Dimension Of Feature Vector Research Articles

Multichannel Two-Dimensional Convolutional Neural Network Based on Interactive Features and Group Strategy for Chinese Sentiment Analysis.

In Chinese sentiment analysis tasks, many existing methods tend to use recurrent neural networks (e.g., long short-term memory networks and gated recurrent units) and standard one-dimensional convolutional neural networks (1D-CNN) to extract features. This is because a recurrent neural network can deal with the order dependence of the data to a certain extent and the one-dimensional convolution can extract local features. Although these methods have good performance in sentiment analysis tasks, recurrent neural networks (RNNs) cannot be parallelized, resulting in time-inefficiency, and the standard 1D-CNN can only extract a single sample feature, with the result that the feature information cannot be fully utilized. To this end, in this paper, we propose a multichannel two-dimensional convolutional neural network based on interactive features and group strategy (MCNN-IFGS) for Chinese sentiment analysis. Firstly, we no longer use word encoding technology but use character-based integer encoding to retain more fine-grained information. Besides, in character-level vectors, the interactive features of different elements are introduced to improve the dimensionality of feature vectors and supplement semantic information so that the input matches the model network. In order to ensure that more sentiment features are learned, group strategies are used to form several feature mapping groups, so the learning object is converted from the traditional single sample to the learning of the feature mapping group, so as to achieve the purpose of learning more features. Finally, multichannel two-dimensional convolutional neural networks with different sizes of convolution kernels are used to extract sentiment features of different scales. The experimental results on the Chinese dataset show that our proposed method outperforms other baseline and state-of-the-art methods.

Power Quality Disturbance Recognition Using Empirical Wavelet Transform and Feature Selection

With the growth of nonlinear electrical equipment, power quality disturbances (PQDs) often appear in electrical systems. To solve this, a practical heuristic methodology for PQD detection and classification based on empirical wavelet transform has been proposed. By using a multiresolution analysis tool, empirical wavelet transform, the voltage waveform signal is decomposed into several sub-signals, and some potential features are extracted in the statistical method. To reduce the feature vector dimensions, the ReliefF algorithm is used for feature selection and optimized for dimensionality reduction, which reduces the complexity of system calculation while ensuring accuracy. Finally, a classifier based on support vector machines (SVM) was built, and with the ranked feature vectors’ input, the PQD can be recognized. The experimental results verify that the classification results achieved high accuracy, which confirms the properties and robustness of the proposed approach in noisy environments.

Performance analysis of machine learning models for intrusion detection system using Gini Impurity-based Weighted Random Forest (GIWRF) feature selection technique

To protect the network, resources, and sensitive data, the intrusion detection system (IDS) has become a fundamental component of organizations that prevents cybercriminal activities. Several approaches have been introduced and implemented to thwart malicious activities so far. Due to the effectiveness of machine learning (ML) methods, the proposed approach applied several ML models for the intrusion detection system. In order to evaluate the performance of models, UNSW-NB 15 and Network TON_IoT datasets were used for offline analysis. Both datasets are comparatively newer than the NSL-KDD dataset to represent modern-day attacks. However, the performance analysis was carried out by training and testing the Decision Tree (DT), Gradient Boosting Tree (GBT), Multilayer Perceptron (MLP), AdaBoost, Long-Short Term Memory (LSTM), and Gated Recurrent Unit (GRU) for the binary classification task. As the performance of IDS deteriorates with a high dimensional feature vector, an optimum set of features was selected through a Gini Impurity-based Weighted Random Forest (GIWRF) model as the embedded feature selection technique. This technique employed Gini impurity as the splitting criterion of trees and adjusted the weights for two different classes of the imbalanced data to make the learning algorithm understand the class distribution. Based upon the importance score, 20 features were selected from UNSW-NB 15 and 10 features from the Network TON_IoT dataset. The experimental result revealed that DT performed well with the feature selection technique than other trained models of this experiment. Moreover, the proposed GIWRF-DT outperformed other existing methods surveyed in the literature in terms of the F1 score.

