Search

Internet of Things (IoT) as an emerging technology is widely used in various applications such as remote healthcare, smart environment, and intelligent transportation systems. It is necessary to address users' concerns about cost, ease of use, privacy, and comprehensive security to grow the popularity of this technology. Intrusion Detection System (IDS) plays an indispensable role in security and preventing unauthorized users to access authorized network resources through analyzing network patterns. Several techniques such as metaheuristic algorithms, machine learning, fuzzy logic, and artificial intelligence algorithms can be applied to increase the accuracy of IDS, feature selection, and network patterns classification. In this paper, a hybrid intrusion detection system based on Support Vector Machine (SVM) and Grey Wolf Optimization (GWO) is presented that utilizes the advantages of these algorithms. In the proposed approach, the support vector machine has been used to train and differentiate anomaly records from normal records and grey wolf optimization has been used to find the kernel function, feature selection, and adjust optimal parameters for the SVM in order to improve the classification. The conducted simulations prove that the proposed approach outperforms in terms of detection accuracy, precision, recall, and F-score on both NSL-KDD and TON_IoT datasets. [ABSTRACT FROM AUTHOR]

Collecting and analyzing data from all devices to improve the efficiency of business processes is an important task of Industrial Internet of Things (IIoT). In the age of data explosion, extensive text data generated by the IIoT have given birth to a variety of text representation methods. The task of text representation is to convert the natural language to a form that computer can understand with retaining the original semantics. However, these methods are difficult to effectively extract the semantic features among words and distinguish polysemy in natural language. Combining the advantages of convolutional neural network (CNN) and variational autoencoder (VAE), this paper proposes an intelligent CNN-VAE text representation algorithm as an advanced learning method for social big data within next-generation IIoT, which help users identify the information collected by sensors and perform further processing. This method employs the convolution layer to capture the local features of the context and uses the variational technique to reconstruct feature space to make it conform to the normal distribution. In addition, the improved word2vec model based on topical word embedding (TWE) is utilized to add topical information to word vectors to distinguish polysemy. This paper takes the social big data as an example to illustrate the way of the proposed algorithm applied in the next-generation IIoT and utilizes Cnews dataset to verify the performance of proposed method with four evaluating metrics (i.e., recall, accuracy, precision, and F1-score). Experimental results indicate that the proposed method outperforms word2vec-avg and CNN-AE in K-nearest neighbor (KNN), random forest (RF), and support vector machine (SVM) classifiers and distinguishes polysemy effectively. [ABSTRACT FROM AUTHOR]

Twin support vector regression (TSVR) has been widely applied in regression problems. TSVR seeks a pair of ε -insensitive proximal planes by solving two support vector machine type problems. TSVR assumes that the matrices appearing in the dual formulation are positive definite. However, in real-world scenarios, such an assumption may not be fulfilled and, hence, leads to suboptimal performance. ε -Twin support vector regression (ε -TSVR) improved the TSVR by introducing the regularisation term to avoid the singularity issues. Most of the twin support vector machine models involve the computation of matrix inverses. Also, TSVR implements the empirical risk minimization principle. In this paper, we propose an improved twin support vector regression (ITSVR) for brain age estimation by introducing different Lagrangian functions for the primal problems of the TSVR. The proposed ITSVR implements the structural risk minimization principle and avoids the computation of the matrix inverses. To solve the optimization problem more efficiently, we used successive overrelaxation (SOR) technique. We evaluated the proposed ITSVR on cognitively healthy subjects, mild cognitive impairment subjects and Alzheimer's disease subjects. The experimental results demonstrate that the proposed ITSVR has superior performance compared to the baseline models for brain age estimation. [ABSTRACT FROM AUTHOR]

In the magnetic-suspension bearing-rotor system, the shape features of the rotor axis trajectory can directly reflect the system operation status and fault information. Accurately classifying the bearing faults can promptly find the cause of the fault and respond quickly and protect it. In this paper, in order to achieve fault identification by identifying and classifying the rotor axis trajectory, we use Hu moment invariants to extract feature vectors from the rotor axis trajectory to identify faults. We use imperial competitive algorithm to reduce redundant data and establish a directed acyclic graph support vector machine to classify and identify feature data. Compared with traditional classification models such as C4.5 and BP neural networks, the experimental results show that the support vector machine model based on Hu moment invariants and simulated annealing has a higher accuracy and robustness in small sample classification. It is suitable for intelligent identification and classification for bearing faults. [ABSTRACT FROM AUTHOR]

