Search

Digital technologies sustain today's world. Every part of the world is working towards digital technologies, which none of us can eliminate. Enormous growth is achieved only by unexpected acceleration by digital technologies, including the Internet of Everything (IoE), Artificial Neural Networks (ANN), Machine Learning (ML), Internet of Things (IoT), Artificial Intelligence (AI), Deep Learning (DL), and many more. These technologies started occupying all the engineering sectors, including manufacturing. This paper focuses on tribology analysis related to manufacturing concerning various digital manufacturing technologies. The paper narration includes Tribology using digital technologies wherein the journals and patent landscape analysis abet them. In trend, Tribology utilizes all these technologies today and envisages its growth with the predominant technological invention in the border view. The survey of various literature reveals that only three digital technologies, including AI, ML, and ANN, are used by tribologists around the globe. Other Technologies like Evolutionary Algorithm (EA), Support Vector Machine (SVM), and Adaptive Neuro-Fuzzy Interference Systems (ANFIS) are not used predominantly. [ABSTRACT FROM AUTHOR]

Kernel-based learning algorithms have been extensively studied over the past two decades for their successful applications in scientific research and industrial problem-solving. In classical kernel methods, such as kernel ridge regression and support vector machines, an unregularized offset term naturally appears. While its importance can be defended in some situations, it is arguable in others. However, it is commonly agreed that the offset term introduces essential challenges to the optimization and theoretical analysis of the algorithms. In this paper, we demonstrate that Kernel Ridge Regression (KRR) with an offset is closely connected to regularization schemes involving centered reproducing kernels. With the aid of this connection and the theory of centered reproducing kernels, we will establish generalization error bounds for KRR with an offset. These bounds indicate that the algorithm can achieve minimax optimal rates. [ABSTRACT FROM AUTHOR]

Many of the used features in sudden cardiac death (SCD) classification algorithms are based on features present in the autonomic system. However, changes in the autonomic system occur in both SCD subjects and patients with congestive heart failure (CHF). Therefore, many overlaps are observed in the features extracted from the cardiac signals of these two groups. To solve this challenge, this paper studies the changes in the multifractal dimension in patients with SCD and compares it with the subjects with CHF using the heart rate variability (HRV) signal processing. For this purpose, HRV signals are initially extracted, and their four sub-signals are determined using the empirical mode decomposition (EMD) method. Afterward, the instant amplitude of each sub-signal obtained in the previous step is calculated using the Teager energy method; thus, new signals are generated through the utilization of these instant amplitudes. Subsequently, modifications in each new signal's fractal dimensions are obtained using the multifractal detrended fluctuation analysis (MF-DFA) method. The appropriate features are selected using the t-test method and are applied to the support vector machine algorithm as input data. The proposed algorithm can differentiate the signal of SCD subjects with an average accuracy of 84.08% in 26 min prior to the event. [ABSTRACT FROM AUTHOR]

Support vector machine is a very classical and popular model for data prediction. Traditional support vector machines use grid search to determine its parameters. In order to improve the accuracy of prediction, more and more frameworks are proposed. Among them, the combination of support vector machine and intelligent optimization algorithm is the most commonly used solution at present. The optimization objective is to determine the optimal penalty factor and kernel parameters of support vector machine to improve the prediction performance. In this paper, 10 intelligent optimization algorithms that are widely used at present are used for the optimization research of support vector machine. The performance of these optimization algorithms in support vector machine parameter optimization is analyzed in detail. Short-term wind speed and network traffic are chosen as the research object, and detailed performance indicators are given to judge the advantages and disadvantages of these intelligent optimization algorithms in optimizing support vector machine performance. Finally, the performance indicators, optimization speed, running memory usage, optimization success rate of different optimized SVM models, and impact of data distribution are analyzed in detail, and some conclusions are drawn. For the parameters optimization of support vector machine, various indicators are comprehensively considered, grey wolf optimizer algorithm and squirrel search algorithm are recommended. [ABSTRACT FROM AUTHOR]

With the rapid development of unmanned aerial vehicle (UAV) technology, UAV has been widely used in agricultural plant protection, electric power inspection, security patrols, and other fields. However, the control system of the UAV is a complex human–computer interaction system, which requires higher requirements in practical applications. Due to differences in hardware design, software development, and other aspects among different manufacturers, these UAV control systems require high hardware requirements, resulting in a long development cycle. At the same time, in practical applications, due to various reasons, there are equipment failures that are difficult to detect and eliminate in a timely manner. This paper used the UAV graphical control strategy identification method based on cloud server technology, and used the support vector machine (SVM) algorithm to analyze its identification accuracy. The research results showed that when other conditions were the same, the number of researchers and experts who were satisfied with the drone trial effect of the cloud server was 42 and 10, respectively, accounting for 84% and 100%. It indicates that they believe that the cloud server can effectively improve the effectiveness of the drone graphical control strategy recognition method, indicating a positive relationship between the two. [ABSTRACT FROM AUTHOR]

Universities play a huge role in the cultivation of talents. Especially in the context of internationalization, the teaching of English as a common language is becoming more and more important. This paper introduced the traditional methods for evaluating the quality of English teaching, established a deep learning algorithm for evaluating the quality of English teaching with the evaluation indicators of the traditional methods combined with the convolutional neural network (CNN) algorithm, conducted simulation experiments on the CNN algorithm, and compared it with the support vector machine (SVM) algorithm. The results showed that the scores obtained by the CNN algorithm had some errors with the actual scores but were much lower than the scores obtained by the SVM algorithm, and the CNN algorithm consumed a shorter time in computing. This paper used the CNN algorithm combined with evaluation indexes constructed by the analytic hierarchy process (AHP) method to evaluate the quality of English teaching and verified the effectiveness of the CNN algorithm through a comparison with the SVM algorithm, which provides an effective reference for intelligent evaluation of English teaching quality. [ABSTRACT FROM AUTHOR]

In this paper, we develop the so-called variable projection support vector machine (VP-SVM) algorithm that is a generalization of the classical SVM. In fact, the VP block serves as an automatic feature extractor to the SVM, which are trained simultaneously. We consider the primal form of the arising optimization task and investigate the use of nonlinear kernels. We show that by choosing the so-called adaptive Hermite function system as the basis of the orthogonal projections in our classification scheme, several real-world signal processing problems can be successfully solved. In particular, we test the effectiveness of our method in two case studies corresponding to anomaly detection. First, we consider the detection of abnormal peaks in accelerometer data caused by sensor malfunction. Then, we show that the proposed classification algorithm can be used to detect abnormalities in ECG data. Our experiments show that the proposed method produces comparable results to the state-of-the-art while retaining desired properties of SVM classification such as light weight architecture and interpretability. We implement the proposed method on a microcontroller and demonstrate its ability to be used for real-time applications. To further minimize computational cost, discrete orthogonal adaptive Hermite functions are introduced for the first time. [ABSTRACT FROM AUTHOR]

