Symmetry

Research

29 pages, 2659 KiB

Open AccessArticle

Lifelong Machine Learning Architecture for Classification

by Xianbin Hong, Sheng-Uei Guan, Ka Lok Man and Prudence W. H. Wong

Symmetry 2020, 12(5), 852; https://doi.org/10.3390/sym12050852 - 22 May 2020

Cited by 10 | Viewed by 4496

Benefiting from the rapid development of big data and high-performance computing, more data is available and more tasks could be solved by machine learning now. Even so, it is still difficult to maximum the power of big data due to each dataset is [...] Read more.

Benefiting from the rapid development of big data and high-performance computing, more data is available and more tasks could be solved by machine learning now. Even so, it is still difficult to maximum the power of big data due to each dataset is isolated with others. Although open source datasets are available, algorithms’ performance is asymmetric with the data volume. Hence, the AI community wishes to raise a symmetric continuous learning architecture which can automatically learn and adapt to different tasks. Such a learning architecture also is commonly called as lifelong machine learning (LML). This learning paradigm could manage the learning process and accumulate meta-knowledge by itself during learning different tasks. The meta-knowledge is shared among all tasks symmetrically to help them to improve performance. With the growth of meta-knowledge, the performance of each task is expected to be better and better. In order to demonstrate the application of lifelong machine learning, this paper proposed a novel and symmetric lifelong learning approach for sentiment classification as an example to show how it adapts different domains and keeps efficiency meanwhile. Full article

(This article belongs to the Special Issue Novel Machine Learning Approaches for Intelligent Big Data 2019)

► Show Figures

Figure 1

15 pages, 2585 KiB

Open AccessArticle

Machine Learning and Big Data in the Impact Literature. A Bibliometric Review with Scientific Mapping in Web of Science

by Jesús López Belmonte, Adrián Segura-Robles, Antonio-José Moreno-Guerrero and María Elena Parra-González

Symmetry 2020, 12(4), 495; https://doi.org/10.3390/sym12040495 - 27 Mar 2020

Cited by 43 | Viewed by 4410

Abstract

Combined use of machine learning and large data allows us to analyze data and find explanatory models that would not be possible with traditional techniques, which is basic within the principles of symmetry. The present study focuses on the analysis of the scientific [...] Read more.

Combined use of machine learning and large data allows us to analyze data and find explanatory models that would not be possible with traditional techniques, which is basic within the principles of symmetry. The present study focuses on the analysis of the scientific production and performance of the Machine Learning and Big Data (MLBD) concepts. A bibliometric methodology of scientific mapping has been used, based on processes of estimation, quantification, analytical tracking, and evaluation of scientific research. A total of 4240 scientific publications from the Web of Science (WoS) have been analyzed. Our results show a constant and ascending evolution of the scientific production on MLBD, 2018 and 2019 being the most productive years. The productions are mainly in English language. The topics are variable in the different periods analyzed, where “machine-learning” is the one that shows the greatest bibliometric indicators, it is found in most of motor topics and is the one that offers the greatest line of continuity between the different periods. It can be concluded that research on MLBD is of interest and relevance to the scientific community, which focuses its studies on the branch of machine-learning. Full article

(This article belongs to the Special Issue Novel Machine Learning Approaches for Intelligent Big Data 2019)

► Show Figures

Figure 1

13 pages, 3155 KiB

Open AccessArticle

Designing a Supermarket Service Robot Based on Deep Convolutional Neural Networks

by Aihua Chen, Benquan Yang, Yueli Cui, Yuefen Chen, Shiqing Zhang and Xiaoming Zhao

Symmetry 2020, 12(3), 360; https://doi.org/10.3390/sym12030360 - 02 Mar 2020

Cited by 7 | Viewed by 2915

Abstract

In order to save people’s shopping time and reduce labor cost of supermarket operations, this paper proposes to design a supermarket service robot based on deep convolutional neural networks (DCNNs). Firstly, according to the shopping environment and needs of supermarket, the hardware and [...] Read more.

