Mathematics

Research

Jump to: Other

11 pages, 3060 KiB

Open AccessArticle

Lightweight Image Denoising Network for Multimedia Teaching System

by Xuanyu Zhang, Chunwei Tian, Qi Zhang, Hong-Seng Gan, Tongtong Cheng and Mohd Asrul Hery Ibrahim

Mathematics 2023, 11(17), 3678; https://doi.org/10.3390/math11173678 - 25 Aug 2023

Viewed by 1367

Abstract

Due to COVID-19, online education has become an important tool for teachers to teach students. Also, teachers depend on a multimedia teaching system (platform) to finish online education. However, interacted images from a multimedia teaching system may suffer from noise. To address this [...] Read more.

Due to COVID-19, online education has become an important tool for teachers to teach students. Also, teachers depend on a multimedia teaching system (platform) to finish online education. However, interacted images from a multimedia teaching system may suffer from noise. To address this issue, we propose a lightweight image denoising network (LIDNet) for multimedia teaching systems. A parallel network can be used to mine complementary information. To achieve an adaptive CNN, an omni-dimensional dynamic convolution fused into an upper network can automatically adjust parameters to achieve a robust CNN, according to different input noisy images. That also enlarges the difference in network architecture, which can improve the denoising effect. To refine obtained structural information, a serial network is set behind a parallel network. To extract more salient information, an adaptively parametric rectifier linear unit composed of an attention mechanism and a ReLU is used into LIDNet. Experiments show that our proposed method is effective in image denoising, which can also provide assistance for multimedia teaching systems. Full article

(This article belongs to the Special Issue Computational Methods and Application in Machine Learning)

► Show Figures

Figure 1

22 pages, 11542 KiB

Open AccessArticle

A Hybrid Medium and Long-Term Relative Humidity Point and Interval Prediction Method for Intensive Poultry Farming

by Hang Yin, Zeyu Wu, Junchao Wu, Junjie Jiang, Yalin Chen, Mingxuan Chen, Shixuan Luo and Lijun Gao

Mathematics 2023, 11(14), 3247; https://doi.org/10.3390/math11143247 - 24 Jul 2023

Cited by 1 | Viewed by 1533

Abstract

The accurate and reliable relative humidity (RH) prediction holds immense significance in effectively controlling the breeding cycle health and optimizing egg production performance in intensive poultry farming environments. However, current RH prediction research mainly focuses on short-term point predictions, which cannot meet the [...] Read more.

The accurate and reliable relative humidity (RH) prediction holds immense significance in effectively controlling the breeding cycle health and optimizing egg production performance in intensive poultry farming environments. However, current RH prediction research mainly focuses on short-term point predictions, which cannot meet the demand for accurate RH control in poultry houses in intensive farming. To compensate for this deficiency, a hybrid medium and long-term RH prediction model capable of precise point and interval prediction is proposed in this study. Firstly, the complexity of RH is reduced using a data denoising method that combines complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and permutation entropy. Secondly, important environmental factors are selected from feature correlation and change trends. Thirdly, based on the results of data denoising and feature selection, a BiGRU-Attention model incorporating an attention mechanism is established for medium and long-term RH point prediction. Finally, the Gaussian kernel density estimation (KDE-Gaussian) method is used to fit the point prediction error, and the RH prediction interval at different confidence levels is estimated. This method was applied to analyze the actual collection of waterfowl (Magang geese) environmental datasets from October 2022 to March 2023. The results indicate that the CEEMDAN-FS-BiGRU-Attention model proposed in this study has excellent medium and long-term point prediction performance. In comparison to LSTM, the mean absolute error (MAE), root mean square error (RMSE), and mean absolute percentage error (MAPE) are reduced by 57.7%, 48.2%, and 56.6%, respectively. Furthermore, at different confidence levels, the prediction interval formed by the KDE-Gaussian method is reliable and stable, which meets the need for accurate RH control in intensive farming environments. Full article

