Principal Component Analysis Feature Research Articles

Target Recognition of SAR Images Based on SVM and KSRC.

A synthetic aperture radar (SAR) target recognition method combining linear and nonlinear feature extraction and classifiers is proposed. The principal component analysis (PCA) and kernel PCA (KPCA) are used to extract feature vectors of the original SAR image, respectively, which are classical and reliable feature extraction algorithms. In addition, KPCA can effectively make up for the weak linear description ability of PCA. Afterwards, support vector machine (SVM) and kernel sparse representation-based classification (KSRC) are used to classify the KPCA and PCA feature vectors, respectively. Similar to the idea of feature extraction, KSRC mainly introduces kernel functions to improve the processing and classification capabilities of nonlinear data. Through the combination of linear and nonlinear features and classifiers, the internal data structure of SAR images and the correspondence between test and training samples can be better investigated. In the experiment, the performance of the proposed method is tested based on the MSTAR dataset. The results show the effectiveness and robustness of the proposed method.

Research on the Application of Wireless Wearable Sensing Devices in Interactive Music

Wireless wearable devices can greatly assist and promote the artistic presentation of interactive music and have attracted the attention of more and more composers, musicians, dancers, and visual artists. It can pick up data information in real time, integrate with performers, and provide immersive performance experience. It not only builds a bridge between subjective feeling and spiritual perception for performers and audience but also enables audience to directly observe art information better. This paper mainly introduces the development process of a wearable sensor system designed for monitoring interactive music movement. Firstly, an interactive music motion model is established according to the principle of human body kinematics, and the experimental scheme of measuring the swaying angle of interactive music with a single sensor device is standardized. A multisensor fusion algorithm is proposed to estimate the swing angle of interactive music. Based on the “cost-incentive” emotional model, the wireless wearable device and interactive music model are regarded as continuous variables determined by the emotional effect value and the incentive value. Extract energy, rhythm, harmony, time domain, and spectrum features of interactive music of wireless wearable devices, and reduce the dimension of a music feature space through principal component analysis, spatial projection, and relief feature selection. Finally, the practicability of the system and the accuracy of the algorithm are verified by experiments. The recognition rate of wireless wearable devices and interactive music realized based on this algorithm was improved.

Information fusion and multi-classifier system for miner fatigue recognition in plateau environments based on electrocardiography and electromyography signals

Background and objectiveHuman factors are important contributors to accidents, especially human error induced by fatigue. In this study, field tests and analyses were conducted on physiological indexes extracted from electrocardiography (ECG) and electromyography (EMG) signals in miners working under the extreme conditions of a plateau environment. To provide insights into models for fatigue classification and recognition based on machine learning, multi-modal feature information fusion and miner fatigue identification based on ECG and EMG signals as physiological indicators were studied. MethodsFifty-five miners were randomly selected as field test subjects, and characteristic signals were extracted from 110 groups of ECG and EMG signals as the basic signals for fatigue analysis. We conducted principal component analysis (PCA) and grey relational analysis (GRA) on the measurement indicators. Support vector machine (SVM), random forest (RF) and extreme gradient boosting (XG-Boost) machine learning models were used for fatigue classification based on multi-modal information fusion. The area under the receiver operating characteristic (ROC) curve and the confusion matrix were used to evaluate the performance of the recognition models. ResultsThe ECG and EMG signals showed obvious changes with fatigue. The results of fatigue model identification showed that PCA feature fusion was superior to GRA feature fusion for all three machine learning approaches, and XG-Boost achieved the best performance, with a recognition accuracy of 89.47%, a sensitivity and specificity of 100%, and an AUC of 0.90. The SVM model also showed good recognition performance (89.47% accuracy, AUC=0.89). The worst performance was that of the RF model, with a recognition accuracy of only 78.95%. ConclusionsThis study shows that the physiological indexes of ECG and EMG exhibit obvious, regular changes with fatigue and that it is feasible to use SVM, RF and XG-Boost models for miner fatigue identification. The PCA fusion technique can improve the identification accuracy more than the GRA method. XG-Boost classification yields the best accuracy and robustness. This study can serve as a reference for clinical research on the identification of human fatigue at high altitudes and for the clinical study of acute mountain sickness and human acclimatization to high altitudes.