This study utilizes classification models to provide a robust algorithm for imbalanced data where the minority class is of the interest, that is, in the context of default payments. In developing an integrated predictive accuracy algorithm, this study proposes machine learning classifiers and applies DNN, SVM, KNN, and ANN. The proposed algorithm utilizes a 30,000 imbalanced dataset to improve the accuracy of the prediction of default payments by implementing oversampling and undersampling strategies, such as synthetic minority oversampling technique (SMOTE), SVM SMOTE, random undersampling, and ALL-KNN. The results indicate that the SVM under the ALL-KNN sampling technique is able to achieve an accuracy of 98.6%, with the lowest cross entropy loss measurement of 0.028. Through the accurate implementation of the neural networks and neurons used in the proposed algorithm, this paper presents better insights into the functioning of the neural networks when used in conjunction with the resampling techniques. Using the methodology and algorithm presented in this study, credit risk assessments can be more accurately predicted in practical applications where most of the clients are categorized as non-default payments. [ABSTRACT FROM AUTHOR]

This paper designs a maritime anomaly detection algorithm based on a support vector machine (SVM) that considers the spatiotemporal and motion features of trajectories. Since trajectories are two-dimensional, it is difficult to present their motion features. To accurately describe trajectory features, a novel trajectory feature extraction method based on statistical theory is proposed in this paper. This method maps trajectories onto a high-dimensional space, which can account for both the spatiotemporal features and motion features of the trajectories. With the proposed feature extraction method, the density-based spatial clustering of applications with noise algorithm is employed to recognize vessel traffic patterns by simultaneously considering the spatiotemporal and motion features. Then, an improved SVM is designed by employing a weighted hybrid kernel function and differential operator to detect anomalous behaviours from recognized vessel traffic patterns that include the spatiotemporal and motion characteristics. Compared with standard SVM, it can adaptively determine the optimal kernel function according to sample set. Finally, a numerical example based on automatic identification system data from the waters off Chengshan Jiao is fulfilled to verify the proposed algorithm effectiveness and accuracy. [ABSTRACT FROM AUTHOR]

Discovering a hearing disorder at an earlier intervention is critical for reducing the effects of hearing loss and the approaches to increase the remaining hearing ability can be implemented to achieve the successful development of human communication. Recently, the explosive dataset features have increased the complexity for audiologists to decide the proper treatment for the patient. In most cases, data with irrelevant features and improper classifier parameters causes a crucial influence on the audiometry system in terms of accuracy. This is due to the dependent processes of these two, where the classification accuracy performance could be worsened if both processes are conducted independently. Although the filter algorithm is capable of eliminating irrelevant features, it still lacks the ability to consider feature reliance and results in a poor selection of significant features. Improper kernel parameter settings may also contribute to poor accuracy performance. In this paper, an ensemble filters feature selection based on Information Gain (IG), Gain Ratio (GR), Chi-squared (CS), and Relief-F (RF) with harmonize optimization of Particle Swarm Optimization (PSO) and Support Vector Machine (SVM) is presented to mitigate these problems. Ensemble filters are utilized so that the initial top dominant features relevant for classification can be considered. Then, PSO and SVM are optimized simultaneously to achieve the optimal solution. The results on a standard Audiology dataset show that the proposed method produces 96.50% accuracy with optimal solution compared to classical SVM, which signifies the proposed method is effective in handling high dimensional data for hearing disorder prediction. [ABSTRACT FROM AUTHOR]

