvious uncertainty owing to the comprehensive influence of steel fiber variety, fiber length, and fiber content. In order to solve this engineering uncertainty, the traditional RBF neural network is improved by using central value and weight learning strategy especially. On this basis, the RBF fuzzy neural network prediction model of the strength of secondary steel fiber-reinforced concrete was innovatively established with the type, length and content of steel fiber as input information and the compressive strength and splitting tensile strength as output information. In order to further verify the engineering reliability of the prediction model, the compressive strength and splitting tensile strength of steel fiber reinforced concrete with rock anchor beams are predicted by the prediction model. The results show that the convergence rate of the prediction model is increased by 15%, and the error between the predicted value and the measured value is less than 10%, which is more efficient and accurate than the traditional one. Additionally, the improved model algorithm is efficient and reasonable, providing technical support for the safe construction of large-volume steel fiber concrete projects, such as rock anchor beams. The fuzzy random method can also be applied to similar engineering fields. [ABSTRACT FROM AUTHOR]

Using logistic regression and neural networks, the aim of this study was to compare model performance when predicting player draft outcome during the 2021 AFL National Draft. Physical testing, in-game movement and technical involvements were collected from 708 elite-junior Australian Rules football players during consecutive seasons. Predictive models were generated using data from 465 players (2017 to 2020). Data from 243 players were then used to prospectively predict the 2021 AFL National Draft. Logistic regression and neural network models were compared for specificity, sensitivity and accuracy using relative cut-off thresholds from 5% to 50%. Using factored and unfactored data, and a range of relative cut-off thresholds, neural networks accounted for 73% of the 40 best performing models across positional groups and data configurations. Neural networks correctly classified more drafted players than logistic regression in 88% of cases at draft rate (15%) and convergence threshold (35%). Using individual variables across thresholds, neural networks (specificity = 79 ± 13%, sensitivity = 61 ± 24%, accuracy = 76 ± 8%) were consistently superior to logistic regression (specificity = 73 ± 15%, sensitivity = 29 ± 14%, accuracy = 66 ± 11%). Where the goal is to identify talented players with draft potential, model sensitivity is paramount, and neural networks were superior to logistic regression. [ABSTRACT FROM AUTHOR]

Cloud Data Computing (CDC) is conducive to precise energy-saving management of user data centers based on the real-time energy consumption monitoring of Information Technology equipment. This work aims to obtain the most suitable energy-saving strategies to achieve safe, intelligent, and visualized energy management. First, the theory of Convolutional Neural Network (CNN) is discussed. Besides, an intelligent energy-saving model based on CNN is designed to ameliorate the variable energy consumption, load, and power consumption of the CDC data center. Then, the core idea of the policy gradient (PG) algorithm is introduced. In addition, a CDC task scheduling model is designed based on the PG algorithm, aiming at the uncertainty and volatility of the CDC scheduling tasks. Finally, the performance of different neural network models in the training process is analyzed from the perspective of total energy consumption and load optimization of the CDC center. At the same time, simulation is performed on the CDC task scheduling model based on the PG algorithm to analyze the task scheduling demand. The results demonstrate that the energy consumption of the CNN algorithm in the CDC energy-saving model is better than that of the Elman algorithm and the ecoCloud algorithm. Besides, the CNN algorithm reduces the number of virtual machine migrations in the CDC energy-saving model by 9.30% compared with the Elman algorithm. The Deep Deterministic Policy Gradient (DDPG) algorithm performs the best in task scheduling of the cloud data center, and the average response time of the DDPG algorithm is 141. In contrast, the Deep Q Network algorithm performs poorly. This paper proves that Deep Reinforcement Learning (DRL) and neural networks can reduce the energy consumption of CDC and improve the completion time of CDC tasks, offering a research reference for CDC resource scheduling. [ABSTRACT FROM AUTHOR]