In order to save people’s shopping time and reduce labor cost of supermarket operations, this paper proposes to design a supermarket service robot based on deep convolutional neural networks (DCNNs). Firstly, according to the shopping environment and needs of supermarket, the hardware and software structure of supermarket service robot is designed. The robot uses a robot operating system (ROS) middleware on Raspberry PI as a control kernel to implement wireless communication with customers and staff. So as to move flexibly, the omnidirectional wheels symmetrically installed under the robot chassis are adopted for tracking. The robot uses an infrared detection module to detect whether there are commodities in the warehouse or shelves or not, thereby grasping and placing commodities accurately. Secondly, the recently-developed single shot multibox detector (SSD), as a typical DCNN model, is employed to detect and identify objects. Finally, in order to verify robot performance, a supermarket environment is designed to simulate real-world scenario for experiments. Experimental results show that the designed supermarket service robot can automatically complete the procurement and replenishment of commodities well and present promising performance on commodity detection and recognition tasks. Full article

(This article belongs to the Special Issue Novel Machine Learning Approaches for Intelligent Big Data 2019)

► Show Figures

Figure 1

18 pages, 1247 KiB

Open AccessArticle

A Semi-Supervised Tri-CatBoost Method for Driving Style Recognition

by Weirong Liu, Kunyuan Deng, Xiaoyong Zhang, Yijun Cheng, Zhiyong Zheng, Fu Jiang and Jun Peng

Symmetry 2020, 12(3), 336; https://doi.org/10.3390/sym12030336 - 26 Feb 2020

Cited by 35 | Viewed by 4428

Abstract

Driving style recognition plays a key role in ensuring driving safety and improving vehicle traffic efficiency. With the development of sensing technology, data-driven methods are more widely uesd to recognize driving style. However, adequately labeling data is difficult for supervised learning methods, while [...] Read more.

Driving style recognition plays a key role in ensuring driving safety and improving vehicle traffic efficiency. With the development of sensing technology, data-driven methods are more widely uesd to recognize driving style. However, adequately labeling data is difficult for supervised learning methods, while the classification accuracy is not sufficiently approved for unsupervised learning methods. This paper proposes a new driving style recognition method based on Tri-CatBoost, which takes CatBoost as base classifier and effectively utilizes the semi-supervised learning mechanism to reduce the dependency on data labels and improve the recognition ability. First, statistical features were extracted from the velocity, acceleration and jerk signals to fully characterize the driving style. The kernel principal component analysis was used to perform nonlinear feature dimension reduction to eliminate feature coupling. CatBoost is an ensemble of symmetric decision trees whose symmetry structure endows it fewer parameters, faster training and testing, and a higher accuracy. Then, a Tri-Training strategy is employed to integrate the base CatBoost classifiers and fully exploit the unlabeled data to generate pseudo-labels, by which the base CatBoost classifiers are optimized. To verify the effectiveness of the proposed method, a large number of experiments are performed on the UAH DriveSet. When the labeling ratio is 50%, the macro precision of Tri-CatBoost is 0.721, which is 15.7% higher than that of unsupervised K-means, 1.6% higher than that of supervised GBDT, 3.7% higher than that of Self-Training, 0.7% higher than that of Co-training, 1.5% higher than that of random forest, 6.7% higher than that of decision tree, and 4.0% higher than that of multilayer perceptron. The macro recall of Tri-CatBoost is 0.744, which is also higher than other methods. The experimental results fully demonstrate the superiority of this work in reducing label dependency and improving recognition performance, which indicates that the proposed method has broad application prospects. Full article

(This article belongs to the Special Issue Novel Machine Learning Approaches for Intelligent Big Data 2019)

► Show Figures

Graphical abstract

17 pages, 486 KiB

Open AccessArticle

An Approach for Streaming Data Feature Extraction Based on Discrete Cosine Transform and Particle Swarm Optimization

by Özge Aydoğdu and Murat Ekinci

Symmetry 2020, 12(2), 299; https://doi.org/10.3390/sym12020299 - 19 Feb 2020

Cited by 11 | Viewed by 2681

Abstract

Incremental feature extraction algorithms are designed to analyze large-scale data streams. Many of them suffer from high computational cost, time complexity, and data dependency, which adversely affects the processing of the data stream. With this motivation, this paper presents a novel incremental feature [...] Read more.

