Search

Accurately predicting the Remaining Useful Life (RUL) of lithium-ion batteries is crucial for battery management systems. Deep learning-based methods have been shown to be effective in predicting RUL by leveraging battery capacity time series data. However, the representation learning of features such as long-distance sequence dependencies and mutations in capacity time series still needs to be improved. To address this challenge, this paper proposes a novel deep learning model, the MLP-Mixer and Mixture of Expert (MMMe) model, for RUL prediction. The MMMe model leverages the Gated Recurrent Unit and Multi-Head Attention mechanism to encode the sequential data of battery capacity to capture the temporal features and a re-zero MLP-Mixer model to capture the high-level features. Additionally, we devise an ensemble predictor based on a Mixture-of-Experts (MoE) architecture to generate reliable RUL predictions. The experimental results on public datasets demonstrate that our proposed model significantly outperforms other existing methods, providing more reliable and precise RUL predictions while also accurately tracking the capacity degradation process. Our code and dataset are available at the website of github. [ABSTRACT FROM AUTHOR]

Semantic image segmentation in computer networks is designed to determine the category to which each pixel in an image belongs. It is a basic computer vision task and has a very wide range of applications in practice. In recent years, semantic image segmentation algorithms in computer networks based on deep learning have attracted widespread attention due to their fast speed and high accuracy. However, due to the large number of downsampling layers in a deep learning model, the segmentation results are usually poor at the edge of an object, and there is currently no universal quantitative evaluation index to measure the performance of segmentation at the edge of an object. Solving these two problems is of great significance to semantic image segmentation algorithms in China. Based on traditional evaluation indicators, this paper proposes a region-based evaluation index to quantitatively measure the performance of segmentation at the edge of an object and proposes an improved loss function to improve model performance. The existing semantic image segmentation methods are summarized. This paper proposes regional-based evaluation indicators. Taking advantage of the particularity of semantic image segmentation tasks, this paper presents an efficient and accurate method for extracting the edges of objects. By defining the distance from pixels to the edges of objects, this paper proposes a fast algorithm for calculating the edge area. Based on this, three methods are proposed as well as an area-based evaluation indicator. The experimental results show that the accuracy of the loss function proposed in this paper, compared with that of the current mainstream cross-entropy loss function, is improved by 1% on the DeepLab model. For area-based evaluation indicators, a 4% accuracy improvement can be achieved, and on other segmentation models, there is also a significant improvement. [ABSTRACT FROM AUTHOR]

Objective: There has been a large amount of research in the field of artificial intelligence (AI) as applied to clinical radiology. However, these studies vary in design and quality and systematic reviews of the entire field are lacking.This systematic review aimed to identify all papers that used deep learning in radiology to survey the literature and to evaluate their methods. We aimed to identify the key questions being addressed in the literature and to identify the most effective methods employed. Methods: We followed the PRISMA guidelines and performed a systematic review of studies of AI in radiology published from 2015 to 2019. Our published protocol was prospectively registered. Results: Our search yielded 11,083 results. Seven hundred sixty-seven full texts were reviewed, and 535 articles were included. Ninety-eight percent were retrospective cohort studies. The median number of patients included was 460. Most studies involved MRI (37%). Neuroradiology was the most common subspecialty. Eighty-eight percent used supervised learning. The majority of studies undertook a segmentation task (39%). Performance comparison was with a state-of-the-art model in 37%. The most used established architecture was UNet (14%). The median performance for the most utilised evaluation metrics was Dice of 0.89 (range.49–.99), AUC of 0.903 (range 1.00–0.61) and Accuracy of 89.4 (range 70.2–100). Of the 77 studies that externally validated their results and allowed for direct comparison, performance on average decreased by 6% at external validation (range increase of 4% to decrease 44%). Conclusion: This systematic review has surveyed the major advances in AI as applied to clinical radiology. Key Points: • While there are many papers reporting expert-level results by using deep learning in radiology, most apply only a narrow range of techniques to a narrow selection of use cases. • The literature is dominated by retrospective cohort studies with limited external validation with high potential for bias. • The recent advent of AI extensions to systematic reporting guidelines and prospective trial registration along with a focus on external validation and explanations show potential for translation of the hype surrounding AI from code to clinic. [ABSTRACT FROM AUTHOR]

Natural hazard named entity recognition is a technique used to recognize natural hazard entities from a large number of texts. The method of natural hazard named entity recognition can facilitate acquisition of natural hazards information and provide reference for natural hazard mitigation. The method of named entity recognition has many challenges, such as fast change, multiple types and various forms of named entities. This can introduce difficulties in research of natural hazard named entity recognition. To address the above problem, this paper constructed a natural disaster annotated corpus for training and evaluation model, and selected and compared several deep learning methods based on word vector features. A deep learning method for natural hazard named entity recognition can automatically mine text features and reduce the dependence on manual rules. This paper compares and analyzes the deep learning models from three aspects: pretraining, feature extraction and decoding. A natural hazard named entity recognition method based on deep learning is proposed, namely XLNet-BiLSTM-CRF model. Finally, the research hotspots of natural hazards papers in the past 10 years were obtained through this model. After training, the precision of the XLNet-BilSTM-CRF model is 92.80%, the recall rate is 91.74%, and the F1-score is 92.27%. The results show that this method, which is superior to other methods, can effectively recognize natural hazard named entities. [ABSTRACT FROM AUTHOR]

In order to improve the accuracy of CNN (convolutional neural network) in image classification, an enhanced Inception-ResNet-v2 model based on CNN is designed through the comparative study and analysis of the structure of classification model. This paper proposes to use multi-scale depthwise separable convolution to replace the convolution structure in Inception-ResNet-v2 model, which can reduce the amount of model parameters and extract features under different receptive fields. At the same time, this paper establishes channel filtering module based on global information comparison to filter and join channels, which realizes the effective extraction of features. Finally, through data enhancement, batch normalization and learning rate adjustment, the effect of the model used in this paper is better than most other models in each dataset, and the accuracy rate can reach 94.8%. [ABSTRACT FROM AUTHOR]

City bridge crack detection is an important problem in the field of image processing, which is very important for city road planning and development. Aiming at the problem that traditional bridge cracks detection algorithms cannot satisfy the requirements of high precision and high efficiency at the same time, this paper proposes a new deep learning method based on search strategy for city bridge cracks detection. Firstly, the sliding window algorithm is used to divide the bridge cracks image into smaller bridge crack meta-image and bridge background meta-image. Based on the analysis of the meta-image, a city bridge cracks detection network (CBCDN) model is proposed. CBCDN is used to identify bridge background surface elements and bridge crack surface elements. Then, the CBCDN based on the new window sliding algorithm is used to detect the bridge cracks. Finally, a novel search strategy is adopted to accelerate the CBCDN. The experimental results show that the proposed algorithm has a better detection effect and stronger generalization ability compared with the traditional algorithms. We also make a comparison with the state-of-the-art bridge cracks detection models; the results show that the proposed network model can better detect the bridge cracks in the city scene, and it can obtain a better effect in terms of objective and subjective evaluation. [ABSTRACT FROM AUTHOR]