(This article belongs to the Special Issue Computational Methods and Application in Machine Learning)

► Show Figures

Figure 1

19 pages, 1921 KiB

Open AccessArticle

FDDS: Feature Disentangling and Domain Shifting for Domain Adaptation

by Huan Chen, Farong Gao and Qizhong Zhang

Mathematics 2023, 11(13), 2995; https://doi.org/10.3390/math11132995 - 5 Jul 2023

Cited by 1 | Viewed by 1500

Abstract

Domain adaptation is a learning strategy that aims to improve the performance of models in the current field by leveraging similar domain information. In order to analyze the effects of feature disentangling on domain adaptation and evaluate a model’s suitability in the original [...] Read more.

Domain adaptation is a learning strategy that aims to improve the performance of models in the current field by leveraging similar domain information. In order to analyze the effects of feature disentangling on domain adaptation and evaluate a model’s suitability in the original scene, we present a method called feature disentangling and domain shifting (FDDS) for domain adaptation. FDDS utilizes sample information from both the source and target domains, employing a non-linear disentangling approach and incorporating learnable weights to dynamically separate content and style features. Additionally, we introduce a lightweight component known as the domain shifter into the network architecture. This component allows for classification performance to be maintained in both the source and target domains while consuming moderate overhead. The domain shifter uses the attention mechanism to enhance the ability to extract network features. Extensive experiments demonstrated that FDDS can effectively disentangle features with clear feature separation boundaries while maintaining the classification ability of the model in the source domain. Under the same conditions, we evaluated FDDS and advanced algorithms on digital and road scene datasets. In the 19 classification tasks for road scenes, FDDS outperformed the competition in 11 categories, particularly showcasing a remarkable 2.7% enhancement in the accuracy of the bicycle label. These comparative results highlight the advantages of FDDS in achieving high accuracy in the target domain. Full article

(This article belongs to the Special Issue Computational Methods and Application in Machine Learning)

► Show Figures

Figure 1

18 pages, 11181 KiB

Open AccessArticle

A Kind of Water Surface Multi-Scale Object Detection Method Based on Improved YOLOv5 Network

by Zhongli Ma, Yi Wan, Jiajia Liu, Ruojin An and Lili Wu

Mathematics 2023, 11(13), 2936; https://doi.org/10.3390/math11132936 - 30 Jun 2023

Cited by 4 | Viewed by 1632

Abstract

Visual-based object detection systems are essential components of intelligent equipment for water surface environments. The diversity of water surface target types, uneven distribution of sizes, and difficulties in dataset construction pose significant challenges for water surface object detection. This article proposes an improved [...] Read more.

Visual-based object detection systems are essential components of intelligent equipment for water surface environments. The diversity of water surface target types, uneven distribution of sizes, and difficulties in dataset construction pose significant challenges for water surface object detection. This article proposes an improved YOLOv5 target detection method to address the characteristics of diverse types, large quantities, and multiple scales of actual water surface targets. The improved YOLOv5 model optimizes the extraction of bounding boxes using K-means++ to obtain a broader distribution of predefined bounding boxes, thereby enhancing the detection accuracy for multi-scale targets. We introduce the GAMAttention mechanism into the backbone network of the model to alleviate the significant performance difference between large and small targets caused by their multi-scale nature. The spatial pyramid pooling module in the backbone network is replaced to enhance the perception ability of the model in segmenting targets of different scales. Finally, the Focal loss classification loss function is incorporated to address the issues of overfitting and poor accuracy caused by imbalanced class distribution in the training data. We conduct comparative tests on a self-constructed dataset comprising ten categories of water surface targets using four algorithms: Faster R-CNN, YOLOv4, YOLOv5, and the proposed improved YOLOv5. The experimental results demonstrate that the improved model achieves the best detection accuracy, with an 8% improvement in [email protected] compared to the original YOLOv5 in multi-scale water surface object detection. Full article