A Study on the Effect of Features Obtained From Signal Segments on Classification Success

Successful classification depends on the selection of the distinctive features and the effective channel subset used in the classification. In this study, novel and practical methods are proposed for determining the distinctive features and detecting effective channel subsets in the multi channel classification systems such as EEG. Two different feature extraction methods are compared in the study. The first one is based on classical Wavelet transform and the second is our proposed approach which used the slope of signal segments. Feature vectors are generated from some signal properties such as the mean, standard deviation, numerical integral of the Wavelet coefficients for classical Wavelet transform based feature extraction method. For our proposed method, only the slopes of signal segments are used for the feature vectors. In the proposed Signal Path Slope (SPS) feature extraction method, differently from the classical Wavelet based method, a Savitzky Golay (S-G) filter with an optimal frame length is applied to the signal before segmentation to make the path of the signal more prominent in time domain. In this way, the distinctive classification features are extracted by using S-G filter. For channel selection, an iterative channel selection method based on the classification results which divide the dataset labelled dataset into two groups as % 90 pre-training and %10 pre-test data is proposed. The dataset provided as dataset-3 in BCI competition IV is used in this study. The feature vectors extracted by using the proposed methods are classified for each method with the Support Vector Machine classifier. The results are given comparatively and it is observed that our proposed method has less computational complexity and more successful classification than Wavelet based classical feature extraction methods. The highest classification accuracies of % 67.74 and % 49.27 for subject-1 and subject-2 respectively are obtained with a low dimensional feature vector by proposed SPS feature extraction method. The classification accuracies achieved in the study are increased by % 8.24 for subject-1 and % 14.97 for subject-2 when compared average of the competition results. The significant increase in the success for both subjects shows the consistency of the proposed methods. By this study, it is observed that there is a subject-specific signal pattern related to motor imagery tasks in the brain. This pattern distinctive features is successfully determined by using the proposed methods.

Identification of Combined Power Quality Disturbances in the Presence of Distributed Generations using Variational Mode Decomposition and K-nearest Neighbors Classifier

Identification of combined power quality disturbances in the modern power systems by considering the development of different types of loads and distribution generations has become increasingly important. The novelty of this paper comes from the accurate and fast identification of the combined power quality disturbances in the presence of different distributed generations and loads such as photovoltaic cell, wind turbine with doubly fed induction generators, diesel engines, electric arc furnace, DC machine, 6-pulse and 12-pulse rectifier loads. In this paper, the features are extracted using variational mode decomposition, just from voltage waveforms. To reduce the redundant data, dimension of features vector, and time, the Relief-F method and correlation feature selection method are applied on the extracted features and these two methods are compared together. In this paper, the K-nearest neighbors classifier is used to classify the multiple power quality disturbances. To verify the effectiveness of the proposed method, different scenarios such as misfiring, variation of sun radiation and wind speed, entrance and exit of loads, capacitors and distributed generators, different fault at the grid in half-load to full-load were simulated. This method can be used as an added algorithm for smart metering in modern and smart power systems.

An Integrated Deep Learning Framework for Fruits Diseases Classification

Agriculture has been an important research area in the field of image processing for the last five years. Diseases affect the quality and quantity of fruits, thereby disrupting the economy of a country. Many computerized techniques have been introduced for detecting and recognizing fruit diseases. However, some issues remain to be addressed, such as irrelevant features and the dimensionality of feature vectors, which increase the computational time of the system. Herein, we propose an integrated deep learning framework for classifying fruit diseases. We consider seven types of fruits, i.e., apple, cherry, blueberry, grapes, peach, citrus, and strawberry. The proposed method comprises several important steps. Initially, data increase is applied, and then two different types of features are extracted. In the first feature type, texture and color features, i.e., classical features, are extracted. In the second type, deep learning characteristics are extracted using a pretrained model. The pretrained model is reused through transfer learning. Subsequently, both types of features are merged using the maximum mean value of the serial approach. Next, the resulting fused vector is optimized using a harmonic threshold-based genetic algorithm. Finally, the selected features are classified using multiple classifiers. An evaluation is performed on the PlantVillage dataset, and an accuracy of 99% is achieved. A comparison with recent techniques indicate the superiority of the proposed method.

