Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
4.5
2.7
Journals
Applied Sciences
Special Issues
Selected Papers from FCPAE2022 and 4th International Conference on Artificial...
share announcement

Selected Papers from FCPAE2022 and 4th International Conference on Artificial Intelligence and Advanced Manufacturing (AIAM2022)

A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Applied Industrial Technologies".

Deadline for manuscript submissions: closed (31 December 2022) | Viewed by 43788

Special Issue Editors

Prof. Dr. Shengzong Zhou

E-Mail Website
Guest Editor
1. Federation of Chinese Professional Associations in Europe, Franz-Schubert-Weg 70, 61118 Bad Vilbel, Germany
2. Fujian Institute of Research on the Structure of Matter, Chinese Academy of Sciences, Fuzhou 350002, China
Interests: computer software and theory; software engineering and computer application technology research
Special Issues, Collections and Topics in MDPI journals
Prof. Dr. Jingsha He

E-Mail Website
Guest Editor
Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China
Interests: information security; wireless networks; blockchain technology; digital forensics
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

With the increased integration of advances in robotics and automaton, sensors and high-speed computing performance, the AI and manufacturing industry is entering a period of substantial innovation and change. Over the past few decades, AI has played a vital role in manufacturing industry, from big data to full automation. However, in the current complex, competitive, and dynamic external environment, manufacturing in many countries is facing huge bottlenecks and challenges for further development.

The FCPAE2022 and 4th International Conference on Artificial Intelligence and Advanced Manufacture (AIAM2022) aims to bring together researchers and scientists from artificial intelligence and advanced manufacturing and researchers from various application areas to discuss problems and solutions in the area, to identify new issues, and to shape future directions for research.

This Special Issue will focus on introducing a new generation of intelligent manufacturing systems and technologies and their applications, such as AI system, smart industrial internet of things, machine learning and AI for intelligent manufacturing, smart factory and logistics, manufacturing process and management, sustainable, flexible, virtual, digital manufacturing, and other related topics.

We invite you and your colleagues to submit a contribution in the form of an original scientific research article for this Special Issue. We encourage the submission to the thank presenters and speakers in advance for your attendance at this conference and look forward to a stimulating exchange.

The conference AIAM2022 will be held in Hamburg, Germany between October 7 and 9, 2022.

Prof. Dr. Shengzong Zhou
Prof. Dr. Jingsha He
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Applied Sciences is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Published Papers (25 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

17 pages, 1866 KiB  
Article
DEEDP: Document-Level Event Extraction Model Incorporating Dependency Paths
by Hui Li, Xin Zhao, Lin Yu, Yixin Zhao and Jie Zhang
Appl. Sci. 2023, 13(5), 2846; https://doi.org/10.3390/app13052846 - 22 Feb 2023
Cited by 1 | Viewed by 1753
Abstract
Document-level event extraction (DEE) aims at extracting event records from given documents. Existing DEE methods handle troublesome challenges by using multiple encoders and casting the task into a multi-step paradigm. However, most of the previous approaches ignore a missing feature by using mean [...] Read more.
Document-level event extraction (DEE) aims at extracting event records from given documents. Existing DEE methods handle troublesome challenges by using multiple encoders and casting the task into a multi-step paradigm. However, most of the previous approaches ignore a missing feature by using mean pooling or max pooling operations in different encoding stages and have not explicitly modeled the interdependency features between input tokens, and thus the long-distance problem cannot be solved effectively. In this study, we propose Document-level Event Extraction Model Incorporating Dependency Paths (DEEDP), which introduces a novel multi-granularity encoder framework to tackle the aforementioned problems. Specifically, we first designed a Transformer-based encoder, Transformer-M, by adding a Syntactic Feature Attention mechanism to the Transformer, which can capture more interdependency information between input tokens and help enhance the semantics for sentence-level representations of entities. We then stacked Transformer-M and Transformer to integrate sentence-level and document-level features; we thus obtained semantic enhanced document-aware representations for each entity and model long-distance dependencies between arguments. Experimental results on the benchmarks MUC-4 and ChFinAnn demonstrate that DEEDP achieves superior performance over the baselines, proving the effectiveness of our proposed methods. Full article
(This article belongs to the Special Issue Selected Papers from FCPAE2022 and 4th International Conference on Artificial Intelligence and Advanced Manufacturing (AIAM2022))
►▼ Show Figures

Figure 1

15 pages, 4244 KiB  
Article
Erasure Codes for Cold Data in Distributed Storage Systems
by Chao Yin, Zhiyuan Xu, Wei Li, Tongfang Li, Sihao Yuan and Yan Liu
Appl. Sci. 2023, 13(4), 2170; https://doi.org/10.3390/app13042170 - 08 Feb 2023
Viewed by 2000
Abstract
Replication and erasure codes are always used for storing large amounts of data in distributed storage systems. Erasure code technology can maximize the storage space of distributed storage systems as well as guaranteeing their availability and reliability, but it will decrease the performance [...] Read more.
Replication and erasure codes are always used for storing large amounts of data in distributed storage systems. Erasure code technology can maximize the storage space of distributed storage systems as well as guaranteeing their availability and reliability, but it will decrease the performance of the system when encoding and decoding. Since cold data do not require high real-time data availability, we focus on the cold data using erasure codes. We propose a new erasure code process named NewLib code based on the Liberation code, which designs the data alignment after stripping the encoding data. The NewLib code improves the performance of reading and writing in the distributed storage systems. At the same time, we developed a node scheduling scheme called N-Schedule, which divides the data nodes into multiple virtual nodes according to the storage space and computing power. The virtual nodes are dispersed into a hash ring by a consistent hash to construct a fully symmetric and decentralized hash ring in order to achieve uniform data distribution and task scheduling. The experimental results show our scheme can improve the performance of the system. Full article
(This article belongs to the Special Issue Selected Papers from FCPAE2022 and 4th International Conference on Artificial Intelligence and Advanced Manufacturing (AIAM2022))
►▼ Show Figures