IQ-Data-Based WiFi Signal Classification Algorithm Using the Choi-Williams and Margenau-Hill-Spectrogram Features: A Case in Human Activity Recognition

This paper presents a novel approach that applies WiFi-based IQ data and time–frequency images to classify human activities automatically and accurately. The proposed strategy first uses the Choi–Williams distribution transform and the Margenau–Hill spectrogram transform to obtain the time–frequency images, followed by the offset and principal component analysis (PCA) feature extraction. The offset features were extracted from the IQ data and several spectra with maximum energy values in the time domain, and the PCA features were extracted via the whole images and several image slices on them with rich unit information. Finally, a traditional supervised learning classifier was used to label various activities. With twelve-thousand experimental samples from four categories of WiFi signals, the experimental data validated our proposed method. The results showed that our method was more robust to varying image slices or PCA numbers over the measured dataset. Our method with the random forest (RF) classifier surpassed the method with alternative classifiers on classification performance and finally obtained a 91.78% average sensitivity, 91.74% average precision, 91.73% average F1-score, 97.26% average specificity, and 95.89% average accuracy.

Selection of breast features for young women in northwestern China based on the random forest algorithm

In the research of breast morphology, numerous breast features are measured, whereas only a few parameters are adopted for classification. Therefore, how to extract the key variables from the multi-dimensional features in a rational way is an issue that is focused upon. This study aimed to reduce the complexity of the dimensionality reduction for further improving the objectivity and interpretability of the selected breast features. Since the random forest (RF) algorithm can quantify the feature importance during training, the method was adopted to determine the optimal breast features for classification and recognition in this paper. Firstly, the anthropometric data of 360 females from northwestern China aged from 19 to 27 years were measured by non-contact three-dimensional body scanning technology and the contact manual measurement method. Then, the k-means clustering was applied to categorize breast shapes, and the RF algorithm was utilized to quantify and rank the importance of 25 breast features. Finally, to verify the availability of the RF algorithm on breast feature selection, the t-distributed stochastic neighbor embedding method was adopted to visualize the distribution of breast shape clusters into two dimensions. Meanwhile, four neural networks were determined to recognize the breast morphology. The results demonstrate that fewer breast features can effectively increase the accuracy of breast shape classification and recognition. The best performance of breast shape classification and recognition is obtained when the number of breast features is 13. In this case, the average Hamming loss of four neural networks is the smallest (0.1136). Interestingly, the bust circumference and the horizontal curve of breasts across the bust points are found to be the most important of the 25 breast features in this paper. The importance of the breast curve features is higher than that of the breast cross-sectional features, while the breast positioning features have the lowest importance. Meanwhile, the RF algorithm is verified to be more effective than traditional dimensionality reduction methods, such as principal component analysis, hierarchical clustering, and recursive feature elimination. The approach developed in this paper can be generalized to the dimensionality reduction of other body morphology.

Serial correlated–uncorrelated concurrent space method for process monitoring

Due to the closed-loop feedback control system, the data collected in the industry process is always temporal serial correlated. Moreover, different types of sensor data (such as temperature, pressure, liquid level, flow and so on) would show different temporal serial correlations. Meanwhile, the current process monitoring method considers all types of sensor data equally, ignoring the difference in temporal serial correlations caused by various sensor types. In response to this, serial correlated–uncorrelated concurrent space method is proposed in this work, where process variable original space is divided into serial correlated space and serial uncorrelated space via the degree of temporal serial correlations. In addition, the proposed method not only considers the local monitoring within space via principal component analysis and slow feature analysis respectively, but also monitors the information between-space based on the moving window and the mutual information. Finally, on the basis of the monitoring statistic within space and between-space, the comprehensive monitoring indicator is constructed via the local outlier factor method. The advantage and superiority of the proposed method is illustrated via testing on Tennessee Eastman process and Continuous Stirred Tank Reactor process.