Abnormal cells in the human body that keep on mutating are termed to be cancer in medical terms. There are multiple types of cancer identified in human beings. It is very much essential to identify and classify the type of cancer in its earlier stage. This objective can be satisfied by artificial intelligence which has a subfield of machine learning to create a generalized model that could identify and classify cancer with increased performance. To perform the identification and classification of various cancer types, in this paper, two techniques are adopted. The optimized feature set computation was done using the Kernel-Induced Matriarch path tracking Elephant Herding Optimization (KIM-EHO) and the classification for the given samples was done using the Support Vector Machines (SVM). The proposed techniques are implemented with the benchmark datasets and the results proved that the proposed methodologies outperformed the existing methods in terms of accuracy, specificity, sensitivity and time complexity. [ABSTRACT FROM AUTHOR]

Brain–computer interfaces (BCIs) establish a direct communication channel between the human brain and external devices. Among various methods, electroencephalography (EEG) stands out as the most popular choice for BCI design due to its non-invasiveness, ease of use, and cost-effectiveness. This paper aims to present and compare the accuracy and robustness of an EEG system employing one or two channels. We present both hardware and algorithms for the detection of open and closed eyes. Firstly, we utilize a low-cost hardware device to capture EEG activity from one or two channels. Next, we apply the discrete Fourier transform to analyze the signals in the frequency domain, extracting features from each channel. For classification, we test various well-known techniques, including Linear Discriminant Analysis (LDA), Support Vector Machine (SVM), Decision Tree (DT), or Logistic Regression (LR). To evaluate the system, we conduct experiments, acquiring signals associated with open and closed eyes, and compare the performance between one and two channels. The results demonstrate that employing a system with two channels and using SVM, DT, or LR classifiers enhances robustness compared to a single-channel setup and allows us to achieve an accuracy percentage greater than 95% for both eye states. [ABSTRACT FROM AUTHOR]

Classification of microarray data is one of the major research interests in the biomedical field. It allows physicians for early detection of cancer through analysis of the Deoxyribonucleic acid (DNA). Classification of these sensitive data is still challenging due to the small sample and more feature size. In this paper, the authors have used an ensemble model for classifying two types of leukemia as Acute lymphocytic leukemia (ALL) and Acute myelocytic leukemia (AML). The work is carried out with other types of genetic data such as Leukemia, lung tumor, liver cancer, and liver Cirrhosis. The biomedical data are imbalanced. The ensemble classifier is based on a stacked approach where deep neural network (DNN) classifiers are used as the base classifier. The structure of each DNN is chosen as the homogenous type for the same training process for all classifiers. Because of the adaptive nature and random weight initialization, it provides different results for each classifier. The outputs of the base classifiers are again fed to a gradient boosting ensemble model termed a meta classifier. The meta classifier provides the final classification output. For comparison purposes, two types of meta-classifiers such as support vector machine (SVM) and ensemble gradient boosting are used in the proposed work. The performance of the model is verified well and the results are provided in the result section. From the experimental result, it is observed that the classification accuracy is 96% with SVM and 98% with boosted meta classifier for leukemia data, whereas 99.04% for lung tumor and 99.03% for liver Cirrhosis. [ABSTRACT FROM AUTHOR]

With the deepening application of wearable devices in the field of indoor positioning, the mining and application of human behavior patterns based on new technologies such as mobile terminals, channel technologies and intelligent algorithms have gradually become a research hotspot in the field of intelligent positioning. At this stage, outdoor positioning satellite technology has been gradually improved, but it cannot work effectively in indoor environment, and indoor positioning technology has not formed a set of standard and effective scheme at this stage, which leads to a scene of a hundred contentions for indoor positioning technology. This paper proposes an indoor intelligent localization algorithm based on channel state information, which first forms the measurements of antenna subarrays by the fixed antenna subset arrays located in different paths to achieve the phase estimation based on channel state; then determines the AoA of the direct path from the target to the AP using ToF information and eliminates the STO noise of channel state information by unfolding the best linear fit of CSI phase; again the AoA and ToF estimates from multiple measurements are plotted in two-dimensional space, and the direct path possibility estimation is achieved by identifying the estimates through five clusters of Gaussian-averaged clustering algorithm; finally the coordinates of the target to be located are obtained by coupling direct propagation path, estimation clustering and least-squares estimation using three APs as the receiver and the target to be located as the transmitter. The simulation results show that the intelligent localization algorithm proposed in this paper is able to lack the localization accuracy at the decimeter level in the indoor localization environment with three fixed APs, and the average error is better than the localization algorithms of support vector machine, deep learning and limit learning. [ABSTRACT FROM AUTHOR]

With the continuous expansion of urbanization, the problem of human settlements has become increasingly prominent. Green, economical, intelligent and livable cities have become the urgent needs of future urban planning. The evaluation of urban livability is not only one of the judgment criteria of urban competitiveness, but also an important factor affecting the speed of urban development. Among them, the safety factor of the city is the important guarantee of other aspects, so this paper intends to design a high-precision face recognition algorithm to make efforts for the safety construction of livable cities. Aiming at the shortcomings of the standard support vector machine (SVM), combined with the quantum-behaved mechanism, a quantum-behaved genetic algorithm–SVM (QBGA–SVM) is proposed in the paper. The experimental results for the human face databases show that QBGA–SVM is superior to the comparison algorithms in both accuracy and stability. Finally, QBGA–SVM is applied to face images of the real world, and the results are better than the other algorithms. [ABSTRACT FROM AUTHOR]

Gait recognition based on acceleration sensor signals is more suitable for complex environments than other signal-based methods, which can be used for data acquisition for gait recognition. However, most traditional methods only consider the position matching of multiple accelerometers, ignoring the comfort of the collector. In recent years, support vector machine (SVM) has been widely used in portrait recognition, language, and video processing. It has a flexible and powerful processing ability for nonlinear sequence input, and is a sparse and robust classifier. In this paper, we propose a multi-feature SVM algorithm ME-SVM, which is classified after multi-feature fusion. Usually, in the research of action recognition based on acceleration sensors, researchers classify from a single eigenvalue, but this paper optimizes this and further improves the recognition performance. Simulation and experimental results show that the algorithm has high accuracy and robustness. [ABSTRACT FROM AUTHOR]

