Classifier Fusion Model Research Articles

‘The Best of Two Worlds’—Combining Classifier Fusion and Ecological Models to Map and Explain Landscape Invasion by an Alien Shrub

The spread of invasive alien species promotes ecosystem structure and functioning changes, with detrimental effects on native biodiversity and ecosystem services, raising challenges for local management authorities. Predictions of invasion dynamics derived from modeling tools are often spatially coarse and therefore unsuitable for guiding local management. Accurate information on the occurrence of invasive plants and on the main factors that promote their spread is critical to define successful control strategies. For addressing this challenge, we developed a dual framework combining satellite image classification with predictive ecological modeling. By combining data from georeferenced invaded areas with multispectral imagery with 10-meter resolution from Sentinel-2 satellites, a map of areas invaded by the woody invasive Acacia longifolia in a municipality of northern Portugal was devised. Classifier fusion techniques were implemented through which eight statistical and machine-learning algorithms were ensembled to produce accurate maps of invaded areas. Through a Random Forest (RF) model, these maps were then used to explore the factors driving the landscape-level abundance of A. longifolia. RF models were based on explanatory variables describing hypothesized environmental drivers, including climate, topography/geomorphology, soil properties, fire disturbance, landscape composition, linear structures, and landscape spatial configuration. Satellite-based maps synoptically described the spatial patterns of invaded areas, with classifications attaining high accuracy values (True Skill Statistic, TSS: 0.895, Area Under the Receiver Operating Curve, ROC: 0.988, Kappa: 0.857). The predictive RF models highlighted the primary role of climate, followed by landscape composition and configuration, as the most important drivers explaining the species abundance at the landscape level. Our innovative dual framework—combining image classification and predictive ecological modeling—can guide decision-making processes regarding effective management of invasions by prioritizing the invaded areas and tackling the primary environmental and anthropogenic drivers of the species’ abundance and spread.

A Concept-based Sentiment Analysis Approach for Arabic

Concept-Based Sentiment Analysis (CBSA) methods are considered to be more advanced and more accurate when it compared to ordinary Sentiment Analysis methods, because it has the ability of detecting the emotions that conveyed by multi-word expressions concepts in language. This paper presented a CBSA system for Arabic language which utilizes both of machine learning approaches and concept-based sentiment lexicon. For extracting concepts from Arabic, a rule-based concept extraction algorithm called semantic parser is proposed. Different types of feature extraction and representation techniques are experimented among the building prosses of the sentiment analysis model for the presented Arabic CBSA system. A comprehensive and comparative experiments using different types of classification methods and classifier fusion models, together with different combinations of our proposed feature sets, are used to evaluate and test the presented CBSA system. The experiment results showed that the best performance for the sentiment analysis model is achieved by combined Support Vector Machine-Logistic Regression (SVM-LR) model where it obtained a F-score value of 93.23% using the Concept-Based-Features+Lexicon-Based-Features+Word2vec-Features (CBF+LEX+W2V) features combinations

Partial discharge development stage division based on multi-classifier fusion

The oil-paper insulation air gap discharge experiment was carried out by the step-up method, and the 29-dimensional discharge characteristic parameters were extracted. The oil-paper insulation air gap discharge experiment was carried out by the step-up method, and the 29-dimensional discharge characteristic parameters were extracted. According to K-means clustering, the partial discharge development stage is divided into four stages: initial discharge stage, discharge development stage, discharge stability stage and near breakdown stage. The three basic classifiers of random forest, support vector machine and back propagation neural network are trained by the credibility-based adaptive weighted voting algorithm to train a new fusion classifier. Compared with the traditional classification fusion device, the proposed classifier fusion model can effectively improve the accuracy of the identification of the discharge development stage, up to 87.5% or more.