Opposition Observations of 162173 Ryugu: Normal Albedo Map Highlights Variations in Regolith Characteristics

Abstract On 2019 January 8, the Telescopic Optical Navigation Camera (ONC-T) on board the Hayabusa2 spacecraft observed the Cb-type asteroid 162173 Ryugu under near-opposition illumination and viewing conditions from approximately 20 km in distance. Although opposition observations have never been used for mapping purposes of a planetary body, we found three advantages for mapping under these conditions: (1) images are free of topographic shadows, (2) the reflectance is nearly independent of the orientation of the surface, and (3) spurious color artifacts that may appear near shadowed terrain are avoided. We present normal albedo maps, one for each of the seven filters (0.40–0.95 μm), using an empirical photometric correction. Global coverage of Ryugu is 99.4%. The 0.55 μm band average normal albedo is 4.06% ± 0.10%. Various spectral variations are derived from these maps. Spectral features of regions and boulders are quantified by examining the normal albedo-derived spectral slope and UV index (spectral slope from visible to ultraviolet wavelength) value. In terms of space weathering, three spectral characteristics are observed over the majority of Ryugu: (1) reddening, (2) increases in reflectance at ultraviolet wavelengths compared to visible, and (3) darkening. By contrast, the bright boulders (“type 3”) show a different trend, with wide variations in the 0.95 μm albedo and UV index. Finally, principal component analysis (PCA) comparisons with other asteroids strongly suggest that the main components of Ryugu belong to the B-Cb-type populations. The PCA feature of the fresh material on Ryugu is close to the Eulalia family.

Design of Deep Learning Algorithm for IoT Application by Image based Recognition

The Internet of Things (IoT) is an ecosystem comprised of multiple devices and connections, a large number of users, and a massive amount of data. Deep learning is especially suited for these scenarios due to its appropriateness for "big data" difficulties and future concerns. Nonetheless, guaranteeing security and privacy has emerged as a critical challenge for IoT administration. In many recent cases, deep learning algorithms have proven to be increasingly efficient in performing security assessments for IoT devices without resorting to handcrafted rules. This research work integrates principal component analysis (PCA) for feature extraction with superior performance. Besides, the primary objective of this research work is to gather a comprehensive survey data on the types of IoT deployments, along with security and privacy challenges with good recognition rate. The deep learning method is performed through PCA feature extraction for improving the accuracy of the process. Our other primary goal in this study paper is to achieve a high recognition rate for IoT based image recognition. The CNN approach was trained and evaluated on the IoT image dataset for performance evaluation using multiple methodologies. The initial step would be to investigate the application of deep learning for IoT image acquisition. Additionally, when it comes to IoT image registering, the usefulness of the deep learning method has been evaluated for increasing the appropriateness of image recognition with good testing accuracy. The research discoveries on the application of deep learning in the Internet of Things (IoT) system are summarized in an image-based identification method that introduces a variety of appropriate criteria.

Enhanced features in principal component analysis with spatial and temporal windows for damage identification

Principal component analysis (PCA) methods have been widely applied to damage identification in the long-term structural health monitoring (SHM) of infrastructure. Usually, the first few eigenvector components derived by PCA methods are treated as damage-sensitive features. In this paper, the effective method of double-window PCA (DWPCA) and novel features are proposed for better damage identification performance. In the proposed method, spatial and temporal windows are introduced to the traditional PCA method. The spatial windows are applied to group damage-sensitive sensors and exclude those sensors insensitive to damage, while the temporal window is applied to better discriminate eigenvectors between the damaged and healthy states. In addition, the length and directional angle of the eigenvector variation between the healthy and damaged states are used as the damage-sensitive features, instead of the components of the eigenvector variation used in previous studies. Numerical simulations based on a large-scale bridge reveal that the proposed features are successful in identifying the damage located far from sensors due to the use of both spatial and temporal windows as well as the length of the eigenvector variation. In addition, compared to the previous PCA and moving PCA methods, the novel features have higher sensitivity and resolution in damage identification.

