Explore the vast range of titles available.

Algorithms for locomotion mode recognition (LMR) based on surface electromyography and mechanical sensors have recently been developed and could be used for the neural control of powered prosthetic legs. However, the variations in input signals, caused by physical changes at the sensor interface and human physiological changes, may threaten the reliability of these algorithms. This study aimed to investigate the effectiveness of applying adaptive pattern classifiers for LMR. Three adaptive classifiers, i.e., entropy-based adaptation (EBA), LearnIng From Testing data (LIFT), and Transductive Support Vector Machine (TSVM), were compared and offline evaluated using data collected from two able-bodied subjects and one transfemoral amputee. The offline analysis indicated that the adaptive classifier could effectively maintain or restore the performance of the LMR algorithm when gradual signal variations occurred. EBA and LIFT were recommended because of their better performance and higher computational efficiency. Finally, the EBA was implemented for real-time human-in-the-loop prosthesis control. The online evaluation showed that the applied EBA effectively adapted to changes in input signals across sessions and yielded more reliable prosthesis control over time, compared with the LMR without adaptation. The developed novel adaptive strategy may further enhance the reliability of neurally-controlled prosthetic legs.

Performance degradation will be caused by a variety of interfering factors for pattern recognition-based myoelectric control methods in the long term. This paper proposes an adaptive learning method with low computational cost to mitigate the effect in unsupervised adaptive learning scenarios. We presents a particle adaptive classifier (PAC), by constructing a particle adaptive learning strategy and universal incremental least square support vector classifier (LS-SVC). We compared PAC performance with incremental support vector classifier (ISVC) and non-adapting SVC (NSVC) in a long-term pattern recognition task in both unsupervised and supervised adaptive learning scenarios. Retraining time cost and recognition accuracy were compared by validating the classification performance on both simulated and realistic long-term EMG data. The classification results of realistic long-term EMG data showed that the PAC significantly decreased the performance degradation in unsupervised adaptive learning scenarios compared with NSVC (9.03% ± 2.23%, p < 0.05) and ISVC (13.38% ± 2.62%, p = 0.001), and reduced the retraining time cost compared with ISVC (2 ms per updating cycle vs. 50 ms per updating cycle).

An efficient feature extraction method for two classes of electroencephalography (EEG) is demonstrated using Common Spatial Patterns (CSP) with optimal spatial filters. However, the effects of artifacts and non-stationary uncertainty are more pronounced when CSP filtering is used. Furthermore, traditional CSP methods lack frequency domain information and require many input channels. Therefore, to overcome this shortcoming, a feature extraction method based on Online Recursive Independent Component Analysis (ORICA)-CSP is proposed. For EEG-based brain—computer interfaces (BCIs), especially online and real-time BCIs, the most widely used classifiers used to be linear discriminant analysis (LDA) and support vector machines (SVM). Previous evaluations clearly show that SVMs generally outperform other classifiers in terms of performance. In this case, Adaptive Support Vector Machine (A-SVM) is used for classification together with the ORICA-CSP method. The results are promising, and the experiments are performed on EEG data of 4 classes’ motor images, namely Dataset 2a of BCI Competition IV.