Dynamic facial expression recognition of sprinters based on multi-scale detail enhancement

In order to solve the problems of low average gradient and long recognition time in traditional facial expression recognition method, a multi-scale detail enhancement method for facial dynamic expression recognition of sprint athletes is proposed. A principal component analysis method was used to establish the facial expression feature subspace of sprinters, to project and reduce the dimension of the facial dynamic expression feature vector of sprinters, and to obtain the low frequency information and high frequency information of the facial image of sprinters by bilateral filtering. The multi-scale details of expression are enhanced by using side suppression network model and improving image S curve. The feature vector of facial dynamic expression is input into support vector machine to recognise the facial dynamic expression of sprinter. Experimental results show that the average value of annoying gradient is about 98 and the shortest time s. is about 1.9.

UHF RFID Indoor Localization Algorithm Based on BP-SVR

With the widespread of Internet of Things (IoT), Radio Frequency Identification (RFID) technology is used in various fields. In the complex indoor environment, the traditional RFID indoor localization algorithm cannot give superior performance. Because a large number of antennas cannot be deployed in practical applications, the dimension of the signal strength feature vector obtained is relatively low, and it is not easy to fully describe the information in the environmental field. Thus, must adopt the appropriate antenna placement structure, the phase difference information can be effectively used as the feature. In this paper, a method of indoor localization algorithm based on Back Propagation–Support Vector Regression (BP-SVR) is proposed, which takes the signal strength and phase difference of the RFID tag as the feature inputs and uses the hidden layer of the neural network to enhance the dimensionality of the data. Moreover, the Sequential Minimal Optimization (SMO) algorithm is used to increase the rate of model learning. The method was valid in a 2D scene. Experimental results show that the method has an average positioning error of 9.5cm in the indoor area of 6m <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\times $ </tex-math></inline-formula> 8m.

Research on adaptive conversion of AI language based on rough set

In order to solve the problems of high complexity and low computational efficiency in traditional artificial intelligence (AI) language conversion methods, an adaptive AI language conversion method based on rough set is proposed. AI language preprocessing is realised by pre-emphasising, adding window, frame processing and endpoint detection. The attribute reduction algorithm based on rough set theory is used to select the features of AI language. The dimension of input feature vector is reduced. The experimental results show that after feature extraction, the computational efficiency is obviously improved, and the efficiency of the proposed method is the highest, averaging close to 100%. Compared with the traditional method, the complexity of the proposed method is lower, and the average complexity is 1.68% during the ten experimental iterations. This method simplifies the adaptive conversion process of AI language and has high computational efficiency.

Application Research of Trademark Recognition Technology based on SIFT Feature Recognition Algorithm in Advertising Design

Now-a-days, due to the sharp increase in the number of advertising designs, creative duplication is easy to occur in advertising design. If this situation is not discovered in time, it may cause legal disputes and cause damage to the reputation and property of the enterprise. In view of the above situation, this paper proposes a trademark recognition technology based on SIFT feature recognition algorithm to avoid duplication of advertisement design and cause copyright disputes. Aiming at the defect that the dimension of the image feature vector extracted by SIFT algorithm is too high, the principal component analysis method is used to reduce its dimension. For the problem of unsatisfactory image recognition rate accuracy of SIFT algorithm, a support vector machine is used to classify the extracted feature vector, so as to improve the image recognition rate. Based on the above content, build a trademark recognition model. The research results show that the recognition accuracy of the model reaches 98.82%, 0.66% and 0.58% higher than that of Model 1 and Model 2; AUC value of model 3 is 0.962, 0.039 higher than model 2 and 0.107 higher than model 1. The above results show that the proposed trademark recognition model can better identify similar advertising designs, thereby avoiding design duplication and legal disputes.

