Acyclic Graph Support Vector Machine Research Articles

Quantum support vector machine for multi classification

Classical machine learning algorithms seem to be totally incapable of processing tremendous data, while quantum machine learning algorithms could deal with big data unhurriedly and provide exponential acceleration over classical counterparts. In this paper, we propose two quantum support vector machine algorithms for multi classification. One is the quantum version of the directed acyclic graph support vector machine. The other one is to use the Grover search algorithm before measurement, which amplifies the amplitude of the phase storing of the classification result. For k classification, the former provides quadratic reduction in computational complexity when classifying. The latter accelerates the training speed significantly and more importantly, the classification result can be read out with a probability of at least 50% using only one measurement. We conduct numerical simulations on two algorithms, and their classification success rates are 96% and 88.7%, respectively.

An Intelligent Detection Method for Obstacles in Agricultural Soil with FDTD Modeling and MSVMs

Unknown objects in agricultural soil can be important because they may impact the health and productivity of the soil and the crops that grow in it. Challenges in collecting soil samples present opportunities to utilize Ground Penetrating Radar (GPR) image processing and artificial intelligence techniques to identify and locate unidentified objects in agricultural soil, which are important for agriculture. In this study, we used finite-difference time-domain (FDTD) simulated models to gather training data and predict actual soil conditions. Additionally, we propose a multi-class support vector machine (MSVM) that employs a semi-supervised algorithm to classify buried object materials and locate their position in soil. Then, we extract echo signals from the electromagnetic features of the FDTD simulation model, including soil type, parabolic shape, location, and energy magnitude changes. Lastly, we compare the performance of various MSVM models with different kernel functions (linear, polynomial, and radial basis function). The results indicate that the FDTD-Yee method enhances the accuracy of simulating real agricultural soils. The average recognition rate of the hyperbola position formed by the GPR echo signal is 91.13%, which can be utilized to detect the position and material of unknown and underground objects. For material identification, the directed acyclic graph support vector machine (DAG-SVM) model attains the highest classification accuracy among all soil layers when using an RBF kernel. Overall, our study demonstrates that an artificial intelligence model trained with the FDTD forward simulation model can effectively detect objects in farmland soil.

Railway Track Recognition Based on Radar Cross-Section Statistical Characterization Using mmWave Radar

The track settlement has a great influence on the safe operation of high-speed trains. The existing track settlement measurement approach requires sophisticated or expensive equipments, and the real-time performance is limited. To address the issue, an ultra-high resolution track settlement detection method is proposed by using millimeter wave radar based on frequency modulated continuous wave (FMCW). Firstly, by constructing the RCS statistical feature data set of multiple objects in the track settlement measurement environment, a directed acyclic graph-support vector machine (DAG-SVM) based method is designed to solve the problem of track recognition in multi-object scenes. Then, the adaptive chirp-z-transform (ACZT) algorithm is used to estimate the distance between the radar and the track surface, which realizes automatic real-time track settlement detection. An experimental platform has been constructed to verify the effectiveness of the proposed method. The experimental results show that the accuracy of track classification and identification is at least 95%, and the accuracy of track settlement measurement exceeds 0.5 mm, which completely meets the accuracy requirements of the railway system.

A hybrid of fast K-nearest neighbor and improved directed acyclic graph support vector machine for large-scale supersonic inlet flow pattern recognition