Figure 1

12 pages, 1369 KiB  
Communication
Matrix Chain Multiplication and Equivalent Reduced-Order Parallel Calculation Method for a Robotic Arm
by Jiyang Yu, Dan Huang, Wenjie Li, Xianjie Wang and Xiaolong Shi
Appl. Sci. 2023, 13(3), 1931; https://doi.org/10.3390/app13031931 - 02 Feb 2023
Viewed by 1305
Abstract
Intelligence development has put forward increasing requirements of real-time planning and dynamic feedback in controlling robotic arms. It has become essential in engineering applications to complete the kinematics calculation of complex manipulators in real time. This paper proposes a matrix cascading multiplication equivalent [...] Read more.
Intelligence development has put forward increasing requirements of real-time planning and dynamic feedback in controlling robotic arms. It has become essential in engineering applications to complete the kinematics calculation of complex manipulators in real time. This paper proposes a matrix cascading multiplication equivalent reduced-order parallel computing method for the multiplication of homogeneous matrices in the process of forward and inverse kinematics solutions, which reduces the order of the matrix according to the distribution of zero vectors in the homogeneous matrix calculations. The method removes the unnecessary multiplication in joint homogeneous matrixes containing zero vectors. It obtains the optimal calculation order of the cascade matrix multiplication through dynamic planning searches, improving the efficiency of effective dot product calculation by parallel computation. Calculation processes and specific examples are presented in this paper. Compared with the previous algorithms, the proposed algorithm reduces the calculation cycle by 90%, effectively improving the real-time calculation efficiency in the complex control process. Full article
(This article belongs to the Special Issue Selected Papers from FCPAE2022 and 4th International Conference on Artificial Intelligence and Advanced Manufacturing (AIAM2022))
►▼ Show Figures

Figure 1

24 pages, 11145 KiB  
Article
Resonance Detection Method and Realization of Bearing Fault Signal Based on Kalman Filter and Spectrum Analysis
by Xinxin Chen and Shuli Sun
Appl. Sci. 2023, 13(3), 1472; https://doi.org/10.3390/app13031472 - 22 Jan 2023
Cited by 2 | Viewed by 1257
Abstract
The rolling bearing is an important part of mechanical equipment, and its performance significantly affects the quality and life of the mechanical equipment. This article uses the integrated fiber Bragg grating resonant structure sensor excited by periodic micro-shocks caused by micro faults to [...] Read more.
The rolling bearing is an important part of mechanical equipment, and its performance significantly affects the quality and life of the mechanical equipment. This article uses the integrated fiber Bragg grating resonant structure sensor excited by periodic micro-shocks caused by micro faults to realize the extraction of information relating to potential faults. Because the fault signal is weak and can easily be interfered with by ambient noise, in order to extract the effective signal, this article determines the autoregressive model of bearing vibration by the final prediction error criterion and the recursive least squares estimation algorithm. The augmented state space model is established based on the autoregressive model. A Kalman filter is used to reduce the noise interference, and then the reduction noisy signal is analyzed by power spectrum and improved autocorrelation envelope spectrum to realize the detection of bearing faults. Through data analysis and method comparison, the proposed improved autocorrelation envelope spectrum analysis can directly extract the bearing fault frequency, which is superior to other methods such as cepstral analysis. Full article
(This article belongs to the Special Issue Selected Papers from FCPAE2022 and 4th International Conference on Artificial Intelligence and Advanced Manufacturing (AIAM2022))
►▼ Show Figures

Figure 1

15 pages, 4531 KiB  
Article
Research on Speech Emotion Recognition Method Based A-CapsNet
by Yingmei Qi, Heming Huang and Huiyun Zhang
Appl. Sci. 2022, 12(24), 12983; https://doi.org/10.3390/app122412983 - 17 Dec 2022
Cited by 2 | Viewed by 1172
Abstract
Speech emotion recognition is a crucial work direction in speech recognition. To increase the performance of speech emotion detection, researchers have worked relentlessly to improve data augmentation, feature extraction, and pattern formation. To address the concerns of limited speech data resources and model [...] Read more.
Speech emotion recognition is a crucial work direction in speech recognition. To increase the performance of speech emotion detection, researchers have worked relentlessly to improve data augmentation, feature extraction, and pattern formation. To address the concerns of limited speech data resources and model training overfitting, A-CapsNet, a neural network model based on data augmentation methodologies, is proposed in this research. In order to solve the issue of data scarcity and achieve the goal of data augmentation, the noise from the Noisex-92 database is first combined with four different data division methods (emotion-independent random-division, emotion-dependent random-division, emotion-independent cross-validation and emotion-dependent cross-validation methods, abbreviated as EIRD, EDRD, EICV and EDCV, respectively). The database EMODB is then used to analyze and compare the performance of the model proposed in this paper under different signal-to-noise ratios, and the results show that the proposed model and data augmentation are effective. Full article
(This article belongs to the Special Issue Selected Papers from FCPAE2022 and 4th International Conference on Artificial Intelligence and Advanced Manufacturing (AIAM2022))
►▼ Show Figures