The convolutional neural network (CNN) has brought about a drastic change in the field of image processing and pattern recognition. The filters of CNN model correspond to the activation maps that extract features from the input images. Thus, the number of filters and filter size are of significant importance to learning and recognition accuracy of CNN model-based systems such as the biometric-based person authentication system. The present paper proposes to analyze the impact of varying the number of filters of CNN models on the accuracy of the biometric-based single classifiers using human face, fingerprint and iris for person identification, and also biometric-based super-classification using both bagging- and programming-based boosting methods. The present paper gives an insight to the optimal set of filters in CNN model that gives the maximum overall accuracy of the classifier system. [ABSTRACT FROM AUTHOR]

Objectives: We systematically reviewed the current literature evaluating the ability of fully-automated deep learning (DL) and semi-automated traditional machine learning (TML) MRI-based artificial intelligence (AI) methods to differentiate clinically significant prostate cancer (csPCa) from indolent PCa (iPCa) and benign conditions. Methods: We performed a computerised bibliographic search of studies indexed in MEDLINE/PubMed, arXiv, medRxiv, and bioRxiv between 1 January 2016 and 31 July 2021. Two reviewers performed the title/abstract and full-text screening. The remaining papers were screened by four reviewers using the Checklist for Artificial Intelligence in Medical Imaging (CLAIM) for DL studies and Radiomics Quality Score (RQS) for TML studies. Papers that fulfilled the pre-defined screening requirements underwent full CLAIM/RQS evaluation alongside the risk of bias assessment using QUADAS-2, both conducted by the same four reviewers. Standard measures of discrimination were extracted for the developed predictive models. Results: 17/28 papers (five DL and twelve TML) passed the quality screening and were subject to a full CLAIM/RQS/QUADAS-2 assessment, which revealed a substantial study heterogeneity that precluded us from performing quantitative analysis as part of this review. The mean RQS of TML papers was 11/36, and a total of five papers had a high risk of bias. AUCs of DL and TML papers with low risk of bias ranged between 0.80–0.89 and 0.75–0.88, respectively. Conclusion: We observed comparable performance of the two classes of AI methods and identified a number of common methodological limitations and biases that future studies will need to address to ensure the generalisability of the developed models. [ABSTRACT FROM AUTHOR]

Underwater target detection and classification based on sonar images is a challenging task because of the complex underwater environment. In recent years, deep learning technology has effectively improved the detection accuracy of underwater targets compared to traditional sonar image target detection methods, which have a low accuracy and poor robustness. However, deep learning algorithms for sonar image target detection have fewer training samples and a low detection speed. To solve these problems, an improved YOLOv4 based sonar target detection and classification algorithm is proposed in this paper. First, the feature extraction network CSPDarknet-53 in YOLOv4 is improved to reduce both the model parameters and the network depth. Second, the PANet feature enhancement module in the YOLOv4 model is replaced by the adaptive spatial feature fusion module (ASFF) to obtain a better feature fusion effect. In addition, the number of fusion feature layers is increased to improve the receptive field and detection accuracy. Furthermore, this paper uses the k-means++ algorithm to cluster the sonar image dataset to obtain the appropriate size and number of anchor boxes for model training. The experimental results show that the proposed method has better performance in detection accuracy and detection speed compared to YOLOv4 and YOLOv4-tiny. [ABSTRACT FROM AUTHOR]

Traditional object recognition algorithms cannot meet the requirements of object recognition accuracy in the actual warehousing and logistics field. In recent years, the rapid development of the deep learning theory has provided a technical approach for solving the above problems, and a number of object recognition algorithms has been proposed based on deep learning, which have been promoted and applied. However, deep learning has the following problems in the application process of object recognition: First, the nonlinear modeling ability of the activation function in the deep learning model is poor; second, the deep learning model has a large number of repeated pooling operations during which information is lost. In view of these shortcomings, this paper proposes multiple-parameter exponential linear units with uniform and learnable parameter forms and introduces two learned parameters in the exponential linear unit (ELU), enabling it to represent piecewise linear and exponential nonlinear functions. Therefore, the ELU has good nonlinear modeling capabilities. At the same time, to improve the problem of losing information in the large number of repeated pooling operations, this paper proposes a new global convolutional neural network structure. This network structure makes full use of the local and global information of different layer feature maps in the network. It can reduce the problem of losing feature information in the large number of pooling operations. Based on the above ideas, this paper suggests an object recognition algorithm based on the optimized nonlinear activation function-global convolutional neural network. Experiments were carried out on the CIFAR100 dataset and the ImageNet dataset using the object recognition algorithm proposed in this paper. The results show that the object recognition method suggested in this paper not only has a better recognition accuracy than traditional machine learning and other deep learning models but also has a good stability and robustness. [ABSTRACT FROM AUTHOR]

Thousands of research papers are being published every day, and among all these research works, one of the fastest-growing fields is computer science (CS). Thus, learning which research areas are trending in this particular field of study is advantageous to a significant number of scholars, research institutions, and funding organizations. Many scientometric studies have been done focusing on analyzing the current CS trends and predicting future ones from different perspectives as a consequence. Despite the large datasets from this vast number of CS publications and the power of deep learning methods in such big data problems, deep neural networks have not yet been used to their full potential in this area. Therefore, the objective of this paper is to predict the upcoming years' CS trends using long short-term memory neural networks. Accordingly, CS papers from 1940 and their corresponding fields of study from the microsoft academic graph dataset have been exploited for solving this research trend prediction problem. The prediction accuracy of the proposed method is then evaluated using RMSE and coefficient of determination (R2) metrics. The evaluations show that the proposed method outperforms the baseline approaches in terms of the prediction accuracy in all considered time periods. Subsequently, adopting the proposed method's predictions, we investigate future trending areas in computer science research from various viewpoints. [ABSTRACT FROM AUTHOR]

The challenge of spatial resource allocation is pervasive across various domains such as transportation, industry, and daily life. As the scale of real-world issues continues to expand and demands for real-time solutions increase, traditional algorithms face significant computational pressures, struggling to achieve optimal efficiency and real-time capabilities. In recent years, with the escalating computational power of computers, the remarkable achievements of reinforcement learning in domains like Go and robotics have demonstrated its robust learning and sequential decision-making capabilities. Given these advancements, there has been a surge in novel methods employing reinforcement learning to tackle spatial resource allocation problems. These methods exhibit advantages such as rapid solution convergence and strong model generalization abilities, offering a new perspective on resolving spatial resource allocation problems. Despite the progress, reinforcement learning still faces hurdles when it comes to spatial resource allocation. There remains a gap in its ability to fully grasp the diversity and intricacy of real-world resources. The environmental models used in reinforcement learning may not always capture the spatial dynamics accurately. Moreover, in situations laden with strict and numerous constraints, reinforcement learning can sometimes fall short in offering feasible strategies. Consequently, this paper is dedicated to summarizing and reviewing current theoretical approaches and practical research that utilize reinforcement learning to address issues pertaining to spatial resource allocation. In addition, the paper accentuates several unresolved challenges that urgently necessitate future focus and exploration within this realm and proposes viable approaches for these challenges. This research furnishes valuable insights that may assist scholars in gaining a more nuanced understanding of the problems, opportunities, and potential directions concerning the application of reinforcement learning in spatial resource allocation. [ABSTRACT FROM AUTHOR]