(This article belongs to the Special Issue Computational Methods and Application in Machine Learning)

► Show Figures

Figure 1

13 pages, 650 KiB

Open AccessArticle

PLDH: Pseudo-Labels Based Deep Hashing

by Huawen Liu, Minhao Yin, Zongda Wu, Liping Zhao, Qi Li, Xinzhong Zhu and Zhonglong Zheng

Mathematics 2023, 11(9), 2175; https://doi.org/10.3390/math11092175 - 5 May 2023

Cited by 1 | Viewed by 1386

Abstract

Deep hashing has received a great deal of attraction in large-scale data analysis, due to its high efficiency and effectiveness. The performance of deep hashing models heavily relies on label information, which is very expensive to obtain. In this work, a novel end-to-end [...] Read more.

Deep hashing has received a great deal of attraction in large-scale data analysis, due to its high efficiency and effectiveness. The performance of deep hashing models heavily relies on label information, which is very expensive to obtain. In this work, a novel end-to-end deep hashing model based on pseudo-labels for large-scale data without labels is proposed. The proposed hashing model consists of two major stages, where the first stage aims to obtain pseudo-labels based on deep features extracted by a pre-training deep convolution neural network. The second stage generates hash codes with high quality by the same neural network in the previous stage, coupled with an end-to-end hash layer, whose purpose is to encode data into a binary representation. Additionally, a quantization loss is introduced and interwound within these two stages. Evaluation experiments were conducted on two frequently-used image collections, CIFAR-10 and NUS-WIDE, with eight popular shallow and deep hashing models. The experimental results show the superiority of the proposed method in image retrieval. Full article

(This article belongs to the Special Issue Computational Methods and Application in Machine Learning)

► Show Figures

Figure 1

20 pages, 12211 KiB

Open AccessArticle

A Multi-Factor Selection and Fusion Method through the CNN-LSTM Network for Dynamic Price Forecasting

by Yishun Liu, Chunhua Yang, Keke Huang and Weiping Liu

Mathematics 2023, 11(5), 1132; https://doi.org/10.3390/math11051132 - 24 Feb 2023

Cited by 4 | Viewed by 1934

Abstract

Commodity prices are important factors for investment management and policy-making, and price forecasting can help in making better business decisions. Due to the complex and volatile nature of the market, commodity prices tend to change frequently and fluctuate violently, often influenced by many [...] Read more.

Commodity prices are important factors for investment management and policy-making, and price forecasting can help in making better business decisions. Due to the complex and volatile nature of the market, commodity prices tend to change frequently and fluctuate violently, often influenced by many potential factors with strong nonstationary and nonlinear characteristics. Thus, it is difficult to obtain satisfactory prediction effects by only using the historical data of prices individually. To address this problem, a novel dynamic price forecasting method based on multi-factor selection and fusion with CNN-LSTM is proposed. First, the factors related to commodity price are collected, and Granger causality inference is used to identify causal factors that affect the commodity price. Then, XGBoost is used to evaluate the importance of the remaining factors and screen out critical factors to reduce the interference of redundant information. Due to the high amount and complicated changes of the selected factors, a convolutional neural network is employed to fuse the selected factors and extract the hidden features. Finally, a long short-term memory network is adopted to establish a multi-input predictor to obtain the dynamic price. Compared with several advanced approaches, the evaluation results indicate that the proposed method has an excellent performance in dynamic price forecasting. Full article

(This article belongs to the Special Issue Computational Methods and Application in Machine Learning)

► Show Figures

Figure 1

17 pages, 1369 KiB

Open AccessArticle

Behavior Cloning and Replay of Humanoid Robot via a Depth Camera

by Quantao Wang, Ziming He, Jialiang Zou, Haobin Shi and Kao-Shing Hwang

Mathematics 2023, 11(3), 678; https://doi.org/10.3390/math11030678 - 29 Jan 2023

Cited by 1 | Viewed by 2389

Abstract

The technique of behavior cloning is to equip a robot with the capability of learning control skills through observation, which can naturally perform human–robot interaction. Despite many related studies in the context of humanoid robot behavior cloning, the problems of the unnecessary recording [...] Read more.