Inlet flow pattern recognition is one of the most crucial issues and also the foundation of protection control for supersonic air-breathing propulsion systems. This article proposes a hybrid algorithm of fast K-nearest neighbors (F-KNN) and improved directed acyclic graph support vector machine (I-DAGSVM) to solve this issue based on a large amount of experimental data. The basic idea behind the proposed algorithm is combining F-KNN and I-DAGSVM together to reduce the classification error and computational cost when dealing with big data. The proposed algorithm first finds a small set of nearest samples from the training set quickly by F-KNN and then trains a local I-DAGSVM classifier based on these nearest samples. Compared with standard KNN which needs to compare each test sample with the entire training set, F-KNN uses an efficient index-based strategy to quickly find nearest samples, but there also exists misclassification when the number of nearest samples belonging to different classes is the same. To cope with this, I-DAGSVM is adopted, and its tree structure is improved by a measure of class separability to overcome the sequential randomization in classifier generation and to reduce the classification error. In addition, the proposed algorithm compensates for the expensive computational cost of I-DAGSVM because it only needs to train a local classifier based on a small number of samples found by F-KNN instead of all training samples. With all these strategies, the proposed algorithm combines the advantages of both F-KNN and I-DAGSVM and can be applied to the issue of large-scale supersonic inlet flow pattern recognition. The experimental results demonstrate the effectiveness of the proposed algorithm in terms of classification accuracy and test time.

A vision-based fall detection framework for the elderly in a room environment using motion features and DAG-SVM

Falls are one of the major health risks for the elderly in public health care issues, thus fall detection is particularly necessary for the seniors. In this paper, we propose a novel computer vision-based fall activity detection framework which is based on a new feature extraction method of human motion. We detect falls by analyzing the motion process of human body rather than conventional human shape analysis. Approximate ellipse is first adopted to fit human silhouette, and the areas outside the ellipse are removed to confirm human body silhouette (HBS). Then HBS is divided into three regions, and the motion features are extracted from the centroid coordinate changes of each region. A directed acyclic graph support vector machine (DAG-SVM) classifier is finally applied to detect falls from normal daily activities. The advantage of the proposed method is that it can not only effectively distinguish falls from fall-like activities but also detect the falls parallel to camera optical axis. Experimental results show that our method achieves a state-of-the-art accuracy in fall detection. This method is lightweight and thus can be integrated into embedded devices for real-time health surveillance.

Facial Expression Recognition Using Kernel Entropy Component Analysis Network and DAGSVM

Facial expression recognition (FER) plays a significant part in artificial intelligence and computer vision. However, most of facial expression recognition methods have not obtained satisfactory results based on low-level features. The existed methods used in facial expression recognition encountered the major issues of linear inseparability, large computational burden, and data redundancy. To obtain satisfactory results, we propose an innovative deep learning (DL) model using the kernel entropy component analysis network (KECANet) and directed acyclic graph support vector machine (DAGSVM). We use the KECANet in the feature extraction stage. In the stage of output, binary hashing and blockwise histograms are adopted. We sent the final output features to the DAGSVM classifier for expression recognition. We test the performance of our proposed method on three databases of CK+, JAFFE, and CMU Multi-PIE. According to the experiment results, the proposed method can learn high-level features and provide more recognition information in the stage of training, obtaining a higher recognition rate.

A Hybrid Model Combining Learning Distance Metric and DAG Support Vector Machine for Multimodal Biometric Recognition

Metric learning has significantly improved machine learning applications such as face re-identification and image classification using K-Nearest Neighbor (KNN) and Support Vector Machine (SVM) classifiers. However, to the best of our knowledge, it has not been investigated yet, especially for the multimodal biometric recognition problem in immigration, forensic and surveillance applications with uncontrolled ear datasets. Therefore, it is interesting and very attractive to propose a novel framework for multimodal biometric recognition based on Learning Distance Metric (LDM) via kernel SVM. This paper considers metric learning for SVM by investigating a hybrid Learning Distance Metric and Directed Acyclic Graph SVM (LDM-DAGSVM) model for multimodal biometric recognition, where LDM and DAGSVM are two emerging techniques in dealing with classification problems. Different from existing multimodal biometric recognition methods, the proposed approach aims to learn Mahalanobis distance metric via kernel SVM to maximize the inter-class variations and minimize the intra-class variations, simultaneously. Experimental results on the uncontrolled datasets such as AR face and AWE ear datasets show that the proposed approach achieves competitive performance compared with models working on individual modalities and overperforms the state-of-the-art multimodal methods. The proposed model achieves five-fold classification accuracy around 99.85 % for the face and ear images.