Siamese-based trackers have achieved excellent performance and attracted extensive attention, which regard the tracking task as a similarity learning between the target template and search regions. However, most Siamese-based trackers do not effectively exploit correlations of the spatial and channel-wise information to represent targets. Meanwhile, the cross-correlation is a linear matching method and neglects the structured and part-level information. In this paper, we propose a novel tracking algorithm for feature extraction of target templates and search region images. Based on convolutional neural networks and shuffle attention, the tracking algorithm computes the similarity between the template and a search region through a graph attention matching. The proposed tracking algorithm exploits the correlations between the spatial and channel-wise information to highlight the target region. Moreover, the graph matching can greatly alleviate the influences of appearance variations such as partial occlusions. Extensive experiments demonstrate that the proposed tracking algorithm achieves excellent tracking results on multiple challenging benchmarks. Compared with other state-of-the-art methods, the proposed tracking algorithm achieves excellent tracking performance. [ABSTRACT FROM AUTHOR]

Video question answering (Video-QA) is a subject undergoing intense study in Artificial Intelligence, which is one of the tasks which can evaluate such AI abilities. In this paper, we propose a Modality Attention Fusion framework with Hybrid Multi-head Self-attention (MAF-HMS). MAF-HMS focuses on the task of answering multiple-choice questions regarding a video-subtitle-QA representation by fusion of attention and self-attention between each modality. We use BERT to extract text features, and use Faster R-CNN to ex-tract visual features to provide a useful input representation for our model to answer questions. In addition, we have constructed a Modality Attention Fusion (MAF) framework for the attention fusion matrix from different modalities (video, subtitles, QA), and use a Hybrid Multi-headed Self-attention (HMS) to further determine the correct answer. Experiments on three separate scene datasets show our overall model outperforms the baseline methods by a large margin. Finally, we conducted extensive ablation studies to verify the various components of the network and demonstrate the effectiveness and advantages of our method over existing methods through question type and required modality experimental results. [ABSTRACT FROM AUTHOR]

Cholesteatoma is a progressive middle ear disease that can only be treated surgically but with a high recurrence rate. Depending on the extent of the disease, a surgical approach, such as microsurgery with a retroarticular incision or transcanal endoscopic surgery, is performed. However, the current examination cannot sufficiently predict the progression before surgery, and changes in approach may be made during the surgery. Large amounts of data are typically required to train deep neural network models; however, the prevalence of cholesteatomas is low (1-in-25, 000). Developing analysis methods that improve the accuracy with such a small number of samples is an important issue for medical artificial intelligence (AI) research. This paper presents an AI-based system to automatically detect mastoid extensions using CT. This retrospective study included 164 patients (80 with mastoid extension and 84 without mastoid extension) who underwent surgery. This study adopted a relatively lightweight neural network model called MobileNetV2 to learn and predict the CT images of 164 patients. The training was performed with eight divided groups for cross-validation and was performed 24 times with each of the eight groups to verify accuracy fluctuations caused by randomly augmented learning. An evaluation was performed by each of the 24 single-trained models, and 24 sets of ensemble predictions with 23 models for 100% original size images and 400% zoomed images. Fifteen otolaryngologists diagnosed the images and compared the results. The average accuracy of predicting 400% zoomed images using ensemble prediction model was 81.14% (sensitivity = 84.95%, specificity = 77.33%). The average accuracy of the otolaryngologists was 73.41% (sensitivity, 83.17%; specificity, 64.13%), which was not affected by their clinical experiences. Noteworthily, despite the small number of cases, we were able to create a highly accurate AI. These findings represent an important first step in the automatic diagnosis of the cholesteatoma extension. [ABSTRACT FROM AUTHOR]

Protein secondary structure prediction is extremely important for determining the spatial structure and function of proteins. In this paper, we apply an optimized convolutional neural network and long short-term memory neural network models to protein secondary structure prediction, which is called OCLSTM. We use an optimized convolutional neural network to extract local features between amino acid residues. Then use the bidirectional long short-term memory neural network to extract the remote interactions between the internal residues of the protein sequence to predict the protein structure. Experiments are performed on CASP10, CASP11, CASP12, CB513, and 25PDB datasets, and the good performance of 84.68%, 82.36%, 82.91%, 84.21% and 85.08% is achieved respectively. Experimental results show that the model can achieve better results. [ABSTRACT FROM AUTHOR]