The technique of behavior cloning is to equip a robot with the capability of learning control skills through observation, which can naturally perform human–robot interaction. Despite many related studies in the context of humanoid robot behavior cloning, the problems of the unnecessary recording of similar actions and more efficient storage forms than recording actions by joint angles or motor counts are still worth discussing. To reduce the storage burden on robots, we implemented an end-to-end humanoid robot behavior cloning system, which consists of three modules, namely action emulation, action memorization, and action replay. With the help of traditional machine learning methods, the system can avoid recording similar actions while storing actions in a more efficient form. A jitter problem in the action replay is also handled. In our system, an action is defined as a sequence of many pose frames. We propose a revised key-pose detection algorithm to keep minimal poses of each action to minimize storage consumption. Subsequently, a clustering algorithm for key poses is implemented to save each action in the form of identifiers series. Finally, a similarity equation is proposed to avoid the unnecessary storage of similar actions, in which the similarity evaluation of actions is defined as an LCS problem. Experiments on different actions have shown that our system greatly reduces the storage burden of the robot while ensuring that the errors are within acceptable limits. The average error of the revised key-pose detection algorithm is reduced by 69% compared to the original and 26% compared to another advanced algorithm. The storage consumption of actions is reduced by 97% eventually. Experimental results demonstrate that the system can efficiently memorize actions to complete behavioral cloning. Full article

(This article belongs to the Special Issue Computational Methods and Application in Machine Learning)

► Show Figures

Figure 1

17 pages, 7437 KiB

Open AccessArticle

by Jing Cheng, Jiayi Zhao, Weidong Xu, Tao Zhang, Feng Xue and Shaoying Liu

Mathematics 2023, 11(3), 527; https://doi.org/10.3390/math11030527 - 18 Jan 2023

Cited by 1 | Viewed by 1943

Abstract

Applying robots to mobile application testing is an emerging approach to automated black-box testing. The key to supporting automated robot testing is the efficient modeling of GUI elements. Since the application under testing often contains a large number of similar GUIs, the GUI [...] Read more.

Applying robots to mobile application testing is an emerging approach to automated black-box testing. The key to supporting automated robot testing is the efficient modeling of GUI elements. Since the application under testing often contains a large number of similar GUIs, the GUI model obtained often contains many redundant nodes. This causes the state space explosion of GUI models which has a serious effect on the efficiency of GUI testing. Hence, how to accurately identify isomorphic GUIs and construct quasi-concise GUI models are key challenges faced today. We thus propose a semantic similarity-based approach to identifying isomorphic GUIs for mobile applications. Using this approach, the information of GUI elements is first identified by deep learning network models, then, the GUI structure model feature vector and the semantic model feature vector are extracted and finally merged to generate a GUI embedding vector with semantic information. Finally, the isomorphic GUIs are identified by cosine similarity. Then, three experiments are conducted to verify the generalizability and effectiveness of the method. The experiments demonstrate that the proposed method can accurately identify isomorphic GUIs and shows high compatibility in terms of cross-platform and cross-device applications. Full article

(This article belongs to the Special Issue Computational Methods and Application in Machine Learning)

► Show Figures

Figure 1

24 pages, 5220 KiB

Open AccessArticle

Flight Delay Propagation Prediction Based on Deep Learning

by Jingyi Qu, Shixing Wu and Jinjie Zhang

Mathematics 2023, 11(3), 494; https://doi.org/10.3390/math11030494 - 17 Jan 2023

Cited by 14 | Viewed by 4443

Abstract

The current flight delay not only affects the normal operation of the current flight, but also spreads to the downstream flights through the flights schedule, resulting in a wide range of flight delays. The analysis and prediction of flight delay propagation in advance [...] Read more.