An Advanced Genetic Algorithm with Improved Support Vector Machine for Multi-Class Classification of Real Power Quality Events

This article proposes an application of non-dominated sorting genetic algorithm III (NSGA III) and directed acyclic graph support vector machine (DAG-SVM) based combined approach for recognition and classification of power quality disturbances. Power disturbances are non-stationary and non-linear by nature and require a large number of features vectors for detection, which results in high computation time and error. The proposed method first employs NSGA III algorithm for an effective features extraction from power signals. The numbers of features required for detection are less in case of proposed NSGA III algorithm. The NSGA III algorithm generates optimal solutions based on multi objective optimization and then fitness function is generated with the help of Pareto front to obtain unique features set from power signals. The NSGA III not only has exact localization of power quality events and stronger robustness but also reduces the computational time in comparison with the traditional NSGA II. The obtained unique feature vectors are used for training of DAG-SVM to classify the power quality disturbances. In case of N-classes, the proposed DAG-SVM generates N(N-1)/2 classifiers, one for each pair of classes and makes the decision accurate and faster. The short event detection, lesser computational timing, superior classification accuracy, and high anti-noise performance are the main advantages of the proposed method. Furthermore, Virtex-5 FPGA based processor is used to test and validate the feasibility of the proposed method for real time analysis of power quality events.

Automatic identification and classification of power quality events using a hybrid intelligent approach

This article proposes an implementation of Enhanced-Non-dominated Sorting Genetic Algorithm (E-NSGA III) and Directed Acyclic Graph-Support Vector Machine (DAG-SVM) based combined approach for recognition and classification of power quality events. The function of E-NSGA III is to extract features and DAG-SVM for the purpose of classification of power quality events with minimum error. The non-stationary and non- linear nature of power quality disturbances makes it a suitable choice for E-NSGA III. This technique gives unique Pareto-optimal solutions based on multi-objective optimization. Considering equal priority for all the objectives, a fitness function is used to obtain the best solution set from the first Pareto front. Non-dominated sorting sets a dominated count and assigns domination to each individual. Dominated count means the number of times an individual data point has been dominated by another data point. The obtained unique feature vectors are used for training of DAG-SVM classifier to classify the power quality disturbances. Many power quality events including harmonics, swell, sag, transient, swell with harmonics and sag with harmonics are taken into consideration for investigation of power signal disturbances. Comparative investigation reveals the novelty and efficacy of the proposed hybrid technique in comparison of support vector machine, radial basis feed-forward neural network, probabilistic neural network, support vector machine and type-1 and type-II based fuzzy classifier under serve noise conditions. The simulation results show that the Directed Acyclic Graph Support Vector Machine gives the best classification accuracy of 99.20% and less computation time.

Dual Tree Complex Wavelet Transform with Multiobjective Optimization Algorithm for Real‐Time Power Quality Events Classification

AbstractThis article proposes an application of Dual Tree Complex Wavelet Transform (DTCWT) with non‐dominated sorting genetic algorithm III (NSGA III) based multi‐objective optimization and directed acyclic graph support vector machine (DAG‐SVM) for recognition and classification of power quality events. The proposed method first employs DTCWT for extraction of features then NSGA III algorithm for an effective optimization of extracted features. After that, DAG‐SVM based classifier are used to predict the classes of PQ disturbances. The NSGA III algorithm generates optimalsolutions based on multi objective optimization and then fitness function is generated with the help of Pareto front to obtain unique features set from power signals. The NSGA III not only optimizes selected features with DTCWT but also reduces the computational time in comparison with the traditional NSGA II. The obtained unique feature vectors are used for training of Directed Acyclic Graph‐SVM to classify the power quality disturbances. The short event detection, lesser computational timing, superior classification accuracy, and high anti‐noise performance are the main advantages of the proposed method.