Clothes Retrieval Using M-AlexNet With Mish Function and Feature Selection Using Joint Shannon’s Entropy Pearson’s Correlation Coefficient

The online retrieval of images related to clothes is a crucial task because finding the exact items like the query image from a large amount of data is extremely challenging. However, large variations in clothes images degrade the retrieval accuracy of visual searches. Another problem with retrieval accuracy is high dimensions of feature vectors obtained from pre-trained deep CNN models. This research is an effort to enhance the training and test accuracy of clothes retrieval by using two different means. Initially, features are extracted using the modified AlexNet (M-AlexNet) with little modification in which ReLU activation function is replaced with a self-regularized Mish activation function because of its non-monotonic nature. The M-AlexNet with Mish is trained on CIFAR-10 dataset using SoftMax classifier. Another contribution is to reduce the dimensions of feature vectors obtained from M-AlexNet. The dimensions of features are reduced by selecting the top <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">k</i> ranked features and removing some of the dissimilar features using the proposed Joint Shannon’s Entropy Pearson Correlation Coefficient (JSE-PCC) technique to enhance the clothes retrieval performance. To calculate the efficacy of suggested methods, the comparison is performed with other deep CNN models such as baseline AlexNet, VGG-16, VGG-19, and ResNet50 on DeepFashion2, MVC, and the proposed Clothes Image Dataset (CID). Extensive experiments indicate that AlexNet with Mish attains 85.15%, 82.04%, and 83.65% accuracy on DeepFashion2, MVC, and 83.65% on CID datasets respectively. Hence, M-AlexNet and the proposed feature selection technique surpassed the results with a margin of 5.11% on DeepFashion2, 1.95% on MVC, and 3.51% CID datasets.

Brain tumor magnetic resonance images classification based machine learning paradigms

Cancer of the nervous system is one of the most common types of cancer in the world and mostly due to presence of a tumour in the brain. The symptoms and severity of the brain tumour depend on its location. The tumour within the brain may develop from nerves, dura (meningioma), pituitary gland (pituitary adenoma), or from the brain tissue itself (glioma). In this study we proposed a feature engineering approach for classification magnetic resonance imaging (MRI) of 3 kinds of most common brain tumour, i.e. glioma, meningioma, pituitary, and no-tumour. Here 5 machine learning classifiers were used, i.e. support vector machine, K-nearest neighbour (KNN), Naive Bayes, Decision Tree, and Ensemble classifier with their paradigms. The handcrafted features such as histogram of oriented gradients, local binary pattern features, and grey level co-occurrence matrix are extracted from the MRI, and the feature fusion technique is adopted to enhance the dimension of feature vector. The Fine KNN outperforms among the classifiers for recognition of 4 kinds of MRI: glioma, meningioma, pituitary, and no tumour, and achieved 91.1% accuracy and 0.95 area under the curve (AUC). The proposed method, i.e. Fine KNN, achieved 91.1% accuracy and 0.96 AUC. Furthermore, this model has the possibility to integrate in low-end devices unlike deep learning, which required a complex system.

A multi-layer two-dimensional convolutional neural network for sentiment analysis

The sentiment analysis method combining long short-term memory (LSTM) network and one-dimensional convolutional neural network (1D-CNN) has become the focus in sentiment analysis tasks. However, 1D-CNN usually captures local features, and LSTM is time-inefficient due to its serialisation characteristics. To this end, we propose a multi-layer two-dimensional convolutional neural network (ML-2D-CNN) for sentiment analysis. In our method, the character-based integer encoding method is used to retain fine-grained sentiment information. Besides, we innovatively introduce interactive features to improve the dimension of feature vectors and enhance sentiment information. The group expansion strategy is used to form several feature mapping groups, which is conducive to the learning of similar sentiment features in the group. Finally, we exploit multi-layer 2D-CNN to extract and mine the fine-grained information of the text. Extensive experiments are conducted on the SST dataset. The experimental results demonstrate that our proposed method is superior to other baseline and state-of-the-art methods.

