Abstract: Due to the efficiency of learning relationships and complex structures hidden in data, graph-oriented methods have been widely investigated and achieve promising performance. Generally, in the field of multi-view learning, these algorithms construct informative graph for each view, on which the following clustering or classification procedure are based. However, in many real-world data sets, original data always contain noises and outlying entries that result in unreliable and inaccurate graphs, which cannot be ameliorated in the previous methods. In this paper, we propose a novel multi-view learning model which performs clustering/semi-supervised classification and local structure learning simultaneously. The obtained optimal graph can be partitioned into specific clusters directly. Moreover, our model can allocate ideal weight for each view automatically without explicit weight definition and penalty parameters. An efficient algorithm is proposed to optimize this model. Extensive experimental results on different real-world data sets show that the proposed model outperforms other state-of-the-art multi-view algorithms.

Abstract: While convolutional neural networks (CNNs) have successfully been applied for skin lesion classification, previous studies have generally considered only a single clinical/macroscopic image and output a binary decision. In this work, we have presented a method which combines multiple imaging modalities together with patient metadata to improve the performance of automated skin lesion diagnosis. We evaluated our method on a binary classification task for comparison with previous studies as well as a five class classification task representative of a real-world clinical scenario. We showed that our multimodal classifier outperforms a baseline classifier that only uses a single macroscopic image in both binary melanoma detection (AUC 0.866 vs 0.784) and in multiclass classification (mAP 0.729 vs 0.598). In addition, we have quantitatively showed the automated diagnosis of skin lesions using dermatoscopic images obtains a higher performance when compared to using macroscopic images. We performed experiments on a new data set of 2917 cases where each case contains a dermatoscopic image, macroscopic image and patient metadata.

Abstract: Classification features are crucial for an intrusion detection system (IDS), and the detection performance of IDS will change dramatically when providing different input features. Moreover, the large number of network traffic and their high-dimensional features will result in a very lengthy classification process. Recently, there is an increasing interest in the application of deep learning approaches for classification and learn feature representations. So, in this paper, we propose using the stacked sparse autoencoder (SSAE), an instance of a deep learning strategy, to extract high-level feature representations of intrusive behavior information. The original classification features are introduced into SSAE to learn the deep sparse features automatically for the first time. Then, the low-dimensional sparse features are used to build different basic classifiers. We compare SSAE with other feature extraction methods proposed by previous researchers. The experimental results both in binary classification and multiclass classification indicate the following: 1) the high-dimensional sparse features learned by SSAE are more discriminative for intrusion behaviors compared to previous methods and 2) the classification process of basic classifiers is significantly accelerated by using high-dimensional sparse features. In summary, it is shown that the SSAE is a feasible and efficient feature extraction method and provides a new research method for intrusion detection.

Abstract: The main purpose of this study was to produce landslide susceptibility maps using various ensemble-based machine learning models (i.e., the AdaBoost, LogitBoost, Multiclass Classifier, and Bagging models) for the Sacheon-myeon area of South Korea. A landslide inventory map including a total of 762 landslides was compiled based on reports and aerial photograph interpretations. The landslides were randomly separated into two datasets: 70% of landslides were selected for the model establishment and 30% were used for validation purposes. Additionally, 20 landslide condition factors divided into five categories (topographic factors, hydrological factors, soil map, geological map, and forest map) were considered in the landslide susceptibility mapping. The relationships among landslide occurrence and landslide conditioning factors were analyzed and the landslide susceptibility maps were calculated and drawn using the AdaBoost, LogitBoost, Multiclass Classifier, and Bagging models. Finally, the maps were validated using the area under the curve (AUC) method. The Multiclass Classifier method had higher prediction accuracy (85.9%) than the Bagging (AUC = 85.4%), LogitBoost (AUC = 84.8%), and AdaBoost (84.0%) methods.