Machine Learning-Enabled Cooperative Spectrum Sensing for Non-Orthogonal Multiple Access

In this paper, multiple machine learning-enabled solutions are adopted to tackle the challenges of complex sensing model in cooperative spectrum sensing for non-orthogonal multiple access transmission mechanism, including unsupervised learning algorithms (K-Means clustering and Gaussian mixture model) as well as supervised learning algorithms (directed acyclic graph-support vector machine, K-nearest-neighbor and back-propagation neural network). In these solutions, multiple secondary users (SUs) collaborate to perceive the presence of primary users (PUs), and the state of each PU need to be detected precisely. Furthermore, the sensing accuracy is analyzed in detail from the aspects of the number of SUs, the training data volume, the average signal-to-noise ratio of receivers, the ratio of PUs' power coefficients, as well as the training time and test time. Numerical results illustrate the effectiveness of our proposed solutions.

Fast CU partition decision for H.266/VVC based on the improved DAG-SVM classifier model

One of the biggest changes in H.266/Versatile Video Coding (VVC) is introduced quad-tree with nested multi-type tree (QTMT) coding tree architecture, where the multi-type tree (MTT) structure in H.266/VVC includes binary tree (BT) and ternary tree (TT). Compared with H.265/High Efficiency Video Coding (HEVC) which only is divided by quad-tree (QT), the QTMT architecture makes the coding unit (CU) partition procedure more complexity. In this paper, we design a fast CU partition decision algorithm based on the improved Directed Acyclic Graph Support Vector Machine (DAG-SVM) model to reduce the complexity of CU partition. The video sequences are first encoded on the H.266/VVC and Test Model 4.0 (VTM 4.0), and the characteristics of the video sequences are extracted for training through the improved F-score method, where the correlation between a feature and CU partition is high. Then, the offline training is used for the improved DAG-SVM model. Finally, the trained DAG-SVM model is embedded in VTM 4.0 to early forecast the optimal CU partition modes. Simulation results indicate that the proposed method increases the time savings to 54.74% while maintaining the encoding performance. Furthermore, the proposed method exceeds the latest methods of H.266/VVC.

Recognition classification based on Hu moment invariants and imperial competitive algorithm for axis trajectory of magnetic bearing-rotor system

In the magnetic-suspension bearing-rotor system, the shape features of the rotor axis trajectory can directly reflect the system operation status and fault information. Accurately classifying the bearing faults can promptly find the cause of the fault and respond quickly and protect it. In this paper, in order to achieve fault identification by identifying and classifying the rotor axis trajectory, we use Hu moment invariants to extract feature vectors from the rotor axis trajectory to identify faults. We use imperial competitive algorithm to reduce redundant data and establish a directed acyclic graph support vector machine to classify and identify feature data. Compared with traditional classification models such as C4.5 and BP neural networks, the experimental results show that the support vector machine model based on Hu moment invariants and simulated annealing has a higher accuracy and robustness in small sample classification. It is suitable for intelligent identification and classification for bearing faults.

Monitoring tip-based nanomachining process by time series analysis using support vector machine

In this paper, time-series data analysis and pattern recognition using a multi-class support vector machine (SVM) were studied to monitor the state changes of the AFM tip-based nanomachining process with respect to the machining performance and tip wear. Time series data (i.e. machining force from the process), which has transient, nonlinear, and non-stationary characteristics, was collected by a data acquisition system. Three status detection features including the maximum force, peak-to-peak force value, and the variance of the collected lateral machining force, were extracted to classify the state of the nanomachining process. Directed Acyclic Graph Support Vector Machines (DAGSVM) with a Gaussian Radial Basis Kernel Function (RBF Kernel) was constructed to identify the different process states. Using this multi-class SVM, the machining process and the tip wear can be classified into three regions, which are effective machining with a sharp tip, transition region and bad/no machining with severe tip wear. The experimental data showed that the accuracy of the SVM was over 94.73% in both binary and ternary classifications, which confirmed that the SVM-based pattern recognition technology via time series data could successfully monitor the tip wear and process performance for tip-based nanomachining process.

