Comparative study to realize an automatic speaker recognition system

In this research, we present an automatic speaker recognition system based on adaptive orthogonal transformations. To obtain the informative features with a minimum dimension from the input signals, we created an adaptive operator, which helped to identify the speaker’s voice in a fast and efficient manner. We test the efficiency and the performance of our method by comparing it with another approach, mel-frequency cepstral coefficients (MFCCs), which is widely used by researchers as their feature extraction method. The experimental results show the importance of creating the adaptive operator, which gives added value to the proposed approach. The performance of the system achieved 96.8% accuracy using Fourier transform as a compression method and 98.1% using Correlation as a compression method.

Color-Based Feature Extraction Method for Skin Segmentation Based on SVM

Different colored digital images can be represented in a variety of color spaces. Red-Green-Blue is the most commonly used color space. That can be transformed into Luminance, Blue difference, Red difference. These color pixels' defined features provide strong information about whether they belong to human skin or not. A novel color-based feature extraction method is proposed in this paper, which makes use of both red, green, blue, luminance, hue, and saturation information. The proposed method is used on an image database that contains people of various ages, races, and genders. The obtained features are used to segment the human skin using the Support-Vector- Machine algorithm, and the promising performance results of 89.86% accuracy are then compared to the most commonly used methods in the literature. Keywords: Skin segmentation, SVM, feature extraction, digital images

Enhanced Recognition of Amputated Wrist and Hand Movements by Deep Learning Method Using Multimodal Fusion of Electromyography and Electroencephalography

Motion classification can be performed using biometric signals recorded by electroencephalography (EEG) or electromyography (EMG) with noninvasive surface electrodes for the control of prosthetic arms. However, current single-modal EEG and EMG based motion classification techniques are limited owing to the complexity and noise of EEG signals, and the electrode placement bias, and low-resolution of EMG signals. We herein propose a novel system of two-dimensional (2D) input image feature multimodal fusion based on an EEG/EMG-signal transfer learning (TL) paradigm for detection of hand movements in transforearm amputees. A feature extraction method in the frequency domain of the EEG and EMG signals was adopted to establish a 2D image. The input images were used for training on a model based on the convolutional neural network algorithm and TL, which requires 2D images as input data. For the purpose of data acquisition, five transforearm amputees and nine healthy controls were recruited. Compared with the conventional single-modal EEG signal trained models, the proposed multimodal fusion method significantly improved classification accuracy in both the control and patient groups. When the two signals were combined and used in the pretrained model for EEG TL, the classification accuracy increased by 4.18–4.35% in the control group, and by 2.51–3.00% in the patient group.

Comparison of different feature extraction methods for applicable automated ICD coding

Background Automated ICD coding on medical texts via machine learning has been a hot topic. Related studies from medical field heavily relies on conventional bag-of-words (BoW) as the feature extraction method, and do not commonly use more complicated methods, such as word2vec (W2V) and large pretrained models like BERT. This study aimed at uncovering the most effective feature extraction methods for coding models by comparing BoW, W2V and BERT variants. Methods We experimented with a Chinese dataset from Fuwai Hospital, which contains 6947 records and 1532 unique ICD codes, and a public Spanish dataset, which contains 1000 records and 2557 unique ICD codes. We designed coding tasks with different code frequency thresholds (denoted as $$f_s$$ f s ), with a lower threshold indicating a more complex task. Using traditional classifiers, we compared BoW, W2V and BERT variants on accomplishing these coding tasks. Results When $$f_s$$ f s was equal to or greater than 140 for Fuwai dataset, and 60 for the Spanish dataset, the BERT variants with the whole network fine-tuned was the best method, leading to a Micro-F1 of 93.9% for Fuwai data when $$f_s=200$$ f s = 200 , and a Micro-F1 of 85.41% for the Spanish dataset when $$f_s=180$$ f s = 180 . When $$f_s$$ f s fell below 140 for Fuwai dataset, and 60 for the Spanish dataset, BoW turned out to be the best, leading to a Micro-F1 of 83% for Fuwai dataset when $$f_s=20$$ f s = 20 , and a Micro-F1 of 39.1% for the Spanish dataset when $$f_s=20$$ f s = 20 . Our experiments also showed that both the BERT variants and BoW possessed good interpretability, which is important for medical applications of coding models. Conclusions This study shed light on building promising machine learning models for automated ICD coding by revealing the most effective feature extraction methods. Concretely, our results indicated that fine-tuning the whole network of the BERT variants was the optimal method for tasks covering only frequent codes, especially codes that represented unspecified diseases, while BoW was the best for tasks involving both frequent and infrequent codes. The frequency threshold where the best-performing method varied differed between different datasets due to factors like language and codeset.