Figure 1

14 pages, 3042 KiB  
Article
Three-Phase Fault Arc Phase Selection Based on Global Attention Temporal Convolutional Neural Network
by Qiongfang Yu, Liang Zhao and Yi Yang
Appl. Sci. 2022, 12(21), 11280; https://doi.org/10.3390/app122111280 - 07 Nov 2022
Cited by 2 | Viewed by 1295
Abstract
For low-voltage three-phase systems, the deep fault arc features are difficult to extract, and the phase information has strong timing. This phenomenon leads to the problem of low accuracy of fault phase selection. This paper proposes a three-phase fault arc phase selection method [...] Read more.
For low-voltage three-phase systems, the deep fault arc features are difficult to extract, and the phase information has strong timing. This phenomenon leads to the problem of low accuracy of fault phase selection. This paper proposes a three-phase fault arc phase selection method based on a global temporal convolutional network. First, this method builds a low-voltage three-phase arc fault data acquisition platform and establishes a dataset. Second, the experimental data were decomposed by variational mode decomposition and analyzed in the time-frequency domain. The decomposed data are reconstructed and used as input to the model. Finally, in order to reduce the fault features lost during the causal convolution operation, the global attention mechanism is used to extract deep fault characterization to identify faults and their differences. The experimental results show that the accuracy of the three-phase arc fault arc phase selection of the model can reach 98.62%, and the accuracy of single-phase fault detection can reach 99.39%. This model can effectively extract three-phase arc fault and phase characteristics. This paper provides a new idea for series fault arc detection and three-phase fault arc phase selection research. Full article
(This article belongs to the Special Issue Selected Papers from FCPAE2022 and 4th International Conference on Artificial Intelligence and Advanced Manufacturing (AIAM2022))
►▼ Show Figures

Figure 1

12 pages, 1372 KiB  
Article
Learning Embedding for Signed Network in Social Media with Hierarchical Graph Pooling
by Jiawang Chen and Zhenqiang Wu
Appl. Sci. 2022, 12(19), 9795; https://doi.org/10.3390/app12199795 - 28 Sep 2022
Cited by 1 | Viewed by 1264
Abstract
Signed network embedding concentrates on learning fixed-length representations for nodes in signed networks with positive and negative links, which contributes to many downstream tasks in social media, such as link prediction. However, most signed network embedding approaches neglect hierarchical graph pooling in the [...] Read more.
Signed network embedding concentrates on learning fixed-length representations for nodes in signed networks with positive and negative links, which contributes to many downstream tasks in social media, such as link prediction. However, most signed network embedding approaches neglect hierarchical graph pooling in the networks, limiting the capacity to learn genuine signed graph topology. To overcome this limitation, this paper presents a unique deep learning-based Signed network embedding model with Hierarchical Graph Pooling (SHGP). To be more explicit, a hierarchical pooling mechanism has been developed to encode the high-level features of the networks. Moreover, a graph convolution layer is introduced to aggregate both positive and negative information from neighbor nodes, and the concatenation of two parts generates the final embedding of the nodes. Extensive experiments on three large real-world signed network datasets demonstrate the effectiveness and excellence of the proposed method. Full article
(This article belongs to the Special Issue Selected Papers from FCPAE2022 and 4th International Conference on Artificial Intelligence and Advanced Manufacturing (AIAM2022))
►▼ Show Figures

Figure 1

13 pages, 4259 KiB  
Article
RM-Line: A Ray-Model-Based Straight-Line Extraction Method for the Grid Map of Mobile Robot
by Haoxin Liu and Yonghui Zhang
Appl. Sci. 2022, 12(19), 9754; https://doi.org/10.3390/app12199754 - 28 Sep 2022
Cited by 1 | Viewed by 970
Abstract
This paper proposes a ray-model-based straight-line extraction method for the grid map of a mobile robot, call RM-Line. First, the edge map is obtained, with the help of the connectivity of the blank grid. Then, points containing complete line information, called active points, [...] Read more.
This paper proposes a ray-model-based straight-line extraction method for the grid map of a mobile robot, call RM-Line. First, the edge map is obtained, with the help of the connectivity of the blank grid. Then, points containing complete line information, called active points, are obtained using a screening model. Lastly, a ray model is designed to extraction line segments. We evaluate the algorithm using the number of lines, the average distance from grids to the lines, and the running time. Experiments show that the proposed algorithm has better performance on grid maps compared to the state-of-the-art algorithms. Full article
(This article belongs to the Special Issue Selected Papers from FCPAE2022 and 4th International Conference on Artificial Intelligence and Advanced Manufacturing (AIAM2022))
►▼ Show Figures

Figure 1

20 pages, 6160 KiB  
Article
Roll Eccentricity Signal Detection and Its Engineering Application Based on SFFT-IAA
by Zhe Yang, Ding Liu and Gang Zheng
Appl. Sci. 2022, 12(17), 8913; https://doi.org/10.3390/app12178913 - 05 Sep 2022
Cited by 2 | Viewed by 1629
Abstract
The roll eccentricity signal is a weak and complex periodic signal that is difficult to be identified. To improve the detection accuracy of the roll eccentricity signal and to compensate effectively, this study proposed a roll eccentricity signal detection method by combining the [...] Read more.
The roll eccentricity signal is a weak and complex periodic signal that is difficult to be identified. To improve the detection accuracy of the roll eccentricity signal and to compensate effectively, this study proposed a roll eccentricity signal detection method by combining the sparse fast Fourier transform (SFFT) and the iterative adaptive approach (IAA). The proposed method can rapidly determine the frequency range of the roll eccentricity signal by using the SFFT. Then, it divides the frequency range into several small frequency bands. In each small frequency band, the frequency, amplitude, and phase angle of each harmonic component of the roll eccentricity signal were estimated by using IAA. The simulation results show that the proposed method can find all frequency components, and the frequency estimation accuracy is higher than 99.88%. Finally, the engineering application of this method and the eccentricity compensation control were investigated. In engineering applications, the proposed method can reduce the thickness fluctuation of the finished strip by 89.2%, and the product quality is improved significantly. The simulation results and engineering experiments show that the proposed method has an excellent effect on detecting and compensating roll eccentricity signals. Full article
(This article belongs to the Special Issue Selected Papers from FCPAE2022 and 4th International Conference on Artificial Intelligence and Advanced Manufacturing (AIAM2022))
►▼ Show Figures