Nowadays, images have become one of the most popular forms of communication as image editing tools have evolved. Image manipulation, particularly image colorization, has become easier, making it harder to differentiate between fake colorized images and actual images. Furthermore, the RGB space is no longer considered to be the best option for color-based detection techniques due to the high correlation between channels and its blending of luminance and chrominance information. This paper proposes a new approach for fake colorized image detection based on a novel image representation created by combining color information from three separate color spaces (HSV, Lab, and Ycbcr) and selecting the most different channels from each color space to reconstruct the image. Features from the proposed image representation are extracted based on transfer learning using the pre-trained CNNs ResNet50 model. The Support Vector Machine (SVM) approach has been used for classification purposes due to its high ability for generalization. Our experiments indicate that our proposed models outperform other state-of-the-art fake colorized image detection methods in several aspects. [ABSTRACT FROM AUTHOR]

Accurate classification of the medical signals is urgently needed in clinical medicine. This paper aims to create a classifier to shorten the time of the classification and ensure the sorting accuracy, which assists physicians in saving diagnostic time and formulating the treatment plans. We create the classifier based on Kolmogorov complexity, Shannon entropy, Higuchi's Hurst exponent and multifractal features. We obtain a feature value from Kolmogorov complexity, Shannon entropy and Higuchi's Hurst exponent, and three feature values based on multifractal features to compose a vector and analyze it. Furthermore, we study a vector composed of six multifractal features as a control group. Electrocardiogram (ECG) and electroencephalogram (EEG) signals are applied to examine the performance of the classifier by support vector machine (SVM). The accuracy of ECG signals based on mixed classification (MC–ECG–SVM) reaches 94.17%, which is approximately 15% higher than that of ECG signals only based on multifractal features classification (UC–ECG–SVM). The sensitivities of MC–ECG–SVM and UC–ECG–SVM are 86.09% and 64.54%, respectively. The specificities of MC–ECG–SVM and UC–ECG–SVM are 98.26% and 93.65%, respectively. Analogously, the accuracy, sensitivity, and specificity of EEG signals based on mixed classification (MC–EEG–SVM) reach 95.29%, 96.28%, and 94.55%, respectively. The accuracy, sensitivity, and specificity of EEG signals based on multifractal features classification (UC–EEG–SVM) are 87.40%, 89.28%, and 88.11%, respectively. Therefore, the mixed classification method is more accurate than the classification method only based on multifractal features. [ABSTRACT FROM AUTHOR]

Due to recent cyberattacks on the Cyber-Physical Systems, the traditional security schemes face difficulties in dealing with such attacks as the attackers nowadays have adopted many intelligent mechanisms involving advanced information and communication technologies to launch attacks. This recent type of attack provides a significant impact on the resiliency of the software-defined networks. In this paper, we present a real-time delay attack on fault-resilient software-defined networks. The main objective of the time delay attack is to reduce the resiliency in the SDN-RM by adding a delay in the LLDP packets in the OpenFlow Switch. This addition of delay causes degradation in the network performance resulting in a low success rate in the SDN-RM mechanisms. In this paper, we present a machine learning-based detection system for detecting the attacks. The integration of machine learning techniques with network resilience solutions can effectively address the issue of predicting and classifying the LLDP packets that are delayed at a particular switch. Another issue is the detection of the malicious switch at the controller side which results in the improvement of the resiliency in SDN-RM. We propose a machine learning solution to detect the anomalies that are present in the topology and can be detected at the controller side. We use machine learning models such as k-nearest neighbors, support vector machines (SVM), Random Forest, and decision trees to detect the poisonous switches. The delay-based time attack detection system (DTA-DS) helps the controller to take a reactive decision to improve resilience by detecting poisonous network switches. With the help of the preventive approach, we achieve high-fault resiliency in fault resilient-based software-defined networks. [ABSTRACT FROM AUTHOR]

This paper proposes a semi-automatic method of geographic information linking based on spatial relationships, entity names, entity categories and other features, combined with semantic and machine learning methods. First, we extracted geographic information from three geographic information sources: Open Street Map, Wikimapia, and Google places. The extracted geographic information is mainly for urban buildings in different regions. Secondly, we analyzed and extracted the characteristics of geographic information data to construct a geographic information ontology, and realized the integration of geographic data through the mapping of geographic information source data and geographic information ontology. Finally, the linking method of fusion classification algorithm support vector machine and K-nearest neighbor method are discussed separately. At the same time, it is compared with the linking method proposed by Samal et al. to comprehensively verify the accuracy of the method proposed in this paper from multiple angles, laying a good foundation for seismic information integration. [ABSTRACT FROM AUTHOR]

Twitter Spam has turned out to be a significant predicament of these days. Current works concern on exploiting the machine learning models to detect the spams in Twitter by determining the statistic features of the tweets. Even though these models result in better success, it is hard to sustain the performances attained by the supervised approaches. This paper intends to introduce a deep learning-assisted spam classification model on twitter. This classification is based on sentiments and topics modeled in it. The initial step is data collection. Subsequently, the collected data are preprocessed with "stop word removal, stemming and tokenization". The next step is feature extraction, wherein, the post tagging, headwords, rule-based lexicon, word length, and weighted holoentropy features are extracted. Then, the proposed sentiment score extraction is carried out to analyze their variations in nonspam and spam information. At last, the diffusions of spam data on Twitter are classified into spam and nonspams. For this, an Optimized Deep Ensemble technique is introduced that encloses "neural network (NN), support vector machine (SVM), random forest (RF) and convolutional neural network (DNN)". Particularly, the weights of DNN are optimally tuned by an arithmetic crossover-based cat swarm optimization (AC-CS) model. At last, the supremacy of the developed approach is examined via evaluation over extant techniques. Accordingly, the proposed AC-CS + ensemble model attained better accuracy value when the learning percentage is 80, which is 18.1%, 14.89%, 11.7%, 12.77%, 10.64%, 6.38%, 6.38%, and 6.38% higher than SVM, DNN, RNN, DBN, MFO + ensemble model, WOA + ensemble model, EHO + ensemble model and CSO + ensemble model models. [ABSTRACT FROM AUTHOR]