The prevalence of cardiovascular disease (CVD) has surged in recent years, making it the foremost cause of mortality among humans. The Electrocardiogram (ECG), being one of the pivotal diagnostic tools for cardiovascular diseases, is increasingly gaining prominence in the field of machine learning. However, prevailing neural network models frequently disregard the spatial dimension features inherent in ECG signals. In this paper, we propose an ECG autoencoder network architecture incorporating low-rank attention (LRA-autoencoder). It is designed to capture potential spatial features of ECG signals by interpreting the signals from a spatial perspective and extracting correlations between different signal points. Additionally, the low-rank attention block (LRA-block) obtains spatial features of electrocardiogram signals through singular value decomposition, and then assigns these spatial features as weights to the electrocardiogram signals, thereby enhancing the differentiation of features among different categories. Finally, we utilize the ResNet-18 network classifier to assess the performance of the LRA-autoencoder on both the MIT-BIH Arrhythmia and PhysioNet Challenge 2017 datasets. The experimental results reveal that the proposed method demonstrates superior classification performance. The mean accuracy on the MIT-BIH Arrhythmia dataset is as high as 0.997, and the mean accuracy and F 1 -score on the PhysioNet Challenge 2017 dataset are 0.850 and 0.843. [ABSTRACT FROM AUTHOR]

Utilizing vast annotated datasets for supervised training of deep learning models is an absolute necessity. The focus of this paper is to demonstrate a supervisory training technique using perspective transformation-based data augmentation to train various cutting-edge architectures for the ego-lane detection task. Creating a reliable dataset for training such models has been challenging due to the lack of efficient augmentation methods that can produce new annotated images without missing important features about the lane or the road. Based on extensive experiments for training the three architectures: SegNet, U-Net, and ResUNet++, we show that the perspective transformation data augmentation strategy noticeably improves the performance of the models. The model achieved validation dice of 0.991 when ResUNET++ was trained on data of size equal to 6000 using the PTA method and achieved a dice coefficient of 96.04% when had been tested on the KITTI Lane benchmark, which contains 95 images for different urban scenes, which exceeds the results of the other papers. An ensemble learning approach is also introduced while testing the models to achieve the most robust performance under various challenging conditions. [ABSTRACT FROM AUTHOR]

Given the rapid and significant increase in email data, it is crucial for both individuals and organisations to prioritise the implementation of strong cybersecurity measures to combat attacks such as phishing emails. While continuous research has been made to find the most efficient approach to combating phishing emails, cybercriminals on the other hand continue to be determined, and their techniques become more and more sophisticated. In this paper, we present a novel approach for email classification using a Siamese deep learning network in order to verify authorship. We used the writing style and behavioural characteristics of the authors in this approach to identify the true source of emails and classify them as phishing, legitimate, harassment, or suspicious. This model was evaluated on the SeFACED dataset, where it received an accuracy of 90,12%, showcasing its efficacy in classifying emails, which enhanced email security and contributed to a safer online environment. [ABSTRACT FROM AUTHOR]

The paper proposes the noninvasive image egg growing monitoring method based on an illumination and transfer learning. During the egg growing, the size of egg air cell is increased. The segmentation is performed to extract cells and segmentation parameters are adjusted and trained on an air cell datasets by transfer learning to separate air cells with high light transmittance from the background. The improved DeepLabV3+ network model for image egg monitoring is proposed. The network embeds coordinate attention in the lightweight network MobilenetV2. The decoder feature fusion method is improved to a semantic embedding branch structure. The middle-level features that have been newly introduced are merged with the high-level features and low-level features. The results show that the mean intersection over union of the model reaches 89.06% and that the mean pixel accuracy rate reaches 94.66%. The method can effectively segment the air cell part of the eggs. The feasibility of the method was verified by measuring the air cells of egg growing process from the 7th to the 19th day. [ABSTRACT FROM AUTHOR]

Alzheimer’s disease (AD) is a neurodegenerative disorder that affects millions of people worldwide, making early detection essential for effective intervention. This review paper provides a comprehensive analysis of the use of deep learning techniques, specifically convolutional neural networks (CNN) and vision transformers (ViT), for the classification of AD using brain imaging data. While previous reviews have covered similar topics, this paper offers a unique perspective by providing a detailed comparison of CNN and ViT for AD classification, highlighting the strengths and limitations of each approach. Additionally, the review presents an updated and thorough analysis of the most recent studies in the field, including the latest advancements in CNN and ViT architectures, training methods, and performance evaluation metrics. Furthermore, the paper discusses the ethical considerations and challenges associated with the use of deep learning models for AD classification, such as the need for interpretability and the potential for bias. By addressing these issues, this review aims to provide valuable insights for future research and clinical applications, ultimately advancing the field of AD classification using deep learning techniques. [ABSTRACT FROM AUTHOR]

This paper proposes a novel data-enhanced virtual texture generation network for use in deep learning detection systems. The current methods of data enhancement, such as image flipping, scaling ratios, or Generative Adversarial Networks, have limitations as they cannot determine characteristics beyond the training data. The proposed system uses the texture characteristics of a learning surface to generate surface textures through the Open Graphics Library, which can simulate material textures, light sources, and shadow effects. This enables the generation of required texture parameters for the Reinforcement Learning Network to conduct parameter search. The generated image is authenticated by a discriminator, and the reward score is fed back into the critic network to update the value network. The proposed system can complement the imbalance of defective data types, generate large quantities of random and non-defective data, and automatically classify and label during the generation process, reducing labor consumption and improving labeling accuracy. The study found that the proposed data enhancement method can increase the diversity of data characteristics, and the generated data can increase the recall rate of test and verification data sets. Specifically, the proposed system increased the recall rate of test data sets with different distributions from 78.21% to 82.40% and the recall rate of verification data sets with the same distribution from 81.64 to 91.94%. [ABSTRACT FROM AUTHOR]