A Method for Diagnosing Mechanical Faults of on-Load Tap Changer Based on Ensemble Empirical Mode Decomposition, Volterra Model and Decision Acyclic Graph Support Vector Machine

A method combined ensemble empirical mode decomposition, Volterra model and decision acyclic graph support vector machine was proposed to improve adaptability, feature resolution, and identification accuracy when diagnosing mechanical faults in an on-load tap changer of a transformer. In detail, the ensemble empirical mode decomposition algorithm was applied to decompose the multi-channel vibration signals in the switchover process of the on-load tap changer. Then, a Volterra model for the mechanical state of the on-load tap changer was established based on time-frequency characteristics obtained through the use of the ensemble empirical mode decomposition algorithm. Moreover, a matrix of coefficient vectors was also used in the Volterra model. This method will not only reduce the aliasing effect of empirical mode decomposition but also obtain high-resolution characteristics of nonstationary vibration signals. Furthermore, taking the singular values of the Volterra coefficient matrix as the fault characteristic, the data states of the model for diagnosing the on-load tap changer were automatically classified and identified by establishing a rapid, multi-classification decision acyclic graph support vector machine model with a low misjudgment rate. Finally, based on a certain on-load tap changer, the test platform for simulating mechanical faults was built. On this basis, by using the proposed method, the vibration signals generated due to typical mechanical faults, such as loosening of moving contacts, lessening of transition contact, and motor jam were acquired and analyzed, thus validating the effectiveness of the method through case studies. Compared with other methods, the new method could overcome many defects in existing methods and it has higher fault identification accuracy.

Classification and regression analysis using support vector machine for classifying and locating faults in a distribution system

Various fault location methods have been developed in the past to identify the faulty phase, fault type, faulty section, and distance. However, this identification is commonly conducted in a separate manner. An effective fault location should be able to identify all of these at the same time. Therefore, in this work, a method using a support vector machine (SVM) to identify the fault type, faulty section, and distance considering the faulty phase is proposed. The proposed method uses voltage sag magnitude of the distribution system as the main feature for the SVM to identify faults. The fault type is classified using a directed acyclic graph SVM. The possible faulty sections are identified by estimating the fault resistance using support vector regression and matching the voltage sag data in the database with the actual voltage sag data. The most possible faulty sections are ranked using ranking analysis. The fault distance for the possible faulty sections is then identified using support vector regression analysis and its overfitting or underfitting issues are addressed by the proper selection of a regularization parameter. The feasibility of the proposed method was tested on an actual Malaysian distribution system. The results of faulty phase, fault type, faulty section, and fault distance are analyzed. The performance of the proposed method is compared with various other intelligent methods such as the artificial neural network, deep neural network, extreme learning machine, and kriging method. The test results indicate that the faulty phase and fault type yield 100 % accurate results. All the faulty sections are identified and the proposed method obtains reliable fault location.

Cross-Voting SVM Method for Multiple Vehicle Classification in Wireless Sensor Networks.

A novel multi-class classification method named the voting-cross support vector machine (SVM) method was proposed in this study, for classifying vehicle targets in wireless sensor networks. The advantages and disadvantages of available methods were summarized, after a comparative analysis of commonly used multi-objective classification algorithms. To improve the classification accuracy of multi-class classification and ensure the low complexity of the algorithm for engineering implementation on wireless sensor network (WSN) nodes, a framework was proposed for cross-matching and voting on the category to which the vehicle belongs after combining the advantages of the directed acyclic graph SVM (DAGSVM) method and binary-tree SVM method. The SVM classifier was selected as the basis two-class classifier in the framework, after comparing the classification performance of several commonly used methods. We utilized datasets acquired from a real-world experiment to validate the proposed method. The calculated results demonstrated that the cross-voting SVM method could effectively increase the classification accuracy for the classification of multiple vehicle targets, with a limited increase in the algorithm complexity. The application of the cross-voting SVM method effectively improved the target classification accuracy (by approximately 7%), compared with the DAGSVM method and the binary-tree SVM method, whereas time consumption decreased by approximately 70% compared to the DAGSVM method.