A novel pixel’s fractional mean-based image enhancement algorithm for better image splicing detection

Image manipulation has become widely accessible to the masses over the past years due to the sophisticated image editing tools which are readily-available and easy to use. As a result, image forgery has increased such that it has become infeasible to discriminate authentic from tampered images with the naked eye. Image forgery plays a prominent role in the spread of misinformation, which might be criminalized under certain jurisdictions. Image splicing is a common type of image manipulation and constitutes one of the most widespread image tampering methods on the internet. Efforts have been made to tackle the implications of image forgery by developing computer algorithms that can discriminate tampered images, however, more research is needed to keep up with the advancements of image editing tools. Previously, we have explored fractional calculus in other image processing applications. In this study, we propose a novel pixel’s fractional mean (PFM) algorithm to enhance images prior to classification for better detection of image splicing forgery based on texture features. The proposed PFM enhances each pixel separately depending on the occurrence number of the pixel’s intensity. Two sets of texture algorithms are used to extract essential features from suspected spliced images. These features are then used with the “support vector machine” (SVM) classifier to classify authentic and spliced images. The proposed model demonstrated an accuracy rate of 97% when evaluated with the publicly-available image splicing dataset “CASIA v2.0”. With a relatively low dimension feature vector, the proposed model demonstrates high accuracy and efficiency, which corroborate the benefit of using fractional calculus in image processing algorithms.

Accurate Quaternion Polar Harmonic Transform for Color Image Analysis

Polar harmonic transforms (PHTs) have been applied in pattern recognition and image analysis. But the current computational framework of PHTs has two main demerits. First, some significant color information may be lost during color image processing in conventional methods because they are based on RGB decomposition or graying. Second, PHTs are influenced by geometric errors and numerical integration errors, which can be seen from image reconstruction errors. This paper presents a novel computational framework of quaternion polar harmonic transforms (QPHTs), namely, accurate QPHTs (AQPHTs). First, to holistically handle color images, quaternion-based PHTs are introduced by using the algebra of quaternions. Second, the Gaussian numerical integration is adopted for geometric and numerical error reduction. When compared with CNNs (convolutional neural networks)-based methods (i.e., VGG16) on the Oxford5K dataset, our AQPHT achieves better performance of scaling invariant representation. Moreover, when evaluated on standard image retrieval benchmarks, our AQPHT using smaller dimension of feature vector achieves comparable results with CNNs-based methods and outperforms the hand craft-based methods by 9.6% w.r.t mAP on the Holidays dataset.

Defect type identification of thin-walled stainless steel seamless pipe based on eddy current testing

Aimed at eddy current detection of defects in thin-walled stainless steel seamless pipes, an effective detection method for identifying defect types is proposed. First, the empirical mode decomposition (EMD) method is used to process the collected eddy current signals and obtain the principal intrinsic mode function (IMF) components of different defects. The Hilbert-Huang transform (HHT) is used to extract the frequency-domain features of the principal IMF components, which are combined with the time-domain features to form an effective defect feature vector. Then, principal component analysis (PCA) is used to reduce the dimensions of the defect feature vector and the redundant information is removed to obtain the principal component vector of the defect. Finally, two radial basis function (RBF) neural networks are used to identify and classify the defect types and three error evaluation indicators are selected to evaluate the performance of the classification network models.

Machine learning of transcripts and audio recordings of spontaneous speech for diagnosis of Alzheimer’s disease