This paper is to explore the improvement of clinical symptoms in patients with cardiovascular neurosis (CN) by physical exercise based on the deep learning architecture of edge computing, and to deeply explore the effect of physical exercise on autonomic function. Fifty-two patients with CN in this cardiovascular rehabilitation center were randomly divided into drug group and exercise group, with 26 cases in each group, and their electrocardiogram (ECG) was examined. Based on the deep learning architecture of edge computing, a four-layer stacked sparse auto encoder (SSAE) deep neural network was constructed, and the accuracy rates of least squares support vector machine (LSSVM), message passing neural network (MPNN), convolutional neural network (CNN), and SSAEs were measured to be 95.4%, 93.6%, 96.3%, and 99.5%, respectively. After physical exercise intervention, the total score of Symptom Checklist 90 (SCL-90) as well as each single item score were lower in the exercise group than in the drug group (P < 0. 0 5). Heart rate recovery (HRR1) improved more significantly after 1 min of exercise in patients in the exercise group (P < 0. 0 5). The low-frequency (LF) power and normalized low-frequency (LFn) power of blood pressure variability (BPV) parameters in the exercise group were lower than those in the drug group (P < 0. 0 5); the total power (TP), high-frequency (HF) power, and normalized high-frequency (HFn) power of heart rate variability (HRV) parameters in the exercise group were higher than those in the drug group (P < 0. 0 5), LF/HF in the exercise group was lower than that in the drug group (P < 0. 0 5); and the baroreflex sensitivity (BRS) in the exercise group was higher than that in the drug group (P < 0. 0 5). A four-layer SSAEs was successfully constructed; the mechanism of exercise may be related to the regulation of cardiovascular autonomic nervous function, and it can effectively prevent and treat the clinical symptoms of patients with CN. [ABSTRACT FROM AUTHOR]

The geochemical characteristics of magmatic rocks can distinguish the tectonic setting of magma formation and their geochemical signatures are discriminated by using the whole-rock geochemical data. As a new attempt of artificial intelligence technology in geochemistry, the machine learning discrimination method is gradually complementary to the classical discriminative graphical method. However, the feature selection of high-dimensional data and the determination of many unknown parameters are the two main factors affecting the classification accuracy of the algorithm. In this paper, a particle swarm optimized support vector machine (PSO-SVM) model is established to classify the tectonic environments of basaltic rocks in the GEOROC database. The model mainly relies on the powerful search capability of the particle swarm algorithm to find the best parameter combination selected by the SVM based on experience to improve the accuracy. In this study, based on the basalt samples in the database and the confusion matrix, the performance of PSO-SVM model is evaluated by simulation experiments. The results show that the model proposed in this paper is more effective in distinguishing the basaltic tectonic environments, with an accuracy of more than 90%. Therefore, compared with the traditional discriminant map method, the machine learning method based on the fusion of two algorithms performs better in the tectonic environment classification problems. [ABSTRACT FROM AUTHOR]

The automatic and accurate identification of apoptosis facilitates large-scale cell analysis. Most identification approaches using nucleus fluorescence imaging are based on specific morphological parameters. However, these parameters cannot completely describe nuclear morphology, thus limiting the identification accuracy of models. This paper proposes a new feature extraction method to improve the performance of the model for apoptosis identification. The proposed method uses a histogram of oriented gradient (HOG) of high-frequency wavelet coefficients to extract internal and edge texture information. The HOG vectors are classified using support vector machine. The experimental results demonstrate that the proposed feature extraction method well performs apoptosis identification, attaining 9 5. 7 % accuracy with low cost in terms of time. We confirmed that our method has potential applications to cell biology research. [ABSTRACT FROM AUTHOR]

The purpose of this paper is to introduce a novel learning approach to solve the heat transfer problem from convecting-radiating fin model. This model is a nonlinear differential equation in which different boundary conditions cause different profile shapes including rectangular, triangular, trapezoidal and concave parabolic. We consider one-dimensional, steady conduction in the fin and neglect radiative exchange between adjacent fins and between the fin and its primary surface. Our method is based on using the quasilinearization method to linearize the nonlinear models and applying shifted Gegenbauer polynomials as new kernel in least squares support vector machines method. The results of fin efficiency and heat transfer rate of the problems which compared with available previous results indicate better efficiency and accuracy of the proposed approach. [ABSTRACT FROM AUTHOR]

Facial paralysis (FP) is the most common illness. Nerve damage can cause the affected muscles of the face to lose control. Most FP diagnosis systems heavily depend on skilled clinicians and lack automatic quantitative assessment. This paper introduces a novel automatic facial paralysis recognition (autoFPR) approach, a four-stage machine learning solution, for classifying FP and healthy subjects. Our solution includes the creation of the dataset, feature extraction, dimensionality reduction, and classification. The FP and healthy subject videos are collected from the publicly available YouTube Facial Palsy database and the 300VW database, respectively. Facial features are extracted from the collected facial videos using landmarks, action units, eye gaze, and head pose. Five different experiments were performed to find the best facial paralysis recognition technique. autoFPR can distinguish subjects with facial paralysis and healthy individuals by using movement changes in their eyebrows, eyes, and corners of the mouth. Our goal is to prove that machine learning classifiers are capable of diagnosing FP. We evaluate system performance using accuracy, precision, recall, and F1. Feature selection plus principal component analysis with support vector machine achieved the highest accuracy, with 97.3% for the extracted features. [ABSTRACT FROM AUTHOR]

In this paper, we assess the effectiveness of a widely used machine learning technique, support vector machines (SVM) for computing reactive islands in a benchmark system for testing molecular dynamics algorithms, the Voter97 model. Reactive islands are the phase space geometrical structure that mediate chemical reactions dynamics. The Voter97 model contains particular challenges for reaction dynamics methods as the reactant and product potential wells are separated by an intermediate well. We show that SVM can accurately compute the reactive islands in the Voter97 model and we assess the accuracy and the computational effort of the approach by comparing it with brute force methods for computing the reactive islands. [ABSTRACT FROM AUTHOR]