The current flight delay not only affects the normal operation of the current flight, but also spreads to the downstream flights through the flights schedule, resulting in a wide range of flight delays. The analysis and prediction of flight delay propagation in advance can help civil aviation departments control the flight delay rate and reduce the economic loss caused by flight delays. Due to the small number of data samples that can constitute flight chains, it is difficult to construct flight chain data. In recent years, the analysis of the flight delay propagation problem is generally based on traditional machine learning methods with a small sample size. After obtaining a large amount of raw data from the China Air Traffic Management Bureau, we have constructed 36,287 pieces of three-level flight chain data. Based on these data, we tried to use a deep learning method to analyze and forecast flight delays. In the field of deep learning, there are CNN models and RNN models that deal with classification problems well. Based on these two classes of models, we modify and innovate the study of the problem of flight delay propagation and prediction. Firstly, the CNN-based CondenseNet algorithm is used to predict the delay level of the three-level flight chain data. Based on this, the CondenseNet network is improved by inserting CBAM modules and named CBAM-CondenseNet. The experimental results show that the improved algorithm can effectively improve the network performance, and the prediction accuracy can reach 89.8%. Compared with the traditional machine learning method, the average prediction accuracy increased by 8.7 percentage points. On the basis of the CNN model, we also considered the superiority of the LSTM (Long Short-Term Memory network) considering the processing time sequence information, and then constructed the CNN-MLSTM network and injected the SimAM module to enhance the attention of flight chain data. In the experiment of flight delay propagation prediction, the accuracy rate is 91.36%, which is a significant improvement compared to using the CNN or LSTM alone. Full article

(This article belongs to the Special Issue Computational Methods and Application in Machine Learning)

► Show Figures

Figure 1

22 pages, 850 KiB

Open AccessArticle

ReqGen: Keywords-Driven Software Requirements Generation

by Ziyan Zhao, Li Zhang, Xiaoli Lian, Xiaoyun Gao, Heyang Lv and Lin Shi

Mathematics 2023, 11(2), 332; https://doi.org/10.3390/math11020332 - 9 Jan 2023

Cited by 4 | Viewed by 2233

Abstract

Software requirements specification is undoubtedly critical for the whole software life-cycle. Currently, writing software requirements specifications primarily depends on human work. Although massive studies have been proposed to speed up the process via proposing advanced elicitation and analysis techniques, it is still a [...] Read more.

Software requirements specification is undoubtedly critical for the whole software life-cycle. Currently, writing software requirements specifications primarily depends on human work. Although massive studies have been proposed to speed up the process via proposing advanced elicitation and analysis techniques, it is still a time-consuming and error-prone task, which needs to take domain knowledge and business information into consideration. In this paper, we propose an approach, named ReqGen, which can provide further assistance by automatically generating natural language requirements specifications based on certain given keywords. Specifically, ReqGen consists of three critical steps. First, keywords-oriented knowledge is selected from the domain ontology and is injected into the basic Unified pre-trained Language Model (UniLM) for domain fine-tuning. Second, a copy mechanism is integrated to ensure the occurrence of keywords in the generated statements. Finally, a requirements-syntax-constrained decoding is designed to close the semantic and syntax distance between the candidate and reference specifications. Experiments on two public datasets from different groups and domains show that ReqGen outperforms six popular natural language generation approaches with respect to the hard constraint of keywords’ (phrases’) inclusion, BLEU, ROUGE, and syntax compliance. We believe that ReqGen can promote the efficiency and intelligence of specifying software requirements. Full article

(This article belongs to the Special Issue Computational Methods and Application in Machine Learning)

► Show Figures

Figure 1

17 pages, 1534 KiB

Open AccessArticle

Online Trajectory Optimization Method for Large Attitude Flip Vertical Landing of the Starship-like Vehicle

by Hongbo Chen, Zhenwei Ma, Jinbo Wang and Linfeng Su

Mathematics 2023, 11(2), 288; https://doi.org/10.3390/math11020288 - 5 Jan 2023

Cited by 4 | Viewed by 2835 | Correction

Abstract

A high-precision online trajectory optimization method combining convex optimization and Radau pseudospectral method is presented for the large attitude flip vertical landing problem of a starship-like vehicle. During the landing process, the aerodynamic influence on the starship-like vehicle is significant and non-negligible. A [...] Read more.