Analyzing and predicting the trend of price fluctuation has been receiving more and more attention, as price risk has become the focus of risk control research in heating oil futures market. A novel time series prediction model combined with the complex network method is put forward in the paper. First of all, this paper counts the cumulative time interval of different nodes in the network, and fits its growth trend with the Fourier model. Then a novel price fluctuation prediction model is established based on the effective information such as some topology properties extracted from the network. The results show that the Fourier model can predict the emergence time of new nodes in the next stage, and the established price fluctuation prediction model can infer the names of nodes in the prediction interval, so as to determine the forward-looking behavior of price evolution. Besides, liken to the NAR neural network, the prediction results obtained by the proposed method also show superiority, which has important theoretical value and academic significance for early warning and prediction of price behavior in the heating oil futures market. [ABSTRACT FROM AUTHOR]

Analyzing geological drilling hole images acquired by Axial View Panoramic Borehole Televiewer (APBT) is a key step to explore the geological structure in a geological exploration. Conventionally, the borehole images are examined by technicians, which is inefficient and subjective. In this paper, three dominant types of borehole-wall images on coal-rock mass structure, namely, border images, fracture images and intact rock mass images are mainly studied. The traditional image classification methods based on unified feature extraction algorithm and single classifier is not effect for the borehole images. Therefore, this paper proposes a novel two-stage classification approach to improve the classification performance of borehole images. In the first-stage classification, the border images are identified from three kinds of images based on texture features and gray-scale histograms features. For the remaining two types of images, in the second-stage classification, Gabor filter is first applied to segment the region of interest (ROI) (such as microfracture, absciss layer and horizontal cracks, etc.) and the central interference region. Then, using the same feature vector after eliminating the central interference region, fracture images are separated from intact rock mass images. We test our two-stage classification system with real borehole images. The results of experimental show that the two-stage classification method can effectively classify three major borehole-wall images with the correction rate of 95.55% in the first stage and 95% in the second stage. [ABSTRACT FROM AUTHOR]

Combining a deep neural network with fuzzy theory, this paper proposes an advertising click-through rate (CTR) prediction approach based on a fuzzy deep neural network (FDNN). In this approach, fuzzy Gaussian-Bernoulli restricted Boltzmann machine (FGBRBM) is first applied to input raw data from advertising datasets. Next, fuzzy restricted Boltzmann machine (FRBM) is used to construct the fuzzy deep belief network (FDBN) with the unsupervised method layer by layer. Finally, fuzzy logistic regression (FLR) is utilized for modeling the CTR. The experimental results show that the proposed FDNN model outperforms several baseline models in terms of both data representation capability and robustness in advertising click log datasets with noise. [ABSTRACT FROM AUTHOR]

In this paper, we propose a hybrid method to forecast the stock prices called High-order-fuzzy-fluctuation-Trends-based Back Propagation(HTBP)Neural Network model. First, we compare each value of the historical training data with the previous day's value to obtain a fluctuation trend time series (FTTS). On this basis, the FTTS blur into fuzzy time series (FFTS) based on the fluctuation of the increasing, equality, decreasing amplitude and direction. Since the relationship between FFTS and future wave trends is nonlinear, the HTBP neural network algorithm is used to find the mapping rules in the form of self-learning. Finally, the results of the algorithm output are used to predict future fluctuations. The proposed model provides some innovative features:(1)It combines fuzzy set theory and neural network algorithm to avoid overfitting problems existed in traditional models. (2)BP neural network algorithm can intelligently explore the internal rules of the actual existence of sequential data, without the need to analyze the influence factors of specific rules and the path of action. (3)The hybrid modal can reasonably remove noises from the internal rules by proper fuzzy treatment. This paper takes the TAIEX data set of Taiwan stock exchange as an example, and compares and analyzes the prediction performance of the model. The experimental results show that this method can predict the stock market in a very simple way. At the same time, we use this method to predict the Shanghai stock exchange composite index, and further verify the effectiveness and universality of the method. [ABSTRACT FROM AUTHOR]