Using deep learning models to deal with the classification tasks in network traffic offers a new approach to address the imbalanced Internet of Things malicious traffic classification problems. However, the employment difficulty of these models may be immense due to their high resource consumption and inadequate interpretability. Fortunately, the effectiveness of sampling methods based on the statistical principles in imbalance data distribution indicates the path. In this paper, we address these challenges by proposing a hybrid sampling method, termed HSS, which integrates undersampling and oversampling techniques. Our approach not only mitigates the imbalance in malicious traffic but also fine-tunes the sampling threshold to optimize performance, as substantiated through validation tests. Employed across three distinct classification tasks, this method furnishes simplified yet representative samples, enhancing the baseline models' classification capabilities by a minimum of 6.02% and a maximum of 182.66%. Moreover, it notably reduces resource consumption, with sample numbers diminishing to a ratio of at least 83.53%. This investigation serves as a foundation, demonstrating the efficacy of HSS in bolstering security measures in IoT networks, potentially guiding the development of more adept and resource-efficient solutions. [ABSTRACT FROM AUTHOR]

This paper contributes to the ongoing debate on the nature and characteristics of the volatility transmission channels of major crash events in international stock markets between 03 July 1997 and 09 March 2021. Using dynamic conditional correlations (DCC) for conditional correlations and volatility clustering, GARCH-BEKK for the direction of transmission of disturbances, and the Diebold-Yilmaz spillover index for the level of volatility contagion, the paper finds that the climbs in external shock transmissions have long-lasting impacts in domestic markets due to the contagion effect during crisis periods. The findings also reveal that the heavier magnitude of financial stress is transmitted between Asian countries via the Hong Kong stock market. Additionally, the degree of volatility spillovers between advanced and emerging equity markets is smaller compared to the pure spillovers between advanced markets or emerging markets, offering a window of opportunity for international market participants in terms of portfolio diversification and risk management applications. Furthermore, the study introduces a novel early warning system created by integrating DCC correlations with a state-of-the-art deep learning model to predict the global financial crisis and COVID-19 crisis. The experimental analysis of long short-term memory network finds evidence of contagion risk by verifying bursts in volatility spillovers and generating signals with high accuracy before the 12-month crisis period. This provides supplementary information that contributes to the decision-making process of practitioners, as well as offering indicative evidence that facilitates the assessment of market vulnerability for policymakers. [ABSTRACT FROM AUTHOR]

This paper introduces the collection of the Journal on Machine Learning (ML) and the user. It provides a brief history of ML from the 1950's through to the current time, sketching the nature of the kinds of precursor AI techniques used in such things as expert systems right the way through to the emergence of ML and its tool sets, including deep learning. It concludes with the 'generative AI' used in such ML technologies as PaLM and GPT-3. The history highlights key changes and developments in ML, the especial importance and limitations of deep learning, and the changing attitudes and expectations of users in an environment when ML can and often is oversold. The paper then explores the ways CSCW research has addressed the social context of organisational systems and how the same can apply for ML tools and techniques. It urges research that focuses on the particular ways that ML comes to fit into 'real world' collaborative work sites and hence speaks to the CSCW cannon. [ABSTRACT FROM AUTHOR]

Diabetes mellitus is a chronic metabolic disorder that affects millions of individuals worldwide, presenting significant challenges in disease management and long-term complications. Continuous Glucose Monitoring (CGM) has emerged as a valuable tool for monitoring blood glucose levels in diabetic patients, offering real-time data for enhanced disease control. However, the ability to predict glucose fluctuations in advance can greatly improve management strategies and minimize the risk of hyperglycemic or hypoglycemic episodes. This research paper proposes a novel approach to diabetes management by leveraging deep learning algorithms for CGM data analysis and prediction. The model utilizes a vast dataset of CGM readings, patient characteristics, and lifestyle factors, enabling it to recognize complex patterns and trends in glucose fluctuations. Through recurrent neural networks and other deep learning architectures, the model can learn from temporal dependencies in the data, making accurate predictions about future glucose levels. The predictive capabilities of the deep learning model offer personalized insights, alerting patients and healthcare providers to potential glucose excursions before they occur. Such early warnings enable timely adjustments to medication, diet, and lifestyle, promoting improved blood sugar control and reducing the risk of diabetes-related complications. While the potential of deep learning in diabetes management is promising, this research paper highlights the importance of rigorous validation and integration into clinical practice. Challenges such as data quality, model interpretability, and patient engagement must be addressed for successful implementation. In conclusion, this research presents a groundbreaking application of deep learning in diabetes management, demonstrating the potential to transform the way blood glucose levels are monitored and predicted. By harnessing the power of advanced data analytics, this model can pave the way towards personalized and proactive diabetes care, leading to better patient outcomes and ultimately enhancing the quality of life for individuals living with diabetes. [ABSTRACT FROM AUTHOR]

A neural network model needs to be manually designed for ancient mural dynasty recognition, and this paper proposes an ancient mural dynasty recognition algorithm that is based on a neural architecture search (NAS). First, the structural edge information of mural images is extracted for use by the neural network model in recognizing mural missions. Second, an NAS algorithm that is based on contrast selection (CS) simplifies the architecture search to an incremental CS and then searches for the optimal network architecture on the mural dataset. Finally, the identified optimal network architecture is used for training and testing to complete the mural dynasty recognition task. The results show that the top accuracy of the proposed method on the mural dataset is 88.10%, the recall rate is 87.52%, and the precision rate is 87.69%. Each evaluation index used by the neural network model is superior to that of classical network models such as AlexNet and ResNet-50. Compared with NAS methods such as ASNG and MIGO, the accuracy of mural dynasty recognition is higher by an average of 4.27% when using the proposed method. The proposed method is verified on CIFAR-10, CIFAR-100, ImageNet16-120 and other datasets and achieves a good recognition accuracy in the NAS-bench-201 search space, which averages 93.26%, 70.73% and 45.34%, respectively, on the abovementioned datasets. [ABSTRACT FROM AUTHOR]

With the advent of Mobile Edge Computing (MEC), shifting data processing from cloud centers to the network edge presents an advanced computational paradigm for addressing latency-sensitive applications. Specifically, in radar systems, the real-time processing and prediction of radar echo data pose significant challenges in dynamic and resource-constrained environments. MEC, by processing data near its source, not only significantly reduces communication latency and enhances bandwidth utilization but also diminishes the necessity of transmitting large volumes of data to the cloud, which is crucial for improving the timeliness and efficiency of radar data processing. To meet this demand, this paper proposes a model that integrates a spatiotemporal Attention Module (STAM) with a Long Short-Term Memory Gated Recurrent Unit (ST-ConvLSGRU) to enhance the accuracy of radar echo prediction while leveraging the advantages of MEC. STAM, by extending the spatiotemporal receptive field of the prediction units, effectively captures key inter-frame motion information, while optimizations to the convolutional structure and loss function further boost the model's predictive performance. Experimental results demonstrate that our approach significantly improves the accuracy of short-term weather forecasting in a mobile edge computing environment, showcasing an efficient and practical solution for processing radar echo data under dynamic, resource-limited conditions. [ABSTRACT FROM AUTHOR]