Abstract: Digital pathology has entered a new era with the availability of whole slide scanners that create the high-resolution images of full biopsy slides. Consequently, the uncertainty regarding the correspondence between the image areas and the diagnostic labels assigned by pathologists at the slide level, and the need for identifying regions that belong to multiple classes with different clinical significances have emerged as two new challenges. However, generalizability of the state-of-the-art algorithms, whose accuracies were reported on carefully selected regions of interest (ROIs) for the binary benign versus cancer classification, to these multi-class learning and localization problems is currently unknown. This paper presents our potential solutions to these challenges by exploiting the viewing records of pathologists and their slide-level annotations in weakly supervised learning scenarios. First, we extract candidate ROIs from the logs of pathologists’ image screenings based on different behaviors, such as zooming, panning, and fixation. Then, we model each slide with a bag of instances represented by the candidate ROIs and a set of class labels extracted from the pathology forms. Finally, we use four different multi-instance multi-label learning algorithms for both slide-level and ROI-level predictions of diagnostic categories in whole slide breast histopathology images. Slide-level evaluation using 5-class and 14-class settings showed average precision values up to 81% and 69%, respectively, under different weakly labeled learning scenarios. ROI-level predictions showed that the classifier could successfully perform multi-class localization and classification within whole slide images that were selected to include the full range of challenging diagnostic categories.

Abstract: Traditional classification systems rely heavily on sufficient training data with accurate labels However, the quality of the collected data depends on the labelers, among which inexperienced labelers may exist and produce unexpected labels that may degrade the performance of a learning system In this paper, we investigate the multiclass classification problem where a certain amount of training examples are randomly labeled Specifically, we show that this issue can be formulated as a label noise problem To perform multiclass classification, we employ the widely used importance reweighting strategy to enable the learning on noisy data to more closely reflect the results on noise-free data We illustrate the applicability of this strategy to any surrogate loss functions and to different classification settings The proportion of randomly labeled examples is proved to be upper bounded and can be estimated under a mild condition The convergence analysis ensures the consistency of the learned classifier to the optimal classifier with respect to clean data Two instantiations of the proposed strategy are also introduced Experiments on synthetic and real data verify that our approach yields improvements over the traditional classifiers as well as the robust classifiers Moreover, we empirically demonstrate that the proposed strategy is effective even on asymmetrically noisy data

Abstract: With the increment of cyber traffic, there is a growing demand for cyber security. How to accurately detect cyber intrusions is the hotspot of recent research. Traditional Intrusion Detection Systems (IDS), based on traditional machine learning methods, lacks reliability and accuracy. In this paper, we build an IDS model with deep learning methodology. Instead of the traditional machine learning used in previous researches, we think deep learning has the potential to perform better in extracting features of massive data considering the massive cyber traffic in real life. Therefore, we propose to train an IDS model based on Convolution Neural Networks (CNN), a typical deep learning method, using entire NSL-KDD dataset. We study the performance of the model using multi class classification to compare with the performance of traditional machine learning methods including Random Forest (RF) and Support Vector Machine (SVM), and deep learning methods including Deep Belief Network (DBN) and Long Short Term Memory (LSTM). The experimental results show that the performance of our IDS model is superior to the performance of models based on traditional machine learning methods and novel deep learning methods in multi-class classification. Our model improves the accuracy of the intrusion detection and provides a new research direction for intrusion detection.

Abstract: Top-k error is currently a popular performance measure on large scale image classification benchmarks such as ImageNet and Places. Despite its wide acceptance, our understanding of this metric is limited as most of the previous research is focused on its special case, the top-1 error. In this work, we explore two directions that shed more light on the top-k error. First, we provide an in-depth analysis of established and recently proposed single-label multiclass methods along with a detailed account of efficient optimization algorithms for them. Our results indicate that the softmax loss and the smooth multiclass SVM are surprisingly competitive in top-k error uniformly across all k, which can be explained by our analysis of multiclass top-k calibration. Further improvements for a specific k are possible with a number of proposed top-k loss functions. Second, we use the top-k methods to explore the transition from multiclass to multilabel learning. In particular, we find that it is possible to obtain effective multilabel classifiers on Pascal VOC using a single label per image for training, while the gap between multiclass and multilabel methods on MS COCO is more significant. Finally, our contribution of efficient algorithms for training with the considered top-k and multilabel loss functions is of independent interest.