Designing a single domain generalization (DG) framework that generalizes from one source domain to arbitrary unseen domains is practical yet challenging in medical image segmentation, mainly due to the domain shift and limited source domain information. To tackle these issues, we reason that domain-adaptive classifier learning and domain-agnostic feature extraction are key components in single DG, and further propose an adaptive infinite prototypes (InfProto) scheme to facilitate the learning of the two components. InfProto harnesses high-order statistics and infinitely samples class-conditional instance-specific prototypes to form the classifier for discriminability enhancement. We then introduce probabilistic modeling and provide a theoretic upper bound to implicitly perform the infinite prototype sampling in the optimization of InfProto. Incorporating InfProto, we design a hierarchical domain-adaptive classifier to elasticize the model for varying domains. This classifier infinitely samples prototypes from the instance and mini-batch data distributions, forming the instance-level and mini-batch-level domain-adaptive classifiers, thereby generalizing to unseen domains. To extract domain-agnostic features, we assume each instance in the source domain is a micro source domain and then devise three complementary strategies, i.e., instance-level infinite prototype exchange, instance-batch infinite prototype interaction, and consistency regularization, to constrain outputs of the hierarchical domain-adaptive classifier. These three complementary strategies minimize distribution shifts among micro source domains, enabling the model to get rid of domain-specific characterizations and, in turn, concentrating on semantically discriminative features. Extensive comparison experiments demonstrate the superiority of our approach compared with state-of-the-art counterparts, and comprehensive ablation studies verify the effect of each proposed component. Notably, our method exhibits average improvements of 15.568% and 17.429% in dice on polyp and surgical instrument segmentation benchmarks.

Human Activity Recognition (HAR) involves the recognition of human activities using sensor data. Most of the techniques for HAR involve hand-crafted features and hence demand a good amount of human intervention. Moreover, the activity data obtained from sensors are highly imbalanced and hence demand a robust classifier design. In this paper, a novel classifier “ICGNet” is proposed for HAR, which is a hybrid of Convolutional Neural Network (CNN) and Gated Recurrent Unit (GRU). The CNN block used in the proposed network derives its inspiration from the famous Inception module. It uses multiple-sized convolutional filters simultaneously over the input and thus can capture the information in the data at multiple scales. These multi-sized filters introduced at the same level in the convolution network helps to compute more abstract features for local patches of data. It also makes use of 1 × 1 convolution to pool the input across channel dimension, and the intuition behind it is that it helps the model extract the valuable information hidden across the channels. The proposed ICGNet leverages the strengths of CNN and GRU and hence can capture local features and long-term dependencies in the multivariate time series data. It is an end-to-end model for HAR that can process raw data captured from wearable sensors without using any manual feature engineering. Integrating the adaptive user interfaces, the proposed HAR system can be applied to Human-Computer Interaction (HCI) fields such as interactive games, robot learning, health monitoring, and pattern-based surveillance. The overall accuracies achieved on two benchmark datasets viz. MHEALTH and PAMAP2 are 99.25% and 97.64%, respectively. The results indicate that the proposed network outperformed the similar architectures proposed for HAR in the literature.

This paper presents the identification and classification of Indian agricultural crop species using a novel combined local binary histogram pattern of gradient (LBHPG) image feature extraction technique. Initially, a partition of the leaf image background is done through the newly developed fast adaptive fuzzy C-mean clustering (FAFCM) technique. After that, leaf objects within the image are identified using the LBHPG method. For the classification, KNN, PNN, and SVM shallow machine learning classifiers are used for crop species identification. The performance evaluation is done using LBP and HOG individually along with the new proposed LBHPG technique for classification using KNN, PNN, and SVM Classifiers. The performance evaluation is based on six metrics parameters of the confusion matrix, viz., accuracy, sensitivity, specificity, precision, recall, and F-measure. The experimental results show that the proposed novel LBHP feature extraction technique with PNN Classifier gives the highest accuracy of 94.58%.

In current consequence of haematology, blood cancer i.e. acute lymphoblastic leukemia is very frequently founded in medical practice, which is characterized by over activation and functional abnormality of bone marrow. The abnormality is identified through physical examination with a screening of blood smears. However, this method is error prone and labor intensive task for haematologist. Hence, haematologist needs a specific computer aided diagnostic system (CAD) that can deal with these limitations of prior systems and capable of discriminating immature leukemic cells from mature healthy cells. Thus, this work addresses the problem of segmenting a microscopic blood image into different regions, and then further analyzes those regions for localization of the immature lymphoblast cell. Further, it investigates the use of different geometrical, chromatic and statistical textures features for nucleus as well as cytoplasm and pattern recognition techniques for sub typing immature acute lymphoblasts as per FAB (French– American – British) classification. This can facilitate haematologist for acquiring essential information about prognosis and for an appropriate cure for leukemia. The exhaustive experiments have been conducted on 260 microscopic blood images (i.e. 130 normal and 130 cancerous cells) taken from ALL-IDB database. The proposed techniques consisting of the segmentation module used for segmenting the nucleus and cytoplasm of each leukocyte cell, feature extraction module, feature dimensionality reduction module that uses principal component analysis (PCA) to mapped the higher feature space to lower feature space and classification module that employs the standard classifiers, like support vector machines, smooth support vector machines, k-nearest neighbour, probabilistic neural network and adaptive neuro fuzzy inference system.