A high-precision online trajectory optimization method combining convex optimization and Radau pseudospectral method is presented for the large attitude flip vertical landing problem of a starship-like vehicle. During the landing process, the aerodynamic influence on the starship-like vehicle is significant and non-negligible. A planar landing dynamics model with pitching motion is developed considering that there is no extensive lateral motion modulation during the whole flight. Combining the constraints of its powered descent landing process, a model of the fuel optimal trajectory optimization problem in the landing point coordinate system is given. The nonconvex properties of the trajectory optimization problem model are analyzed and discussed, and the advantages of fast solution and convergence certainty of convex optimization, and high discretization precision of the pseudospectral method, are fully utilized to transform the strongly nonconvex optimization problem into a series of finite-dimensional convex subproblems, which are solved quickly by the interior point method solver. Hardware-in-the-loop simulation experiments verify the effectiveness of the online trajectory optimization method. This method has the potential to be an online guidance method for the powered descent landing problem of starship-like vehicles. Full article

(This article belongs to the Special Issue Computational Methods and Application in Machine Learning)

► Show Figures

Figure 1

18 pages, 1368 KiB

Open AccessArticle

MACA: Multi-Agent with Credit Assignment for Computation Offloading in Smart Parks Monitoring

by Liang She, Jianyuan Wang, Yifan Bo and Yangyan Zeng

Mathematics 2022, 10(23), 4616; https://doi.org/10.3390/math10234616 - 6 Dec 2022

Cited by 1 | Viewed by 1473

Abstract

Video monitoring has a wide range of applications in a variety of scenarios, especially in smart parks. How to improve the efficiency of video data processing and reduce resource consumption have become of increasing concern. The high complexity of traditional computation offloading algorithms [...] Read more.

Video monitoring has a wide range of applications in a variety of scenarios, especially in smart parks. How to improve the efficiency of video data processing and reduce resource consumption have become of increasing concern. The high complexity of traditional computation offloading algorithms makes it difficult to apply them to real-time decision-making scenarios. Thus, we propose a multi-agent deep reinforcement learning algorithm with credit assignment (MACA) for computation offloading in smart park monitoring. By making online decisions after offline training, the agent can give consideration to both decision time and accuracy in effectively solving the problem of the curse of dimensionality. Via simulation, we compare the performance of MACA with traditional deep Q-network reinforcement learning algorithm and other methods. Our results show that MACA performs better in scenarios where there are a higher number of agents and can minimize request delay and reduce task energy consumption. In addition, we also provide results from a generalization capability verified experiment and ablation study, which demonstrate the contribution of MACA algorithm to each component. Full article

(This article belongs to the Special Issue Computational Methods and Application in Machine Learning)

► Show Figures

Figure 1

20 pages, 2673 KiB

Open AccessArticle

A Hybrid Prediction Model Based on KNN-LSTM for Vessel Trajectory

by Lixiang Zhang, Yian Zhu, Jiang Su, Wei Lu, Jiayu Li and Ye Yao

Mathematics 2022, 10(23), 4493; https://doi.org/10.3390/math10234493 - 28 Nov 2022

Cited by 7 | Viewed by 2293

Abstract

Trajectory prediction technology uses the trajectory data of historical ships to predict future ship trajectory, which has significant application value in the field of ship driving and ship management. With the popularization of Automatic Identification System (AIS) equipment in-stalled on ships, many ship [...] Read more.

