Search

Copyright of Application Research of Computers / Jisuanji Yingyong Yanjiu is the property of Application Research of Computers Edition 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.)

The federated learning framework that uses autoencoder model to detect malicious model updates is an excellent defense framework for poisoning attacks. However, the existing autoencoder-based models face several challenges such as training difficulties and limited anomaly detection capability. In view of the above problems, this paper proposed an algorithm for detecting malicious model updates of federated learning based on β-VAE: the central server stabilized the training dataset by suppressing random attributes of the training samples, and used the dataset to train β-VAE anomaly detection model in real time. The model computed the anomaly score of task model updates uploaded by the clients, and then to detect and exclude malicious model updates based on the dynamic threshold of anomaly score. This paper evaluated the performance of the proposed algorithm on three federated learning tasks. Specifically, these tasks include classification on the MNIST dataset using the logistic regression (LR) model, classification on the FEMNIST dataset using the convolutional neural network (CNN) model, and character prediction on the Shakespeare dataset using the recurrent neural network (RNN) model. The experimental results show that, the task model under this algorithm achieves higher accuracy compared to other defense algorithms. This indicates that in Non-IID scenarios, the algorithm exhibits strong robustness against poisoning attacks in federated learning. [ABSTRACT FROM AUTHOR]

Implementing fast and accurate hand detection on embedded devices mainly face two challenges. Firstly, it is difficult for complex deep learning networks to achieve real-time hand detection. Secondly, the complexity of the scene leads to a decrease in the accuracy of hand detection algorithms based on RGB color images. Unlike mainstream RGB image based detection technologies, this paper adopted a lightweight hand detection algorithm based on ToF infrared images to attain precise and swift hand detection within the infrared images. Firstly, this paper gathered 22 419 static infrared images using this self-engineered equipment, thereby establishing an infrared dataset tailored for hand detection. Subsequently, it enhanced a general object detection algorithm to create a lightweight hand detection network known as Retina Hand, using two different lightweight networks, MobileNetV1 and Shuffle NetV2, as the backbone network of the model. Furthermore, this paper proposed an attention-enhanced feature pyramid structure called Attention-FPN. This structure integrated attention mechanisms to enhance the detection process. Ultimately, this paper conducted comparative experiments on the infrared dataset against conventional methods to validate the effectiveness of the method. [ABSTRACT FROM AUTHOR]

Currently, human sleep staging methods based on electroencephalogram (EEG) signals show a trend towards single-channel and deep network models, however, single-channel information acquisition makes EEG lose the positional information of brain regions, and the features characterizing sleep stages in EEG tend to be sparse and thus difficult to extract, at the same time, the common problems of deep networks-the artificial setting of the model and its training hyperparameters make the training process blind and inefficient, and these problems lead to the low accuracy of automatic sleep staging methods. Therefore, this paper proposed to use the inter-layer feature reuse function of DenseNet to explore the sleep state information hidden in EEG signals, and improved the DenseNet model for the low-frequency characteristics of single-channel EEG signals in the frequency domain and the long-range dependence of single-channel EEG signals in the time domain, so as to achieve the fast and accurate sleep staging of the human body. In order to further improve the performance of DenseNet, it used a deep deterministic policy gradient (DDPG) algorithm to optimize and automatically adjust the key hyperparameters of DenseNet using the reinforcement learning idea during the network learning and training process. The experimental results show that the staging accuracy of the algorithm model on the Sleep-EDFx dataset reaches 89.23%, and the overall performance is better than other advanced staging algorithms in recent years, demonstrating good application prospects. [ABSTRACT FROM AUTHOR]

NeRF is a deep learning model aimed at modeling three-dimensional implicit spaces, and it holds significant value in the representation and rendering of 3D scenes. However, due to the complex training process, substantial computational resources, and time requirements, the usability and practicality of the NeRF algorithm are somewhat limited. Addressing the pain points of NeRF optimization has become a hot topic in the field of computer vision. This paper aimed to provide a comprehensive review of the optimization and application of NeRF. Firstly, it delved into the basic principles of NeRF and outlined the current optimization status from the perspectives of rendering quality, computational complexity, and pose. Secondly, it enumerated the application scenarios of NeRF to provide references for future, more efficient and practical algorithmic optimizations. Finally, it summarized the strengths and limitations of NeRF and proposed potential future directions tailored to harness the tremendous potential of NeRF in 3D rendering, scene synthesis, and beyond. [ABSTRACT FROM AUTHOR]