Prediction of rectal toxicity of radiotherapy for prostate cancer based on multi-modality feature and multi-classifiers

To evaluate rectal toxicity of radiotherapy for prostate cancer using a novel predictive model based on multi-modality and multi-classifier fusion. We retrospectively collected the clinical data from 44 prostate cancer patients receiving external beam radiation (EBRT), including the treatment data, clinical parameters, planning CT data and the treatment plans. The clinical parameter features and dosimetric features were extracted as two different modality features, and a subset of features was selected to train the 5 base classifiers (SVM, Decision Tree, K-nearest-neighbor, Random forests and XGBoost). To establish the multi-modality and multi-classifier fusion model, a multi-criteria decision-making based weight assignment algorithm was used to assign weights for each base classifier under the same modality. A repeat 5-fold cross-validation and the 4 indexes including the area under ROC curve (AUC), accuracy, sensitivity and specificity were used to evaluate the proposed model. In addition, the proposed model was compared quantitatively with different feature selection methods, different weight allocation algorithms, the model based on single mode single classifier, and two integrated models using other fusion methods. Repeated (5 times) 5-fold cross validation of the proposed model showed an accuracy of 0.78 for distinguishing toxicity from non-toxicity with an AUC of 0.83, a specificity of 0.79 and a sensitivity of 0.76. Compared with the models based on a single mode or a single classifier and other fusion models, the proposed model can more accurately predict rectal toxicity of radiotherapy for prostate cancer.

An optimized feature selection technique based on incremental feature analysis for bio-metric gait data classification

The classification of humanoid locomotion is a troublesome exercise because of non-linearity associate with gait signals. The classification using the different machine learning technique leads for over fitting and under fitting. To select the optimized feature is a difficult task. The high dimension feature vector requires a high computational cost. The hand craft feature selection machine learning techniques performed poor. We have used the incremental feature selection strategy for feature selection. In this paper we first selected the feature and identify the principle feature then we classify gait data using different machine learning technique (KNN, ANN, SVM, DNN and classifier fusion) and shown the performance comparison. Experimental result on real time datasets propose method is better than previous method as far as humanoid locomotion classification is concerned and the generalization accuracy provided by new feature selection method i.e. incremental feature selection (IFS) with analysis of variance (ANOVA) (Zhang et al., 20). During the feature extraction, 17 features were selected from the existing literatures (Wang et al. in IEEE Trans Circ Syst Video Technol 14(2):149–158, 15). Using all the features could lead to over fitting, information redundancy and dimension disaster. Thus, a system with optimal features was selected using ANOVA combined with IFA. These selected features were then fed as an input to the ANN, SVM, KNN and DNN model. These individual classifiers were combined to produce classifier fusion model. The 5-fold cross-validation was used to evaluate the performance of the proposed model. Based on the empirical results it may be concluded that classifier fusion provides satisfactory results (92.23 %) compared to other individual classifiers. One-way analysis of variance test, Friedman’s test and Kruskal-Wallis test has also been conducted to validate the statistical significance of the results. The proposed system can be used as recommender system based on behavioral gait pattern about the performance of player of Indian cricket team, Biometric and help to diagnosis Parkinson disease.

Dynamic hand gesture recognition using vision-based approach for human–computer interaction

In this work, a vision-based approach is used to build a dynamic hand gesture recognition system. Various challenges such as complicated background, change in illumination and occlusion make the detection and tracking of hand difficult in any vision-based approaches. To overcome such challenges, a hand detection technique is developed by combining three-frame differencing and skin filtering. The three-frame differencing is performed for both colored and grayscale frames. The hand is then tracked using modified Kanade---Lucas---Tomasi feature tracker where the features were selected using the compact criteria. Velocity and orientation information were added to remove the redundant feature points. Finally, color cue information is used to locate the final hand region in the tracked region. During the feature extraction, 44 features were selected from the existing literatures. Using all the features could lead to overfitting, information redundancy and dimension disaster. Thus, a system with optimal features was selected using analysis of variance combined with incremental feature selection. These selected features were then fed as an input to the ANN, SVM and kNN model. These individual classifiers were combined to produce classifier fusion model. Fivefold cross-validation has been used to evaluate the performance of the proposed model. Based on the experimental results, it may be concluded that classifier fusion provides satisfactory results (92.23 %) compared to other individual classifiers. One-way analysis of variance test, Friedman's test and Kruskal---Wallis test have also been conducted to validate the statistical significance of the results.