Trajectory prediction technology uses the trajectory data of historical ships to predict future ship trajectory, which has significant application value in the field of ship driving and ship management. With the popularization of Automatic Identification System (AIS) equipment in-stalled on ships, many ship trajectory data are collected and stored, providing a data basis for ship trajectory prediction. Currently, most of the ship trajectory prediction methods do not fully consider the influence of ship density in different sea areas, leading to a large difference in the prediction effect in different sea areas. This paper proposes a hybrid trajectory prediction model based on K-Nearest Neighbor (KNN) and Long Short-Term Memory (LSTM) methods. In this model, different methods are used to predict trajectory based on trajectory density. For offshore waters with a high density of trajectory, an optimized K-Nearest Neighbor algorithm is used for prediction. For open sea waters with low density of trajectory, the Long Short-Term Memory model is used for prediction. To further improve the prediction effect, the spatio-temporal characteristics of the trajectory are fully considered in the prediction process of the model. The experimental results for the dataset of historical data show that the mean square error of the proposed method is less than 2.92 × 10⁻⁹. Compared to the prediction methods based on the Kalman filter, the mean square error decreases by two orders of magnitude. Compared to the prediction methods based on recurrent neural network, the mean square error decreases by 82%. The advantage of the proposed model is that it can always obtain a better prediction result under different conditions of trajectory density available for different sea areas. Full article

(This article belongs to the Special Issue Computational Methods and Application in Machine Learning)

► Show Figures

Figure 1

16 pages, 1862 KiB

Open AccessArticle

Social Recommendation Based on Multi-Auxiliary Information Constrastive Learning

by Feng Jiang, Yang Cao, Huan Wu, Xibin Wang, Yuqi Song and Min Gao

Mathematics 2022, 10(21), 4130; https://doi.org/10.3390/math10214130 - 5 Nov 2022

Cited by 2 | Viewed by 1668

Abstract

Social recommendation can effectively alleviate the problems of data sparseness and the cold start of recommendation systems, attracting widespread attention from researchers and industry. Current social recommendation models use social relations to alleviate the problem of data sparsity and improve recommendation performance. Although [...] Read more.

Social recommendation can effectively alleviate the problems of data sparseness and the cold start of recommendation systems, attracting widespread attention from researchers and industry. Current social recommendation models use social relations to alleviate the problem of data sparsity and improve recommendation performance. Although self-supervised learning based on user–item interaction can enhance the performance of such models, multi-auxiliary information is neglected in the learning process. Therefore, we propose a model based on self-supervision and multi-auxiliary information using multi-auxiliary information, such as user social relationships and item association relationships, to make recommendations. Specifically, the user social relationship and item association relationship are combined to form a multi-auxiliary information graph. The user–item interaction relationship is also integrated into the same heterogeneous graph so that multiple pieces of information can be spread in the same graph. In addition, we utilize the graph convolution method to learn user and item embeddings, whereby the user embeddings reflect both user–item interaction and user social relationships, and the item embeddings reflect user–item interaction and item association relationships. We also design multi-view self-supervising auxiliary tasks based on the constructed multi-auxiliary views. Signals generated by self-supervised auxiliary tasks can alleviate the problem of data sparsity, further improving user/item embedding quality and recommendation performance. Extensive experiments on two public datasets verify the superiority of the proposed model. Full article

(This article belongs to the Special Issue Computational Methods and Application in Machine Learning)

► Show Figures

Figure 1

19 pages, 1777 KiB

Open AccessArticle

Path-Wise Attention Memory Network for Visual Question Answering

by Yingxin Xiang, Chengyuan Zhang, Zhichao Han, Hao Yu, Jiaye Li and Lei Zhu

Mathematics 2022, 10(18), 3244; https://doi.org/10.3390/math10183244 - 7 Sep 2022

Cited by 1 | Viewed by 1935

Abstract

Visual question answering (VQA) is regarded as a multi-modal fine-grained feature fusion task, which requires the construction of multi-level and omnidirectional relations between nodes. One main solution is the composite attention model which is composed of co-attention (CA) and self-attention(SA). However, the existing [...] Read more.