A Two-Staged Feature Extraction Method Based on Total Variation for Hyperspectral Images

Effective feature extraction (FE) has always been the focus of hyperspectral images (HSIs). For aerial remote-sensing HSIs processing and its land cover classification, in this article, an efficient two-staged hyperspectral FE method based on total variation (TV) is proposed. In the first stage, the average fusion method was used to reduce the spectral dimension. Then, the anisotropic TV model with different regularization parameters was utilized to obtain featured blocks of different smoothness, each containing multi-scale structure information, and we stacked them as the next stage’s input. In the second stage, equipped with singular value transformation to reduce the dimension again, we followed an isotropic TV model based on split Bregman algorithm for further detail smoothing. Finally, the feature-extracted block was fed to the support vector machine for classification experiments. The results, with three hyperspectral datasets, demonstrate that our proposed method can competitively outperform state-of-the-art methods in terms of its classification accuracy and computing time. Also, our proposed method delivers robustness and stability by comprehensive parameter analysis.

An airfoil geometric-feature extraction and discrepant data fusion learning method

The perception of geometric-features of airfoils is the basis in aerodynamic area for performance prediction, parameterization, aircraft inverse design, etc. There are three approaches to percept the geometric shape of airfoils, namely manual design of airfoil geometry parameters, polynomial definition and deep learning. The first two methods directly define geometric-features or polynomials of airfoil curves, but the number of extracted features is limited. Deep learning algorithms can extract a large number of potential features (called latent features). However, the features extracted by deep learning lack explicit geometrical meaning. Motivated by the advantages of polynomial definition and deep learning, we propose a geometric-feature extraction method (named Bézier-based feature extraction, BFE) for airfoils, which consists of two parts: manifold metric feature extraction and geometric-feature fusion encoder (GF encoder). Manifold metric feature extraction, with the help of the Bézier curve, captures manifold metrics (a sort of geometric-features) from tangent space of airfoil curves, and the GF-encoder combines airfoil coordinate data and manifold metrics together to form novel fused geometric-features. To validate the feasibility of the fused geometric-features, two experiments based on the public UIUC airfoil dataset are conducted. Experiment I is used to extract manifold metrics of airfoils and export the fused geometric-features. Experiment II, based on the Multi-task learning (MTL), is used to fuse the discrepant data (i.e., the fused geometric-features and the flight conditions) to predict the aerodynamic performance of airfoils. The results show that the BFE can generate more smooth and realistic airfoils than Auto-Encoder, and the fused geometric-features extracted by BFE can be used to reduce the prediction errors of C L and C D .

Finely Crafted Features for Traffic Sign Recognition

Traffic sign recognition (TSR) is the basic technology of the Advanced Driving Assistance System (ADAS) and intelligent automobile, whileas high-qualified feature vector plays a key role in TSR. Therefore, the feature extraction of TSR has become an active research in the fields of computer vision and intelligent automobiles. Although deep learning features have made a breakthrough in image classification, it is difficult to apply to TSR because of its large scale of training dataset and high space-time complexity of model training. Considering visual characteristics of traffic signs and external factors such as weather, light, and blur in real scenes, an efficient method to extract high-qualified image features is proposed. As a result, the lower-dimension feature can accurately depict the visual feature of TSR due to powerful descriptive and discriminative ability. In addition, benefiting from a simple feature extraction method and lower time cost, our method is suitable to recognize traffic signs online in real-world applications scenarios. Extensive quantitative experimental results demonstrate the effectiveness and efficiency of our method.

Research on gearbox impact feature extraction method based on improved ESMD

A gearbox vibration signal contains non-linear impact characteristics and the significant feature information tends to be overwhelmed by other interference components, which make it difficult to extract the typical fault features fully and effectively. Aiming at the key issue of how to effectively extract the impact characteristics, a fault diagnosis method based on improved extreme symmetric mode decomposition (ESMD) and a support vector machine (SVM) is proposed in this paper. The vibration signal is adaptively decomposed into multiple intrinsic mode function (IMF) components by the improved ESMD and then a certain number of components are selected with the maximum kurtosis-envelope spectrum index. The singular spectral entropy, energy entropy and permutation entropy of each component are applied to construct the feature vector set, in which the dimensionality of the set is reduced with the distance separability criterion. Finally, the dimension-reduced feature vector set is input into the SVM for pattern recognition. Dynamic simulation and experimental gearbox research show that the improved ESMD method can extract and identify gearbox fault information effectively.