This paper mainly studies the globally fixed-time synchronization of a class of coupled neutral-type neural networks with mixed time-varying delays via discontinuous feedback controllers. Compared with the traditional neutral-type neural network model, the model in this paper is more general. A class of general discontinuous feedback controllers are designed. With the help of the definition of fixed-time synchronization, the upper right-hand derivative and a defined simple Lyapunov function, some easily verifiable and extensible synchronization criteria are derived to guarantee the fixed-time synchronization between the drive and response systems. Finally, two numerical simulations are given to verify the correctness of the results. [ABSTRACT FROM AUTHOR]

The devastating impact of the Severe Acute Respiratory Syndrome-Coronavirus 2 (SARS-CoV-2) pandemic almost halted the global economy and is responsible for 6 million deaths with infection rates of over 524 million. With significant reservations, initially, the SARS-CoV-2 virus was suspected to be infected by and closely related to Bats. However, over the periods of learning and critical development of experimental evidence, it is found to have some similarities with several gene clusters and virus proteins identified in animal-human transmission. Despite this substantial evidence and learnings, there is limited exploration regarding the SARS-CoV-2 genome to putative microRNAs (miRNAs) in the virus life cycle. In this context, this paper presents a detection method of SARS-CoV-2 precursor-miRNAs (pre-miRNAs) that helps to identify a quick detection of specific ribonucleic acid (RNAs). The approach employs an artificial neural network and proposes a model that estimated accuracy of 98.24%. The sampling technique includes a random selection of highly unbalanced datasets for reducing class imbalance following the application of matriculation artificial neural network that includes accuracy curve, loss curve, and confusion matrix. The classical approach to machine learning is then compared with the model and its performance. The proposed approach would be beneficial in identifying the target regions of RNA and better recognising of SARS-CoV-2 genome sequence to design oligonucleotide-based drugs against the genetic structure of the virus. [ABSTRACT FROM AUTHOR]

Nasopharyngeal carcinoma (NPC) is one of the most common types of cancers in South China and Southeast Asia. Clinical data has shown that early detection is essential for improving treatment effectiveness and survival rate. Unfortunately, because the early symptoms of NPC are rather minor and similar to that of diseases such as Chronic Rhinosinusitis (CRS), early detection is a challenge. This paper proposes using machine learning methods to detect NPC using routine medical test data, namely Random Forest (RF), Support Vector Machine (SVM), and Artificial Neural Network (ANN), k-Nearest-Neighbor (KNN) and Logistic Regression (LR). We collected a dataset containing 523 newly diagnosed NPC patients before treatment, 501 newly diagnosed CRS patients before treatment as well as 600 healthy controls. The routine medical test data including age, gender, blood test features, liver function test features, and urine sediment test features. For comparison, we also used data from Epstein-Barr Virus (EBV) antibody tests, which is a specialized test not included among routine medical tests. In our first test, all four methods were tested on classifying NPC vs CRS vs controls; RF gives the best overall performance. Using only routine medical test data, it gives an accuracy of 83.1%, outperforming LR by 12%. In our second test, using only routine medical test data, when classifying NPC vs non-NPC (i.e. CRS or controls), RF achieves an accuracy of 88.2%. In our third test, when classifying NPC vs. controls, RF using only routine test data achieves an accuracy significantly better than RF using only EBV antibody data. Finally, in our last test, RF trained with NPC vs controls, using routine test data only, continued to perform well on an entirely separate dataset. This is a promising result because preliminary NPC detection using routine medical data is easy and inexpensive to implement. We believe this approach will play an important role in the detection and treatment of NPC in the future. [ABSTRACT FROM AUTHOR]