Visual question answering (VQA) is regarded as a multi-modal fine-grained feature fusion task, which requires the construction of multi-level and omnidirectional relations between nodes. One main solution is the composite attention model which is composed of co-attention (CA) and self-attention(SA). However, the existing composite models only consider the stack of single attention blocks, lack of path-wise historical memory, and overall adjustments. We propose a path attention memory network (PAM) to construct a more robust composite attention model. After each single-hop attention block (SA or CA), the importance of the cumulative nodes is used to calibrate the signal strength of nodes’ features. Four memoried single-hop attention matrices are used to obtain the path-wise co-attention matrix of path-wise attention (PA); therefore, the PA block is capable of synthesizing and strengthening the learning effect on the whole path. Moreover, we use guard gates of the target modal to check the source modal values in CA and conditioning gates of another modal to guide the query and key of the current modal in SA. The proposed PAM is beneficial to construct a robust multi-hop neighborhood relationship between visual and language and achieves excellent performance on both VQA2.0 and VQA-CP V2 datasets. Full article

(This article belongs to the Special Issue Computational Methods and Application in Machine Learning)

► Show Figures

Figure 1

20 pages, 1250 KiB

Open AccessArticle

Deep Multi-Semantic Fusion-Based Cross-Modal Hashing

by Xinghui Zhu, Liewu Cai, Zhuoyang Zou and Lei Zhu

Mathematics 2022, 10(3), 430; https://doi.org/10.3390/math10030430 - 29 Jan 2022

Cited by 3 | Viewed by 2949

Abstract

Due to the low costs of its storage and search, the cross-modal retrieval hashing method has received much research interest in the big data era. Due to the application of deep learning, the cross-modal representation capabilities have risen markedly. However, the existing deep [...] Read more.

Due to the low costs of its storage and search, the cross-modal retrieval hashing method has received much research interest in the big data era. Due to the application of deep learning, the cross-modal representation capabilities have risen markedly. However, the existing deep hashing methods cannot consider multi-label semantic learning and cross-modal similarity learning simultaneously. That means potential semantic correlations among multimedia data are not fully excavated from multi-category labels, which also affects the original similarity preserving of cross-modal hash codes. To this end, this paper proposes deep multi-semantic fusion-based cross-modal hashing (DMSFH), which uses two deep neural networks to extract cross-modal features, and uses a multi-label semantic fusion method to improve cross-modal consistent semantic discrimination learning. Moreover, a graph regularization method is combined with inter-modal and intra-modal pairwise loss to preserve the nearest neighbor relationship between data in Hamming subspace. Thus, DMSFH not only retains semantic similarity between multi-modal data, but integrates multi-label information into modal learning as well. Extensive experimental results on two commonly used benchmark datasets show that our DMSFH is competitive with the state-of-the-art methods. Full article

(This article belongs to the Special Issue Computational Methods and Application in Machine Learning)

► Show Figures

Figure 1

Other

Jump to: Research

1 pages, 128 KiB

Open AccessCorrection

Correction: Chen et al. Online Trajectory Optimization Method for Large Attitude Flip Vertical Landing of the Starship-like Vehicle. Mathematics 2023, 11, 288

by Hongbo Chen, Zhenwei Ma, Jinbo Wang and Linfeng Su

Mathematics 2024, 12(8), 1138; https://doi.org/10.3390/math12081138 - 10 Apr 2024

Viewed by 406

Abstract

Additional Notes on Article [...] Full article

(This article belongs to the Special Issue Computational Methods and Application in Machine Learning)

Journal Menu

Journal Browser

Computational Methods and Application in Machine Learning

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Related Special Issue

Published Papers (17 papers)

Research

Other

Further Information

Guidelines

MDPI Initiatives

Follow MDPI