The use of handwritten recognition tools has increased yearly in various commercialized fields. Due to this, handwritten classification, recognition, and detection have become an exciting research subject for many scholars. Different techniques have been provided to improve character recognition accuracy while reducing time for languages like English, Arabic, Chinese and European languages. The local or regional languages need to consider for research to increase the scope of handwritten recognition tools to the global level. This paper presents a machine learning-based technique that provides an accurate, robust, and fast solution for handwritten Pashto text classification and recognition. Pashto belongs to cursive script division, which has numerous challenges to classify and recognize. The first challenge during this research is developing efficient and full-fledged datasets. The efficient recognition or prediction of Pashto handwritten text is impossible by using ordinary feature extraction due to natural transformations and handwriting variations. We propose some useful invariant features extracting techniques for handwritten Pashto text, i.e., radial, orthographic grid, perspective projection grid, retina, the slope of word trajectories, and cosine angles of tangent lines. During the dataset creation, salt and pepper noise was generated, which was removed using the statistical filter. Another challenge to face was the invalid disconnected handwritten stroke trajectory of words. We also proposed a technique to minimize the problem of disconnection of word trajectory. The proposed approach uses a linear support vector machine (SVM) and RBF-based SVM for classification and recognition. [ABSTRACT FROM AUTHOR]

In this paper, we propose an improved algorithm based on the original two-dimensional (2D) multifractal detrended fluctuation analysis (2D MF-DFA) that involves increasing the number of cumulative summations in the computational steps of 2D MF-DFA. The proposed method aims to modify the distribution of the generalized Hurst exponent to ensure that skin lesion image features are extracted based on enhanced multifractal features. We calculate the generalized Hurst exponent using 0, 1, or 2 cumulative summation processes. A support vector machine (SVM) is adopted to examine the classification performance under these three conditions. Computation shows that the process involving two cumulative summations achieves an accuracy, sensitivity, and specificity of 9 5. 6 9 ± 0. 1 1 7 4 % , 9 4. 2 5 ± 0. 0 9 4 2 % , and 9 7. 6 3 ± 0. 1 4 6 6 % , respectively, which indicates that its performance is much better than with 0 and 1 cumulative summations. [ABSTRACT FROM AUTHOR]

The problem of human activity recognition (HAR) has been increasingly attracting the efforts of the research community, having several applications. It consists of recognizing human motion and/or behavior within a given image or a video sequence, using as input raw sensor measurements. In this paper, a multimodal approach addressing the task of video-based HAR is proposed. It is based on 3D visual data that are collected using an RGB + depth camera, resulting to both raw video and 3D skeletal sequences. These data are transformed into six different 2D image representations; four of them are in the spectral domain, another is a pseudo-colored image. The aforementioned representations are based on skeletal data. The last representation is a "dynamic" image which is actually an artificially created image that summarizes RGB data of the whole video sequence, in a visually comprehensible way. In order to classify a given activity video, first, all the aforementioned 2D images are extracted and then six trained convolutional neural networks are used so as to extract visual features. The latter are fused so as to form a single feature vector and are fed into a support vector machine for classification into human activities. For evaluation purposes, a challenging motion activity recognition dataset is used, while single-view, cross-view and cross-subject experiments are performed. Moreover, the proposed approach is compared to three other state-of-the-art methods, demonstrating superior performance in most experiments. [ABSTRACT FROM AUTHOR]

In the area of ophthalmology, glaucoma affects an increasing number of people. It is a major cause of blindness. Early detection avoids severe ocular complications such as glaucoma, cystoid macular edema, or diabetic proliferative retinopathy. Intelligent artificial intelligence has been confirmed beneficial for glaucoma assessment. In this paper, we describe an approach to automate glaucoma diagnosis using funds images. The setup of the proposed framework is in order: The Bi-dimensional Empirical Mode Decomposition (BEMD) algorithm is applied to decompose the Regions of Interest (ROI) to components (BIMFs+residue). CNN architecture VGG19 is implemented to extract features from decomposed BEMD components. Then, we fuse the features of the same ROI in a bag of features. These last very long; therefore, Principal Component Analysis (PCA) are used to reduce features dimensions. The bags of features obtained are the input parameters of the implemented classifier based on the Support Vector Machine (SVM). To train the built models, we have used two public datasets, which are ACRIMA and REFUGE. For testing our models, we have used a part of ACRIMA and REFUGE plus four other public datasets, which are RIM-ONE, ORIGA-light, Drishti-GS1, and sjchoi86-HRF. The overall precision of 98.31%, 98.61%, 96.43%, 96.67%, 95.24%, and 98.60% is obtained on ACRIMA, REFUGE, RIM-ONE, ORIGA-light, Drishti-GS1, and sjchoi86-HRF datasets, respectively, by using the model trained on REFUGE. Again an accuracy of 98.92%, 99.06%, 98.27%, 97.10%, 96.97%, and 96.36% is obtained in the ACRIMA, REFUGE, RIM-ONE, ORIGA-light, Drishti-GS1, and sjchoi86-HRF datasets, respectively, using the model training on ACRIMA. The experimental results obtained from different datasets demonstrate the efficiency and robustness of the proposed approach. A comparison with some recent previous work in the literature has shown a significant advancement in our proposal. [ABSTRACT FROM AUTHOR]

In recent years, Polycystic Ovary Syndrome (PCOS) becomes one of the most prominent research areas, where several researchers are concentrating to improve the accuracy of PCOS classification. It is much difficult to find the presence of PCOS in women with traditional techniques and various researchers are dealt with the problem that affects the accuracy in detecting such symptom. In this paper, we have proposed Integrated Transfer Learning-based Convolutional Neural Network (ITL-CNN) model to improve the classification accuracy for the detection of PCOS using ultrasound images. In this proposed model, we have used active contour with modified Otsu method and Multifactor Dimension Reduction-based GIST feature extractor for improving the performance of the ITL-CNN model. The performance of the proposed model is analyzed using various performance metrics such as accuracy, sensitivity, precision, recall, and F1 score. Furthermore, the results show that the proposed ITL-CNN model outperforms by achieving 98.9% of accuracy when compared with other existing techniques such as Convolutional Neural Network (CNN), Artificial Neural Network (ANN), Support Vector Machine (SVM), and Gaussian Naïve Bayes (NB). [ABSTRACT FROM AUTHOR]

