Mathematics

Editorial

4 pages, 176 KiB

Open AccessEditorial

Preface to the Special Issue “Advancement of Mathematical Methods in Feature Representation Learning for Artificial Intelligence, Data Mining and Robotics”—Special Issue Book

by Weihua Ou, Jianping Gou, Shaoning Zeng and Lan Du

Mathematics 2023, 11(4), 940; https://doi.org/10.3390/math11040940 - 13 Feb 2023

Viewed by 1009

Abstract

The feature representation learning is the basic task that plays an important role in artificial intelligence, data mining and robotics [...] Full article

(This article belongs to the Special Issue Advancement of Mathematical Methods in Feature Representation Learning for Artificial Intelligence, Data Mining and Robotics)

Research

Jump to: Editorial, Review

16 pages, 415 KiB

Open AccessArticle

Embedding Uncertain Temporal Knowledge Graphs

by Tongxin Li, Weiping Wang, Xiaobo Li, Tao Wang, Xin Zhou and Meigen Huang

Mathematics 2023, 11(3), 775; https://doi.org/10.3390/math11030775 - 03 Feb 2023

Cited by 8 | Viewed by 2106

Abstract

Knowledge graph (KG) embedding for predicting missing relation facts in incomplete knowledge graphs (KGs) has been widely explored. In addition to the benchmark triple structural information such as head entities, tail entities, and the relations between them, there is a large amount of [...] Read more.

Knowledge graph (KG) embedding for predicting missing relation facts in incomplete knowledge graphs (KGs) has been widely explored. In addition to the benchmark triple structural information such as head entities, tail entities, and the relations between them, there is a large amount of uncertain and temporal information, which is difficult to be exploited in KG embeddings, and there are some embedding models specifically for uncertain KGs and temporal KGs. However, these models either only utilize uncertain information or only temporal information, without integrating both kinds of information into the underlying model that utilizes triple structural information. In this paper, we propose an embedding model for uncertain temporal KGs called the confidence score, time, and ranking information embedded jointly model (CTRIEJ), which aims to preserve the uncertainty, temporal and structural information of relation facts in the embedding space. To further enhance the precision of the CTRIEJ model, we also introduce a self-adversarial negative sampling technique to generate negative samples. We use the embedding vectors obtained from our model to complete the missing relation facts and predict their corresponding confidence scores. Experiments are conducted on an uncertain temporal KG extracted from Wikidata via three tasks, i.e., confidence prediction, link prediction, and relation fact classification. The CTRIEJ model shows effectiveness in capturing uncertain and temporal knowledge by achieving promising results, and it consistently outperforms baselines on the three downstream experimental tasks. Full article

(This article belongs to the Special Issue Advancement of Mathematical Methods in Feature Representation Learning for Artificial Intelligence, Data Mining and Robotics)

► Show Figures

Figure 1

18 pages, 1485 KiB

Open AccessArticle

A Novel Deep Reinforcement Learning Based Framework for Gait Adjustment

by Ang Li, Jianping Chen, Qiming Fu, Hongjie Wu, Yunzhe Wang and You Lu

Mathematics 2023, 11(1), 178; https://doi.org/10.3390/math11010178 - 29 Dec 2022

Cited by 1 | Viewed by 1295

Abstract

Nowadays, millions of patients suffer from physical disabilities, including lower-limb disabilities. Researchers have adopted a variety of physical therapies based on the lower-limb exoskeleton, in which it is difficult to adjust equipment parameters in a timely fashion. Therefore, intelligent control methods, for example, [...] Read more.

Nowadays, millions of patients suffer from physical disabilities, including lower-limb disabilities. Researchers have adopted a variety of physical therapies based on the lower-limb exoskeleton, in which it is difficult to adjust equipment parameters in a timely fashion. Therefore, intelligent control methods, for example, deep reinforcement learning (DRL), have been used to control the medical equipment used in human gait adjustment. In this study, based on the key-value attention mechanism, we reconstructed the agent’s observations by capturing the self-dependent feature information for decision-making in regard to each state sampled from the replay buffer. Moreover, based on Softmax Deep Double Deterministic policy gradients (SD3), a novel DRL-based framework, key-value attention-based SD3 (AT_SD3), has been proposed for gait adjustment. We demonstrated the effectiveness of our proposed framework in gait adjustment by comparing different gait trajectories, including the desired trajectory and the adjusted trajectory. The results showed that the simulated trajectories were closer to the desired trajectory, both in their shapes and values. Furthermore, by comparing the results of our experiments with those of other state-of-the-art methods, the results proved that our proposed framework exhibited better performance. Full article

(This article belongs to the Special Issue Advancement of Mathematical Methods in Feature Representation Learning for Artificial Intelligence, Data Mining and Robotics)

► Show Figures

Figure 1

12 pages, 470 KiB

Open AccessArticle

Keyword-Enhanced Multi-Expert Framework for Hate Speech Detection

by Weiyu Zhong, Qiaofeng Wu, Guojun Lu, Yun Xue and Xiaohui Hu

Mathematics 2022, 10(24), 4706; https://doi.org/10.3390/math10244706 - 11 Dec 2022

Cited by 1 | Viewed by 1476

Abstract

The proliferation of hate speech on the Internet is harmful to the psychological health of individuals and society. Thus, establishing and supporting the development of hate speech detection and deploying evasion techniques is a vital task. However, existing hate speech detection methods tend [...] Read more.

The proliferation of hate speech on the Internet is harmful to the psychological health of individuals and society. Thus, establishing and supporting the development of hate speech detection and deploying evasion techniques is a vital task. However, existing hate speech detection methods tend to ignore the sentiment features of target sentences and have difficulty identifying some implicit types of hate speech. The performance of hate speech detection can be significantly improved by gathering more sentiment features from various sources. In the use of external sentiment information, the key information of the sentences cannot be ignored. Thus, this paper proposes a keyword-enhanced multiexperts framework. To begin, the multi-expert module of multi-task learning is utilized to share parameters and thereby introduce sentiment information. In addition, the critical features of the sentences are highlighted by contrastive learning. This model focuses on both the key information of the sentence and the external sentiment information. The final experimental results on three public datasets demonstrate the effectiveness of the proposed model. Full article

(This article belongs to the Special Issue Advancement of Mathematical Methods in Feature Representation Learning for Artificial Intelligence, Data Mining and Robotics)

► Show Figures

Figure 1

13 pages, 788 KiB

Open AccessArticle

Dual-Word Embedding Model Considering Syntactic Information for Cross-Domain Sentiment Classification

by Zihao Lu, Xiaohui Hu and Yun Xue

Mathematics 2022, 10(24), 4704; https://doi.org/10.3390/math10244704 - 11 Dec 2022

Cited by 2 | Viewed by 1231

Abstract

The purpose of cross-domain sentiment classification (CDSC) is to fully utilize the rich labeled data in the source domain to help the target domain perform sentiment classification even when labeled data are insufficient. Most of the existing methods focus on obtaining domain transferable [...] Read more.