Abstract: This study aims to systematically review prior research on the evaluation and benchmarking of automated acute leukaemia classification tasks The review depends on three reliable search engines: ScienceDirect, Web of Science and IEEE Xplore A research taxonomy developed for the review considers a wide perspective for automated detection and classification of acute leukaemia research and reflects the usage trends in the evaluation criteria in this field The developed taxonomy consists of three main research directions in this domain The taxonomy involves two phases The first phase includes all three research directions The second one demonstrates all the criteria used for evaluating acute leukaemia classification The final set of studies includes 83 investigations, most of which focused on enhancing the accuracy and performance of detection and classification through proposed methods or systems Few efforts were made to undertake the evaluation issues According to the final set of articles, three groups of articles represented the main research directions in this domain: 56 articles highlighted the proposed methods, 22 articles involved proposals for system development and 5 papers centred on evaluation and comparison The other taxonomy side included 16 main and sub-evaluation and benchmarking criteria This review highlights three serious issues in the evaluation and benchmarking of multiclass classification of acute leukaemia, namely, conflicting criteria, evaluation criteria and criteria importance It also determines the weakness of benchmarking tools To solve these issues, multicriteria decision-making (MCDM) analysis techniques were proposed as effective recommended solutions in the methodological aspect This methodological aspect involves a proposed decision support system based on MCDM for evaluation and benchmarking to select suitable multiclass classification models for acute leukaemia The said support system is examined and has three sequential phases Phase One presents the identification procedure and process for establishing a decision matrix based on a crossover of evaluation criteria and acute leukaemia multiclass classification models Phase Two describes the decision matrix development for the selection of acute leukaemia classification models based on the integrated Best and worst method (BWM) and VIKOR Phase Three entails the validation of the proposed system

Abstract: In this letter, we exploit the potential benefits of machine learning in enhancing physical layer security in multi-input multi-output multi-antenna-eavesdropper wiretap channels. To this end, we focus on the scenario where the source adopts transmit antenna selection (TAS) as the transmission strategy. We assume that the channel state information (CSI) of the legitimate receiver is available to the source, while the CSI of the eavesdropper can be either known or not known at the source. By modeling the problem of TAS as a multiclass classification problem, we propose two machine learning-based schemes, namely, the support vector machine-based scheme and the naive-Bayes-based scheme, to select the optimal antenna that maximizes the secrecy performance of the considered system. Compared to the conventional TAS scheme, we show that our proposed schemes can achieve almost the same secrecy performance with relatively small feedback overhead. The work presented here provides insights into the design of new machine learning-based secure transmission schemes.

Abstract: Medical imaging plays an integral role in the identification, segmentation, and classification of brain tumors. The invention of MRI has opened new horizons for brain-related research. Recently, researchers have shifted their focus towards applying digital image processing techniques to extract, analyze and categorize brain tumors from MRI. Categorization of brain tumors is defined in a hierarchical way moving from major to minor ones. A plethora of work could be seen in literature related to the classification of brain tumors in categories such as benign and malignant. However, there are only a few works reported on the multiclass classification of brain images where each part of the image containing tumor is tagged with major and minor categories. The precise classification is difficult to achieve due to ambiguities in images and overlapping characteristics of different type of tumors. In the current study, a comprehensive review of recent research on brain tumors multiclass classification using MRI is provided. These multiclass classification studies are categorized into two major groups: XX and YY and each group are further divided into three sub-groups. A set of common parameters from the reviewed works is extracted and compared to highlight the merits and demerits of individual works. Based on our analysis, we provide a set of recommendations for researchers and professionals working in the area of brain tumors classification.

Abstract: Arrhythmia is considered a life-threatening disease causing serious health issues in patients, when left untreated. An early diagnosis of arrhythmias would be helpful in saving lives. This study is conducted to classify patients into one of the sixteen subclasses, among which one class represents absence of disease and the other fifteen classes represent electrocardiogram records of various subtypes of arrhythmias. The research is carried out on the dataset taken from the University of California at Irvine Machine Learning Data Repository. The dataset contains a large volume of feature dimensions which are reduced using wrapper based feature selection technique. For multiclass classification, support vector machine (SVM) based approaches including one-against-one (OAO), one-against-all (OAA), and error-correction code (ECC) are employed to detect the presence and absence of arrhythmias. The SVM method results are compared with other standard machine learning classifiers using varying parameters and the performance of the classifiers is evaluated using accuracy, kappa statistics, and root mean square error. The results show that OAO method of SVM outperforms all other classifiers by achieving an accuracy rate of 81.11% when used with 80/20 data split and 92.07% using 90/10 data split option.