Existing action recognition algorithms require a set of positive exemplars to train a classifier for each action. However, the amount of action classes is very large and the users’ queries vary dramatically. It is impractical to pre-define all possible action classes beforehand. To address this issue, we propose to perform action recognition with no positive exemplars, which is often known as the zero-shot learning. Current zero-shot learning paradigms usually train a series of attribute classifiers and then recognize the target actions based on the attribute representation. To ensure the maximum coverage of ad-hoc action classes, the attribute-based approaches require large numbers of reliable and accurate attribute classifiers, which are often unavailable in the real world. In this paper, we propose an approach that merely takes an action name as the input to recognize the action of interest without any pre-trained attribute classifiers and positive exemplars. Given an action name, we first build an analogy pool according to an external ontology, and each action in the analogy pool is related to the target action at different levels. The correlation information inferred from the external ontology may be noisy. We then propose an algorithm, namely adaptive multi-model rank-preserving mapping (AMRM), to train a classifier for action recognition, which is able to evaluate the relatedness of each video in the analogy pool adaptively. As multiple mapping models are employed, our algorithm has better capability to bridge the gap between visual features and the semantic information inferred from the ontology. Extensive experiments demonstrate that our method achieves the promising performance for action recognition only using action names, while no attributes and positive exemplars are available.

Detection of surface defects on organic light emitting diode (OLED) panels pose challenges such as irregular shapes and sizes along with varying textures and patterns on the panels. These challenges can be addressed by designing invariant features and training an anomaly detection algorithm such as support vector data description (SVDD). However, these hand designed features may not be capable of handling test datasets that have undergone distributional shift due to changes in lighting configuration or panel specification. This leads to a degradation of the classifier performance. In this paper, we propose a domain adaptation technique for outlier detection called as adaptive support vector data description (A-SVDD) to tackle distributional change in OLED panel datasets. The proposed method aims to learn an incremental classifier based on the existing classifier using an objective function similar to SVDD. We also investigate the application of features called as local inlier–outlier ratios augmented with modified local binary pattern (LBP) for detection of OLED panel defects in the context of SVDD and A-SVDD. In the experiments, the proposed domain adaptation technique is compared with baseline methods and existing approaches to demonstrate its effectiveness. A detailed evaluation of the features was performed in the context of A-SVDD and SVDD on several defects like scratch, spot, stain and pit to demonstrate that the combination of local inlier–outlier ratios and modified LBP significantly increases the detection accuracy.

Emotions play an indispensable role in human behaviors, and interaction based on emotion perception is attracting more attention. A method based on feature priority evaluation and classifier reinforcement is proposed in order to improve the accuracy of four-type subject-cross emotion identification. Firstly, the mixed-cross data processing strategy is employed to reduce the sample differences of extracted features. Then the feature selection method of feature priority evaluation with symmetric uncertainty is proposed to implement feature optimization for fused multi-channel features, which can effectively achieve representation of emotion states. Finally, the classifier reinforcement method of SVM-Adaboost is suggested to improve the classification performance of conventional SVM. The database DEAP is employed to verify the validity of the proposed method. Experimental results from different point of view show that the proposed method present a good emotion identification performance with accuracy 86.44%.