Effect of variation in gesticulation pattern in dynamic hand gesture recognition system

This paper presents a hand gesture recognition system which addresses the effect of variations in gesture pattern during gesticulation. Different gestures can be gesticulated in various patterns which increase the difficulties in recognizing the gestures. We have proposed two new features such as left sector trajectory features and right sector trajectory features which are able to recognize gestures even with the presence of variations in the gesticulation pattern. The effectiveness of the proposed system is illustrated by different experiments with our own gesture database. A comparative study has been made with the proposed features and three state-of-art features such as orientation; combination of location, orientation, velocity; and combination of ellipse and position features. The performance of the system was evaluated using this proposed set of features for different individual classifiers such as ANN, SVM, k-NN, Naïve Bayes and ELM. Finally, the decisions of the individual classifiers were combined using major voting rule to result in classifier fusion model. Based on the experimental results it may be concluded that classifier fusion provides satisfactory results compared to other individual classifiers. An accuracy of 91.07% was achieved using the classifier fusion technique as compared to baseline CRF (79.45%) and HCRF (83.07%) models.

Hand gesture recognition using two-level speed normalization, feature selection and classifier fusion

Hand gesture recognition provides an alternative way to many devices for human computer interaction. In this work, we have developed a classifier fusion based dynamic free-air hand gesture recognition system to identify the isolated gestures. Different users gesticulate at different speed for the same gesture. Hence, when comparing different samples of the same gesture, variations due to difference in gesturing speed should not contribute to the dissimilarity score. Thus, we have introduced a two-level speed normalization procedure using DTW and Euclidean distance-based techniques. Three features such as `orientation between consecutive points', `speed' and `orientation between first and every trajectory points' were used for the speed normalization. Moreover, in feature extraction stage, 44 features were selected from the existing literatures. Use of total feature set could lead to overfitting, information redundancy and may increase the computational complexity due to higher dimension. Thus, we have tried to overcome this difficulty by selecting optimal set of features using analysis of variance and incremental feature selection techniques. The performance of the system was evaluated using this optimal set of features for different individual classifiers such as ANN, SVM, k-NN and Naive Bayes. Finally, the decisions of the individual classifiers were combined using classifier fusion model. Based on the experimental results it may be concluded that classifier fusion provides satisfactory results compared to other individual classifiers. An accuracy of 94.78 % was achieved using the classifier fusion technique as compared to baseline CRF (85.07 %) and HCRF (89.91 %) models.

Risk prediction of product‐harm events using rough sets and multiple classifier fusion: an experimental study of listed companies in China

AbstractWith the increasing of frequency and destructiveness of product‐harm events, study on enterprise crisis management becomes essentially important, but little literature thoroughly explores the risk prediction method of product‐harm event. In this study, an initial index system for risk prediction was built based on the analysis of the key drivers of the product‐harm event's evolution; ultimately, nine risk‐forecasting indexes were obtained using rough set attribute reduction. With the four indexes of cumulative abnormal returns as the input, fuzzy clustering was used to classify the risk level of a product‐harm event into four grades. In order to control the uncertainty and instability of single classifiers in risk prediction, multiple classifier fusion was introduced and combined with self‐organising data mining (SODM). Further, an SODM‐based multiple classifier fusion (SB‐MCF) model was presented for the risk prediction related to a product‐harm event. The experimental results based on 165 Chinese listed companies indicated that the SB‐MCF model improved the average predictive accuracy and reduced variation degree simultaneously. The statistical analysis demonstrated that the SB‐MCF model significantly outperformed six widely used single classification models (e.g. neural networks, support vector machine, and case‐based reasoning) and other six commonly used multiple classifier fusion methods (e.g. majority voting, Bayesian method, and genetic algorithm).