Dynamic industrial process monitoring based on concurrent fast and slow‐time‐varying feature analytics

AbstractDynamic features always demonstrate the coexistences of local fast‐variabilities and the overall slow‐trend. Single model based methods cannot achieve a satisfactory monitoring result in industrial processes with composite dynamicities. A comprehensive dynamic process monitoring method based on concurrent fast and slow‐time‐varying feature analytics is proposed in this paper. A sequential correlation coefficient is defined firstly, and all the process variables are divided into fast and slow‐time‐varying blocks. Afterwards, dynamic inner principal component analysis (DiPCA) and slow feature analysis (SFA) are employed to establish monitoring models in both blocks, respectively. Based on Bayesian inference mechanism, a novel weighted fusion strategy is designed. Finally, the proposed method is verified by the Tennessee Eastman process. With the integration of the monitoring results in both blocks, the performance of the proposed method is superior to the traditional ones.

Identification of paralytic shellfish poison producing algae based on three-dimensional fluorescence spectra and quaternion principal component analysis

In view of the problem of the paralytic shellfish poison producing algae on-line measurement and identification, a new feature extraction method of paralytic shellfish poison producing algae measurement and identification based on quaternion principal component analysis (QPCA) is investigated. The three-dimensional (3D) fluorescence spectra of three common species of paralytic shellfish poison producing algae and eight species common of non paralytic shellfish poison producing algae are analyzed. The quaternion parallel representation model of algae three-dimensional fluorescence spectrum data is established, then the features of quaternion principal component is extracted to use as the input of k-nearest neighbor (KNN) classifier, and the identification of paralytic shellfish poison producing algae is realized by the three-dimensional fluorescence spectra coupled with quaternion principal component analysis. The results show that under the quaternion parallel representation model, the recognition accuracy rate of multiplication feature, modulus feature and summation feature is 90%, 95% and 100% respectively. Compared with that of the principal component analysis feature extraction method, the recognition accuracy rate in pure samples by summation feature of quaternion principal component is improved by 10%. This study provides an experimental basis for the accurate monitoring technology of three-dimensional fluorescence spectrum of paralytic shellfish poison producing algae.

LightGBM Indoor Positioning Method Based on Merged Wi-Fi and Image Fingerprints.

Smartphones are increasingly becoming an efficient platform for solving indoor positioning problems. Fingerprint-based positioning methods are popular because of the wide deployment of wireless local area networks in indoor environments and the lack of model propagation paths. However, Wi-Fi fingerprint information is singular, and its positioning accuracy is typically 2–10 m; thus, it struggles to meet the requirements of high-precision indoor positioning. Therefore, this paper proposes a positioning algorithm that combines Wi-Fi fingerprints and visual information to generate fingerprints. The algorithm involves two steps: merged-fingerprint generation and fingerprint positioning. In the merged-fingerprint generation stage, the kernel principal component analysis feature of the Wi-Fi fingerprint and the local binary pattern features of the scene image are fused. In the fingerprint positioning stage, a light gradient boosting machine (LightGBM) is trained with mutually exclusive feature bundling and histogram optimization to obtain an accurate positioning model. The method is tested in an actual environment. The experimental results show that the positioning accuracy of the LightGBM method is 90% within a range of 1.53 m. Compared with the single-fingerprint positioning method, the accuracy is improved by more than 20%, and the performance is improved by more than 15% compared with other methods. The average locating error is 0.78 m.