This paper aims to propose a prediction method based on Deep Learning (DL) and Internet of Things (IoT) technology, focusing on the ecological security and tourist satisfaction of Ice-and-Snow Tourism (IST) to solve practical problems in this field. Accurate predictions of ecological security and tourist satisfaction in IST have been achieved by collecting and analyzing environment and tourist behavior data and combining with DL models, such as convolutional and recurrent neural networks. The experimental results show that the proposed method has significant advantages in performance indicators, such as accuracy, F1 score, Mean Squared Error (MSE), and correlation coefficient. Compared to other similar methods, the method proposed improves accuracy by 3.2%, F1 score by 0.03, MSE by 0.006, and correlation coefficient by 0.06. These results emphasize the important role of combining DL with IoT technology in predicting ecological security and tourist satisfaction in IST. [ABSTRACT FROM AUTHOR]

Copyright of Frontiers of Information Technology & Electronic Engineering is the property of Springer Nature and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

This paper proposes a new GARCH specification that adapts the architecture of a long-term short memory neural network (LSTM). It is shown that classical GARCH models generally give good results in financial modeling, where high volatility can be observed. In particular, their high value is often praised in Value-at-Risk. However, the lack of nonlinear structure in most approaches means that conditional variance is not adequately represented in the model. On the contrary, the recent rapid development of deep learning methods is able to describe any nonlinear relationship in a clear way. We propose GARCHNet, a nonlinear approach to conditional variance that combines LSTM neural networks with maximum likelihood estimators in GARCH. The variance distributions considered in the paper are normal, t and skewed t, but the approach allows extension to other distributions. To evaluate our model, we conducted an empirical study on the logarithmic returns of the WIG 20 (Warsaw Stock Exchange Index), S&P 500 (Standard & Poor's 500) and FTSE 100 (Financial Times Stock Exchange) indices over four different time periods from 2005 to 2021 with different levels of observed volatility. Our results confirm the validity of the solution, but we provide some directions for its further development. [ABSTRACT FROM AUTHOR]

Currently, human-vehicle recognition (HVR) method has been applied in road monitoring, congestion control, and safety protection situations. However, traditional vision-based HVR methods suffer from problems such as high construction cost and low robustness in scenarios with insufficient lighting. For this reason, it is necessary to develop a low-cost and high-robust HVR method for intelligent street light systems (ISLS). A well-designed HVR method can aid the brightness adjustment in ISLSs that operate exclusively at night, facilitating lower power consumption and carbon emission. The paper proposes a novel wireless sensing-based human-vehicle recognition (WsHVR) method based on deep learning technologies, which can be applied in ISLSs that assembled with wireless sensor network (WSN). To solve the problem of limited recognition ability of wireless sensing technology, a deep feature extraction model that combines multi-scale convolution and attention mechanism is proposed, in which the received signal strength (RSS) features of road users are extracted by multi-scale convolution. WsHVR integrates an adaptive registration convolutional attention mechanism (ARCAM) to further feature extraction and classification. The final normalized classification result is obtained by SoftMax function. Experiments show that the proposed WsHVR outperforms existing methods with an accuracy of 99.07%. The dataset and source code related to the paper have been published at https://github.com/TZ-mx/WiParam and https://github.com/TZ-mx/WsHVR, respectively. The proposed WsHVR method has high performance in the field of human-vehicle recognition, potentially providing valuable guidance for the design of intelligent streetlight systems in intelligent transportation systems. [ABSTRACT FROM AUTHOR]

YouTube video recommendation algorithm plays an important role in enhancing user engagement and profitability (or monetization), yet it struggles to deal with disturbing visual content. Real-time analysis using deep learning techniques can play a vital role to identify and filter the disturbing content in online videos. In this paper, we propose an end-to-end trainable two-stream deep learning framework that analyzes and classifies the different categories of disturbing content embedded in child-friendly cartoon videos on YouTube and YouTube Kids platforms. At first, the model extracts the static and motion features from videos through an individual pretrained convolutional neural network (CNN) i.e., EfficientNet-B7. In the next phase, the extracted features are processed by spatio-temporal bidirectional long short-term memory (BiLSTM) network to capture the long-term global temporal dependencies of videos. The learned video representations are forwarded to the classifier for multiclass classification into six categories. Three different types of fusion strategies are investigated to combine the spatial and temporal streams. The evaluation of these methods is performed through extensive experiments on a customized large-scale dataset–YouTube cartoon content filtering (YT-C2F) dataset. The spatio-temporal EfficientNet-BiLSTM network with feature-level fusion displays the best results (f1-score = 0.9316) and shows the efficiency of using a two-stream network compared to single-stream baseline methods. This paper makes two-fold contributions. First, using only static information from videos in a deep learning framework is less effective than using both static and motion information. Second, the feature-level fusion of two streams of networks generates better classification results than early and late fusion techniques. The performance comparison of the proposed model with existing state-of-the-art techniques confirmed the competitive or even better results of our framework. [ABSTRACT FROM AUTHOR]

Accurate atom mapping, which establishes correspondences between atoms in reactants and products, is a crucial step in analyzing chemical reactions. In this paper, we present a novel end-to-end approach that formulates the atom mapping problem as a deep graph matching task. Our proposed model, AMNet (Atom Matching Network), utilizes molecular graph representations and employs various atom and bond features using graph neural networks to capture the intricate structural characteristics of molecules, ensuring precise atom correspondence predictions. Notably, AMNet incorporates the consideration of molecule symmetry, enhancing accuracy while simultaneously reducing computational complexity. The integration of the Weisfeiler-Lehman isomorphism test for symmetry identification refines the model's predictions. Furthermore, our model maps the entire atom set in a chemical reaction, offering a comprehensive approach beyond focusing solely on the main molecules in reactions. We evaluated AMNet's performance on a subset of USPTO reaction datasets, addressing various tasks, including assessing the impact of molecular symmetry identification, understanding the influence of feature selection on AMNet performance, and comparing its performance with the state-of-the-art method. The result reveals an average accuracy of 97.3% on mapped atoms, with 99.7% of reactions correctly mapped when the correct mapped atom is within the top 10 predicted atoms. Scientific contribution The paper introduces a novel end-to-end deep graph matching model for atom mapping, utilizing molecular graph representations to capture structural characteristics effectively. It enhances accuracy by integrating symmetry detection through the Weisfeiler-Lehman test, reducing the number of possible mappings and improving efficiency. Unlike previous methods, it maps the entire reaction, not just main components, providing a comprehensive view. Additionally, by integrating efficient graph matching techniques, it reduces computational complexity, making atom mapping more feasible. [ABSTRACT FROM AUTHOR]