Application of Multiple Classifier Fusion in the Discriminant Analysis of near Infrared Spectroscopy for Agricultural Products

Near infrared spectroscopy combined with chemometrics and pattern recognition has become a primary focus in the discriminant analysis of agricultural products. To date, most studies have focused on using a single classifier to discriminate the origins, varieties and grades of products. Others have focused on using multiple classifier fusion by weighted voting. Due to their attributes of continuity and internal similarity, discriminant models sometimes present poor performance. In this study, we achieved better performance by applying multiple classifier fusion models, including support vector machine (SVM), discriminant partial least squares (DPLS) and principal component and Fisher criterion (PPF). PPF showed continuity and similarity among different parts of tobacco leaves [i.e. upper (B), cutter (C) and lug (X)]. The similarities between each class and the others were quantified to values, and the sum of the similarity values of each class was defined as its similarity. SVM–DPLS–PPF fusion by voting and similarity constraint for decision resulted in better performance, with the correct discriminant rate improved on average by 14.1%, 8.2%, 17.3% and 4.6% compared with those achieved using SVM, DPLS, PPF and SVM–DPLS–PPF fusion by weighted voting for decision, respectively; in addition, the incorrect discriminant rate between B and X was reduced to zero. Therefore, we demonstrated the feasibility of using SVM–DPLS–PPF fusion by voting and similarity constraint for decision to discriminate between different parts of tobacco leaves. This technique could provide a new method for tobacco quality management, computer-aided grading and intelligent acquisition. It also provides a new discriminant method for analysing the attributes of continuity and similarity of agricultural products using near infrared spectroscopy.

English

Diagnosis techniques based on the dissolved gas analysis (DGA) have been developed to detect incipient faults in power transformers. Various methods exist based on DGA such as IEC, Roger, Dornenburg, and etc. However, these methods have been applied to different problems with different standards. Furthermore, it is difficult to achieve an accurate diagnosis by DGA without experienced experts. In order to resolve these drawbacks, this paper proposes a novel diagnosis method using Area Under Receiver Operating Characteristics Curve (AUROCC)-based Genetic Fuzzy SVM fusion model. Recently, the use of Receiver Operating Characteristic (ROC) Curve and the area under the ROC Curve called Area Under Receiver Operating Characteristics Curve (AUROCC) has been receiving much attention as a measure of the performance of machine learning algorithms. In this paper, we propose a SVM classifier fusion model using genetic fuzzy system. Genetic algorithms are applied to tune the optimal fuzzy membership functions. The performance of SVM classifiers are evaluated by their AUROCCs. Our experiments show that AUROCC-based genetic fuzzy SVM fusion model produces not only better AUROCC but also better accuracy than individual SVM classifiers

An enhanced classifier fusion model for classifying biomedical data

Classification is a technique where we discover the hidden class level of the unknown data. As different classification methods produces different accuracy according to the class level; classifier fusion is the solution to achieve more accuracy in every level of the input data. Selection of a suitable classifier in classifier fusion is a tedious task. In the proposed model, the output of the three classifiers is fed to the dynamic classifier fusion technique. This model will use each classifier for every individual data. We have used principal component analysis (PCA) to deal with issues of high dimensionality in biomedical classification. Three types of classification techniques on microarray data like multi layer perceptron (MLP), FLANN and PSO-FLANN have been implemented and compared; it has been observed that MLP is showing better result. We have also proposed a model for classifier fusion, where the model will choose the relevant classifiers according to the different region of datasets.

A framework for machine learning based on dynamic physical fields

Despite recent successes and advancements in artificial intelligence and machine learning, this domain remains under continuous challenge and guidance from phenomena and processes observed in natural world. Humans remain unsurpassed in their efficiency of dealing and learning from uncertain information coming in a variety of forms, whereas more and more robust learning and optimisation algorithms have their analytical engine built on the basis of some nature-inspired phenomena. Excellence of neural networks and kernel-based learning methods, an emergence of particle-, swarms-, and social behaviour-based optimisation methods are just few of many facts indicating a trend towards greater exploitation of nature inspired models and systems. This work intends to demonstrate how a simple concept of a physical field can be adopted to build a complete framework for supervised and unsupervised learning methodology. An inspiration for artificial learning has been found in the mechanics of physical fields found on both micro and macro scales. Exploiting the analogies between data and charged particles subjected to gravity, electrostatic and gas particle fields, a family of new algorithms has been developed and applied to classification, clustering and data condensation while properties of the field were further used in a unique visualisation of classification and classifier fusion models. The paper covers extensive pictorial examples and visual interpretations of the presented techniques along with some comparative testing over well-known real and artificial datasets.