Incremental feature extraction algorithms are designed to analyze large-scale data streams. Many of them suffer from high computational cost, time complexity, and data dependency, which adversely affects the processing of the data stream. With this motivation, this paper presents a novel incremental feature extraction approach based on the Discrete Cosine Transform (DCT) for the data stream. The proposed approach is separated into initial and sequential phases, and each phase uses a fixed-size windowing technique for processing the current samples. The initial phase is performed only on the first window to construct the initial model as a baseline. In this phase, normalization and DCT are applied to each sample in the window. Subsequently, the efficient feature subset is determined by a particle swarm optimization-based method. With the construction of the initial model, the sequential phase begins. The normalization and DCT processes are likewise applied to each sample. Afterward, the feature subset is selected according to the initial model. Finally, the k-nearest neighbor classifier is employed for classification. The approach is tested on the well-known streaming data sets and compared with state-of-the-art incremental feature extraction algorithms. The experimental studies demonstrate the proposed approach’s success in terms of recognition accuracy and learning time. Full article

(This article belongs to the Special Issue Novel Machine Learning Approaches for Intelligent Big Data 2019)

► Show Figures

Figure 1

19 pages, 4345 KiB

Open AccessArticle

A Method of L1-Norm Principal Component Analysis for Functional Data

by Fengmin Yu, Liming Liu, Nanxiang Yu, Lianghao Ji and Dong Qiu

Symmetry 2020, 12(1), 182; https://doi.org/10.3390/sym12010182 - 20 Jan 2020

Cited by 5 | Viewed by 2912

Abstract

Recently, with the popularization of intelligent terminals, research on intelligent big data has been paid more attention. Among these data, a kind of intelligent big data with functional characteristics, which is called functional data, has attracted attention. Functional data principal component analysis (FPCA), [...] Read more.

Recently, with the popularization of intelligent terminals, research on intelligent big data has been paid more attention. Among these data, a kind of intelligent big data with functional characteristics, which is called functional data, has attracted attention. Functional data principal component analysis (FPCA), as an unsupervised machine learning method, plays a vital role in the analysis of functional data. FPCA is the primary step for functional data exploration, and the reliability of FPCA plays an important role in subsequent analysis. However, classical L2-norm functional data principal component analysis (L2-norm FPCA) is sensitive to outliers. Inspired by the multivariate data L1-norm principal component analysis methods, we propose an L1-norm functional data principal component analysis method (L1-norm FPCA). Because the proposed method utilizes L1-norm, the L1-norm FPCs are less sensitive to the outliers than L2-norm FPCs which are the characteristic functions of symmetric covariance operator. A corresponding algorithm for solving the L1-norm maximized optimization model is extended to functional data based on the idea of the multivariate data L1-norm principal component analysis method. Numerical experiments show that L1-norm FPCA proposed in this paper has a better robustness than L2-norm FPCA, and the reconstruction ability of the L1-norm principal component analysis to the original uncontaminated functional data is as good as that of the L2-norm principal component analysis. Full article

(This article belongs to the Special Issue Novel Machine Learning Approaches for Intelligent Big Data 2019)

► Show Figures

Figure 1

26 pages, 4420 KiB

Open AccessArticle

Investigation of Fusion Features for Apple Classification in Smart Manufacturing

by Ahsiah Ismail, Mohd Yamani Idna Idris, Mohamad Nizam Ayub and Lip Yee Por

Symmetry 2019, 11(10), 1194; https://doi.org/10.3390/sym11101194 - 24 Sep 2019

Cited by 8 | Viewed by 3609

Abstract

Smart manufacturing optimizes productivity with the integration of computer control and various high level adaptability technologies including the big data evolution. The evolution of big data offers optimization through data analytics as a predictive solution in future planning decision making. However, this requires [...] Read more.