Abstract: This paper focuses on the effective classification of the behavior of users accessing computing devices to authenticate them. The authentication is based on keystroke dynamics which captures the user's behavioral biometric and applies machine learning concepts to classify them. The users type a strong passcode ".tie5Roanl" to record their typing pattern. In order to confirm identity anonymous data from 94 users were collected to carry out the research. Given the raw data, features were extracted from the attributes based on the button pressed and action timestamp events. The Support Vector Machine (SVM) classifier uses multi-class classification with one vs. one decision shape function to classify different users. To reduce the classification error, it is essential to identify the important features from the raw data. In an effort to confront the generation of features from attributes an efficient feature extraction algorithm has been developed, obtaining high classification performance are now being sought.In this paper, we have applied minimum redundancy maximum relevance mRMR feature selection to increase the classification performance metrics and to confirm the identity of the users based on the way they access computing devices. From the results, we conclude that touch pressure, touch size and coordinates effectively contribute to identifying each user. The research will contribute significantly to the field of cyber-security by forming a robust au thentication system using machine learning algorithms.

Abstract: Objective: In this study, electroencephalography data of imagined words were classified using four different feature extraction approaches. Eight subjects were recruited for the recording of imagination with five different words, namely; “go,” “back,” “left,” “right,” and “stop.” Methods: One hundred trials for each word were recorded for both imagination and perception, although this study utilized only imagination data. Two different connectivity methods were applied, namely; a covariance-based and a maximum linear cross-correlation-based connectivity measure. These connectivity measures were further computed to extract the phase-only data as an additional method of feature extraction. In addition, four different channel selections were used. The final connectivity matrix from each of the four methods was vectorized and used as the feature vector for the classifier. To classify EEG data, a sigmoid activation function-based linear extreme learning machine was used. Result and Significance: We achieved a maximum classification rate of 40.30% ( p $ 0.007) and 87.90% ( p $ 0.003) in multiclass (five classes) and binary settings, respectively. Thus, our results suggested that EEG responses to imagined speech could be successfully classified using an extreme learning machine. Conclusion: This study involving the classification of imagined words can be a milestone contribution toward the development of practical brain–computer interface systems using silent speech.

Abstract: In recent years many sparse linear discriminant analysis methods have been proposed for high-dimensional classification and variable selection. However, most of these proposals focus on binary classification and they are not directly applicable to multiclass classification problems. There are two sparse discriminant analysis methods that can handle multiclass classification problems, but their theoretical justifications remain unknown. In this paper, we propose a new multiclass sparse discriminant analysis method that estimates all discriminant directions simultaneously. We show that when applied to the binary case our proposal yields a classification direction that is equivalent to those by two successful binary sparse LDA methods in the literature. An efficient algorithm is developed for computing our method with high-dimensional data. Variable selection consistency and rates of convergence are established under the ultrahigh dimensionality setting. We further demonstrate the superior performance of our proposal over the existing methods on simulated and real data.

Abstract: An automatic detection system for distinguishing healthy, ictal, and inter-ictal EEG signals plays an important role in medical practice. This paper presents a very large scale integration (VLSI) architecture of three-class classification for epilepsy and seizure detection. In order to find out the most efficient three-class classification scheme for hardware implementation, several multiclass non-linear support vector machine (NLSVM) classifiers are compared and validated using software implementation. Finally, the one-against-one (OAO) multiclass NLSVM is selected due to its highest accuracy. The designed system consists of a discrete wavelet transform (DWT)-based feature extraction module, a modified sequential minimal optimization (MSMO) training module, and an OAO multiclass classification module. A lifting structure of Daubechies order 4 wavelet is introduced in three-level DWT to save circuit area and speed up the computational time. The MSMO is used for on-chip training. The circuit of the largest absolute value decision is designed to avoid the unclassifiable problem in the OAO multiclass classification. The designed system is implemented on a field-programmable gate array (FPGA) platform and evaluated using the publicly available epilepsy dataset. The experimental results demonstrate that the designed system achieves high accuracy with low-dimensional feature vectors.