The purpose of cross-domain sentiment classification (CDSC) is to fully utilize the rich labeled data in the source domain to help the target domain perform sentiment classification even when labeled data are insufficient. Most of the existing methods focus on obtaining domain transferable semantic information but ignore syntactic information. The performance of BERT may decrease because of domain transfer, and traditional word embeddings, such as word2vec, cannot obtain contextualized word vectors. Therefore, achieving the best results in CDSC is difficult when only BERT or word2vec is used. In this paper, we propose a Dual-word Embedding Model Considering Syntactic Information for Cross-domain Sentiment Classification. Specifically, we obtain dual-word embeddings using BERT and word2vec. After performing BERT embedding, we pay closer attention to semantic information, mainly using self-attention and TextCNN. After word2vec word embedding is obtained, the graph attention network is used to extract the syntactic information of the document, and the attention mechanism is used to focus on the important aspects. Experiments on two real-world datasets show that our model outperforms other strong baselines. Full article

(This article belongs to the Special Issue Advancement of Mathematical Methods in Feature Representation Learning for Artificial Intelligence, Data Mining and Robotics)

► Show Figures

Figure 1

14 pages, 491 KiB

Open AccessArticle

Deep Large-Margin Rank Loss for Multi-Label Image Classification

by Zhongchen Ma, Zongpeng Li and Yongzhao Zhan

Mathematics 2022, 10(23), 4584; https://doi.org/10.3390/math10234584 - 03 Dec 2022

Cited by 2 | Viewed by 1073

Abstract

The large-margin technique has served as the foundation of several successful theoretical and empirical results in multi-label image classification. However, most large-margin techniques are only suitable to shallow multi-label models with preset feature representations and a few large-margin techniques of neural networks only [...] Read more.

The large-margin technique has served as the foundation of several successful theoretical and empirical results in multi-label image classification. However, most large-margin techniques are only suitable to shallow multi-label models with preset feature representations and a few large-margin techniques of neural networks only enforce margins at the output layer, which are not well suitable for deep networks. Based on the large-margin technique, a deep large-margin rank loss function suitable for any network structure is proposed, which is able to impose a margin on any chosen set of layers of a deep network, allows choosing any

ℓ_{p}

norm (

p \geq 1

) on the metric measuring the margin between labels and is applicable to any network architecture. Although the complete computation of deep large-margin rank loss function has the

O (C^{2})

time complexity, where C denotes the size of the label set, which would cause scalability issues when C is large, a negative sampling technique was proposed to make the loss function scale linearly to C. Experimental results on two large-scale datasets, VOC2007 and MS-COCO, show that the deep large-margin ranking function improves the robustness of the model in multi-label image classification tasks while enhancing the model’s anti-noise performance. Full article

(This article belongs to the Special Issue Advancement of Mathematical Methods in Feature Representation Learning for Artificial Intelligence, Data Mining and Robotics)

► Show Figures

Figure 1

20 pages, 5280 KiB

Open AccessArticle

Deep Learning-Based Cyber–Physical Feature Fusion for Anomaly Detection in Industrial Control Systems

by Yan Du, Yuanyuan Huang, Guogen Wan and Peilin He

Mathematics 2022, 10(22), 4373; https://doi.org/10.3390/math10224373 - 20 Nov 2022

Cited by 5 | Viewed by 1859

Abstract

In this paper, we propose an unsupervised anomaly detection method based on the Autoencoder with Long Short-Term Memory (LSTM-Autoencoder) network and Generative Adversarial Network (GAN) to detect anomalies in industrial control system (ICS) using cyber–physical fusion features. This method improves the recall of [...] Read more.

In this paper, we propose an unsupervised anomaly detection method based on the Autoencoder with Long Short-Term Memory (LSTM-Autoencoder) network and Generative Adversarial Network (GAN) to detect anomalies in industrial control system (ICS) using cyber–physical fusion features. This method improves the recall of anomaly detection and overcomes the challenges of unbalanced datasets and insufficient labeled samples in ICS. As a first step, additional network features are extracted and fused with physical features to create a cyber–physical dataset. Following this, the model is trained using normal data to ensure that it can properly reconstruct the normal data. In the testing phase, samples with unknown labels are used as inputs to the model. The model will output an anomaly score for each sample, and whether a sample is anomalous depends on whether the anomaly score exceeds the threshold. Whether using supervised or unsupervised algorithms, experimentation has shown that (1) cyber–physical fusion features can significantly improve the performance of anomaly detection algorithms; (2) the proposed method outperforms several other unsupervised anomaly detection methods in terms of accuracy, recall, and F1 score; (3) the proposed method can detect the majority of anomalous events with a low false negative rate. Full article

(This article belongs to the Special Issue Advancement of Mathematical Methods in Feature Representation Learning for Artificial Intelligence, Data Mining and Robotics)

► Show Figures

Figure 1

15 pages, 847 KiB

Open AccessArticle

Knowledge-Enhanced Dual-Channel GCN for Aspect-Based Sentiment Analysis

by Zhengxuan Zhang, Zhihao Ma, Shaohua Cai, Jiehai Chen and Yun Xue

Mathematics 2022, 10(22), 4273; https://doi.org/10.3390/math10224273 - 15 Nov 2022

Cited by 8 | Viewed by 1990

Abstract

As a subtask of sentiment analysis, aspect-based sentiment analysis (ABSA) refers to identifying the sentiment polarity of the given aspect. The state-of-the-art ABSA models are developed by using the graph neural networks to deal with the semantics and the syntax of the sentence. [...] Read more.

As a subtask of sentiment analysis, aspect-based sentiment analysis (ABSA) refers to identifying the sentiment polarity of the given aspect. The state-of-the-art ABSA models are developed by using the graph neural networks to deal with the semantics and the syntax of the sentence. These methods are challenged by two issues. For one thing, the semantic-based graph convolution networks fail to capture the relation between aspect and its opinion word. For another, minor attention is assigned to the aspect word within graph convolution, resulting in the introduction of contextual noise. In this work, we propose a knowledge-enhanced dual-channel graph convolutional network. On the task of ABSA, a semantic-based graph convolutional netwok (GCN) and a syntactic-based GCN are established. With respect to semantic learning, the sentence semantics are enhanced by using commonsense knowledge. The multi-head attention mechanism is taken to construct the semantic graph and filter the noise, which facilitates the information aggregation of the aspect and the opinion words. For syntactic information processing, the syntax dependency tree is pruned to remove the irrelevant words, based on which more attention weights are given to the aspect words. Experiments are carried out on four benchmark datasets to evaluate the working performance of the proposed model. Our model significantly outperforms the baseline models and verifies its effectiveness in ABSA tasks. Full article

(This article belongs to the Special Issue Advancement of Mathematical Methods in Feature Representation Learning for Artificial Intelligence, Data Mining and Robotics)

► Show Figures

Figure 1

14 pages, 648 KiB

Open AccessArticle

Triplet Contrastive Learning for Aspect Level Sentiment Classification

by Haoliang Xiong, Zehao Yan, Hongya Zhao, Zhenhua Huang and Yun Xue

Mathematics 2022, 10(21), 4099; https://doi.org/10.3390/math10214099 - 03 Nov 2022

Cited by 10 | Viewed by 1658

Abstract

The domain of Aspect Level Sentiment Classification, in which the sentiment toward a given aspect is analyzed, attracts much attention in NLP. Recently, the state-of-the-art Aspect Level Sentiment Classification methods are devised by using the Graph Convolutional Networks to deal with both the [...] Read more.