Evolutionary Processes Involved in the Emergence and Expansion of an Atypical O. sativa Group in Madagascar

Understanding crops genetic diversity and the evolutionary processes that accompanied their worldwide spread is useful for designing effective breeding strategies. Madagascar Island was one of the last major Old World areas where human settlement brought the introduction of Oryza sativa. Early studies in the island had reported the presence of a rice group specific to Madagascar. Using 24 K SNP, we compared diversity patterns at the whole genome and at haplotype (30 SNP-long segments along the genome) levels, between 620 Malagasy and 1929 Asian rice accessions. The haplotype level analysis aimed at identifying local genotypic variations, relative to the whole genome level, using a group assignment method that relies on kernel density estimation in a Principal Component Analysis feature space. Migration bottleneck had resulted in 10–25% reduction of diversity among the Malagasy representatives of indica and japonica populations. Compared to their Asian counterpart, they showed slightly lower indica and japonica introgressions, suggesting the two populations had undergone less recombination when migration to the island occurred. The origins of the Malagasy indica and japonica groups were delineated to indica subpopulation from the Indian subcontinent and to tropical japonica from the Malay Archipelago, respectively. The Malagasy-specific group (Gm) had a rather high gene diversity and an original haplotype pattern: much lower share of indica haplotypes, and much higher share of Aus and japonica haplotypes than indica. Its emergence and expansion are most probably due to inter-group recombination facilitated by sympatry between indica-Aus admixes and “Bulu” type landraces of japonica in the central high plateaux of Madagascar, and to human selection for adaptation to the lowland rice cultivation. Pattern of rice genetic diversity was also tightly associated with the history of human settlement in the island. Emergence of the Gm group is associated with the latest arrivals of Austronesians, who founded the Merina kingdom in the high plateaux and developed lowland rice cultivation. As an intermediary form between Aus, indica and japonica, the three pillars of O. sativa domestication, Gm represents a very valuable genetic resource in breeding for adaptation to cold tolerance in tropical highlands. We proposed the name Rojo for this new rice group.

Learning to recognize while learning to speak: Self-supervision and developing a speaking motor

Traditionally, learning speech synthesis and speech recognition were investigated as two separate tasks. This separation hinders incremental development for concurrent synthesis and recognition, where partially-learned synthesis and partially-learned recognition must help each other throughout lifelong learning. This work is a paradigm shift—we treat synthesis and recognition as two intertwined aspects of a lifelong learning agent. Furthermore, in contrast to existing recognition or synthesis systems, babies do not need their mothers to directly supervise their vocal tracts at every moment during the learning. We argue that self-generated non-symbolic states/actions at fine-grained time level help such a learner as necessary temporal contexts. Here, we approach a new and challenging problem—how to enable an autonomous learning system to develop an artificial speaking motor for generating temporally-dense (e.g., frame-wise) actions on the fly without human handcrafting a set of symbolic states. The self-generated states/actions are Muscles-like, High-dimensional, Temporally-dense and Globally-smooth (MHTG), so that these states/actions are directly attended for concurrent synthesis and recognition for each time frame. Human teachers are relieved from supervising learner’s motor ends. The Candid Covariance-free Incremental (CCI) Principal Component Analysis (PCA) is applied to develop such an artificial speaking motor where PCA features drive the motor. Since each life must develop normally, each Developmental Network-2 (DN-2) reaches the same network (maximum likelihood, ML) regardless of randomly initialized weights, where ML is not just for a function approximator but rather an emergent Turing Machine. The machine-synthesized sounds are evaluated by both the neural network and humans with recognition experiments. Our experimental results showed learning-to-synthesize and learning-to-recognize-through-synthesis for phonemes. This work corresponds to a key step toward our goal to close a great gap toward fully autonomous machine learning directly from the physical world.

A Robust Machine Learning Algorithm for Cosmic Galaxy Images Classification Using Neutrosophic Score Features.