Figure 1

19 pages, 2357 KiB  
Article
Time Series Classification with Shapelet and Canonical Features
by Hai-Yang Liu, Zhen-Zhuo Gao, Zhi-Hai Wang and Yun-Hao Deng
Appl. Sci. 2022, 12(17), 8685; https://doi.org/10.3390/app12178685 - 30 Aug 2022
Cited by 3 | Viewed by 2011
Abstract
Shapelet-based time series classification methods are widely adopted models for time series classification tasks. However, the high computational cost greatly limits the practicability of the Shapelet-based methods. What is more, traditional Shapelet can only describe the overall shape characteristics of subsequences under the [...] Read more.
Shapelet-based time series classification methods are widely adopted models for time series classification tasks. However, the high computational cost greatly limits the practicability of the Shapelet-based methods. What is more, traditional Shapelet can only describe the overall shape characteristics of subsequences under the Euclidean distance metric, so it is vulnerable to noise. Other than Shapelet, there are other types of discriminative information contained in the subsequences. To deal with the aforementioned problems, an accurate and efficient time series classification algorithm, named Shapelet with Canonical Time Series Features, is proposed in this paper. The proposed algorithm is based on the following three key strategies: (1) randomly selecting Shapelet and limiting the scope of Shapelet to improve efficiency; (2) embedding multiple canonical time series features in Shapelet to improve the adaptability of the algorithm to different classification problems and make up for the accuracy loss caused by the random selection of Shapelet; and (3) building a random forest classifier based on the new feature representations to ensure the generalization ability of the algorithm. Experimental results on 112 UCR time series datasets show that the proposed algorithm is more accurate than the STC algorithm which is based on Shapelet exact search and the Shapelet transform technique, as well as many other types of state-of-the-art time series classification algorithms. Moreover, extensive experimental comparisons verify the significant advantages of the proposed algorithm in terms of efficiency. Full article
(This article belongs to the Special Issue Selected Papers from FCPAE2022 and 4th International Conference on Artificial Intelligence and Advanced Manufacturing (AIAM2022))
►▼ Show Figures

Figure 1

13 pages, 4830 KiB  
Article
Shear Sonic Prediction Based on DELM Optimized by Improved Sparrow Search Algorithm
by Lei Qiao, Zhining Jia, You Cui, Kun Xiao and Haonan Su
Appl. Sci. 2022, 12(16), 8260; https://doi.org/10.3390/app12168260 - 18 Aug 2022
Cited by 5 | Viewed by 1267
Abstract
In the geophysical exploration field, the sonic log (DT) and shear sonic log (DTS) are frequently used as quick and affordable procedures for reservoir evaluation. Due to the high acquisition costs, DTS is only accessible in a few wells within an oil/gas field. [...] Read more.
In the geophysical exploration field, the sonic log (DT) and shear sonic log (DTS) are frequently used as quick and affordable procedures for reservoir evaluation. Due to the high acquisition costs, DTS is only accessible in a few wells within an oil/gas field. Numerous attempts have been made to establish a precise relationship between DTS and other petrophysical data. In this study, a method based on the deep extreme learning machine optimized by the improved sparrow search algorithm (ISSA-DELM) is proposed to improve the accuracy and stability of the DTS prediction. Firstly, the deep extreme learning machine (DELM) model is constructed by combining the extreme learning machine and the autoencoder algorithm. Secondly, aimed at the defects of the sparrow search algorithm (SSA), an improved sparrow search algorithm (ISSA) with the firefly search disturbance is proposed by merging the iterative strategy of the firefly algorithm and applied to optimize the initial input weights of the DELM. Finally, the ISSA-DELM is applied to the prediction of the DTS in a block of the Ordos Basin in China. The quantitative prediction results show that the RMSE, MAE, and R-square predicted by the ISSA-DELM model are 6.1255, 4.1369, and 0.9916, respectively. The comprehensive performance is better than the ELM, the DELM, and the DELM optimized by the optimization algorithms, such as the genetic algorithm (GA), the particle swarm optimization (PSO), and the SSA. Therefore, it can be concluded that the method provides an effective method for missing DTS estimation. Full article
(This article belongs to the Special Issue Selected Papers from FCPAE2022 and 4th International Conference on Artificial Intelligence and Advanced Manufacturing (AIAM2022))
►▼ Show Figures

Figure 1

10 pages, 2013 KiB  
Article
Multi-Modal Sentiment Analysis Based on Interactive Attention Mechanism
by Jun Wu, Tianliang Zhu, Xinli Zheng and Chunzhi Wang
Appl. Sci. 2022, 12(16), 8174; https://doi.org/10.3390/app12168174 - 16 Aug 2022
Cited by 1 | Viewed by 1924
Abstract
In recent years, multi-modal sentiment analysis has become more and more popular in the field of natural language processing. Multi-modal sentiment analysis mainly concentrates on text, image and audio information. Previous work based on BERT utilizes only text representation to fine-tune BERT, while [...] Read more.
In recent years, multi-modal sentiment analysis has become more and more popular in the field of natural language processing. Multi-modal sentiment analysis mainly concentrates on text, image and audio information. Previous work based on BERT utilizes only text representation to fine-tune BERT, while ignoring the importance of nonverbal information. Most current research methods are fine-tuning models based on BERT that do not optimize BERT’s internal structure. Therefore, in this paper, we propose an optimized BERT model that is composed of three modules: the Hierarchical Multi-head Self Attention module realizes the hierarchical extraction process of the features; the Gate Channel module replaces BERT’s original Feed-Forward layer to realize information filtering; the tensor fusion model based on self-attention mechanism utilized to implement the fusion process of different modal features. In CMU-MOSI, a public mult-imodal sentiment analysis dataset, the accuracy and F1-Score were improved by 0.44% and 0.46% compared with the original BERT model using custom fusion. Compared with traditional models, such as LSTM and Transformer, they are improved to a certain extent. Full article
(This article belongs to the Special Issue Selected Papers from FCPAE2022 and 4th International Conference on Artificial Intelligence and Advanced Manufacturing (AIAM2022))
►▼ Show Figures