Integrating energy systems with information systems in smart grids offers a promising avenue for combating electricity theft by leveraging real-time data insights. Suspicious activity indicative of theft can be identified through anomalous consumption patterns observed in smart networks. However, a smart model is required for capturing and analysing the data intelligently to accurately detect electricity theft. In the paper, electricity theft has been detected using an encoder-decoder-based classifier that integrates two models of convolutional neural networks (CNN). The aim is to scan the strength of the data and built a smart model that analysed the connections in complex data and determine the pattern of theft. The model comprises three compartments: the auto-encoder, the wide convolutional neural network (1-D CNN model), and the deep convolutional neural network (2-D CNN model). The auto-encoder has been trained on the complex and in-depth linkage between the theft data and the normal data as it removes noise and unnecessary information. The 1-D CNN model gathers relevant connections and general features, while the 2-D CNN model determines the rate at which energy theft occurs and differentiates between the energy-stealing consumers and normal consumers. The efficacy of the approach is underscored by its superiority over traditional deep learning and machine learning techniques. This paper elucidates the distinct advantages and applications of the proposed model in combating electricity theft within smart grid environments. [ABSTRACT FROM AUTHOR]

Deep metric learning (DML) models aim to learn semantically meaningful representations in which similar samples are pulled together and dissimilar samples are pushed apart. However, the classification effect is limited due to the high time complexity of previous models and their poor performance in extracting data relationships. This paper presents a novel relationship constraint deep metric learning (RCDML) approach, including proxy relationship constraint (PRC) and sample relationship constraint (SRC) for inter-class separability and intra-class compactness, to solve the above problems and improve the classification effect. The PRC combines the proxy-to-proxy relationship loss term with the proxy-to-sample relationship loss function to maximize the proxy features, hence enhancing inter-class separability by decreasing proxy similarity. Additionally, the SRC combines the sample-to-sample relationship loss term with the proxy-to-sample relationship loss function to maximize the sample features, which promotes intra-class compactness by increasing the similarity between the most different samples of the same class. Unlike existing proxy-based and pair-based methods, the relationship constraint framework uses a diverse range of proxy and sample data relationships. In addition, the proxy correction (PC) module is used to optimize the proxy. Extensive tests conducted on the widely popular CUB-200-2011, CARS-196, and SOP datasets show that the framework is effective and attains state-of-the-art performance. [ABSTRACT FROM AUTHOR]

This paper proposes a forward layer-wise learning algorithm for CNNs in classification problems. The algorithm utilizes the Separation Index (SI) as a supervised complexity measure to evaluate and train each layer in a forward manner. The proposed method explains that gradually increasing the SI through layers reduces the input data's uncertainties and disturbances, achieving a better feature space representation. Hence, by approximating the SI with a variant of local triplet loss at each layer, a gradient-based learning algorithm is suggested to maximize it. Inspired by the NGRAD (Neural Gradient Representation by Activity Differences) hypothesis, the proposed algorithm operates in a forward manner without explicit error information from the last layer. The algorithm's performance is evaluated on image classification tasks using VGG16, VGG19, AlexNet, and LeNet architectures with CIFAR-10, CIFAR-100, Raabin-WBC, and Fashion-MNIST datasets. Additionally, the experiments are applied to text classification tasks using the DBPedia and AG's News datasets. The results demonstrate that the proposed layer-wise learning algorithm outperforms state-of-the-art methods in accuracy and time complexity. [ABSTRACT FROM AUTHOR]

Multiple object tracking (MOT) in unmanned surface vehicle (USV) videos has many application scenarios in the military and civilian fields. State-of-the-art MOT methods first extract a set of detections from the video frames, then utilize IoU distance to associate the detections of current frame and tracklets of last frame, and finally adopt linear Kalman filter to estimate the current position of tracklets. However, some problems in USV videos seriously affect the tracking performance, such as low frame rate, wobble of observation platform, nonlinear motion of objects, small objects and ambiguous appearance. In this paper, we fully explore the motion cue in USV videos and propose a simple but effective tracker, named MotionTrack. Equipping with YOLOv7 as object detector, the data association of MotionTrack is mainly composed of cascade matching with Gaussian distance module and observation-centric Kalman filter module. We validate the effectiveness with extensive experiments on the recent Jari-Maritime-Tracking-2022 dataset, achieving new state-of-the-art 46.9 MOTA, 49.2 IDF1 with 35.2 FPS running speed on a single 3090 GPU. The source code, pretrained models with deploy versions are released at https://github.com/lzq11/MotionTrack. [ABSTRACT FROM AUTHOR]

Recently, there has been a global shift toward clean energy sources, and wind turbines (WT) play a crucial role as one of the most popular renewable generation sources. Despite their significant potential, WTs incur high operation and maintenance (O &M) costs due to the challenging operational conditions they face, such as pollution and atmospheric discharges. These stresses reduce the life expectancy of such equipment by increasing the occurrence of failures, thereby diminishing wind farm reliability. To mitigate these failure events, the prediction of the remaining useful life (RUL) of WTs is essential. This prediction, specifically direct RUL prediction, is often made by data-driven methods. However, to achieve competitive levels of accuracy, data-driven methods found in the literature often rely on extensive datasets or high-complexity deep learning models, because historical data containing failures in WTs are scarce, which presents challenges in practical implementation. This paper introduces a novel methodology for rotor RUL prediction in WTs. This method achieved an accuracy of over 80 % using simple machine learning algorithms trained with limited data, making it easy to implement and cost-effective. It is expected that this methodology will assist energy companies in optimizing their operation and maintenance planning processes and contribute to the national energy sector's progress toward achieving global sustainable goals. [ABSTRACT FROM AUTHOR]

Understanding users' exact feelings and enhancing enterprise customer relationship management depend heavily on emotion and sentiment analysis in intelligent customer service conversations. However, the research that is currently available analyzes either emotion or sentiment. This paper proposes a multi-task ensemble model that can perform multiple tasks of emotion and sentiment analysis simultaneously. This ensemble model via a multi-layer perceptron (MLP) network develops three deep learning models based on convolutional neural network (CNN), long short-term memory (LSTM), and gated recurrent unit (GRU) for predicting intelligent customer service dialogue emotion and sentiment analysis, including "emotion classification and intensity", "valence and arousal for emotion", "valence and arousal for sentiment", and "3-class categorical classification for sentiment". The underlying problems cover two granularity analysis (i.e., coarse-grained and fine-grained) in the intelligent customer service domain. Experimental results suggest that the proposed multi-task ensemble model outperforms the single-task framework, and the method performs well in emotion and sentiment analysis tasks in intelligent service conversation. [ABSTRACT FROM AUTHOR]

The fusion of multimodal medical images has garnered painstaking attention for clinical diagnosis and surgical planning. Although various scholars have designed numerous fusion methods, the challenges of extracting substantial features without introducing noise and non-uniform contrast hindered the overall quality of fused photos. This paper presents a multimodal medical image fusion (MMIF) using a novel deep convolutional neural network (D-CNN) along with preprocessing schemes to circumvent the mentioned issues. A non-linear average median filtering (NL-AMF) and multiscale improved top-hat (MI-TH) approach are utilized at the preprocessing stage to remove noise and improve the contrast of images. The non-linear anisotropic diffusion (NL-AD) scheme is employed to split the photos into base and detailed parts. The fusion of base parts is accomplished by a dimension reduction method to retain the energy information. In contrast, the detailed parts are fused by novel D-CNN to preserve the enriched detailed features effectively. The simulation results demonstrate that the proposed method produces better brightness contrast and more image details than existing methods by acquiring 0.7649 to 0.8986, 0.3520 to 0.4783, 0.7639 to 0.9056, 68.8932 to 81.0487 gain for quality transfer ratio from source photo to a generated photo ( Q G AB ), feature mutual information (FMI), structural similarity index (SSIM), and average pixel intensity (API) respectively. [ABSTRACT FROM AUTHOR]