The domain of Aspect Level Sentiment Classification, in which the sentiment toward a given aspect is analyzed, attracts much attention in NLP. Recently, the state-of-the-art Aspect Level Sentiment Classification methods are devised by using the Graph Convolutional Networks to deal with both the semantics and the syntax of the sentence. Generally, the parsing of syntactic structure inevitably incorporates irrelevant information toward the aspect. Besides, the syntactic and semantic alignment and uniformity that contribute to the sentiment delivery is currently neglected during processing. In this work, a Triplet Contrastive Learning Network is developed to coordinate the syntactic information and the semantic information. To start with, the aspect-oriented sub-tree is constructed to replace the syntactic adjacency matrix. Further, a sentence-level contrastive learning scheme is proposed to highlight the features of sentiment words. Based on The Triple Contrastive Learning, the syntactic information and the semantic information are thoroughly interacted and coordinated whilst the global semantics and syntax can be exploited. Extensive experiments are performed on three benchmark datasets and achieve accuracies (BERT-based) of 87.40, 82.80, 77.55 on Rest14, Lap14, and Twitter datasets, which demonstrate that our approach achieves state-of-the-art results in Aspect Level Sentiment Classification task. Full article

(This article belongs to the Special Issue Advancement of Mathematical Methods in Feature Representation Learning for Artificial Intelligence, Data Mining and Robotics)

► Show Figures

Figure 1

16 pages, 410 KiB

Open AccessArticle

Pairwise Constraints Multidimensional Scaling for Discriminative Feature Learning

by Linghao Zhang, Bo Pang, Haitao Tang, Hongjun Wang, Chongshou Li and Zhipeng Luo

Mathematics 2022, 10(21), 4059; https://doi.org/10.3390/math10214059 - 01 Nov 2022

Cited by 2 | Viewed by 1169

Abstract

As an important data analysis method in the field of machine learning and data mining, feature learning has a wide range of applications in various industries. The traditional multidimensional scaling (MDS) maintains the topology of data points in the low-dimensional embeddings obtained during [...] Read more.

As an important data analysis method in the field of machine learning and data mining, feature learning has a wide range of applications in various industries. The traditional multidimensional scaling (MDS) maintains the topology of data points in the low-dimensional embeddings obtained during feature learning, but ignores the discriminative nature between classes of low-dimensional embedded data. Thus, the discriminative multidimensional scaling based on pairwise constraints for feature learning (pcDMDS) model is proposed in this paper. The model enhances the discriminativeness from two aspects. The first aspect is to increase the compactness of the new data representation in the same cluster through fuzzy k-means. The second aspect is to obtain more extended pairwise constraint information between samples. In the whole feature learning process, the model considers both the topology of samples in the original space and the cluster structure in the new space. It also incorporates the extended pairwise constraint information in the samples, which further improves the model’s ability to obtain discriminative features. Finally, the experimental results on twelve datasets show that pcDMDS performs

10.31 %

and

8.31 %

higher than PMDS model in terms of accuracy and purity. Full article

(This article belongs to the Special Issue Advancement of Mathematical Methods in Feature Representation Learning for Artificial Intelligence, Data Mining and Robotics)

► Show Figures

Figure 1

12 pages, 1421 KiB

Open AccessArticle

A KGE Based Knowledge Enhancing Method for Aspect-Level Sentiment Classification

by Haibo Yu, Guojun Lu, Qianhua Cai and Yun Xue

Mathematics 2022, 10(20), 3908; https://doi.org/10.3390/math10203908 - 21 Oct 2022

Cited by 7 | Viewed by 1485

Abstract

ALSC (Aspect-level Sentiment Classification) is a fine-grained task in the field of NLP (Natural Language Processing) which aims to identify the sentiment toward a given aspect. In addition to exploiting the sentence semantics and syntax, current ALSC methods focus on introducing external knowledge [...] Read more.

ALSC (Aspect-level Sentiment Classification) is a fine-grained task in the field of NLP (Natural Language Processing) which aims to identify the sentiment toward a given aspect. In addition to exploiting the sentence semantics and syntax, current ALSC methods focus on introducing external knowledge as a supplementary to the sentence information. However, the integration of the three categories of information is still challenging. In this paper, a novel method is devised to effectively combine sufficient semantic and syntactic information as well as use of external knowledge. The proposed model contains a sentence encoder, a semantic learning module, a syntax learning module, a knowledge enhancement module, an information fusion module and a sentiment classifier. The semantic information and syntactic information are respectively extracted via a self-attention network and a graphical convolutional network. Specifically, the KGE (Knowledge Graph Embedding) is employed to enhance the feature representation of the aspect. Then, the attention-based gate mechanism is taken to fuse three types of information. We evaluated the proposed model on three benchmark datasets and the experimental results establish strong evidence of high accuracy. Full article

(This article belongs to the Special Issue Advancement of Mathematical Methods in Feature Representation Learning for Artificial Intelligence, Data Mining and Robotics)

► Show Figures

Figure 1

18 pages, 5896 KiB

Open AccessArticle

Plug-and-Play-Based Algorithm for Mixed Noise Removal with the Logarithm Norm Approximation Model

by Jinhua Liu, Jiayun Wu, Mulian Xu and Yuanyuan Huang

Mathematics 2022, 10(20), 3810; https://doi.org/10.3390/math10203810 - 15 Oct 2022

Cited by 3 | Viewed by 1307

Abstract

During imaging and transmission, images are easily affected by several factors, including sensors, camera motion, and transmission channels. In practice, images are commonly corrupted by a mixture of Gaussian and impulse noises, further complicating the denoising problem. Therefore, in this work, we propose [...] Read more.

During imaging and transmission, images are easily affected by several factors, including sensors, camera motion, and transmission channels. In practice, images are commonly corrupted by a mixture of Gaussian and impulse noises, further complicating the denoising problem. Therefore, in this work, we propose a novel mixed noise removal model that combines a deterministic low-rankness prior and an implicit regularization scheme. In the optimization model, we apply the matrix logarithm norm approximation model to characterize the global low-rankness of the original image. We further adopt the plug-and-play (PnP) scheme to formulate an implicit regularizer by plugging an image denoiser, which is used to preserve image details. The above two building blocks are complementary to each other. The mixed noise removal algorithm is thus established. Within the framework of the PnP scheme, we address the proposed optimization model via the alternating directional method of multipliers (ADMM). Finally, we perform extensive experiments to demonstrate the effectiveness of the proposed algorithm. Correspondingly, the simulation results show that our algorithm can recover the global structure and detailed information of images well and achieves superior performance over competing methods in terms of quantitative evaluation and visual inspection. Full article

(This article belongs to the Special Issue Advancement of Mathematical Methods in Feature Representation Learning for Artificial Intelligence, Data Mining and Robotics)

► Show Figures

Figure 1

18 pages, 17685 KiB

Open AccessArticle

Tensor Affinity Learning for Hyperorder Graph Matching

by Zhongyang Wang, Yahong Wu and Feng Liu

Mathematics 2022, 10(20), 3806; https://doi.org/10.3390/math10203806 - 15 Oct 2022

Cited by 1 | Viewed by 1160

Abstract

Hypergraph matching has been attractive in the application of computer vision in recent years. The interference of external factors, such as squeezing, pulling, occlusion, and noise, results in the same target displaying different image characteristics under different influencing factors. After extracting the image [...] Read more.

Hypergraph matching has been attractive in the application of computer vision in recent years. The interference of external factors, such as squeezing, pulling, occlusion, and noise, results in the same target displaying different image characteristics under different influencing factors. After extracting the image feature point description, the traditional method directly measures the feature description using distance measurement methods such as Euclidean distance, cosine distance, and Manhattan distance, which lack a sufficient generalization ability and negatively impact the accuracy and effectiveness of matching. This paper proposes a metric-learning-based hypergraph matching (MLGM) approach that employs metric learning to express the similarity relationship between high-order image descriptors and learns a new metric function based on scene requirements and target characteristics. The experimental results show that our proposed method performs better than state-of-the-art algorithms on both synthetic and natural images. Full article

(This article belongs to the Special Issue Advancement of Mathematical Methods in Feature Representation Learning for Artificial Intelligence, Data Mining and Robotics)

► Show Figures

Figure 1

14 pages, 1325 KiB

Open AccessArticle

Resolving Cross-Site Scripting Attacks through Fusion Verification and Machine Learning

by Jiazhong Lu, Zhitan Wei, Zhi Qin, Yan Chang and Shibin Zhang

Mathematics 2022, 10(20), 3787; https://doi.org/10.3390/math10203787 - 14 Oct 2022

Cited by 7 | Viewed by 1732

Abstract

The frequent variations of XSS (cross-site scripting) payloads make static and dynamic analysis difficult to detect effectively. In this paper, we proposed a fusion verification method that combines traffic detection with XSS payload detection, using machine learning to detect XSS attacks. In addition, [...] Read more.