The development of galaxy images classification automated schemes is necessary to identify, classify, and study the evolution and formation of galaxies in our universe as it is one of the main challenges faced by astronomers today. Scientists can also build a deeper understanding of galaxies evolution and formation by classifying them into various classes. This paper proposed a robust novel hybrid automated intelligent algorithm based on neutrosophic techniques (NTs) and machine learning techniques for classifying the galaxy morphological astronomical images into various types of galaxies images (Hubble types) based on its features into three main classes; Elliptical, Spiral and Irregular. A nine classifiers performance was assessed based on the machine learning (ML) techniques by usinga combination of a sets of morphic features (MFs); obtained from image analysis and principal component analysis (PCA) features. The results indicated that; the classifier which called, multilayer perceptron (MLP) gives the better results for the features set consisting of nine MFs and 24 PCs features among all tested cases; Mean squared error (MSE) = 0.0021; Normalized mean squared error (NMSE)= 0.0371; Correlation coefficient (r) = 0.9889, and the Error = 0.7751 with an accuracy 99.2249 %. Then, to improve the system efficiency; the neutrosophic techniques were applied in combination with the classifier that gave the best results in the previous step on the same extracted features to get a three robust component namely; membership, indeterminacy and non-membership components to fed to the neural network. The results showed that; the combination between the NTs and MLP classifier for (MFs with 4PCs) gives the best results; MSE = 0.0001; NMSE = 0.0009; r = 0.9997, and Error = 0.4212 with an accuracy about 99.5788 % in total for all chosen sets of features. The results showed the high performance of the proposed method comparing with other methods. The experimental results are performed based on a sample from (EFIGI) catalog.

Linear dynamical systems approach for human action recognition with dual-stream deep features

Human action recognition with a dual-stream architecture using linear dynamical systems (LDSs) approach is discussed in this paper. First, a slice process is established to extract original slices from video sequences. Two slicing methods are adopted to subtract or reserve the remaining frames in the video sequences. By applying background subtraction to adjacent frames of the original slices, difference slices are also expressed. To capture the spatial component of the background and difference expressed in each slice simultaneously, a framework based on pre-trained convolutional neural networks (CNNs) is introduced for dual-stream deep feature extraction. Subsequently, LDSs are established to model the timing relationship between adjacent slices and obtain the temporal component of the background and difference features, which are expressed as linear dynamical background feature (LD-BF) and linear dynamical difference feature (LD-DF). Practical experiments were conducted to demonstrate the effectiveness and robustness of the proposed approach using different datasets. Specifically, our experiments were conducted on the UCF50, UCF101, and hmdb51 datasets. The impact of retaining various principal component analysis (PCA) feature dimensions and distinct slicing methods in terms of detail recognition were evaluated. In particular, combining LD-BF with LD-DF under appropriate feature dimensions and slicing methods further improved the accuracy for the UCF50, UCF101, and hmdb51 datasets. In addition, the computational cost of the feature extraction process was evaluated to illustrate the efficiency of the proposed approach. The experimental results show that the proposed approach is competitive with state-of-the-art approaches in the three datasets.

Classification and localization of transmission line faults using curve fitting technique with Principal component analysis features

This paper investigates the application of Principal Component Analysis (PCA) for the development of a simple method of classification and localization of power system faults for a 150 km long transmission line. The proposed work uses only a quarter cycle pre-fault and half cycle post-fault receiving end line current signals for fast identification and isolation of the faulty line. This work analyzes current data of ten different fault classes. The fault signals are recorded at fourteen intermediate geometric locations, out of which, three locations are used for developing the PCA-ratio based classifier and a total of six locations are used for developing the localizer model. PCA is applied here to develop PC score indices, based on which, fault signature curve is developed using best fit analogy. This curve works as the key signature of localizer for each class and phase. The work is made more practically suited by incorporating noise in the signals. Thus an effort has been made in the proposed work for developing a complete practical fault diagnosis algorithm with an aim to achieve high level of accuracy both to classify and localize fault. The proposed classifier is found to produces 100% accuracy, and the localizer is found to achieve an average localization error of only 0.1189% for 40 dB SNR and 0.3965% error at a further higher noise level of 25 dB SNR, with less than 4% of maximum error.

Machine Learning and Feature Selection Methods for EGFR Mutation Status Prediction in Lung Cancer

The evolution of personalized medicine has changed the therapeutic strategy from classical chemotherapy and radiotherapy to a genetic modification targeted therapy, and although biopsy is the traditional method to genetically characterize lung cancer tumor, it is an invasive and painful procedure for the patient. Nodule image features extracted from computed tomography (CT) scans have been used to create machine learning models that predict gene mutation status in a noninvasive, fast, and easy-to-use manner. However, recent studies have shown that radiomic features extracted from an extended region of interest (ROI) beyond the tumor, might be more relevant to predict the mutation status in lung cancer, and consequently may be used to significantly decrease the mortality rate of patients battling this condition. In this work, we investigated the relation between image phenotypes and the mutation status of Epidermal Growth Factor Receptor (EGFR), the most frequently mutated gene in lung cancer with several approved targeted-therapies, using radiomic features extracted from the lung containing the nodule. A variety of linear, nonlinear, and ensemble predictive classification models, along with several feature selection methods, were used to classify the binary outcome of wild-type or mutant EGFR mutation status. The results show that a comprehensive approach using a ROI that included the lung with nodule can capture relevant information and successfully predict the EGFR mutation status with increased performance compared to local nodule analyses. Linear Support Vector Machine, Elastic Net, and Logistic Regression, combined with the Principal Component Analysis feature selection method implemented with 70% of variance in the feature set, were the best-performing classifiers, reaching Area Under the Curve (AUC) values ranging from 0.725 to 0.737. This approach that exploits a holistic analysis indicates that information from more extensive regions of the lung containing the nodule allows a more complete lung cancer characterization and should be considered in future radiogenomic studies.

Anomaly Intrusion Detection Using SVM and C4.5 Classification With an Improved Particle Swarm Optimization (I-PSO)

In the last decade, many researchers have proposed several models of classification algorithms for enhancing the accuracy performance of IDSs. However, there is a minor issue arising in the classifier's incapability to process high-dimensional data. Using several classifiers always outperforms a single classifier's performance. This paper proposes a novel intrusion detection system by classifying data with SVM as well as C4.5 decision tree algorithm. The NSL-KDD dataset is first preprocessed with principal component analysis (PCA) and later feature selected with an improved particle swarm optimization (I-PSO). This framework improved the time consumption and inaccurate feature selection issues in other methodologies. Upon simplifying features more effectively, the outcomes display an excellent agreement with the conventional PSO techniques and their results, and also produce enhanced outcomes when compared to only single classifier. The results demonstrate better performance when subject to different attack-scenarios and can be used for enterprise network security applications.

Precise detection of early breast tumor using a novel EEMD-based feature extraction approach by UWB microwave.

The accurate detection of early breast cancer is of great significance to each patient. In recent years, breast cancer non-invasive detection technology based on Ultra-Wideband (UWB) microwave has been proposed and developed extensively, which is complementary to the existing methods. In this paper, a novel approach is proposed for tumor existence detection based on feature extraction algorithm. Firstly, the breast features are obtained by Ensemble Empirical Mode Decomposition (EEMD) and valid correlation Intrinsic Mode Function (IMF) selection. Secondly, raw feature datasets are constructed and then simplified by Principal Component Analysis (PCA) or Recursive Feature Elimination (RFE). Finally, the detection is realized by Support Vector Machines (SVM). The influence of different kernel functions and feature selection methods on detection results is compared. In this study, 11,232 sets of backscatter signals from simulation results of four different categories' breast models are utilized. And feature dataset is constructed by 24 specific features from each signal's four valid components. The results demonstrate that the proposed method can extract representative features and detect the early breast cancer effectively with the accuracy of 84.8%.