Camera pose estimation plays a crucial role in tasks such as autonomous driving and robotics, elucidating the direction and position of the camera in relation to a given scene through the estimation of its positional coordinates and angular deviations around the three coordinate axes. To facilitate the understanding of researchers in the realm of camera pose estimation, this paper comprehensively reviewed the current research status and latest progress in this field will. Firstly, it introduced the fundamental principles, evaluation indicators, and pertinent datasets associated with camera pose estimation. Subsequently, the review elaborated and summarized the two-stage model structure method and single-channel model structure method from the two key technologies of scene relationship construction and camera pose calculation. It conducted classification and analysis based on the diverse core algorithms and scene information employed, with performance comparisons drawn from indoor and outdoor public datasets. Lastly, it expounded the current challenges in the field and future development trends. [ABSTRACT FROM AUTHOR]

Image stitching is an important branch in computer vision and computer graphics, and has a wide range of applications in 3D imaging and other aspects. Compared with the traditional image stitching framework based on feature point detection, the image stitching framework based on deep learning has stronger scene generalization performance. Although there are many research results on image stitching based on deep learning, there is still a lack of comprehensive analysis and summary of the corresponding research. In order to facilitate the subsequent work in this field, this paper sorted out the representative results in this field in the past 10 years. Based on the comparison between traditional stitching methods and deep learning-based image stitching methods, it collated and analysed the learning strategy and model architecture design, classical model review, and dataset from the three sub-problems of homography estimation, image stitching, and image rectangling in the research field of image stitching. It summarized some features of deep learning-based image stitching research methods and summarized the current research status in the field, and prospected the future research prospects. [ABSTRACT FROM AUTHOR]

Predictive business process monitoring(PBPM) represents a vital research field within BPM that aims to accurately predict future behavioral events. At present, deep learning methods are widely used in PBPM research. However, most of these methods consider only a single event-control flow perspective and do not fuse the attribute-data flow perspective for process prediction. To address this issue, this paper proposed a method called the fusion multi-perspective(FMP) framework based on a two-layer BERT neural network. Firstly, the first layer of BERT was used to learn attribute-data flow information. Subsequently, the second layer of BERT learnt event-behavior control flow information. Finally, the FMP framework combined data flow and control flow to achieve multi-perspective process prediction. Experimental results on real event logs demonstrate that, compared to other research methods, the FPM framework yields higher accuracy in predicting the next event activity. This validates that the FPM framework, which merges multi-perspective views of processes, enables a more comprehensive and in-depth analysis of complex process behaviors while enhancing predictive performance. [ABSTRACT FROM AUTHOR]

Knowledge distillation algorithms have a great effect on the streamlining of deep neural networks. The current feature-based knowledge distillation algorithms either focus on a single part for improvement and ignore other beneficial parts, or provides effective guidance for the part that a small model should focus on, which makes the distillation effect insufficient. In order to make full use of the beneficial information of the large model and process it to improve the knowledge conversion rate of the small model, this paper proposed a new distillation algorithm. Firstly, it used the conditional probability distribution to fit the feature spatial distribution of the large model's middle layer, and then extracted the spatial attention maps that tended to be similar after fitting together with other beneficial information. Finally, it used the small convolutional layer, narrowed the gap between models, transmitted the transformed information to the small model to achieve distillation. Experimental results show that the algorithm has the applicability of multiple teacher-student combinations and the generality of multiple data sets, and compared with the current more advanced distillation algorithms, the performance is improved by about 1.19% and the time is shortened by 0.16 h. It has important engineering significance and wide application prospects for large networks' optimization and the application of deep learning on low-resource devices. [ABSTRACT FROM AUTHOR]

The radar echo extrapolation method is widely used in rainfall forecasting. Addressing the issue of insufficient prediction accuracy in radar echoes, this paper proposed a deep learning model DIPredRNN based on recurrent neural networks. This model combined long-term temporal and channel information by introducing a dual attention mechanism of space and channel, improved the long-term dependence of time memory. By introducing an interactive framework of hidden states and inputs, it retained more features and improved the short-term dependence of temporal memory. This model was experimentally compared with classical models and many advanced models on the HKO-7 and Sichuan datasets. The model achieved the best results in comparing multiple indicators such as extrapolated images, MSE, SSIM, CSI-30~50 dbz. The experiment proves that the proposed DIPredRNN network improves the radar echo prediction performance and has advanced performance. [ABSTRACT FROM AUTHOR]