Smart manufacturing optimizes productivity with the integration of computer control and various high level adaptability technologies including the big data evolution. The evolution of big data offers optimization through data analytics as a predictive solution in future planning decision making. However, this requires accurate and reliable informative data as input for analytics. Therefore, in this paper, the fusion features for apple classification is investigated to classify between defective and non-defective apple for automatic inspection, sorting and further predictive analytics. The fusion features with Decision Tree classifier called Curvelet Wavelet-Gray Level Co-occurrence Matrix (CW-GLCM) is designed based on symmetrical pattern. The CW-GLCM is tested on two apple datasets namely NDDA and NDDAW with a total of 1110 apple images. Each dataset consists of a binary class of apple which are defective and non-defective. The NDDAW consists more low-quality region images. Experimental results show that CW-GLCM successfully classify 98.15% of NDDA dataset and 89.11% of NDDAW dataset. A lower classification accuracy is observed in other five existing image recognition methods especially on NDDAW dataset. Finally, the results show that CW-GLCM is more accurate among all the methods with the difference of more than 10.54% of classification accuracy. Full article

(This article belongs to the Special Issue Novel Machine Learning Approaches for Intelligent Big Data 2019)

► Show Figures

Figure 1

13 pages, 2173 KiB

Open AccessArticle

ELPKG: A High-Accuracy Link Prediction Approach for Knowledge Graph Completion

by Jiangtao Ma, Yaqiong Qiao, Guangwu Hu, Yanjun Wang, Chaoqin Zhang, Yongzhong Huang, Arun Kumar Sangaiah, Huaiguang Wu, Hongpo Zhang and Kai Ren

Symmetry 2019, 11(9), 1096; https://doi.org/10.3390/sym11091096 - 02 Sep 2019

Cited by 12 | Viewed by 3427

Abstract

Link prediction in knowledge graph is the task of utilizing the existing relations to infer new relations so as to build a more complete knowledge graph. The inferred new relations plus original knowledge graph is the symmetry of completion knowledge graph. Previous research [...] Read more.

Link prediction in knowledge graph is the task of utilizing the existing relations to infer new relations so as to build a more complete knowledge graph. The inferred new relations plus original knowledge graph is the symmetry of completion knowledge graph. Previous research on link predication only focuses on path or semantic-based features, which can hardly have a full insight of features between entities and may result in a certain ratio of false inference results. To improve the accuracy of link predication, we propose a novel approach named Entity Link Prediction for Knowledge Graph (ELPKG), which can achieve a high accuracy on large-scale knowledge graphs while keeping desirable efficiency. ELPKG first combines path and semantic-based features together to represent the relationships between entities. Then it adopts a probabilistic soft logic-based reasoning method that effectively solves the problem of non-deterministic knowledge reasoning. Finally, the relation between entities is completed based on the entity link prediction algorithm. Extensive experiments on real dataset show that ELPKG outperforms baseline methods on hits@1, hits@10, and MRR. Full article

(This article belongs to the Special Issue Novel Machine Learning Approaches for Intelligent Big Data 2019)

► Show Figures

Figure 1

17 pages, 14714 KiB

Open AccessArticle

Symmetry Encoder-Decoder Network with Attention Mechanism for Fast Video Object Segmentation

by Mingyue Guo, Dejun Zhang, Jun Sun and Yiqi Wu

Symmetry 2019, 11(8), 1006; https://doi.org/10.3390/sym11081006 - 04 Aug 2019

Cited by 2 | Viewed by 4089

Abstract

Semi-supervised video object segmentation (VOS) has obtained significant progress in recent years. The general purpose of VOS methods is to segment objects in video sequences provided with a single annotation in the first frame. However, many of the recent successful methods heavily fine-tune [...] Read more.