Figure 1

12 pages, 4734 KiB  
Article
Real-Time Object Tracking Algorithm Based on Siamese Network
by Wenjun Zhao, Miaolei Deng, Cong Cheng and Dexian Zhang
Appl. Sci. 2022, 12(14), 7338; https://doi.org/10.3390/app12147338 - 21 Jul 2022
Cited by 2 | Viewed by 1563
Abstract
Object tracking is aimed at tracking a given target that is only specified in the first frame. Due to the rapid movement and the interference of cluttered backgrounds, object tracking is a significant challenging issue in computer vision. This research put forward an [...] Read more.
Object tracking is aimed at tracking a given target that is only specified in the first frame. Due to the rapid movement and the interference of cluttered backgrounds, object tracking is a significant challenging issue in computer vision. This research put forward an innovative feature pyramid and optical flow estimation based on the Siamese network for object tracking, which is called SiamFP. The SiamFP jointly trains the optical flow and the tracking task under the Siamese network framework. We employ the optical flow network based on the pyramid correlation mapping to evaluate the movement information of the target in two contiguous frames, to increase the accuracy of the feature representation. Simultaneously, we adopt spatial attention as well as channel attention to effectively restrain the ambient noise, stress the target area, and better extract the features of the given object, so that the tracking algorithm has a higher success rate. The proposed SiamFP obtains state-of-the-art performance on OTB50, OTB2015, and VOT2016 benchmarks while exhibiting better real-time and robustness. Full article
(This article belongs to the Special Issue Selected Papers from FCPAE2022 and 4th International Conference on Artificial Intelligence and Advanced Manufacturing (AIAM2022))
►▼ Show Figures

Figure 1

13 pages, 2180 KiB  
Article
Research on PM2.5 Concentration Prediction Based on the CE-AGA-LSTM Model
by Xiaoxuan Wu, Chen Zhang, Jun Zhu and Xin Zhang
Appl. Sci. 2022, 12(14), 7009; https://doi.org/10.3390/app12147009 - 11 Jul 2022
Cited by 7 | Viewed by 1377
Abstract
The PM2.5 index is an important basis for measuring the degree of air pollution. The accurate prediction of PM2.5 concentration has an important guiding role in air pollution prevention and control. The Pearson Correlation Coefficient (PCC) is a common index used to mine [...] Read more.
The PM2.5 index is an important basis for measuring the degree of air pollution. The accurate prediction of PM2.5 concentration has an important guiding role in air pollution prevention and control. The Pearson Correlation Coefficient (PCC) is a common index used to mine the correlation between meteorological factors and other air pollutants. However, this index cannot be used to mine non-linear correlations, nor can it quantitatively analyze the weight of each related attribute. In order to accurately explore the correlation between meteorological factors and other air pollutants and to achieve an accurate prediction of PM2.5 concentration, this paper proposes a short- and long-time memory (LSTM) network prediction model based on Copula entropy (CE) and the adaptive genetic algorithm (AGA). By calculating CE, the correlation between multiple meteorological factors and various atmospheric pollutants and PM2.5 was analyzed. The correlation of influencing factors was sorted according to the size of the correlation coefficients. The contribution rate of meteorological factors and atmospheric pollutants to PM2.5 concentration was determined, used as the weight of each influencing factor and predicted as the input data of the prediction model. In this paper, a long- and short-term memory network (LSTM) suitable for time series data was selected as the prediction model, while the selection of model parameters was taken into account, and the relevant parameters were sought by an adaptive genetic algorithm (AGA). The air pollutant data and meteorological data of Beijing from 1 January 2016 to 31 December 2016 were selected, and MAE and RMSE were used as evaluation indexes. By comparing the experimental results of the CE-AGA-LSTM with those of other eight prediction models (LR, SVM, RF, ARMA, ST-LSTM, LSTM, CE-LSTM and CE-RNN), we found that among the models, the CE-AGA-LSTM model provided the lowest MAE and RMSE values, i.e., 14.5 and 21.88, respectively. At the same time, the loss rate and accuracy of the CE-AGA-LSTM model were evaluated, and the experimental results verified the validity of the model. Full article
(This article belongs to the Special Issue Selected Papers from FCPAE2022 and 4th International Conference on Artificial Intelligence and Advanced Manufacturing (AIAM2022))
►▼ Show Figures

Figure 1

18 pages, 8380 KiB  
Article
An Image-Encryption Algorithm Based on Stage-Merging Bit Scrambling
by Zhanfang Chen, Ya Yang and Xiaoming Jiang
Appl. Sci. 2022, 12(14), 6972; https://doi.org/10.3390/app12146972 - 09 Jul 2022
Viewed by 1194
Abstract
At present, the existing single-pixel position-scrambling technique is not sensitive to the chaotic sequence used, and adjacent-pixel position scrambling has difficulty ensuring a good scrambling effect and speed at the same time. In this paper, a stage-merging scrambling algorithm is proposed, which combines [...] Read more.
At present, the existing single-pixel position-scrambling technique is not sensitive to the chaotic sequence used, and adjacent-pixel position scrambling has difficulty ensuring a good scrambling effect and speed at the same time. In this paper, a stage-merging scrambling algorithm is proposed, which combines the two-stage scrambling process and can complete the dual scrambling of pixel position and pixel value at the same time. It not only improves the scrambling speed, but also greatly improves the scrambling effects. Then, a complete image encryption and decryption scheme was designed based on stage-merging bit scrambling combined with DNA coding. Security analysis shows that the algorithm can resist various means of attack such as exhaustive attack and differential attack. The research in this paper extends the existing bit-scrambling algorithms and is suitable for practical applications. Full article
(This article belongs to the Special Issue Selected Papers from FCPAE2022 and 4th International Conference on Artificial Intelligence and Advanced Manufacturing (AIAM2022))
►▼ Show Figures