The majority of current machine learning and deep learning solutions for ECG-based emotion recognition utilize fully-supervised learning methods. Several limitations of this approach are that large human-annotated datasets and computing resources are required. Furthermore, the feature representations learned by fully supervised methods tend to be task-specific with limited generalization capability. In response to these issues, this paper proposed an approach based on contrastive lear-ning for ECG-based emotion recognition, which consisted of two steps, such as pre-training and fine-tuning. The goal of pre-training was to learn representations from unlabeled EGG data through contrastive learning. Specifically, it designed two simple and efficient ECG signal augmentation methods, and used these two views to learn robust temporal representations in the time contrastive module, followed by learning discriminative feature representations in the context contrastive module. Fine-tuning used labelled data to learn emotion recognition. Experiments show that the proposed method has reached the maximum accuracy on three public ECG-based emotion recognition datasets. Additionally, the proposed method shows high efficiency under the semi-supervised settings. [ABSTRACT FROM AUTHOR]

As a popular research direction in the field of artificial intelligence, Facial Expression Recognition (FER) is the most direct and effective way for computers to access human emotions. It occupies a key technical position in human-computer interaction, intelligent medical care, fatigue driving, and other R＆D topics. In order to meet the application requirements of high recognition rate, the structure of FER deep learning network becomes more and more complex, occupying a large amount of computing resources and storage space, which seriously affects the real-time requirements of the algorithm. This paper focuses on the problem of how to guarantee the accuracy of the model while effectively improving its computational speed. Firstly, it introduces the important datasets for expression recognition using lightweight networks; Secondly, it analyzes the classical lightweight network models used for facial expression recognition; Thirdly, it describes the principles, characteristics, and applicable scenarios of the main network lightweighting methods; Finally, it summarizes the problems and challenges of lightweight networks in facial expression recognition research and looks forward to the future research direction. [ABSTRACT FROM AUTHOR]

The current research on the application of artificial intelligence techniques to the field of system architecture is promising, especially the research on applying deep learning to data prefetching in multicore architectures has become a research hotspot at home and abroad. This work studied the cache prefetching task based on deep learning and defined the deep learning cache prefetch model formally. Based on the introduction of current common multi-core cache architectures and prefetching techniques, this paper comprehensively analyzed the design ideas of existing typical cache prefetchers based on deep learning. The application of deep learning neural network in the field of multicore cache prefetching mainly adopts machine learning methods such as deep neural network, recurrent neural network, long and short-term memory network and attention mechanism. A comprehensive comparative analysis of existing deep learning-based data prefetching hierarchical neural models reveals that deep learning-based multicore cache prefetching techniques still have certain computational cost, model optimization, and practicality. In the future, there is still much room for research exploration and development prospect in adaptive prefetching models and the practicality of neural network prefetching models. [ABSTRACT FROM AUTHOR]

Atmospheric turbulence is a crucial factor that affects the quality of long-distance imaging. Though current deep learning models can effectively suppress geometric displacement and spatial blurring caused by atmospheric turbulence, such models require a large number of parameters and computational resources. To tackle this problem, this paper proposed a lightweight atmospheric turbulence degraded image restoration model based on generative inversion that entailed three core mo-dules: the DeBlur module, the remove shift module, and the turbulence regeneration module. The DeBlur module used high-dimensional feature mapping blocks, detail feature extraction blocks, and feature compensation blocks to suppress image blurring caused by turbulence. The remove shift module compensated for pixel displacement caused by turbulence using two convolutional layers. The turbulence regeneration module regenerated turbulence degraded images through convolutional operations. In the DeBlur module, it designed an attention-based feature compensation module that integrated the channel attention mechanism and the spatial mixed attention mechanism to focus on essential detail information in the image during training. The proposed model achieved peak signal-to-noise ratios of 19.94 dB and 23.51 dB, and structural similarity values of 0.688 2 and 0.752 1 on publicly available dataset Heat Chamber and self-built dataset Helen, respectively. Furthermore, it reduced the number of parameters and computational resources, compared to the current state-of-the-art(SOTA) method. The experimental results demonstrate the effectiveness of this method in restoring atmospheric turbulence degraded images. [ABSTRACT FROM AUTHOR]