Semi-supervised video object segmentation (VOS) has obtained significant progress in recent years. The general purpose of VOS methods is to segment objects in video sequences provided with a single annotation in the first frame. However, many of the recent successful methods heavily fine-tune the object mask in the first frame, which decreases their efficiency. In this work, to address this issue, we propose a symmetry encoder-decoder network with the attention mechanism for video object segmentation (SAVOS) requiring only one forward pass to segment the target object in a video. Specifically, the encoder generates a low-resolution mask with smoothed boundaries, while the decoder further refines the details of the segmentation mask and integrates lower level features progressively. Besides, to obtain accurate segmentation results, we sequentially apply the attention module on multi-scale feature maps for refinement. We conduct several experiments on three challenging datasets (i.e., DAVIS 2016, DAVIS 2017, and SegTrack v2) to show that SAVOS achieves competitive performance against the state-of-the-art. Full article

(This article belongs to the Special Issue Novel Machine Learning Approaches for Intelligent Big Data 2019)

► Show Figures

Figure 1

15 pages, 5291 KiB

Open AccessArticle

Research on the Method of Color Fundus Image Optic Cup Segmentation Based on Deep Learning

by Zhitao Xiao, Xinxin Zhang, Lei Geng, Fang Zhang, Jun Wu and Yanbei Liu

Symmetry 2019, 11(7), 933; https://doi.org/10.3390/sym11070933 - 17 Jul 2019

Cited by 7 | Viewed by 4103

Abstract

The optic cup is a physiological structure in the fundus and is a small central depression in the eye. It has a normal proportion in the optic papilla. If the ratio is large, its size may be used to determine diseases such as [...] Read more.

The optic cup is a physiological structure in the fundus and is a small central depression in the eye. It has a normal proportion in the optic papilla. If the ratio is large, its size may be used to determine diseases such as glaucoma or congenital myopia. The occurrence of glaucoma is generally accompanied by physical changes to the optic cup, optic disc, and optic nerve fiber layer. Therefore, accurate measurement of the optic cup is important for the detection of glaucoma. The accurate segmentation of the optic cup is essential for the measurement of the size of the optic cup relative to other structures in the eye. This paper proposes a new network architecture we call Segmentation-ResNet Seg-ResNet that takes a residual network structure as the main body, introduces a channel weighting structure that automatically adjusts the dependence of the feature channels, re-calibrates the feature channels, and introduces a set of low-level features that are combined with high-level features to improve network performance. Pre-fusion features and fused features are symmetrical. Hence, this work correlates with the concept of symmetry. Combined with the training strategy of migration learning, the segmentation accuracy is improved while speeding up network convergence. The robustness and effectiveness of the proposed method are demonstrated by testing data from the GlaucomaRepo and Drishti-GS fundus image databases. Full article

(This article belongs to the Special Issue Novel Machine Learning Approaches for Intelligent Big Data 2019)

► Show Figures

Figure 1

21 pages, 50214 KiB

Open AccessArticle

Advanced Machine Learning for Gesture Learning and Recognition Based on Intelligent Big Data of Heterogeneous Sensors

by Jisun Park, Yong Jin, Seoungjae Cho, Yunsick Sung and Kyungeun Cho

Symmetry 2019, 11(7), 929; https://doi.org/10.3390/sym11070929 - 16 Jul 2019

Cited by 3 | Viewed by 3823

Abstract

With intelligent big data, a variety of gesture-based recognition systems have been developed to enable intuitive interaction by utilizing machine learning algorithms. Realizing a high gesture recognition accuracy is crucial, and current systems learn extensive gestures in advance to augment their recognition accuracies. [...] Read more.