Game Theory (GT) is the study of strategic decision making. By virtue of its importance, several GT based methodologies for Feature Selection (FS) are proposed in recent times. FS problem can be abstracted as a game by considering each feature as a player and their values as their strategies. Additionally, overall goal of the game is set to classify a data instance appropriately. Most of the existing GT based FS techniques are restricted to Zero Sum Games, Non-Zero Sum Games and Cooperative Games. The classical setting of assuming that all the details of players are known to all players cannot hold in many real-world problems. When the given features are independent, they cannot be treated alike and a characteristics based uncertainty persists among the features. This uncertainty is handled by none of the game forms used in the existing methods. Unlike the mentioned game techniques, Bayesian Games (BG) address the games with imperfect information. This paper investigate the FS problem in terms of BG and proposes a novel method to select the best features. The proposed BG based FS method is a filter type FS method and it starts with identifying Principle Features (PF) and proceeds to play global pairwise Bayesian games between those PF to obtain feature scores. Later, the features are ranked using these scores. In the final stage, a forward selection method with Support Vector Machine (SVM) is used to evaluate the classification performance of the ranked features and helps in the selection of the optimal set of features. Besides these, to improve the scalability of the proposed method MapReduce paradigm is exploited. In order to show the efficacy of the proposed method, experiments are carried out with seven real-world datasets from UCI and Statlog repositories. The promising results showed a significant improvement in the classification performance with fewer selected features than which is achieved using the existing methods. [ABSTRACT FROM AUTHOR]

In order to enhance the filtering of spam on the Internet and improve the experience of Internet users, this paper proposed to convert the email text into vector features using the vector space model, constructed a two-dimensional matrix, and used a convolutional neural network (CNN) to identify spam on the Internet. The CNN was compared with other two classifiers, support vector machine (SVM), and backward-propagation neural network (BPNN), in simulation experiments. The final results showed that the spam recognition algorithm with CNN as the classifier had better recognition performance than the algorithms with SVM and BPNN classifiers and was also more advantageous in terms of recognition cost and time for spam; in addition, the CNN had the best recognition performance when the number of extracted features was 15. [ABSTRACT FROM AUTHOR]

Rice variety identification is important for genetic breeding classification and crop yield estimation. Traditional identification methods are time-consuming and inaccurate. This paper proposes a method for rice variety identification based on the hyperspectral characteristics of leaves. Hyperspectral data of rice leaves were collected using a geophysical spectrometer imaging system. To reduce the redundance among the hyperspectral data and save the identification cost, locality preserving projections (LPP) is first applied to extract low-dimensional representative features from the leaf hyperspectral data. Then, support vector machine (SVM) is combined for conducting the identification of rice varieties. The experimental results show that the identification rate of 10 varieties of early rice was found to be 91.67% and the identification rate of 10 varieties of late rice was 97.33%. [ABSTRACT FROM AUTHOR]

Hyperspectral image (HSI) classification is an important topic in remote sensing. In this paper, we propose a new method for HSI classification by using minimum noise fraction (MNF), spatial filtering (SF) and support vector machine (SVM). We use MNF to reduce the dimensionality of a hyperspectral data cube before performing classification. We apply 2D SF to the DR output band images and then use SVM to classify the pixels of the data cube. In this way, both spatial information and spectral information are taken into consideration in the classification. Experimental results show that our MNF+SF method is extremely competitive when compared to several existing classification methods. [ABSTRACT FROM AUTHOR]

This paper studies the binary classification problem associated with a family of Lipschitz convex loss functions called large-margin unified machines (LUMs), which offers a natural bridge between distribution-based likelihood approaches and margin-based approaches. LUMs can overcome the so-called data piling issue of support vector machine in the high-dimension and low-sample size setting, while their theoretical analysis from the perspective of learning theory is still lacking. In this paper, we establish some new comparison theorems for all LUM loss functions which play a key role in the error analysis of large-margin learning algorithms. Based on the obtained comparison theorems, we further derive learning rates for regularized LUMs schemes associated with varying Gaussian kernels, which maybe of independent interest. [ABSTRACT FROM AUTHOR]

Brain tumor is one of the most severe nervous system disorders affecting the health of humans and critically it will lead to death. The most elevated disease that causes a major death rate is Glioma, i.e. a primary intracranial tumor. One of the widely used techniques in medical imaging is Magnetic Resonance Imaging (MRI) which turned out as the principle diagnosis model for the analysis of glioma and its treatment. However, the brain tumor segmentation and classification process are more complicated problems to execute. This paper intends to introduce a novel brain tumor classification model that includes four major phases: (i) Pre-processing (ii) Segmentation (iii) Brain Feature extraction (iv) Brain tumor Classification. Initially, the input image is subjected to the pre-processing phase, in which the image is pre-processed under a certain process. The pre-processed images are then subjected to the segmentation phase, which is carried out by the k-means clustering. Subsequently, the segmented images are subjected to the brain feature extraction phase, in which the features are extracted using the hybrid Principal Component Analysis (PCA)-GIST feature extraction method. Then, these features are given as the input to the classification process, where the ensemble classifier is exploited for the same. Moreover, the proposed ensemble technique includes k-Nearest Neighbor (k-NN), Optimized Neural Network (NN), Random Forest (RF), and Support Vector Machine (SVM). To precisely detect the tumor classification, the NN training is performed using Elephant Herding Optimization with mutation operations (EHOMO) Algorithm via selecting the optimal weights. [ABSTRACT FROM AUTHOR]

In this paper, automatic electrocardiogram (ECG) recognition and classification algorithms based on multifractal detrended fluctuation analysis (MF-DFA) and multifractal detrended cross-correlation analysis (MF-DXA) were studied. As human heart is a complex, nonlinear, chaotic system, using multifractal analysis to analyze chaotic systems is also a trend. We performed a comparison study of the multifractal nature of the healthy subjects and that of the cardiac dysfunctions ones. To analyze multifractal property quantitatively, the ranges of the Hurst exponent (Δ h) are computed by MF-DFA and MF-DXA. We found that for MF-DFA, the area of Hurst exponents for atrial premature beat (APB) people was narrower than normal sinus rhythm (NSR) subjects, and for MF-DXA, the difference of Δ h (Δ (Δ h)) of NSR and APB subjects was larger than that of MF-DFA. We then regarded the Hurst exponents (h) as the input vectors and took them into support vector machine (SVM) for classification. The results showed that h obtained from MF-DXA led to a higher classification accuracy than that of MF-DFA. This is related to the widening of the difference in the values of Hurst exponents in MF-DFA and MF-DXA. The proposed MF-DFA-SVM and MF-DXA-SVM systems achieved classification accuracy of 8 6. 5 4 % ± 0. 0 6 8 % and 9 8. 6 3 % ± 0. 0 6 4 4 % , achieved classification sensitivity of 7 5. 0 3 % ± 0. 1 3 2 3 % and 9 0. 7 7 % ± 0. 1 3 0 9 % , achieved classification specificity of 8 6. 6 6 % ± 0. 1 1 3 1 % and 9 6. 4 7 % ± 0. 0 8 9 1 % , respectively. In general, the Hurst exponents obtained from MF-DXA played an important role in classifying ECG of the healthy and that of the cardiac dysfunctions subjects. Moreover, MF-DXA was more accurate than MF-DFA in the classification of ECG studied in this paper. The research in automatic medical diagnosis and early warning of major diseases has very important practical value. [ABSTRACT FROM AUTHOR]

Huge amount of personal data is collected by online applications and its protection based on privacy has brought a lot of major challenging issues. Hence, the K -anonymization with privacy-preserving data publishing has emerged as an active research field. The published data contains personalized information, which may be used for analysis converting it to useful information. In this paper, Quasi identifier (QI) data publishing with data preservation through the K -anonymization process is proposed. Moreover, the risks such as the temporal attack in the previous release of re-identifying QI information are evaluated using the K -anonymity model. The development of independent and ensemble classifiers for finding efficient QI's to avoid temporal attacks is the major objective of this paper. Therefore, the classifiers like Naïve Bayes, Support Vector Machine, and Multilayer Perceptron are used as base classifiers. An ensemble model based on these base classifiers is also used. The experimental results demonstrate that, the proposed classification approach is an effective K-anonymity tool for the enhancement of sequential release. [ABSTRACT FROM AUTHOR]

The need for identity authentication has become essential in various aspects of people's life. In this paper, we propose a novel biometric authentication strategy based on music-induced autobiographical memory electroencephalogram (EEG). Specific music is used to induce the stable autobiographical memory, while the EEG signals are collected through the memory process. Users can authenticate themselves by recollecting their minds when listening to the music, which is closely related to their long-term memory. Based on six types of EEG features from 12 subjects, mean F1 score of 0.937, 0.936 and 0.968 are achieved using Logistic Regression, Support Vector Machine and RUSBoost classifier, respectively. This promising result indicates the high distinctive characteristics in music-induced autobiographical memory EEG, which is suitable for identity authentication applications. [ABSTRACT FROM AUTHOR]

Software Defect Prediction (SDP) involves the early detection of fault-prone modules and reduces the testing efforts and cost. Support Vector Machine (SVM)-based SDP classifiers use large amount of high-dimensional data, and hence feature selection (FS) is applied for better accuracy. Search-based feature selection is found effective to improve the efficiency of predictors. This paper proposes a genetic evolution (GeEv) technique to select features. The GeEv technique involves introduction of diversity at intermediate level by the genetic evolution of random offspring with better survival capability. GeEv searches the feature space for an optimal feature subset using the performance of classification and number of features selected as the fitness function. The FS is modeled as an optimization problem and optimal solution is sought using GeEv. The performance is compared with baseline technique. From the experimental results, it is shown GeEv outperforms the competing FS approach and can achieve better accuracy than others statistically. [ABSTRACT FROM AUTHOR]

Chile presents a high seismicity and very particular characteristics due to its subductive environment and high convergence rate of the interacting plates. In this paper, ground motion models (GMM) for Arias Intensity and strong ground motion duration are developed based on recently compiled Chilean earthquakes records. The Chilean derived GMM are later compared with global and subduction models. For the duration case, two definitions are considered: significant duration and bracketed duration. Care is taken to consider newly define rupture areas for the major earthquake in the catalog, which allows to redefine the distances to be used in the analysis. The strong motion records are processed using robust techniques and standardized procedures. The model parameters are selected using a Bayesian updating method. This allows to estimate the parameters as well as their corresponding uncertainties recognizing the variability of the coefficients and of the selected model. The derived ground motion predictive model associated is validated through a residual analysis and probability distributions, obtained from the adjustment method. Additionally, for the bracketed duration analysis, a classification method based on Support Vector Machine (SVM) is used, with the aim to incorporate the records with duration of zero seconds. The comparison of the resultant model with the existing ones allows to confirm the differences that the tectonic Chilean environment produces, characterized mainly by a high relative convergence rate between plates and interplate thrust earthquakes with high magnitudes. [ABSTRACT FROM AUTHOR]

In the present times, artificial-intelligence based techniques are considered as one of the prominent ways to classify images which can be conveniently leveraged in the real-world scenarios. This technology can be extremely beneficial to the lepidopterists, to assist them in classification of the diverse species of Rhopalocera, commonly called as butterflies. In this article, image classification is performed on a dataset of various butterfly species, facilitated via the feature extraction process of the Convolutional Neural Network (CNN) along with leveraging the additional features calculated independently to train the model. The classification models deployed for this purpose predominantly include K-Nearest Neighbors (KNN), Random Forest and Support Vector Machine (SVM). However, each of these methods tend to focus on one specific class of features. Therefore, an ensemble of multiple classes of features used for classification of images is implemented. This research paper discusses the results achieved from the classification performed on basis of two different classes of features i.e., structure and texture. The amalgamation of the two specified classes of features forms a combined data set, which has further been used to train the Growing Convolutional Neural Network (GCNN), resulting in higher accuracy of the classification model. The experiment performed resulted in promising outcomes with TP rate, FP rate, Precision, recall and F-measure values as 0.9690, 0.0034, 0.9889, 0.9692 and 0.9686 respectively. Furthermore, an accuracy of 96.98% was observed by the proposed methodology. [ABSTRACT FROM AUTHOR]

Feature selection is a preprocessing step that plays a crucial role in the domain of machine learning and data mining. Feature selection methods have been shown to be effective in removing redundant and irrelevant features, improving the learning algorithm's prediction performance. Among the various methods of feature selection based on redundancy, the fast correlation-based filter (FCBF) is one of the most effective. In this paper, we developed a novel extension of FCBF, called resampling FCBF (RFCBF) that combines resampling technique to improve classification accuracy. We performed comprehensive experiments to compare the RFCBF with other state-of-the-art feature selection methods using three competitive classifiers (K-nearest neighbor, support vector machine, and logistic regression) on 12 publicly available datasets. The experimental results show that the RFCBF algorithm yields significantly better results than previous state-of-the-art methods in terms of classification accuracy and runtime. [ABSTRACT FROM AUTHOR]

With the increasing popularity of online social networking platforms, the amount of social data has grown exponentially. Social data analysis is essential as spamming activities and spammers are escalating over online social networking platforms. This paper focuses on spammer detection on the Twitter social networking platform. Although existing researchers have developed numerous machine learning methods to detect spammers, these methods are inefficient for appropriately detecting spammers on Twitter due to the imbalance of spam and nonspam data distribution, the involvement of diverse features and the applicability of data mechanisms by spammers to avoid their detection. This research work proposes a novel hybrid approach of the gravitational search algorithm and the decision tree (HGSDT) for detecting Twitter spammers. The individual decision tree (DT) algorithm is not able to address the challenges as it is unstable and ineffective for the higher level of favorable data for a particular attribute. The gravitational search algorithm (GSA) constructs the DTs with improved performance as the gravitational forces act as the information-transferring agents through mass agents. Moreover, the GSA is efficient in handling the data of higher dimensional search space. In the HGSDT approach, the construction of the DT and splitting of nodes are performed with the heuristic function and Newton's laws. The performance of the proposed HGSDT approach is determined for the Social Honeypot dataset and 1KS-10KN dataset by conducting three different experiments to analyze the impact of training data size, features and spammer ratio. The result of the first experiment shows the need of a higher proportion of training data size, the second experiment signifies the more importance of textual content-based features compared to the other feature categories and the third experiment indicates the requirement of balanced data to attain the effective performance of the proposed approach. The overall performance comparison indicates that the proposed HGSDT approach is superior to the incorporated machine learning methods of DT, support vector machine and back propagation neural network for detecting Twitter spammers. [ABSTRACT FROM AUTHOR]

Traditional machine learning requires users to have a strong ability to control features and distance calculation formulas, especially in the use of support vector machine SVM and nearest neighbor KNN. Traditional machine learning uses PCA in feature extraction will actually lead to Information is lost. In order to solve the problem of low optical film damage detection rate of traditional methods, a new method is proposed in this paper based on a convolutional neural network instead of traditional machine learning to classify CCD images with different damage degrees of SiO2 film and K9 glass. First, film images are collected by online CCD, and the proposed algorithm is designed to extract the image characteristic parameters of the film microscopic images, filter denoising, and run binarization to analyze film images. Second, gray values of images are extracted and classified by unsupervised learning. Finally, the film microscopic images under the microscope are analyzed. The experimental results show that the defect positions on the images can be detected after the images are detected and processed by a convolution neural network, binarization, and connected domains. The defective parts can be intercepted from the images, and the data related is saved for damage type determination. The average classification rate is over 99%, which is better than the traditional method by 9.1%. Therefore, it has a high application value. [ABSTRACT FROM AUTHOR]

This paper analyzes a new regularized learning scheme for high-dimensional partially linear support vector machine (SVM). The proposed approach consists of an empirical risk and the Lasso-type penalty for linear part, as well as the standard functional norm for nonlinear part. Here, the linear kernel is used for model interpretation and feature selection, while the nonlinear kernel is adopted to enhance algorithmic flexibility. In this paper, we develop a new technical analysis on the weighted empirical process, and establish the sharp learning rates for the semi-parametric estimator under the regularized conditions. Specially, our derived learning rates for semi-parametric SVM depend on not only the sample size and the functional complexity, but also the sparsity and the margin parameters. [ABSTRACT FROM AUTHOR]

In recent years, the number of cardiac disease patients has been increasing. Modern medical research has shown that the complexity of electrocardiogram (ECG) signals is related to cardiovascular diseases. This paper investigates the difference in complexity of ECG data from the people with different cardiovascular diseases, such as atrial fibrillation (AF), ventricular arrhythmia (VA) and congestive heart failure (CHF). The empirical mode decomposition (EMD) and multiscale entropy method are used to analyze the ECG data, and a mathematical model established by a support vector machine is used to identify different diseases. The accuracy recognition rate of the AF recognition is 96.25%, and that of the CHF and VA reach 90.26% and 92.20%, respectively. The experimental results show that the recognition method proposed in this paper is successful. [ABSTRACT FROM AUTHOR]

This study presents a novel facial makeup detection scheme using fusion of multi-scale Local Binary Patterns (ms-LBP) texture methods and convolutional neural network (CNN) deep learning extractor. Facial makeups affect the accuracy of face recognition systems due to appearance alteration of individuals. In order to fuse the facial features, the proposed scheme first considers concatenation of extracted global histogram of a whole image using three different LBP operators. The LBP scales are used to extract and then concatenate the local histogram of overlapping and nonoverlapping blocks of images. This way utilizes the advantages of microtexton information of local primitives besides the extracted global textures. Finally, the extracted features using CNN feature extractor are combined with global and local multi-scale textures. In general, CNN deep learning extractor learns high-level discriminative characteristics of images and therefore the proposed system improves the facial makeup detection rate by involving both microtexton and discriminative information of facial images. In addition, the proposed method attempts to select the optimized subset of facial features to increase the detection performance of system by applying Particle Swarm Optimization (PSO) technique after feature level fusion. The paper uses Support Vector Machine (SVM) classifier for classifying the facial vectors into makeup or no-makeup classes. The proposed scheme is then evaluated using YMU, VMU and MIW facial makeup databases with consideration of light, medium and heavy makeups on several datasets. Experimental results analysis clarifies the effectiveness of proposed facial makeup detection framework of this study. [ABSTRACT FROM AUTHOR]

Screening and diagnosing of abnormal Leukocytes are crucial for the diagnosis of immune diseases and Acute Lymphoblastic Leukemia (ALL). As the deterioration of abnormal leukocytes is mainly due to the changes in the chromatin distribution, which significantly affects the absorption and reflection of light, the spectral feature is proved to be important for leukocytes classification and identification. This paper proposes an accurate identification method for healthy and abnormal leukocytes based on microscopic hyperspectral imaging (HSI) technology which combines the spectral information. The segmentation of nucleus and cytoplasm is obtained by the morphological watershed algorithm. Then, the spectral features are extracted and combined with the spatial features. Based on this, the support vector machine (SVM) is applied for classification of five types of leukocytes and abnormal leukocytes. Compared with different classification methods, the proposed method utilizes spectral features which highlight the differences between healthy leukocytes and abnormal leukocytes, improving the accuracy in the classification and identification of leukocytes. This paper only selects one subtype of ALL for test, and the proposed method can be applied for detection of other leukemia in the future. [ABSTRACT FROM AUTHOR]