AbstractBackgroundLanguage deficits may occur in early stages of Alzheimer’s disease (AD). Analysis of individuals’ language changes has been shown to predict the diagnosis and severity of AD. This work explored machine learning methods to detect AD using voice recordings of the Cookie Theft picture description tasks.MethodAn open‐source dataset from Dementia Bank, which included manual transcripts and audio recordings of the Cookie Theft picture description task from 309 individuals with AD and 243 cognitively healthy older adults, was employed in the classification analysis. We analyzed transcripts generated using three different approaches (Figure 1), including a) automatically generated transcripts based on denoised voice recording; b) automatically generated transcripts without the denoising process; and c) manuscript transcripts. Denoising was implemented using noisereduce, a Python library to minimize background noise (CITATION). Automatic transcripts were produced using two toolkits: CMUSpinx pocketsphinx interpreter (PS) and Mozilla DeepSpeech (DS). The Small‐Bidirectional Encoder Representations from Transformers (BERT) model was implemented to extract high dimensional feature vectors to provide contextual representation of transcripts for classification analysis. The experiment was designed to compare the performance of transcript type (manual vs. automatic), recording quality (noise vs. denoise), as well as speech recognition methods (DS vs. PS). A neural network model was constructed to classify between those with AD and healthy controls. The classification analysis was conducted using 10‐fold cross validation. The classification was repeated 20 times and the averaged results were reported (see Table 1).ResultThe performance of each approach is shown as Table 1. Overall, the model that used the features extracted from DS transcripts with denoised speech recordings achieved the best performance which had 92.72% accuracy for AD diagnosis validation results. The comparison between raw and denoised speech recordings showed conflicting performances. Using features from PS transcripts with noisy speech recordings obtained better performance than the denoised one, which was different with features from DS transcripts.ConclusionThe analysis approach which combined transcription driven recognition and transfer learning indicated the potential of better performance in AD diagnosis. Further investigation is needed to understand the reason for its superior performance.

A Data Mining Method For Improving the Prediction Of Bioinformatics Data

The composition of proteins nearly correlated with its function. Therefore, it is very ungently important to discuss a method that can automatically forecast protein structure. The fusion encoding method of PseAA and DC was adopted to describe the protein features. Using this encoding method to express protein sequences will produce higher dimensional feature vectors. This paper uses the algorithm of predigesting the characteristic dimension of proteins. By extracting significant feature vectors from the primitive feature vectors, eigenvectors with high dimensions are changed to eigenvectors with low dimensions. The experimental method of jackknife test is adopted. The consequences indicate that the arithmetic put forwarded here is appropriate for identifying whether the given protein is a homo-oligomer or a hetero-oligomer.

On the solidification of the manifold of the t-distributed stochastic neighbour embedding for condition classification of machine tools

t-distributed stochastic neighbour embedding (t-SNE) is of considerable interest in machining condition monitoring for feature selection. In this paper, the neural networks are introduced to solidify the manifold of the t-SNE prior to classification. This leads to the improved feature selection method, namely the Net-SNE. Conventional statistical features are first extracted from vibration signals to form a high dimensional feature vector. The redundancies in the feature vector are subsequently removed by the t-SNE. Then the neural networks build a mapping model between the high dimensional feature vector and the selected features. The new data is calculated directly using the mapping model. The experiments were conducted on a lathe and a milling machine to collect vibration signals under common working conditions. The K-nearest neighbour classifier is applied to a small sample case and a class-imbalance case to compare the classification performance with and without the Net-SNE. The results demonstrate that the Net-SNE has the advantage over the t-SNE, since it can mine the discriminative features and solidifiy the manifold in the calculation of the new data. Moreover, the proposed method significantly improves the classification accuracy by Net-SNE, along with better classification performance in data-limited situations.

Research on Semantic Similarity of Short Text Based on Bert and Time Warping Distance

The research on semantic similarity of short text plays an important role in machine translation, emotion analysis, information retrieval and other AI business applications. However, according to existing short text similarity research, the characteristics of ambiguous vocabularies are difficult to be effectively analyzed, the solution of the problem caused by words order needs to be further optimized as well. This paper proposes a short text semantic similarity calculation method that combines BERT and time warping distance algorithm, in order to solve the problem of vocabulary ambiguity. The model first uses the pre trained Bert model to extract the semantic features of the short text from the whole level, and obtains a 768 dimensional short text feature vector. Then, it transforms the extracted feature vector into a point sequence in space, uses the CTW algorithm to calculate the time warping distance between the curves connected by the point sequence, and finally uses the weight function designed by the analysis, according to the smaller the time warpage distance is, the higher the degree of small similarity is, to calculate the similarity between short texts. The experimental results show that this model can mine the feature information of ambiguous words, and calculate the similarity of short texts with lexical ambiguity effectively. Compared with other models, it can distinguish the semantic features of ambiguous words more accurately.