Abstract: Genetic Programming (GP) is gaining increased attention as an effective method for inducing classifiers for data classification. However, the manual design of a genetic programming classification algorithm is a non-trivial time consuming process. This research investigates the hypothesis that automating the design of a GP classification algorithm for data classification can still lead to the induction of effective classifiers and also reduce the design time. Two evolutionary algorithms, namely, a genetic algorithm (GA) and grammatical evolution (GE) are used to automate the design of GP classification algorithms. The classification performance of the automated designed GP classifiers i.e. GA designed GP classifiers and GE designed GP classifiers are compared to each other and to manually designed GP classifiers on real-world problems. Furthermore, a comparison of the design times of automated design and manual design is also carried out for the same set of problems. The automated designed classifiers were found to outperform manually designed classifiers across problem domains. Automated design time is also found to be less than manual design time. This study revealed that for the considered datasets GE performs better for binary classification while the GA does better for multiclass classification. Overall the results of the study are in support of the hypothesis.

Abstract: Objective In this paper, we propose a convolutional neural network (CNN)-based deep learning architecture for multiclass classification of obstructive sleep apnea and hypopnea (OSAH) using single-lead electrocardiogram (ECG) recordings. OSAH is the most common sleep-related breathing disorder. Many subjects who suffer from OSAH remain undiagnosed; thus, early detection of OSAH is important. Approach In this study, automatic classification of three classes-normal, hypopnea, and apnea-based on a CNN is performed. An optimal six-layer CNN model is trained on a training dataset (45 096 events) and evaluated on a test dataset (11 274 events). The training set (69 subjects) and test set (17 subjects) were collected from 86 subjects with length of approximately 6 h and segmented into 10 s durations. Main results The proposed CNN model reaches a mean [Formula: see text]-score of 93.0 for the training dataset and 87.0 for the test dataset. Significance Thus, proposed deep learning architecture achieved a high performance for multiclass classification of OSAH using single-lead ECG recordings. The proposed method can be employed in screening of patients suspected of having OSAH.

Abstract: Electroencephalogram (EEG) used to record the electrical activity of the brain is a standout amongst the most helpful tools which are utilized in the diagnosis of neurological disorders. In this paper, we propose two classification methods for automatic epileptic seizure detection based on EEG recordings. The proposed methods use Empirical Mode Decomposition (EMD) for feature extraction and Deep Neural Networks (DNNs) for classification. Multilayer perceptron is used in the first classification method to classify between normal and seizure cases by reducing features' dimension which speeds up the task. The classification accuracy achieved using this method is 100%. Deep Convolutional Neural Network (DCNN) is utilized in the second classification method to accomplish a high accuracy in multiclass classification task. The classification accuracy obtained using DCNN for classifying between the normal, interictal and ictal cases is 98.6%. The evaluation of the proposed methods is conducted using the 10-fold cross-validation methodology to ensure the robustness of the system.

Abstract: The goal of few-shot learning is to learn a classifier that generalizes well even when trained with a limited number of training instances per class. The recently introduced meta-learning approaches tackle this problem by learning a generic classifier across a large number of multiclass classification tasks and generalizing the model to a new task. Yet, even with such meta-learning, the low-data problem in the novel classification task still remains. In this paper, we propose Transductive Propagation Network (TPN), a novel meta-learning framework for transductive inference that classifies the entire test set at once to alleviate the low-data problem. Specifically, we propose to learn to propagate labels from labeled instances to unlabeled test instances, by learning a graph construction module that exploits the manifold structure in the data. TPN jointly learns both the parameters of feature embedding and the graph construction in an end-to-end manner. We validate TPN on multiple benchmark datasets, on which it largely outperforms existing few-shot learning approaches and achieves the state-of-the-art results.

Abstract: Adversarial examples are delicately perturbed inputs, which aim to mislead machine learning models towards incorrect outputs. While existing work focuses on generating adversarial perturbations in multiclass classification problems, many real-world applications fall into the multi-label setting, in which one instance could be associated with more than one label. To analyze the vulnerability and robustness of multi-label learning models, we investigate the generation of multi-label adversarial perturbations. This is a challenging task due to the uncertain number of positive labels associated with one instance, and the fact that multiple labels are usually not mutually exclusive with each other. To bridge the gap, in this paper, we propose a general attacking framework targeting multi-label classification problem and conduct a premier analysis on the perturbations for deep neural networks. Leveraging the ranking relationships among labels, we further design a ranking-based framework to attack multi-label ranking algorithms. Experiments on two different datasets demonstrate the effectiveness of the proposed frameworks and provide insights of the vulnerability of multi-label deep models under diverse targeted attacks.