The frequent variations of XSS (cross-site scripting) payloads make static and dynamic analysis difficult to detect effectively. In this paper, we proposed a fusion verification method that combines traffic detection with XSS payload detection, using machine learning to detect XSS attacks. In addition, we also proposed seven new payload features to improve detection efficiency. In order to verify the effectiveness of our method, we simulated and tested 20 public CVE (Common Vulnerabilities and Exposures) XSS attacks. The experimental results show that our proposed method has better accuracy than the single traffic detection model. Among them, the recall rate increased by an average of 48%, the F1 score increased by an average of 27.94%, the accuracy rate increased by 9.29%, and the accuracy rate increased by 3.81%. Moreover, the seven new features proposed in this paper account for 34.12% of the total contribution rate of the classifier. Full article

(This article belongs to the Special Issue Advancement of Mathematical Methods in Feature Representation Learning for Artificial Intelligence, Data Mining and Robotics)

► Show Figures

Figure 1

16 pages, 58251 KiB

Open AccessArticle

Joint Semantic Intelligent Detection of Vehicle Color under Rainy Conditions

by Mingdi Hu, Yi Wu, Jiulun Fan and Bingyi Jing

Mathematics 2022, 10(19), 3512; https://doi.org/10.3390/math10193512 - 26 Sep 2022

Cited by 4 | Viewed by 1489

Abstract

Color is an important feature of vehicles, and it plays a key role in intelligent traffic management and criminal investigation. Existing algorithms for vehicle color recognition are typically trained on data under good weather conditions and have poor robustness for outdoor visual tasks. [...] Read more.

Color is an important feature of vehicles, and it plays a key role in intelligent traffic management and criminal investigation. Existing algorithms for vehicle color recognition are typically trained on data under good weather conditions and have poor robustness for outdoor visual tasks. Fine vehicle color recognition under rainy conditions is still a challenging problem. In this paper, an algorithm for jointly deraining and recognizing vehicle color, (

J A D A R

), is proposed, where three layers of

U N e t

are embedded into

R e t i n a N e t - 50

to obtain joint semantic fusion information. More precisely, the

U N e t

subnet is used for deraining, and the feature maps of the recovered clean image and the extracted feature maps of the input image are cascaded into the Feature Pyramid Net (

F P N

) module to achieve joint semantic learning. The joint feature maps are then fed into the class and box subnets to classify and locate objects. The

R a i n V e h i c l e C o l o r - 24

dataset is used to train the

J A D A R

for vehicle color recognition under rainy conditions, and extensive experiments are conducted. Since the deraining and detecting modules share the feature extraction layers, our algorithm maintains the test time of

R e t i n a N e t - 50

while improving its robustness. Testing on self-built and public real datasets, the mean average precision (

m A P

) of vehicle color recognition reaches

72.07 %

, which beats both sate-of-the-art algorithms for vehicle color recognition and popular target detection algorithms. Full article

(This article belongs to the Special Issue Advancement of Mathematical Methods in Feature Representation Learning for Artificial Intelligence, Data Mining and Robotics)

► Show Figures

Figure 1

13 pages, 3020 KiB

Open AccessArticle

Syntactically Enhanced Dependency-POS Weighted Graph Convolutional Network for Aspect-Based Sentiment Analysis

by Jinjie Yang, Anan Dai, Yun Xue, Biqing Zeng and Xuejie Liu

Mathematics 2022, 10(18), 3353; https://doi.org/10.3390/math10183353 - 15 Sep 2022

Cited by 6 | Viewed by 1363

Abstract

Aspect-based sentiment analysis (ABSA) is a fine-grained task of sentiment analysis that presents great benefits to real-word applications. Recently, the methods utilizing graph neural networks over dependency trees are popular, but most of them merely considered if there exist dependencies between words, ignoring [...] Read more.

Aspect-based sentiment analysis (ABSA) is a fine-grained task of sentiment analysis that presents great benefits to real-word applications. Recently, the methods utilizing graph neural networks over dependency trees are popular, but most of them merely considered if there exist dependencies between words, ignoring the types of these dependencies, which carry important information, as dependencies with different types have different effects. In addition, they neglected the correlations between dependency types and part-of-speech (POS) labels, which are helpful for utilizing dependency imformation. To address such limitations and the deficiency of insufficient syntactic and semantic feature mining, we propose a novel model containing three modules, which aims to leverage dependency trees more reasonably by distinguishing different dependencies and extracting beneficial syntactic and semantic features to further enhance model performance. To enrich word embeddings, we design a syntactic feature encoder (SynFE). In particular, we design Dependency-POS Weighted Graph Convolutional Network (DPGCN) to weight different dependencies by a graph attention mechanism we proposed. Additionally, to capture aspect-oriented semantic information, we design a semantic feature extractor (SemFE). Extensive experiments on five popular benchmark databases validate that our model can better employ dependency information and effectively extract favorable syntactic and semantic features to achieve new state-of-the-art performance. Full article

(This article belongs to the Special Issue Advancement of Mathematical Methods in Feature Representation Learning for Artificial Intelligence, Data Mining and Robotics)

► Show Figures

Figure 1

19 pages, 1236 KiB

Open AccessArticle

Deep Reinforcement Learning-Based RMSA Policy Distillation for Elastic Optical Networks

by Bixia Tang, Yue-Cai Huang, Yun Xue and Weixing Zhou

Mathematics 2022, 10(18), 3293; https://doi.org/10.3390/math10183293 - 11 Sep 2022

Cited by 5 | Viewed by 2572

Abstract

The reinforcement learning-based routing, modulation, and spectrum assignment has been regarded as an emerging paradigm for resource allocation in the elastic optical networks. One limitation is that the learning process is highly dependent on the training environment, such as the traffic pattern or [...] Read more.

The reinforcement learning-based routing, modulation, and spectrum assignment has been regarded as an emerging paradigm for resource allocation in the elastic optical networks. One limitation is that the learning process is highly dependent on the training environment, such as the traffic pattern or the optical network topology. Therefore, re-training is required in case of network topology or traffic pattern variations, which consumes a great amount of computation power and time. To ease the requirement of re-training, we propose a policy distillation scheme, which distills knowledge from a well-trained teacher model and then transfers the knowledge to the to-be-trained student model, so that the training of the latter can be accelerated. Specifically, the teacher model is trained for one training environment (e.g., the topology and traffic pattern) and the student model is for another training environment. The simulation results indicate that our proposed method can effectively speed up the training process of the student model, and it even leads to a lower blocking probability, compared with the case that the student model is trained without knowledge distillation. Full article

(This article belongs to the Special Issue Advancement of Mathematical Methods in Feature Representation Learning for Artificial Intelligence, Data Mining and Robotics)

► Show Figures

Figure 1

16 pages, 1605 KiB

Open AccessArticle

Research on Adversarial Domain Adaptation Method and Its Application in Power Load Forecasting

by Min Huang and Jinghan Yin

Mathematics 2022, 10(18), 3223; https://doi.org/10.3390/math10183223 - 06 Sep 2022

Cited by 3 | Viewed by 1256

Abstract

Domain adaptation has been used to transfer the knowledge from the source domain to the target domain where training data is insufficient in the target domain; thus, it can overcome the data shortage problem of power load forecasting effectively. Inspired by Generative Adversarial [...] Read more.

Domain adaptation has been used to transfer the knowledge from the source domain to the target domain where training data is insufficient in the target domain; thus, it can overcome the data shortage problem of power load forecasting effectively. Inspired by Generative Adversarial Networks (GANs), adversarial domain adaptation transfers knowledge in adversarial learning. Existing adversarial domain adaptation faces the problems of adversarial disequilibrium and a lack of transferability quantification, which will eventually decrease the prediction accuracy. To address this issue, a novel adversarial domain adaptation method is proposed. Firstly, by analyzing the causes of the adversarial disequilibrium, an initial state fusion strategy is proposed to improve the reliability of the domain discriminator, thus maintaining the adversarial equilibrium. Secondly, domain similarity is calculated to quantify the transferability of source domain samples based on information entropy; through weighting in the process of domain alignment, the knowledge is transferred selectively and the negative transfer is suppressed. Finally, the Building Data Genome Project 2 (BDGP2) dataset is used to validate the proposed method. The experimental results demonstrate that the proposed method can alleviate the problem of adversarial disequilibrium and reasonably quantify the transferability to improve the accuracy of power load forecasting. Full article

(This article belongs to the Special Issue Advancement of Mathematical Methods in Feature Representation Learning for Artificial Intelligence, Data Mining and Robotics)

► Show Figures

Figure 1

19 pages, 908 KiB

Open AccessArticle

Extension Design Pattern of Requirement Analysis for Complex Mechanical Products Scheme Design

by Tichun Wang, Hao Li and Xianwei Wang

Mathematics 2022, 10(17), 3132; https://doi.org/10.3390/math10173132 - 01 Sep 2022

Cited by 1 | Viewed by 1094

Abstract

Due to the configuration process of a complex product scheme, a design structure often has the characteristics of multi-level, multi-attribute, creativity, and complexity; in order to improve the efficiency and quality of product scheme design, it has important research value to reasonably organize, [...] Read more.

Due to the configuration process of a complex product scheme, a design structure often has the characteristics of multi-level, multi-attribute, creativity, and complexity; in order to improve the efficiency and quality of product scheme design, it has important research value to reasonably organize, reason, and reuse design knowledge. In this paper, the extension modeling problem under the extension design mode of complex product scheme is studied, the multitype design knowledge element modeling expression model of complex product scheme design is given, and the extension process model and the implication process model of requirement analysis of complex product scheme design is established. A new demand element weight assignment method based on extension distance is proposed to obtain accurate demand analysis index weight from the perspective of combined qualitative and quantitative analysis. On the basis of constructing the extension correlation degree of demand primitives, this paper puts forward the implementation method of the extension design pattern for the demand analysis of a complex product scheme design and gives the specific implementation algorithm. Finally, an example of product design is given to illustrate the method, and the results show the effectiveness and operability of the method. Full article

(This article belongs to the Special Issue Advancement of Mathematical Methods in Feature Representation Learning for Artificial Intelligence, Data Mining and Robotics)

► Show Figures

Figure 1

14 pages, 847 KiB

Open AccessArticle

Enhancing the Transferability of Adversarial Examples with Feature Transformation

by Hao-Qi Xu, Cong Hu and He-Feng Yin

Mathematics 2022, 10(16), 2976; https://doi.org/10.3390/math10162976 - 18 Aug 2022

Cited by 1 | Viewed by 1351

Abstract

The transferability of adversarial examples allows the attacker to fool deep neural networks (DNNs) without knowing any information about the target models. The current input transformation-based method generates adversarial examples by transforming the image in the input space, which implicitly integrates a set [...] Read more.

The transferability of adversarial examples allows the attacker to fool deep neural networks (DNNs) without knowing any information about the target models. The current input transformation-based method generates adversarial examples by transforming the image in the input space, which implicitly integrates a set of models by concatenating image transformation into the trained model. However, the input transformation-based methods ignore the manifold embedding and hardly extract intrinsic information from high-dimensional data. To this end, we propose a novel feature transformation-based method (FTM), which conducts feature transformation in the feature space. FTM can improve the robustness of adversarial example by transforming the features of data. Combining with FTM, the intrinsic features of adversarial examples are extracted to generate transferable adversarial examples. The experimental results on two benchmark datasets show that FTM could effectively improve the attack success rate (ASR) of the state-of-the-art (SOTA) methods. FTM improves the attack success rate of the Scale-Invariant Method on Inception_v3 from 62.6% to 75.1% on ImageNet, which is a large margin of 12.5%. Full article

(This article belongs to the Special Issue Advancement of Mathematical Methods in Feature Representation Learning for Artificial Intelligence, Data Mining and Robotics)

► Show Figures

Figure 1

20 pages, 31155 KiB

Open AccessArticle

An Improved Matting-SfM Algorithm for 3D Reconstruction of Self-Rotating Objects

by Zinuo Li, Zhen Zhang, Shenghong Luo, Yuxing Cai and Shuna Guo

Mathematics 2022, 10(16), 2892; https://doi.org/10.3390/math10162892 - 12 Aug 2022

Cited by 4 | Viewed by 1759

Abstract

The 3D reconstruction experiment can be performed accurately in most cases based on the structure from motion (SfM) algorithm with the combination of the multi-view stereo (MVS) framework through a video recorded around the object. However, we need to artificially hold the camera [...] Read more.

The 3D reconstruction experiment can be performed accurately in most cases based on the structure from motion (SfM) algorithm with the combination of the multi-view stereo (MVS) framework through a video recorded around the object. However, we need to artificially hold the camera and stabilize the recording process as much as possible to obtain better accuracy. To eliminate the inaccurate recording caused by shaking during the recording process, we tried to fix the camera on a camera stand and placed the object on a motorized turntable to record. However, in this case, the background did not change when the camera position was kept still, and the large number of feature points from the background were not useful for 3D reconstruction, resulting in the failure of reconstructing the targeted object. To solve this problem, we performed video segmentation based on background matting to segment the object from the background, so that the original background would not affect the 3D reconstruction experiment. By intercepting the frames in the video, which eliminates the background as the input of the 3D reconstruction system, we could obtain an accurate 3D reconstruction result of an object that could not be reconstructed originally when the PSNR and SSIM increased to 11.51 and 0.26, respectively. It was proved that this algorithm can be applied to the display of online merchandise, providing an easy way for merchants to obtain an accurate model. Full article

(This article belongs to the Special Issue Advancement of Mathematical Methods in Feature Representation Learning for Artificial Intelligence, Data Mining and Robotics)

► Show Figures

Figure 1

18 pages, 1300 KiB

Open AccessArticle

A Novel Multi-Source Domain Adaptation Method with Dempster–Shafer Evidence Theory for Cross-Domain Classification

by Min Huang and Chang Zhang

Mathematics 2022, 10(15), 2797; https://doi.org/10.3390/math10152797 - 06 Aug 2022

Cited by 2 | Viewed by 1681

Abstract

In this era of big data, Multi-source Domain Adaptation (MDA) becomes more and more popular and is employed to make full use of available source data collected from several different, but related domains. Although multiple source domains provide much information, the processing of [...] Read more.

In this era of big data, Multi-source Domain Adaptation (MDA) becomes more and more popular and is employed to make full use of available source data collected from several different, but related domains. Although multiple source domains provide much information, the processing of domain shifts becomes more challenging, especially in learning a common domain-invariant representation for all domains. Moreover, it is counter-intuitive to treat multiple source domains equally as most existing MDA algorithms do. Therefore, the domain-specific distribution for each source–target domain pair is aligned, respectively. Nevertheless, it is hard to combine adaptation outputs from different domain-specific classifiers effectively, because of ambiguity on the category boundary. Subjective Logic (SL) is introduced to measure the uncertainty (credibility) of each domain-specific classifier, so that MDA could be bridged with DST. Due to the advantage of information fusion, Dempster–Shafer evidence Theory (DST) is utilized to reduce the category boundary ambiguity and output reasonable decisions by combining adaptation outputs based on uncertainty. Finally, extensive comparative experiments on three popular benchmark datasets for cross-domain image classification are conducted to evaluate the performance of the proposed method via various aspects. Full article

(This article belongs to the Special Issue Advancement of Mathematical Methods in Feature Representation Learning for Artificial Intelligence, Data Mining and Robotics)

► Show Figures

Figure 1

13 pages, 554 KiB

Open AccessArticle

Stability of Switched Systems with Time-Varying Delays under State-Dependent Switching

by Chao Liu and Xiaoyang Liu

Mathematics 2022, 10(15), 2722; https://doi.org/10.3390/math10152722 - 01 Aug 2022

Cited by 7 | Viewed by 1377

Abstract

This paper studies the stability of linear switched systems with time-varying delays and all unstable subsystems. According to the largest region function strategy, the state-dependent switching rule is designed. By bringing in integral inequality and multiple Lyapunov-Krasovskii functionals, the stability results of delayed [...] Read more.

This paper studies the stability of linear switched systems with time-varying delays and all unstable subsystems. According to the largest region function strategy, the state-dependent switching rule is designed. By bringing in integral inequality and multiple Lyapunov-Krasovskii functionals, the stability results of delayed switched systems with or without sliding motions under the designed state-dependent switching rule are derived for different assumptions on time delay. Several numerical examples are employed to show the effectiveness and superiority of the proposed results. Full article

(This article belongs to the Special Issue Advancement of Mathematical Methods in Feature Representation Learning for Artificial Intelligence, Data Mining and Robotics)

► Show Figures

Figure 1

12 pages, 2710 KiB

Open AccessArticle

An Improved Soft-YOLOX for Garbage Quantity Identification

by Junran Lin, Cuimei Yang, Yi Lu, Yuxing Cai, Hanjie Zhan and Zhen Zhang

Mathematics 2022, 10(15), 2650; https://doi.org/10.3390/math10152650 - 28 Jul 2022

Cited by 9 | Viewed by 1745

Abstract

Urban waterlogging is mainly caused by garbage clogging the sewer manhole covers. If the amount of garbage at a sewer manhole cover can be detected, together with an early warning signal when the amount is large enough, it will be of great significance [...] Read more.

Urban waterlogging is mainly caused by garbage clogging the sewer manhole covers. If the amount of garbage at a sewer manhole cover can be detected, together with an early warning signal when the amount is large enough, it will be of great significance in preventing urban waterlogging from occurring. Based on the YOLOX algorithm, this paper accomplishes identifying manhole covers and garbage and building a flood control system that can automatically recognize and monitor the accumulation of garbage. This system can also display the statistical results and send early warning information. During garbage identification, it can lead to inaccurate counting and a missed detection if the garbage is occluded. To reduce the occurrence of missed detections as much as possible and improve the performance of detection models, Soft-YOLOX, a method using a new detection model for counting, was used as it can prevent the occurrence of missed detections by reducing the scores of adjacent detection frames reasonably. The Soft-YOLOX improves the accuracy of garbage counting. Compared with the traditional YOLOX, the mAP value of Soft-YOLOX for garbage identification increased from 89.72% to 91.89%. Full article

(This article belongs to the Special Issue Advancement of Mathematical Methods in Feature Representation Learning for Artificial Intelligence, Data Mining and Robotics)

► Show Figures

Figure 1

18 pages, 1322 KiB

Open AccessArticle

Theme-Aware Semi-Supervised Image Aesthetic Quality Assessment

by Xiaodan Zhang, Xun Zhang, Yuan Xiao and Gang Liu

Mathematics 2022, 10(15), 2609; https://doi.org/10.3390/math10152609 - 26 Jul 2022

Cited by 3 | Viewed by 1455

Abstract

Image aesthetic quality assessment (IAQA) has aroused considerable interest in recent years and is widely used in various applications, such as image retrieval, album management, chat robot and social media. However, existing methods need an excessive amount of labeled data to train the [...] Read more.

Image aesthetic quality assessment (IAQA) has aroused considerable interest in recent years and is widely used in various applications, such as image retrieval, album management, chat robot and social media. However, existing methods need an excessive amount of labeled data to train the model. Collecting the enormous quantity of human scored training data is not always feasible due to a number of factors, such as the expensiveness of the labeling process and the difficulty in correctly classifying data. Previous studies have evaluated the aesthetic of a photo based only on image features, but have ignored the criterion bias associated with the themes. In this work, we present a new theme-aware semi-supervised image quality assessment method to address these difficulties. Specifically, the proposed method consists of two steps: a representation learning step and a label propagation step. In the representation learning step, we propose a robust theme-aware attention network (TAAN) to cope with the theme criterion bias problem. In the label propagation step, we use preliminary trained TAAN by step one to extract features and utilize the label propagation with a cumulative confidence (LPCC) algorithm to assign pseudo-labels to the unlabeled data. This enables use of both labeled and unlabeled data to train the TAAN model. To the best of our knowledge, this is the first time that a semi-supervised learning method to address image aesthetic assessment problems has been studied. We evaluate our approach on three benchmark datasets and show that it can achieve almost the same performance as a fully supervised learning method for a small number of samples. Furthermore, we show that our semi-supervised approach is robust to using varying quantities of labeled data. Full article

(This article belongs to the Special Issue Advancement of Mathematical Methods in Feature Representation Learning for Artificial Intelligence, Data Mining and Robotics)

► Show Figures

Figure 1

15 pages, 2175 KiB

Open AccessArticle

Face Recognition via Compact Second-Order Image Gradient Orientations

by He-Feng Yin, Xiao-Jun Wu, Cong Hu and Xiaoning Song

Mathematics 2022, 10(15), 2587; https://doi.org/10.3390/math10152587 - 25 Jul 2022

Cited by 1 | Viewed by 1100

Abstract

Conventional subspace learning approaches based on image gradient orientations only employ first-order gradient information, which may ignore second-order or higher-order gradient information. Moreover, recent researches on the human vision system (HVS) have uncovered that the neural image is a landscape or a surface [...] Read more.

Conventional subspace learning approaches based on image gradient orientations only employ first-order gradient information, which may ignore second-order or higher-order gradient information. Moreover, recent researches on the human vision system (HVS) have uncovered that the neural image is a landscape or a surface whose geometric properties can be captured through second-order gradient information. The second-order image gradient orientations (SOIGO) can mitigate the adverse effect of noise in face images. To reduce the redundancy of SOIGO, we propose compact SOIGO (CSOIGO) by applying linear complex principal component analysis (PCA) in SOIGO. To be more specific, the SOIGO of training data are firstly obtained. Then, linear complex PCA is applied to obtain features of reduced dimensionality. Combined with collaborative-representation-based classification (CRC) algorithm, the classification performance of CSOIGO is further enhanced. CSOIGO is evaluated under real-world disguise, synthesized occlusion, and mixed variations. Under the real disguise scenario, CSOIGO makes 2.67% and 1.09% improvement regarding accuracy when one and two neutral face images per subject are used as training samples, respectively. For the mixed variations, CSOIGO achieves a 0.86% improvement in terms of accuracy. These results indicate that the proposed method is superior to its competing approaches with few training samples, and even outperforms some prevailing deep-neural-network-based approaches. Full article

(This article belongs to the Special Issue Advancement of Mathematical Methods in Feature Representation Learning for Artificial Intelligence, Data Mining and Robotics)

► Show Figures

Figure 1

15 pages, 3034 KiB

Open AccessArticle

Decoupling Induction and Multi-Order Attention Drop-Out Gating Based Joint Motion Deblurring and Image Super-Resolution

by Yuezhong Chu, Xuefeng Zhang and Heng Liu

Mathematics 2022, 10(11), 1837; https://doi.org/10.3390/math10111837 - 26 May 2022

Cited by 2 | Viewed by 1505

Abstract

Resolution decrease and motion blur are two typical image degradation processes that are usually addressed by deep networks, specifically convolutional neural networks (CNNs). However, since real images are usually obtained through multiple degradations, the vast majority of current CNN methods that employ a [...] Read more.

Resolution decrease and motion blur are two typical image degradation processes that are usually addressed by deep networks, specifically convolutional neural networks (CNNs). However, since real images are usually obtained through multiple degradations, the vast majority of current CNN methods that employ a single degradation process inevitably need to be improved to account for multiple degradation effects. In this work, motivated by degradation decoupling and multiple-order attention drop-out gating, we propose a joint deep recovery model to efficiently address motion blur and resolution reduction simultaneously. Our degradation decoupling style improves the continence and the efficiency of model construction and training. Moreover, the proposed multi-order attention mechanism comprehensively and hierarchically extracts multiple attention features and fuses them properly by drop-out gating. The proposed approach is evaluated using diverse benchmark datasets including natural and synthetic images. The experimental results show that our proposed method can efficiently complete joint motion blur and image super-resolution (SR). Full article

(This article belongs to the Special Issue Advancement of Mathematical Methods in Feature Representation Learning for Artificial Intelligence, Data Mining and Robotics)

► Show Figures

Figure 1

12 pages, 339 KiB

Open AccessArticle

Geometric Metric Learning for Multi-Output Learning

by Huiping Gao and Zhongchen Ma

Mathematics 2022, 10(10), 1632; https://doi.org/10.3390/math10101632 - 11 May 2022

Cited by 1 | Viewed by 1186

Abstract

Due to its wide applications, multi-output learning that predicts multiple output values for a single input at the same time is becoming more and more attractive. As one of the most popular frameworks for dealing with multi-output learning, the performance of the k-nearest [...] Read more.

Due to its wide applications, multi-output learning that predicts multiple output values for a single input at the same time is becoming more and more attractive. As one of the most popular frameworks for dealing with multi-output learning, the performance of the k-nearest neighbor (kNN) algorithm mainly depends on the metric used to compute the distance between different instances. In this paper, we propose a novel cost-weighted geometric mean metric learning method for multi-output learning. Specifically, this method learns a geometric mean metric which can make the distance between the input embedding and its correct output be smaller than the distance between the input embedding and the outputs of its nearest neighbors. The learned geometric mean metric can discover output dependencies and move the instances with different outputs far away in the embedding space. In addition, our objective function has a closed solution, and thus the calculation speed is very fast. Compared with state-of-the-art methods, it is easier to explain and also has a faster calculation speed. Experiments conducted on two multi-output learning tasks (i.e., multi-label classification and multi-objective regression) have confirmed that our method provides better results than state-of-the-art methods. Full article

(This article belongs to the Special Issue Advancement of Mathematical Methods in Feature Representation Learning for Artificial Intelligence, Data Mining and Robotics)

► Show Figures

Figure 1

17 pages, 15528 KiB

Open AccessArticle

Blind Image Deblurring via a Novel Sparse Channel Prior

by Dayi Yang, Xiaojun Wu and Hefeng Yin

Mathematics 2022, 10(8), 1238; https://doi.org/10.3390/math10081238 - 09 Apr 2022

Cited by 5 | Viewed by 1597

Abstract

Blind image deblurring (BID) is a long-standing challenging problem in low-level image processing. To achieve visually pleasing results, it is of utmost importance to select good image priors. In this work, we develop the ratio of the dark channel prior (DCP) to the [...] Read more.

Blind image deblurring (BID) is a long-standing challenging problem in low-level image processing. To achieve visually pleasing results, it is of utmost importance to select good image priors. In this work, we develop the ratio of the dark channel prior (DCP) to the bright channel prior (BCP) as an image prior for solving the BID problem. Specifically, the above two channel priors obtained from RGB images are used to construct an innovative sparse channel prior at first, and then the learned prior is incorporated into the BID tasks. The proposed sparse channel prior enhances the sparsity of the DCP. At the same time, it also shows the inverse relationship between the DCP and BCP. We employ the auxiliary variable technique to integrate the proposed sparse prior information into the iterative restoration procedure. Extensive experiments on real and synthetic blurry sets show that the proposed algorithm is efficient and competitive compared with the state-of-the-art methods and that the proposed sparse channel prior for blind deblurring is effective. Full article

(This article belongs to the Special Issue Advancement of Mathematical Methods in Feature Representation Learning for Artificial Intelligence, Data Mining and Robotics)

► Show Figures

Figure 1

14 pages, 2363 KiB

Open AccessArticle

A RUL Prediction Method of Small Sample Equipment Based on DCNN-BiLSTM and Domain Adaptation

by Wenbai Chen, Weizhao Chen, Huixiang Liu, Yiqun Wang, Chunli Bi and Yu Gu

Mathematics 2022, 10(7), 1022; https://doi.org/10.3390/math10071022 - 23 Mar 2022

Cited by 16 | Viewed by 2166

Abstract

To solve the problem of low accuracy of remaining useful life (RUL) prediction caused by insufficient sample data of equipment under complex operating conditions, an RUL prediction method of small sample equipment based on a deep convolutional neural network—bidirectional long short-term memory network [...] Read more.

To solve the problem of low accuracy of remaining useful life (RUL) prediction caused by insufficient sample data of equipment under complex operating conditions, an RUL prediction method of small sample equipment based on a deep convolutional neural network—bidirectional long short-term memory network (DCNN-BiLSTM) and domain adaptation is proposed. Firstly, in order to extract the common features of the equipment under the condition of sufficient samples, a network model that combines the deep convolutional neural network (DCNN) and the bidirectional long short-term memory network (BiLSTM) was used to train the source domain and target domain data simultaneously. The Maximum Mean Discrepancy (MMD) was used to constrain the distribution difference and achieve adaptive matching and feature alignment between the target domain samples and the source domain samples. After obtaining the pre-trained model, fine-tuning was used to transfer the network structure and parameters of the pre-trained model to the target domain for training, perform network optimization and finally obtain an RUL prediction model that was more suitable for the target domain data. The method was validated on a simulation dataset of commercial modular aero-propulsion provided by NASA, and the experimental results show that the method improves the prediction accuracy and generalization ability of equipment RUL under cross-working conditions and small sample conditions. Full article

(This article belongs to the Special Issue Advancement of Mathematical Methods in Feature Representation Learning for Artificial Intelligence, Data Mining and Robotics)

► Show Figures

Figure 1

15 pages, 4207 KiB

Open AccessArticle

Second-Order Spatial-Temporal Correlation Filters for Visual Tracking

by Yufeng Yu, Long Chen, Haoyang He, Jianhui Liu, Weipeng Zhang and Guoxia Xu

Mathematics 2022, 10(5), 684; https://doi.org/10.3390/math10050684 - 22 Feb 2022

Cited by 4 | Viewed by 1629

Abstract

Discriminative correlation filters (DCFs) have been widely used in visual object tracking, but often suffer from two problems: the boundary effect and temporal filtering degradation. To deal with these issues, many DCF-based variants have been proposed and have improved the accuracy of visual [...] Read more.

Discriminative correlation filters (DCFs) have been widely used in visual object tracking, but often suffer from two problems: the boundary effect and temporal filtering degradation. To deal with these issues, many DCF-based variants have been proposed and have improved the accuracy of visual object tracking. However, these trackers only adopt first-order data-fitting information and have difficulty maintaining robust tracking in unconstrained scenarios, especially in the case of complex appearance variations. In this paper, by introducing a second-order data-fitting term to the DCF, we propose a second-order spatial–temporal correlation filter (SSCF) learning model. To be specific, the SSCF tracker both incorporates the first-order and second-order data-fitting terms into the DCF framework and makes the learned correlation filter more discriminative. Meanwhile, the spatial–temporal regularization was integrated to develop a robust model in tracking with complex appearance variations. Extensive experiments were conducted on the benchmarking databases CVPR2013, OTB100, DTB70, UAV123, and UAVDT-M. The results demonstrated that our SSCF can achieve competitive performance compared to the state-of-the-art trackers. When penalty parameter

λ

was set to

10^{- 5}

, our SSCF gained DP scores of 0.882, 0.868, 0.706, 0.676, and 0.928 on the CVPR2013, OTB100, DTB70, UAV123, and UAVDT-M databases, respectively. Full article

(This article belongs to the Special Issue Advancement of Mathematical Methods in Feature Representation Learning for Artificial Intelligence, Data Mining and Robotics)

► Show Figures

Figure 1

16 pages, 2415 KiB

Open AccessArticle

Cascaded Cross-Layer Fusion Network for Pedestrian Detection

by Zhifeng Ding, Zichen Gu, Yanpeng Sun and Xinguang Xiang

Mathematics 2022, 10(1), 139; https://doi.org/10.3390/math10010139 - 04 Jan 2022

Cited by 3 | Viewed by 1444

Abstract

The detection method based on anchor-free not only reduces the training cost of object detection, but also avoids the imbalance problem caused by an excessive number of anchors. However, these methods only pay attention to the impact of the detection head on the [...] Read more.

The detection method based on anchor-free not only reduces the training cost of object detection, but also avoids the imbalance problem caused by an excessive number of anchors. However, these methods only pay attention to the impact of the detection head on the detection performance, thus ignoring the impact of feature fusion on the detection performance. In this article, we take pedestrian detection as an example and propose a one-stage network Cascaded Cross-layer Fusion Network (CCFNet) based on anchor-free. It consists of Cascaded Cross-layer Fusion module (CCF) and novel detection head. Among them, CCF fully considers the distribution of high-level information and low-level information of feature maps under different stages in the network. First, the deep network is used to remove a large amount of noise in the shallow features, and finally, the high-level features are reused to obtain a more complete feature representation. Secondly, for the pedestrian detection task, a novel detection head is designed, which uses the global smooth map (GSMap) to provide global information for the center map to obtain a more accurate center map. Finally, we verified the feasibility of CCFNet on the Caltech and CityPersons datasets. Full article

(This article belongs to the Special Issue Advancement of Mathematical Methods in Feature Representation Learning for Artificial Intelligence, Data Mining and Robotics)

► Show Figures

Figure 1

11 pages, 3737 KiB

Open AccessArticle

A Soft-YoloV4 for High-Performance Head Detection and Counting

by Zhen Zhang, Shihao Xia, Yuxing Cai, Cuimei Yang and Shaoning Zeng

Mathematics 2021, 9(23), 3096; https://doi.org/10.3390/math9233096 - 30 Nov 2021

Cited by 14 | Viewed by 2786

Abstract

Blockage of pedestrians will cause inaccurate people counting, and people’s heads are easily blocked by each other in crowded occasions. To reduce missed detections as much as possible and improve the capability of the detection model, this paper proposes a new people counting [...] Read more.

Blockage of pedestrians will cause inaccurate people counting, and people’s heads are easily blocked by each other in crowded occasions. To reduce missed detections as much as possible and improve the capability of the detection model, this paper proposes a new people counting method, named Soft-YoloV4, by attenuating the score of adjacent detection frames to prevent the occurrence of missed detection. The proposed Soft-YoloV4 improves the accuracy of people counting and reduces the incorrect elimination of the detection frames when heads are blocked by each other. Compared with the state-of-the-art YoloV4, the AP value of the proposed head detection method is increased from 88.52 to 90.54%. The Soft-YoloV4 model has much higher robustness and a lower missed detection rate for head detection, and therefore it dramatically improves the accuracy of people counting. Full article

(This article belongs to the Special Issue Advancement of Mathematical Methods in Feature Representation Learning for Artificial Intelligence, Data Mining and Robotics)

► Show Figures

Figure 1

Review

Jump to: Editorial, Research

35 pages, 13595 KiB

Open AccessEditor’s ChoiceReview

Trends in Vehicle Re-Identification Past, Present, and Future: A Comprehensive Review

by Zakria, Jianhua Deng, Yang Hao, Muhammad Saddam Khokhar, Rajesh Kumar, Jingye Cai, Jay Kumar and Muhammad Umar Aftab

Mathematics 2021, 9(24), 3162; https://doi.org/10.3390/math9243162 - 08 Dec 2021

Cited by 18 | Viewed by 5862

Abstract

Vehicle Re-identification (re-id) over surveillance camera network with non-overlapping field of view is an exciting and challenging task in intelligent transportation systems (ITS). Due to its versatile applicability in metropolitan cities, it gained significant attention. Vehicle re-id matches targeted vehicle over non-overlapping views [...] Read more.

Vehicle Re-identification (re-id) over surveillance camera network with non-overlapping field of view is an exciting and challenging task in intelligent transportation systems (ITS). Due to its versatile applicability in metropolitan cities, it gained significant attention. Vehicle re-id matches targeted vehicle over non-overlapping views in multiple camera network. However, it becomes more difficult due to inter-class similarity, intra-class variability, viewpoint changes, and spatio-temporal uncertainty. In order to draw a detailed picture of vehicle re-id research, this paper gives a comprehensive description of the various vehicle re-id technologies, applicability, datasets, and a brief comparison of different methodologies. Our paper specifically focuses on vision-based vehicle re-id approaches, including vehicle appearance, license plate, and spatio-temporal characteristics. In addition, we explore the main challenges as well as a variety of applications in different domains. Lastly, a detailed comparison of current state-of-the-art methods performances over VeRi-776 and VehicleID datasets is summarized with future directions. We aim to facilitate future research by reviewing the work being done on vehicle re-id till to date. Full article

(This article belongs to the Special Issue Advancement of Mathematical Methods in Feature Representation Learning for Artificial Intelligence, Data Mining and Robotics)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Advancement of Mathematical Methods in Feature Representation Learning for Artificial Intelligence, Data Mining and Robotics

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Published Papers (34 papers)

Editorial

Research

Review

Further Information

Guidelines

MDPI Initiatives

Follow MDPI