With intelligent big data, a variety of gesture-based recognition systems have been developed to enable intuitive interaction by utilizing machine learning algorithms. Realizing a high gesture recognition accuracy is crucial, and current systems learn extensive gestures in advance to augment their recognition accuracies. However, the process of accurately recognizing gestures relies on identifying and editing numerous gestures collected from the actual end users of the system. This final end-user learning component remains troublesome for most existing gesture recognition systems. This paper proposes a method that facilitates end-user gesture learning and recognition by improving the editing process applied on intelligent big data, which is collected through end-user gestures. The proposed method realizes the recognition of more complex and precise gestures by merging gestures collected from multiple sensors and processing them as a single gesture. To evaluate the proposed method, it was used in a shadow puppet performance that could interact with on-screen animations. An average gesture recognition rate of 90% was achieved in the experimental evaluation, demonstrating the efficacy and intuitiveness of the proposed method for editing visualized learning gestures. Full article

(This article belongs to the Special Issue Novel Machine Learning Approaches for Intelligent Big Data 2019)

► Show Figures

Figure 1

15 pages, 2011 KiB

Open AccessArticle

Neighbor Discovery Optimization for Big Data Analysis in Low-Power, Low-Cost Communication Networks

by Sangil Choi and Gangman Yi

Symmetry 2019, 11(7), 836; https://doi.org/10.3390/sym11070836 - 26 Jun 2019

Cited by 1 | Viewed by 2065

Abstract

Big data analysis generally consists of the gathering and processing of raw data and producing meaningful information from this data. These days, large collections of sensors, smart phones, and electronic devices are all connected in the network. One of the primary features of [...] Read more.

Big data analysis generally consists of the gathering and processing of raw data and producing meaningful information from this data. These days, large collections of sensors, smart phones, and electronic devices are all connected in the network. One of the primary features of these devices is low-power consumption and low cost. Power consumption is one of the important research concerns in low-power, low-cost communication networks such as sensor networks. A primary feature of sensor networks is a distributed and autonomous system. Therefore, all network devices in this type of network maintain the network connectivity by themselves using limited energy resources. When they are deployed in the area of interest, the first step for neighbor discovery involves the identification of neighboring nodes for connection and communication. Most wireless sensors utilize a power-saving mechanism by powering on the system if it is off, and vice versa. The neighbor discovery process becomes a power-consuming task if two neighboring nodes do not know when their partner wakes up and sleeps. In this paper, we consider the optimization of the neighbor discovery to reduce the power consumption in wireless sensor networks and propose an energy-efficient neighbor discovery scheme by adapting symmetric block designs, combining block designs, and utilizing the concept of activating nodes based on the multiples of a specific number. The performance evaluation demonstrates that the proposed neighbor discovery algorithm outperforms other competitive approaches by analyzing the wasted awakening slots numerically. Full article

(This article belongs to the Special Issue Novel Machine Learning Approaches for Intelligent Big Data 2019)

► Show Figures

Figure 1

19 pages, 4684 KiB

Open AccessArticle

Research on a Tool Wear Monitoring Algorithm Based on Residual Dense Network

by Yiting Li, Qingsheng Xie, Haisong Huang and Qipeng Chen

Symmetry 2019, 11(6), 809; https://doi.org/10.3390/sym11060809 - 19 Jun 2019

Cited by 10 | Viewed by 2802

Abstract

To accurately and efficiently detect tool wear values during production and processing activities, a new online detection model is proposed called the Residual Dense Network (RDN). The model is created with two main steps: Firstly, the time-domain signals for a cutting tool are [...] Read more.

To accurately and efficiently detect tool wear values during production and processing activities, a new online detection model is proposed called the Residual Dense Network (RDN). The model is created with two main steps: Firstly, the time-domain signals for a cutting tool are obtained (e.g., using acceleration sensors); these signals are processed to denoise and segmented to provide a larger number of uniform samples. This processing helps to improve the robustness of the model. Secondly, a new deep convolutional neural network is proposed to extract features adaptively, by combining the idea of a recursive residual network and a dense network. Notably, this method is specifically tailored to the tool wear value detection problem. In this way, the limitations of traditional manual feature extraction steps can be avoided. The experimental results demonstrate that the proposed method is promising in terms of detection accuracy and speed; it provides a new way to detect tool wear values in practical industrial scenarios. Full article

(This article belongs to the Special Issue Novel Machine Learning Approaches for Intelligent Big Data 2019)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Novel Machine Learning Approaches for Intelligent Big Data 2019

Share This Special Issue

Special Issue Editor

Special Issue Information

Published Papers (13 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI