Comparison of Feature Extraction and Classification Techniques of PE Malware

In recent scenario speaker recognition is used in many places for security purpose. Speaker recognition is technique which can verify or identify the person who is speaking. It is different than speech recognition system. In this paper we have discussed the feature extraction techniques like Mel Frequency Cepstral Co-efficient (MFCC), Linear Predictive Coding (LPC) etc. and classification techniques like Gaussian Mixture Model (GMM), Artificial Neural Networks (ANN) etc. that is available for speaker recognition. Also the survey is about how to get better efficiency in terms of speaker recognition rate by simply modifying the existing feature extraction and classification techniques.

This paper investigates fault diagnosis in batch processes and presents a comparative study of feature extraction and classification techniques applied to a specific biotechnological case study: the fermentation process model by Birol et al. (Comput Chem Eng 26:1553-1565, 2002), which is a benchmark for advanced batch processes monitoring, diagnosis and control. Fault diagnosis is achieved using four approaches on four different process scenarios based on the different levels of noise so as to evaluate their effects on the performance. Each approach combines a feature extraction method, either multi-way principal component analysis (MPCA) or multi-way independent component analysis (MICA), with a classification method, either artificial neural network (ANN) or support vector machines (SVM). The performance obtained by the different approaches is assessed and discussed for a set of simulated faults under different scenarios. One of the faults (a loss in mixing power) could not be detected due to the minimal effect of mixing on the simulated data. The remaining faults could be easily diagnosed and the subsequent discussion provides practical insight into the selection and use of the available techniques to specific applications. Irrespective of the classification algorithm, MPCA renders better results than MICA, hence the diagnosis performance proves to be more sensitive to the selection of the feature extraction technique.

Lately, 3D imaging techniques have achieved a lot of progress due to recent developments in 3D sensor technologies. This leads to a great interest regarding 3D image feature extraction and classification techniques. As pointed out in literature, one of the most important and discriminative features in images is the textural content. Within this context, we propose a texture feature extraction technique for volumetric images with improved discrimination power. The method could be used in textured volumetric data classification tasks. To achieve this, we fuse two complementary pieces of information, feature vectors derived from Local Binary Patterns (LBP) and the Gray-Level Co-occurrence Matrix-based methods. They provide information regarding the image pattern and the contrast, homogeneity and local anisotropy in the volumetric data, respectively. The performance of the proposed technique was evaluated on a public dataset consisting of volumetric textured images affected by several transformations. The classifiers used are the Support Vector Machine, k-Nearest Neighbours and Random Forest. Our method outperforms other handcrafted 3D or 2D texture feature extraction methods and typical deep-learning networks. The proposed technique improves the discrimination power and achieves promising results even if the number of images per class is relatively small.

Isolated Speech recognition systems (ISRS) have been implemented using microprocessors, digital signal processors and FPGAs and have been reported in the literature. In this paper, the study and implementation of an ISRS using Cypress Programmable System on Chip (PSoC) is presented. For the implementation, PSoC5 containing the ARM Cortex-M3 CPU is used. Recognition performance is studied using three feature extraction techniques (Zero crossing, Zero crossing with end point detection and Zero crossing with end point detection and Cochlear filter) and minimum distance classifier. The ISRS is trained and tested using 10 utterances of three words. The performance is evaluated for utterances by both single speaker and multiple speaker. From this study, it is found that the system using the Zero crossing with end point detection and Cochlear filter gives the highest recognition accuracy of 80%and 70% respectively for the utterances by single speaker and multiple speakers. Higher recognition accuracy can be obtained using more robust feature extraction and classification techniques at the cost of increase in the computation complexity and storage space. The proposed ISRS has applications in voice operated robots, appliances and access control systems.

Biometrics is the study of unique characteristics present in the human body such as fingerprint, palm-print, retina, iris, footprint, etc. While other traits have been explored widely, only a few people have been considered the foot-palm region, despite having unique properties. Prior work has explored the foot shape features using length, width, major axis, minor axis, centroid, etc. but they are not reliable for personal verification due to similarity in the physical composition of two persons. It increases the demand for more unique features based on the footprint. Footprint texture features coming from creases of foot palm are unique and permanent like palmprint texture features. Hence the main objective of the paper is to investigate various kinds of texture feature techniques. These techniques will be further used in correct extraction of footprint features. After extraction of footprint features a detailed experimental analysis is performed to discover the uniqueness in foot texture. It is further utilized to test its viability as a human recognition trait. We describe a detailed feature extraction and classification technique applied to a collected footprint data-set. For feature extraction, we use three techniques: Gray Level Co-occurrence Matrix (GLCM), Histogram Oriented Gradient (HOG), and Local Binary Patterns (LBP). Feature classification is performed using four techniques: Linear Discriminant Analysis (LDA), Support Vector Machine (SVM), K-Nearest Neighbor (KNN), and Ensemble Subspace Discriminant (ESD). GLCM provides less accuracy, while HOG generates a big feature vector which takes more execution time. LBP provides a trade-off between the accuracy and the execution time. Detailed quantitative experiments show: GLCM with LDA provides an accuracy of $$88.5\%$$ , HOG with Fine-KNN achieves $$86.5\%$$ accuracy and LBP with LDA achieves the accuracy of $$97.9\%$$ .

The rapid emergence of technology and big data science opened up a significant amount of work that has been carried out in the field of feature extraction and classification techniques of heart sound using various deep learning methods. Practically, medical practitioners use the same old scientific method and practice to seek out any cardiac disorders and predict any abnormality in the human heart. Heart sound normalization, denoising, segmentation, feature extraction, and classification techniques provide a suitable way of study of phonocardiography (PCG) signal analysis which eventually reduces the cost, makes the system compact, and simultaneously, can work with extensive training data. This paper mainly indulges in two parts feature extraction and classification. The proposed deep learning study for PCG signal used online available heart disease datasets, and time domain features like average energy, power, root mean square (RMS), total harmonic distortion, and zero Crossing rates are used. Statistical features used are kurtosis and skewness. The acoustic features used are Mel-frequency cepstrum coefficients (MFCCs), mel, chroma, contrast, and tonnetz. For the classification of heart sound, the proposed modified CNN-based mobile network is used. The modified CNN-based mobile network is very effective in heart sound analysis as it requires very less computation time and storage. The proposed CNN-based modified Mobile Network model attained an accuracy of 99.04 + 0.07% on the test dataset with a sensitivity of 96.8 + 0.03 % and specificity of 97.2 + 0.09%.

Recent research presents a technique to enumerate all valid assignments of “twiddle factors” for power-of-two fast Fourier transform (FFT) flow graphs. Brute-force search employing state-of-the-art Boolean satisfiability (SAT) solvers can then be used to find FFT algorithms within this large solution space which have desirable characteristics. Surprisingly, this approach has discovered FFT algorithms requiring fewer operations than the split-radix algorithm even when all twiddle factors are nth roots of unity. This paper reviews and then extends this prior research to examine fast discrete convolution algorithms when implemented via FFT and inverse FFT (IFFT) algorithms. In particular, we find that the combination of FFT and IFFT algorithms in fast convolution permits greater freedom when selecting valid twiddle factor assignments. We exploit this freedom and use SAT solvers to find new fast convolution algorithms with the lowest operation counts known.

The implementation of a brain–computer interface (BCI) using electroencephalography typically entails two phases: feature extraction and classification utilizing a classifier. Consequently, there are numerous disordered combinations of feature extraction and classification techniques that apply to each classification target and dataset. In this study, we employed a neural network as a classifier to address the versatility of the system in converting inputs of various forms into outputs of various forms. As a preprocessing step, we utilized a transposed convolution to augment the width of the convolution and the number of output features, which were then classified using a convolutional neural network (CNN). Our implementation of a simple CNN incorporating a transposed convolution in the initial layer allowed us to classify the BCI Competition IV Dataset 2a Motor Imagery Task data. Our findings indicate that our proposed method, which incorporates a two-dimensional CNN with a transposed convolution, outperforms the accuracy achieved without the transposed convolution. Additionally, the accuracy obtained was comparable to conventional optimal preprocessing methods, demonstrating the effectiveness of the transposed convolution as a potential alternative for BCI preprocessing.

Several researches focus on the study and conservation of bees, largely because of its importance for agriculture. However, the identification of bee species has hampering new studies, since it demands a very specialized knowledge and is time demanding. Although there are several methods to accomplish this task, many of them are excessively costly, restricting its applicability. For being accessible, the bee wings have been widely used for the extraction of features, since it is possible to apply morphometric techniques using just one image of the wing. As the manual measurement of various features is tedious and error prone, some systems have been developed for this purpose. However, these systems also have limitations, and there is no study concerning classification techniques that can be used for this purpose. This research aims to evaluate the feature extraction and classification techniques in order to determine the combination of more appropriate techniques for discriminating species of bees. The results of our research indicate that the use of a conjunction of Morphometric and Pixel-based features is more effective than only using Morphometric features. Our analysis also concluded that the best classification algorithms using both only Morphometric features and a conjunction of Morphometric and Pixel-based features are, respectively, Nave Bayes and Logistic classifier. The results of this research can guide the development of new systems to identify bee species in order to assist in researches conducted by biologists.

Precise vegetation restoration is critical in drylands, as some inappropriate restoration attempts have even increased water scarcity and degradation in afforestation areas. Potential natural vegetation (PNV) is widely used to provide a reference for the appropriate location and vegetation type of restoration programs while the appropriate restored areas remain unknown. Therefore, we proposed a PNV–potential normalized difference vegetation index (PNDVI) coupling framework based on multiple machine learning (ML) algorithms for precise dryland vegetation restoration. Taking the lower Tarim River Basin (LTRB) with a total area of 1,182 km2 as a case study, its present suitable restoration locations, area, and appropriate planting species were quantitatively estimated. The results showed that the model developed by incorporating PNDVI into PNV with easily measurable and available data such as temperature and soil properties can accurately identify dryland restoration patterns. In LTRB, the potentially suitable habitats of trees and grass are closer to the riverbank, while shrubby habitats are further away from the course, covering 1.88, 2.96, and 25.12 km2, respectively. There is still enormous land potential for further expansion of the current trees and grass in the LTRB, with 2.56 and 1.54% of existing land supposed to be trees and grass, respectively. This study's novel aspect is combining PNV and PNDVI to quantify and estimate precise restoration patterns through multiple ML algorithms. The model developed here can be used to evaluate the suitable reforestation locations, area, and vegetation types in drylands and to provide a basis for precise vegetation restoration.

Malware writers often develop malware with automated measures, so the number of malware has increased dramatically. Automated measures tend to repeatedly use significant modules, which form the basis for identifying malware variants and discriminating malware families. Thus, we propose a novel visualization analysis method for researching malware similarity. This method converts malicious Windows Portable Executable (PE) files into local entropy images for observing internal features of malware, and then normalizes local entropy images into entropy pixel images for malware classification. We take advantage of the Jaccard index to measure similarities between entropy pixel images and the k-Nearest Neighbor (kNN) classification algorithm to assign entropy pixel images to different malware families. Preliminary experimental results show that our visualization method can discriminate malware families effectively.

A Review of Feature Extraction and Classification Techniques in Speech Recognition

A comprehensive overview on signal processing and artificial intelligence techniques applications in classification of power quality disturbances

In this paper we present a novel writer-independent on-line signature verification system. The proposed system obtains a universal signature representation in dissimilarity space, but remains able to compensate for the personal variability of an individual's handwriting by subsequently employing a writer-specific dissimilarity normalisation strategy. Signature modelling is achieved by utilising either quadratic discriminant analysis or a support vector machine with a radial basis function kernel. We also present an experimental comparison between the aforementioned dissimilarity normalisation strategy and an existing dissimilarity individualisation technique, that is the so-called user-specific global-parameter fusion protocol. The feasibility of incorporating either of these techniques into an arbitrary signature modelling framework, as well as the resulting impact on system proficiency, is investigated. When evaluated on 4530 samples collected from 51 writers in the Philips signature database, the most proficient system proposed in this paper achieves equal error rates of 0.65%-1.19% when 5–15 reference signatures are available per writer. We show that the aforementioned system outperforms previous systems that were evaluated on the same data set. We also show that, when evaluated under identical experimental conditions, the dissimilarity normalisation strategy outperforms the fusion protocol in terms of system proficiency. Furthermore, we assert that, unlike the fusion protocol, the dissimilarity normalisation strategy is suitable for incorporation into any existing writer-independent on-line signature verification system, regardless of the feature extraction and/or classification technique(s) utilised.

A partial face recognition strategy based on template matching is proposed in this paper. In real-world face recognition applications such as surveillance or forensics images only a small part of face image is available. In the proposed approach in this paper, instead of comparing the small sub-image to the complete face images in the database, a template matching technique finds face parts on the gallery samples in the database with the best match to the partial image. The feature extraction and classification techniques are applied on the small sub images of the probe and gallery sets to find the identity of the partial probe face. AR, LFW and FERET databases are employed to evaluate the performance of the proposed approach. Normalized sum of squared difference (NSSD) outperforms zero mean normalized cross correlation (ZNCC) in template matching. Based on the experimental results, partial eyes image leads to the best recognition accuracy. Also, reducing the size of sub-image to less than 6.25% of the complete image size, decreases the identification accuracy drastically.