Gait-based human age estimation using age group-dependent manifold learning and regression

Human age estimation from gait is expected to be an important technology for a variety of applications such as automatic customer counting for marketing research or automatic age-based access control restriction for a specific area because the gait can be observable at a distance from a camera (e.g., CCTV). Although the aging process of gait significantly differs among age groups (e.g., children, adults, and the elderly), previous studies on gait-based human age estimation employ a single age group-independent estimation model that suffers from large estimation errors when the age variation increases. We therefore propose an age group-dependent gait-based human age estimation method for better accuracy. Specifically, in the training phase, we first compose age groups that are well-separated from each other by clustering gait features along with their age labels. We then learn a classifier that classifies the gait features for multiple age groups using a directed acyclic graph support vector machine. Next, we learn an age regression model for each age group using support vector regression with a Gaussian kernel in conjunction with a manifold learning technique, i.e., orthogonal locality preserving projection, to better characterize the gait feature. In the test phase, given a gait feature, it is first classified into an age group and then its age is estimated with the age regression model of the classified age group. Experimental results on a gait database that has the world’s largest population of participants ranging from 2 to 90 years old demonstrate the state-of-the-art performance of the proposed method.

Epileptic seizure detection using fuzzy-rules-based sub-band specific features and layered multi-class SVM

In this paper, a new epileptic seizure detection method using fuzzy-rules-based sub-band specific features and layered directed acyclic graph support vector machine (LDAG-SVM) is proposed for classification of electroencephalogram (EEG) signals. Wavelet transformation is used to decompose the input EEG signals into various sub-bands. The nonlinear features, namely approximate entropy, largest Lyapunov exponent and correlation dimension, are extracted from each sub-band. In this proposed work, sub-band specific feature subset that is reduced in size and capable of discriminating samples is selected by employing fuzzy rules. For classification purpose, a new LDAG-SVM is used for detecting epileptic seizure. Every sub-band has its own characteristics. If appropriate features which characterize the specific sub-band are selected, then the classification accuracy is improved and computational complexity is reduced. The important advantage of the fuzzy logic is its close relation to human thinking. Due to the lengthy record and intra-professional variability, automation of epileptic detection is inevitable. Fuzzy rules are the natural choice of employing human expertise to build machine learning system. Performances of the proposed methods are evaluated using two different benchmark EEG datasets, namely Bonn and CHB-MIT. The performance measures such as classification accuracy, sensitivity, specificity, execution time and receiver operating characteristics are used to measure and analyze the performances of the proposed classifier. The proposed LDAG-SVM with fuzzy-rules-based selected sub-band specific features provides better performance in terms of improved classification accuracy with reduced execution time compared to existing methods.

Human fall detection using slow feature analysis

Falls are reported to be the leading causes of accidental deaths among elderly people. Automatic detection of falls from video sequences is an assistant technology for low-cost health care systems. In this paper, we present a novel slow feature analysis based framework for fall detection in a house care environment. Firstly, a foreground human body is extracted by a background subtraction technique. After morphological operations, the human silhouette is refined and covered by a fitted ellipse. Secondly, six shape features are quantified from the covered silhouette to represent different human postures. With the help of the learned slow feature functions, the shape feature sequences are transformed into slow feature sequences with discriminative information about human actions. To represent the fall incidents, the squared first order temporal derivatives of the slow features are accumulated into a classification vector. Lastly, falls are distinguished from other daily actions, such as walking, crouching, and sitting, by the trained directed acyclic graph support vector machine. Experiments on the multiple-camera fall dataset and the SDUFall dataset demonstrate that our method is comparable to other state-of-the-art methods, achieving 94.00% recognition rate on the former dataset and 96.57% on the latter one.