Figure 1

12 pages, 2629 KiB  
Article
Data Privacy Security Mechanism of Industrial Internet of Things Based on Block Chain
by Yinggang Xie, Yuxin Li and Yunbin Ma
Appl. Sci. 2022, 12(14), 6859; https://doi.org/10.3390/app12146859 - 06 Jul 2022
Cited by 6 | Viewed by 1609
Abstract
In order to solve the problem that data of the industrial Internet of Things (IIoT) is easily tampered with and therefore, the authenticity of data may be questioned, a data-privacy security mechanism of the IIoT based on blockchain is proposed. At the same [...] Read more.
In order to solve the problem that data of the industrial Internet of Things (IIoT) is easily tampered with and therefore, the authenticity of data may be questioned, a data-privacy security mechanism of the IIoT based on blockchain is proposed. At the same time, to solve the problem of master node selection and low efficiency in the practical Byzantine fault tolerance (PBFT) algorithm, a reward mechanism based on node behavior is introduced and an improved PBFT algorithm is proposed. The improved PBFT algorithm is more efficient, in line with the application scenarios of the IIoT. Comparative analysis results showed that the proposed blockchain-based data-privacy security mechanism of the IIoT is superior to other models in terms of consensus efficiency, throughput, and block generation speed. Full article
(This article belongs to the Special Issue Selected Papers from FCPAE2022 and 4th International Conference on Artificial Intelligence and Advanced Manufacturing (AIAM2022))
►▼ Show Figures

Figure 1

14 pages, 2399 KiB  
Article
Grammatically Derived Factual Relation Augmented Neural Machine Translation
by Fuxue Li, Jingbo Zhu, Hong Yan and Zhen Zhang
Appl. Sci. 2022, 12(13), 6518; https://doi.org/10.3390/app12136518 - 27 Jun 2022
Cited by 4 | Viewed by 1259
Abstract
Transformer-based neural machine translation (NMT) has achieved state-of-the-art performance in the NMT paradigm. This method assumes that the model can automatically learn linguistic knowledge (e.g., grammar and syntax) from the parallel corpus via an attention network. However, the attention network cannot capture the [...] Read more.
Transformer-based neural machine translation (NMT) has achieved state-of-the-art performance in the NMT paradigm. This method assumes that the model can automatically learn linguistic knowledge (e.g., grammar and syntax) from the parallel corpus via an attention network. However, the attention network cannot capture the deep internal structure of a sentence. Therefore, it is natural to introduce some prior knowledge to guide the model. In this paper, factual relation information is introduced into NMT as prior knowledge, and a novel approach named Factual Relation Augmented (FRA) is proposed to guide the decoder in Transformer-based NMT. In the encoding procedure, a factual relation mask matrix is constructed to generate the factual relation representation for the source sentence, while in the decoding procedure an effective method is proposed to incorporate the factual relation representation and the original representation of the source sentence into the decoder. Positive results obtained in several different translation tasks indicate the effectiveness of the proposed approach. Full article
(This article belongs to the Special Issue Selected Papers from FCPAE2022 and 4th International Conference on Artificial Intelligence and Advanced Manufacturing (AIAM2022))
►▼ Show Figures

Figure 1

18 pages, 8156 KiB  
Article
Visual Scratch Defect Detection System of Aluminum Flat Tube Based on Cubic Bezier Curve Fitting Using Linear Scan Camera
by Jianbin Tang, Songxiao Cao, Jiaze Chen, Tao Song, Zhipeng Xu, Qiaojun Zhou and Qing Jiang
Appl. Sci. 2022, 12(12), 6049; https://doi.org/10.3390/app12126049 - 14 Jun 2022
Cited by 1 | Viewed by 1683
Abstract
This paper presents a scratch detection system based on a cubic Bezier curve fitting using a linear scan camera. The objective was to detect the scratch defects of an aluminum flat tube stably in real-time under complex uncertain background noise. To that end, [...] Read more.
This paper presents a scratch detection system based on a cubic Bezier curve fitting using a linear scan camera. The objective was to detect the scratch defects of an aluminum flat tube stably in real-time under complex uncertain background noise. To that end, according to the features of the input image of the linear scan camera and the scratch defects, the proposed method first segmented the input image to ten equal sections in a longitudinal direction, and for every section, OTSU thresholding and morphological filtering were used to reduce the background noise. After the image preprocessing, every section image was projected along a vertical direction to form a vertical histogram. After that, for each point of every vertical histogram, a novel curve fitting method based on the Monte Carlo method was employed to calculate the best fitted Bezier curve. All the curvatures of the middle point of the best fitted Bezier curves then formed a curvature curve, and the scratches were located by finding the peaks of the curvature curve. Next, the result of the ten sections were fused to find the final positions of the scratches. The experimental results based on the linear scan camera that captured the image of flat tubes on a moving speed of 2m/s showed that the proposed method can detect the scratch defects under complex background noise with a high success rate in real-time. Full article
(This article belongs to the Special Issue Selected Papers from FCPAE2022 and 4th International Conference on Artificial Intelligence and Advanced Manufacturing (AIAM2022))
►▼ Show Figures

Figure 1

11 pages, 2307 KiB  
Article
A Spike Neural Network Model for Lateral Suppression of Spike-Timing-Dependent Plasticity with Adaptive Threshold
by Xueyan Zhong and Hongbing Pan
Appl. Sci. 2022, 12(12), 5980; https://doi.org/10.3390/app12125980 - 12 Jun 2022
Cited by 4 | Viewed by 1672
Abstract
Aiming at the practical constraints of high resource occupancy and complex calculations in the existing Spike Neural Network (SNN) image classification model, in order to seek a more lightweight and efficient machine vision solution, this paper proposes an adaptive threshold Spike Neural Network [...] Read more.
Aiming at the practical constraints of high resource occupancy and complex calculations in the existing Spike Neural Network (SNN) image classification model, in order to seek a more lightweight and efficient machine vision solution, this paper proposes an adaptive threshold Spike Neural Network (SNN) model of lateral inhibition of Spike-Timing-Dependent Plasticity (STDP). The conversion from grayscale image to pulse sequence is completed by convolution normalization and first pulse time coding. The network self-classification is realized by combining the classical Spike-Timing-Dependent Plasticity algorithm (STDP) and lateral suppression algorithm. The occurrence of overfitting is effectively suppressed by introducing an adaptive threshold. The experimental results on the MNIST data set show that compared with the traditional SNN classification model, the complexity of the weight update algorithm is reduced from O(n2) to O(1), and the accuracy rate can still remain stable at about 96%. The provided model is conducive to the migration of software algorithms to the bottom layer of the hardware platform, and can provide a reference for the realization of edge computing solutions for small intelligent hardware terminals with high efficiency and low power consumption. Full article
(This article belongs to the Special Issue Selected Papers from FCPAE2022 and 4th International Conference on Artificial Intelligence and Advanced Manufacturing (AIAM2022))
►▼ Show Figures

Figure 1

24 pages, 7217 KiB  
Article
Multi-Objective Optimization Using Cooperative Garden Balsam Optimization with Multiple Populations
by Xiaohui Wang and Shengpu Li
Appl. Sci. 2022, 12(11), 5524; https://doi.org/10.3390/app12115524 - 29 May 2022
Cited by 1 | Viewed by 1347
Abstract
Traditional multi-objective evolutionary algorithms (MOEAs) consider multiple objectives as a whole when solving multi-objective optimization problems (MOPs). In this paper, the hybridization of garden balsam optimization (GBO) is presented to solve multi-objective optimization, applying multiple populations for multiple objectives individually. Moreover, in order [...] Read more.
Traditional multi-objective evolutionary algorithms (MOEAs) consider multiple objectives as a whole when solving multi-objective optimization problems (MOPs). In this paper, the hybridization of garden balsam optimization (GBO) is presented to solve multi-objective optimization, applying multiple populations for multiple objectives individually. Moreover, in order to improve the diversity of the solutions, both crowding distance computations and epsilon dominance relations are adopted when updating the archive. Furthermore, an efficient selection procedure called co-evolutionary multi-swarm garden balsam optimization (CMGBO) is proposed to ensure the convergence of well-diversified Pareto regions. The performance of the used algorithm is validated on 12 test functions. The algorithm is employed to solve four real-world problems in engineering. The achieved consequences corroborate the advantage of the proposed algorithm with regard to convergence and diversity. Full article
(This article belongs to the Special Issue Selected Papers from FCPAE2022 and 4th International Conference on Artificial Intelligence and Advanced Manufacturing (AIAM2022))
►▼ Show Figures

Figure 1

10 pages, 2136 KiB  
Article
Scene Adaptive Segmentation for Crowd Counting in Population Heterogeneous Distribution
by Hui Gao, Miaolei Deng, Wenjun Zhao and Dexian Zhang
Appl. Sci. 2022, 12(10), 5183; https://doi.org/10.3390/app12105183 - 20 May 2022
Viewed by 1510
Abstract
Crowd counting is an important part of crowd analysis and has been widely applied in the field of public safety and commercial management. Although researchers have proposed many crowd counting methods, there is little research on non-uniform population distribution. In this research, a [...] Read more.
Crowd counting is an important part of crowd analysis and has been widely applied in the field of public safety and commercial management. Although researchers have proposed many crowd counting methods, there is little research on non-uniform population distribution. In this research, a new scene adaptive segmentation network (SASNet) is proposed that can focus on crowd area to estimate accurately crowd density in population heterogeneous distribution. First, an image segmentation module is designed that can adaptive horizontal segment an image according to different density levels, and then obtains a close-up view image and a distant view image. Second, a dual branches network based on convolution neural network (CNN) is exploited that contains a distant view network (DVNet) and a close-up view network (CVNet), so as to extract different scales of image features and then generate density maps by each branch, respectively, so that the crowd counting module has robustness on different scales of target. Finally, a comparative experiment on three well-known crowd counting datasets shows that SASNet achieved stabilized performance and robustness in population heterogeneous distribution. Full article
(This article belongs to the Special Issue Selected Papers from FCPAE2022 and 4th International Conference on Artificial Intelligence and Advanced Manufacturing (AIAM2022))
►▼ Show Figures

Figure 1

15 pages, 3248 KiB  
Article
Research on a mmWave Beam-Prediction Algorithm with Situational Awareness Based on Deep Learning for Intelligent Transportation Systems
by Jia Liang, Kaiming Li, Qun Zhang and Zisen Qi
Appl. Sci. 2022, 12(9), 4779; https://doi.org/10.3390/app12094779 - 09 May 2022
Cited by 2 | Viewed by 1474
Abstract
Simply speaking, automatic driving requires the calculation of a large amount of traffic data and, finally, the obtainment of the optimal driving route and speed. However, the key technical difficulty is the obtainment of data; thus, radar has become an indispensable hardware for [...] Read more.
Simply speaking, automatic driving requires the calculation of a large amount of traffic data and, finally, the obtainment of the optimal driving route and speed. However, the key technical difficulty is the obtainment of data; thus, radar has become an indispensable hardware for automatic driving. Compared to the optical and infrared radar, millimeter-wave radar is not affected by the shape and color of the target, and it is not affected by the atmospheric turbulence, compared to ultrasonic, and so it has a stable detection performance and good environmental adaptability. It is little affected by changes in the weather, and the external environment, rain, snow, dust, and sunshine have no interference in it. The Doppler frequency shift is large, and the accuracy of the relative velocity measurement is improved. However, one challenge for vehicles in fast environments is millimeter-wave-based communication. Because of the short wavelength of the millimeter wave and the high path and penetration losses, the beamforming technology of a large-scale antenna array plays a key role in the construction and maintenance of millimeter-wave communication links. Millimeter waves have wide channel bandwidths, unique channel characteristics, and hardware limitations, and so there are many challenges in the direct use of beamforming technology in millimeter-wave communication. Traditional beam training cannot meet the requirements of low overhead and low delay. This paper, in order to obtain beam information, introduces the context-awareness module to the deep-learning net, which is derived from past observation data. This paper establishes a model that contains the receiver and the surrounding vehicles to perceive the environment. Then, a long short-term memory (LSTM) neural network is used to foresee the acquired power, which is quantized by several beam powers. According to the conclusion, the prediction accuracy is greatly increased, and the model could yield throughput with almost zero overhead and little performance loss. Full article
(This article belongs to the Special Issue Selected Papers from FCPAE2022 and 4th International Conference on Artificial Intelligence and Advanced Manufacturing (AIAM2022))
►▼ Show Figures