Infrared and visible image fusion aims to generate a single fused image that contains abundant texture details and thermal radiance information. For this purpose, many unsupervised deep learning image fusion methods have been proposed, ignoring image content and quality awareness. To address these challenges, this paper presents a quality and content-aware image fusion network, termed QCANet, capable of solving the similarity fusion optimization problems, e.g., the dependence of fusion results on source images and the weighted average fusion effect. Specifically, the QCANet is composed of three modules, i.e., Image Fusion Network (IFNet), Quality-Aware Network (QANet), and Content-Aware Network (CANet). The latter two modules, a.k.a., QANet and CANet, aim to improve the content semantic awareness and quality awareness of IFNet. In addition, a new quality-aware image fusion loss is introduced to avoid the weighted average effect caused by the traditional similarity metric optimization mechanism. Therefore, the stumbling blocks of deep learning in image fusion, i.e., similarity fusion optimization problems, are significantly mitigated. Extensive experiments demonstrate that the quality and content-aware image fusion method outperforms most state-of-the-art methods. [ABSTRACT FROM AUTHOR]

In this paper, we investigate the effectiveness of classical approaches to active learning in the problem of document segmentation with the aim of reducing the size of the training sample. A modified approach to selection of document images for labeling and subsequent model training is presented. The results of active learning are compared to those of transfer learning on fully labeled data. The paper also investigates how the problem domain of a training set, on which a model is initialized for transfer learning, affects the subsequent uptraining of the model. [ABSTRACT FROM AUTHOR]

Technological improvements have increased the number of people who use online social networking sites, resulting in an increase in cyberbullying. Bullies can attack victims through a large network of online social networking platforms. Cyberbullying is an umbrella term encompassing a wide range of online abuse, including but not limited to harassment, doxing, and reputation attacks. These attacks frequently leave the victim(s) with persistent mental scars, leading to desperate measures such as depression, self-harm, and suicidal thoughts. Given the effects of cyberbullying, there is an urgent need to prosecute and prevent such crimes. This paper gives a comprehensive review as well the empirical analysis of the machine learning, ensemble based and transformer-based models for the cyberbullying detection. This paper proposes two architectures to efficiently detect cyberbullying pattern. The proposed ensemble model makes use of CNN to extract the relevant features and the classification is performed by the SVM. Another proposed architecture utilizes the pre-trained model BERT to detect cyberbullying behavior on online platforms. Both the proposed models were tested on two separate datasets and achieved maximum accuracy of 96.88 and 97.34% for ensemble and BERT models, respectively. This paper provides a thorough examination of the various methodologies used for cyberbullying detection and conducts an empirical and comparative analysis of the presented models with traditional and current algorithms. [ABSTRACT FROM AUTHOR]

The object detection of transmission towers is of great significance for transmission and transformation channel monitoring, engineering evaluation, operation and maintenance management. This paper aims to detect different types of transmission towers in satellite remote sensing images according to the characteristics of transmission tower shadow. However, different shooting angles lead to great changes in the shape of the tower shadow. At the same time, the shadows of different types of towers may be very similar. In order to further improve the accuracy of object detection, we first conduct the image preprocessing and image enhancement. Then, the deformable convolution is introduced to better extract the features of transmission tower shadow. At the same time, in order to neutralize the influence of the increase of model parameters caused by deformable convolution, this paper introduces the idea of grouped convolution and proposes a modified bi-directional feature pyramid network (GD-BiFPN) based on the grouped deformable convolution (GDConv). Finally, a lightweight satellite remote sensing object detection model for transmission towers with accuracy up to 96% is implemented with EfficientNet as the backbone and GD-BiFPN as the enhanced feature extraction network. Through ablation and comparison experiments, the effectiveness and advancement of the proposed model in transmission tower remote sensing object detection are verified. [ABSTRACT FROM AUTHOR]

There have been a number of approaches to employ neural networks in self-adaptive systems; in many cases, generic neural networks and deep learning are utilized for this purpose. When this approach is to be applied to improve an adaptation process initially driven by logical adaptation rules, the problem is that (1) these rules represent a significant and tested body of domain knowledge, which may be lost if they are replaced by a neural network, and (2) the learning process is inherently demanding given the black-box nature and the number of weights in generic neural networks to be trained. In this paper, we introduce the rule-specific neural network method that makes it possible to transform the guard of an adaptation rule into a rule-specific neural network, the composition of which is driven by the structure of the logical predicates in the guard. Our experiments confirmed that the black box effect is eliminated, the number of weights is significantly reduced, and much faster learning is achieved whilst the accuracy is preserved. This text is an extended version of the paper presented at the ISOLA 2022 conference (Bureš et al. in Proceedings of ISOLA 2022, Rhodes, Greece, pp. 215–230, 2022). [ABSTRACT FROM AUTHOR]

This paper proposes a bidirectional feature fusion pyramid (B-FPN) Single Shot Multiple Frame Detector (SSD) algorithm. First, a bidirectional feature pyramid (B-FPN) structure is constructed, which realizes the bidirectional fusion of the feature layers and improves the accuracy of detection. Second, we introduce coordinate attention (CA) to focus on the important channel features while preserving their location information, thereby increasing the focus on the important information. Finally, optimizing the loss function speeds up the convergence of the model and further improves the detection accuracy of the network. The experimental results show that on the VOC2007 dataset, the mAP of the algorithm in this paper is 76.48%, which is 3.52% higher than that of the SSD algorithm. On the COCO 2017 dataset, the mAP of the proposed algorithm is 3.85% higher than that of the SSD algorithm. Compared with other mainstream target detection algorithms, the algorithm in this paper has certain advantages in detection accuracy, and can also achieve satisfactory results in detection speed. Finally, the accuracy of foreign object recognition in the special environment of iron ore transportation is 98.26%. [ABSTRACT FROM AUTHOR]

Deep learning models have recently attracted great interest as an effective solution to the challenging problem of human activity recognition (HAR) and its widespread applications in medical rehabilitation and human–computer interaction. However, it is difficult for many existing models to simultaneously extract global temporal features and local spatial features of activity data. This paper proposes a deep learning model, ConvTransformer, based on convolutional neural network (CNN), Transformer, and attention mechanism. The model first uses the convolutional layer to model the local information of the sensor time series signal, then uses Transformer to obtain the temporal correlation of the feature sequence, adds an attention mechanism to highlight essential features, and finally completes the activity recognition through the fully connected layer (FC). We evaluate the model on four public datasets, and the experimental results show that the model achieves 92%, 99%, 97%, and 86% accuracy on the OPPORTUNITY, PAMAP2, SKODA, and USC-HAD datasets, respectively. Compared with the baseline Transformer and existing state-of-the-art methods, the model has higher recognition accuracy and better robustness. In addition, we explore the strengths and limitations of the method proposed in this paper by tuning hyperparameters and optimization strategies. [ABSTRACT FROM AUTHOR]

The price prediction is valuable in energy management system (EMS) because it allows making informed decisions and solving the problem of the uncertainty related to the future ignorance based only on the past knowledge. To this goal, we present in this paper a two-steps EMS in order to control the different operations of a micro-grid (MG). In the first step, we exploit the advantages of the Bidirectional Long-Short Term Memory (BiLSTM) deep learning model to predict the next daily electricity price based on time series. In the second step, we use a type-2 fuzzy logic controller to decide which energy source will exploit the excess energy produced or meet the MG need. Real data is used in this paper to test the effectiveness of the proposed EMS whose superiority is proved through the test period. The BiLSTM forecasting model better performs compared to other related algorithms designed to the electricity price prediction. In addition, the proposed decision-making process can reduce the total MG cost and protect the batteries against the deep discharge and maximum charge in order to prolong their lifespan. We expect that this work can contribute to meet the real-world needs in the management of the electrical system. [ABSTRACT FROM AUTHOR]

Yoga is a centuries-old style of exercise followed by sports personnel, patients, and physiotherapist as their regime. A correct posture and technique are the key points in yoga to reap the maximum benefits. Hence, developing a model to classify yoga postures correctly is a recently emerging research topic. The paper presents a novel architecture that aims to classify various yoga poses. The proposed model estimates and classifies yoga poses into five broad categories with low latency. In the proposed architecture, the images are skeletonized before inputting into the model. The skeletonization process is done using the MediaPipe library for body keypoint detection. The paper compares the performance of various deep learning models with and without skeletonization. Different learning models showed the optimum result with the training of skeletonized images to the network. The comparison is drawn to establish the positive impact of skeletonization on the results obtained by various models. VGG16 achieves the highest validation accuracy on non-skeletonized images (95.6%), followed by InceptionV3, NASNetMobile, YogaConvo2d (proposed model) (89.9%), and lastly, InceptionResNetV2. In contrast, the proposed model YogaConvo2d using skeletonized images reports a validation accuracy of 99.62%, followed by VGG16, InceptionResNetV2, NASNetMobile, and InceptionV3. [ABSTRACT FROM AUTHOR]

The previous studies have demonstrated that the use of deep learning algorithms can make personality prediction based on two-dimensional image information, and the emergence of video provides more possibilities for exploring personality prediction. Compared to image-based personality prediction, using video can provide more information than static images. But videos contain hundreds of frames, not all of which are useful, and processing these images requires a lot of computation. This paper proposes to apply video analysis algorithms to the task of personality prediction and propose the use of LSTM to fuse image feature information. The best prediction effect is confirmed by experiments when the fusion frame number is 16 frames. This paper is based on 3D-ConvNet to build an end-to-end video analysis network and solve the network over fitting problem by pre-training and data augmentation. Experiments show that the accuracy of character prediction can be improved by using 3D-ConvNet to fuse the spatio-temporal information of videos. [ABSTRACT FROM AUTHOR]

Structural topology optimization has gained widespread attention due to more possibilities of innovative structural design. The current research focus/hotspots, application areas, main research scholars, institutions and the countries involved in structural topology optimization are visually presented through clustering and visual analysis based on CiteSpace. The four metric dimensions of the literatures in this paper are as follows: annual quantity of papers and core countries, core authors and co-authors' institutions, hotspots and burst terms, and the highly co-cited papers. The results show the research hotspots in this field are concentrated on keywords such as "level set method", "sensitivity analysis", "homogenization", "genetic algorithm", etc. Regarding the research frontier, "moving morphable component (MMC)", "additive manufacturing (AM)" and "deep learning" are hot topics. In addition, Y. Sui, Z. Kang and O. Sigmund, etc. have high publications. M. Bendsøe and O. Sigmund have high citations. Dalian University of Technology, Technical University of Denmark, etc. are prominent institutions. Moreover, China accounts for more than 34% in the terms of original WOS literatures following by the USA and Australia. This paper could identify structural topology optimization development patterns for the scholars concerned with this field, especially novices, to quickly focus and track the research priorities. [ABSTRACT FROM AUTHOR]

China, India, and the USA are the countries with the highest energy consumption and CO2 emissions globally. As per the report of datacommons.org, CO2 emission in India is 1.80 metric tons per capita, which is harmful to living beings, so this paper presents India's detrimental CO2 emission effect with the prediction of CO2 emission for the next 10 years based on univariate time-series data from 1980 to 2019. We have used three statistical models; autoregressive-integrated moving average (ARIMA) model, seasonal autoregressive-integrated moving average with exogenous factors (SARIMAX) model, and the Holt-Winters model, two machine learning models, i.e., linear regression and random forest model and a deep learning-based long short-term memory (LSTM) model. This paper brings together a variety of models and allows us to work on data prediction. The performance analysis shows that LSTM, SARIMAX, and Holt-Winters are the three most accurate models among the six models based on nine performance metrics. Results conclude that LSTM is the best model for CO2 emission prediction with the 3.101% MAPE value, 60.635 RMSE value, 28.898 MedAE value, and along with other performance metrics. A comparative study also concludes the same. Therefore, the deep learning-based LSTM model is suggested as one of the most appropriate models for CO2 emission prediction. [ABSTRACT FROM AUTHOR]

Camouflage object detection (COD) is designed to locate objects that are "seamlessly" embedded in the surrounding environment. Camouflaged object detection is a challenging task due to the high intrinsic similarities between objects and their backgrounds, as well as the low boundary contrast between them. To address this problem, this paper proposes a new ternary symmetric fusion network (TSFNet), which can detect camouflaged objects by fully fusing features of different levels and scales. Specifically, the network proposed in this paper mainly contains two key modules: the location-attention search (LAS) module and the ternary symmetric interaction fusion (TSIF) module. The location-attention search module makes full use of contextual information to position potential target objects from a global perspective while enhancing feature representation and guiding feature fusion. The ternary symmetric interaction fusion module consists of three branches: bilateral branches gather rich contextual information of multi-level features, and a middle branch provides fusion attention coefficients for the other two branches. The strategy can effectively achieve information fusion between low- and high-level features, and then achieve the refinement of edge details. Experimental results show that the method is an effective COD model and outperforms existing models. Compared with the existing model SINetV2, TSFNet significantly improves the performance by 3.5% weighted F-measure and 8.1% MAE on the COD10K. [ABSTRACT FROM AUTHOR]