Figure 1

15 pages, 3779 KiB  
Article
An Information-Theoretic Approach for Detecting Community Structure Based on Network Representation
by Yinan Chen, Chuanpeng Wang and Dong Li
Appl. Sci. 2022, 12(9), 4203; https://doi.org/10.3390/app12094203 - 21 Apr 2022
Viewed by 1245
Abstract
Community structure is a network characteristic where nodes can be naturally divided into densely connected groups. Community structures are ubiquitous in social, biological, and technological networks. Revealing community structure in the network helps in the understanding of the topological associations and interactions of [...] Read more.
Community structure is a network characteristic where nodes can be naturally divided into densely connected groups. Community structures are ubiquitous in social, biological, and technological networks. Revealing community structure in the network helps in the understanding of the topological associations and interactions of elements in the network, as well as helping to mine their potential information. However, this has been proven to be a difficult challenge. On the one hand, this is because there is no unified definition of the quality of a community; on the other hand, due to the complexity of the network, it is impossible to traverse all the possibilities of community partitions to find the best one. Aiming at performing high-accuracy community detection, an information-theoretic approach AMI-NRL was proposed. The approach first constructs a community evolution process based on the representation of the target network, then finds the most stable community structure during the evolution using an average-mutual-information-based criterion. The experiments show that the approach can effectively detect community structures on real-world datasets and synthetic datasets. Full article
(This article belongs to the Special Issue Selected Papers from FCPAE2022 and 4th International Conference on Artificial Intelligence and Advanced Manufacturing (AIAM2022))
►▼ Show Figures

Figure 1

15 pages, 532 KiB  
Article
Mechanism and Algorithm for Stable Trading Matching between Coal Mining and Power Generation Companies in China
by Ruyi Shi, Zheng Li, Zhenpeng Tang and Di Wang
Appl. Sci. 2022, 12(8), 3919; https://doi.org/10.3390/app12083919 - 13 Apr 2022
Cited by 1 | Viewed by 1276
Abstract
This paper is concerned with stable trading between the coal mining and power generation companies in China. Under the current marketized coal and planned electricity price systems, barriers to price shifting between coal and electricity are created and conflicts between the two sectors [...] Read more.
This paper is concerned with stable trading between the coal mining and power generation companies in China. Under the current marketized coal and planned electricity price systems, barriers to price shifting between coal and electricity are created and conflicts between the two sectors are aggravated. The stable trading matching between coal mining and power generation companies is not only an effective means to resolve the conflict in the coal trading market, but also a ballast stone for price stabilization and supply guarantees in coal trading. Based on the two-sided matching theory, this paper starts from the micro market preference and matching willingness of coal mining and power generation companies, puts forward the conceptual framework of the pairwise stable matching of both sides, innovates a mechanism for trading between coal mining and power generation companies, and designs a stable trading matching algorithm. The algorithm has certain theoretical innovation significance from the matching problem of non-separable commodities to that of separable commodities considering the trading volume between coal mining and power generation companies. Furthermore, it is a complement and perfection of the existing coal–power trading platform in its transaction mechanism and trading function. The results reveal that the trading relations between coal mining and power generation companies under the stable matching mechanism are resistant to disintegration and that the pairwise stable matching result is sensitive. Full article
(This article belongs to the Special Issue Selected Papers from FCPAE2022 and 4th International Conference on Artificial Intelligence and Advanced Manufacturing (AIAM2022))
►▼ Show Figures

Figure 1

10 pages, 1177 KiB  
Article
Blockchain-Based Internet of Things Access Control Technology in Intelligent Manufacturing
by Peng Zhai, Jingsha He and Nafei Zhu
Appl. Sci. 2022, 12(7), 3692; https://doi.org/10.3390/app12073692 - 06 Apr 2022
Cited by 9 | Viewed by 2255
Abstract
The integration of information systems and physical systems is the development trend of today’s manufacturing industry. Intelligent manufacturing is a new model of manufacturing, based on advanced manufacturing technology with human–machine–material collaboration. Internet of Things technology is the core technology of intelligent manufacturing, [...] Read more.
The integration of information systems and physical systems is the development trend of today’s manufacturing industry. Intelligent manufacturing is a new model of manufacturing, based on advanced manufacturing technology with human–machine–material collaboration. Internet of Things technology is the core technology of intelligent manufacturing, and access control technology is one of the main measures to ensure the security of the IoT. In view of the problem that the existing IoT access control model does not support distributed and fine-grained dynamic access control, this paper uses the characteristics of blockchain, such as decentralization and non-tampering, combined with the attribute-based access control (ABAC) method, to propose a distributed access control method, applicable to the IoT environment in the process of intelligent manufacturing. This paper describes a fine-grained access control policy by defining the access control attribute values in a formal language, which supports complex logic operations in the policy and enhances the expressiveness of the model. Distributed access control decision making, using smart contracts for blockchain, improves the decision-making efficiency of the access control model, increases the post-facto audit of the access control behavior, and improves the overall security of IoT data protection. The paper concludes with proof of security and a performance analysis, and the experimental results, such as storage and computing overheads, show that this method can provide fine-grained, dynamic, and distributed access control for devices in intelligent manufacturing, ensuring the security and reliability of access control for IoT devices. Full article
(This article belongs to the Special Issue Selected Papers from FCPAE2022 and 4th International Conference on Artificial Intelligence and Advanced Manufacturing (AIAM2022))
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-25
Back to TopTop