In the lung computer-aided detection (Lung CAD) system, the region of interest (ROI) of lung nodules has more false positives, making the imbalance between positive and negative (true positive and false positive) samples more likely to lead to misclassification of true positive nodules, a cost-sensitive multikernel learning support vector machine (CS-MKL-SVM) algorithm is proposed. Different penalty coefficients are assigned to positive and negative samples, so that the model can better learn the features of true positive nodules and improve the classification effect. To further improve the detection rate of pulmonary nodules and overall recognition accuracy, a score function named F-new based on the harmonic mean of accuracy (ACC) and sensitivity (SEN) is proposed as a fitness function for subsequent particle swarm optimization (PSO) parameter optimization, and a feasibility analysis of this function is performed. Compared with the fitness function that considers only accuracy or sensitivity, both the detection rate and the recognition accuracy of pulmonary nodules can be improved by this new algorithm. Compared with the grid search algorithm, using PSO for parameter search can reduce the model training time by nearly 20 times and achieve rapid parameter optimization. The maximum F-new obtained on the test set is 0.9357 for the proposed algorithm. When the maximum value of F-new is achieved, the corresponding recognition ACC is 91%, and SEN is 96.3%. Compared with the radial basis function in the single kernel, the F-new of the algorithm in this paper is 2.16% higher, ACC is 1.00% higher and SEN is equal. Compared with the polynomial kernel function in the single kernel, the F-new of the algorithm is 3.64% higher, ACC is 1.00% higher and SEN is 7.41% higher. The experimental results show that the F-new, ACC and SEN of the proposed algorithm is the best among them, and the results obtained by using multikernel function combined with F-new index are better than the single kernel function. Compared with the MKL-SVM algorithm of grid search, the ACC of the algorithm in this paper is reduced by 1%, and the results are equal to those of the MKL-SVM algorithm based on PSO only. Compared with the above two algorithms, SEN is increased by 3.71% and 7.41%, respectively. Therefore, it can be seen that the cost sensitive method can effectively reduce the missed detection of nodules, and the availability of the new algorithm can be further verified. [ABSTRACT FROM AUTHOR]

In this paper, we present difference of convex algorithms for solving bilevel programs in which the upper level objective functions are difference of convex functions, and the lower level programs are fully convex. This nontrivial class of bilevel programs provides a powerful modelling framework for dealing with applications arising from hyperparameter selection in machine learning. Thanks to the full convexity of the lower level program, the value function of the lower level program turns out to be convex and hence the bilevel program can be reformulated as a difference of convex bilevel program. We propose two algorithms for solving the reformulated difference of convex program and show their convergence to stationary points under very mild assumptions. Finally we conduct numerical experiments to a bilevel model of support vector machine classification. [ABSTRACT FROM AUTHOR]

State of charge (SOC) is a crucial index for a battery's energy assessment. Its estimation is becoming an increasing challenge in order to assure the battery's safety and efficiency. To this end, many methods can be found in the scientific literature with various accuracy and complexity. However, accurate SOC is highly dependent on the adopted methodology. This paper investigates five methods for estimating battery SOC for lithium-ion (Li-ion) manufacturers. For this purpose, five methods were selected and then used in practice, including the modified Coulomb counting method, the extended Kalman filter, the neural network (NN), and two other techniques based on machine learning known as the support vector machines and the K-nearest neighbor algorithm (KNN), respectively. A detailed analysis based on statistical assessment is performed on an experimental test that covers multiple cycles of charge and discharge modes. The KNN method proved to be more accurate than the EKF approach, which is extensively used for estimating the SOC of Li-ion batteries. The algorithm demonstrated great predictive accuracy, with most predictions having a relative error near zero and a maximum error value of roughly 0.26%. All of the findings validate the methodology's reliability and efficiency. [ABSTRACT FROM AUTHOR]

This paper is proposing an machine learning based expert system for preliminary prediction of the insulation fire resisting performance of shallow floor systems when subject to exposure to the ISO 834 Standard Fire Curve. The proposed system is a digital tool which incorporates a machine learning algorithm trained on the outcomes of pre-run two-dimensional finite element heat transfer analyses of shallow floor system details. The algorithm predicts the insulation performance of similar details with a measurable accuracy of 96% (i.e the insulation rating band was predicted correctly in 96% of the cases) without the requirement for an explicit deterministic analysis. The paper presents the challenges and prerequisites to build such an expert system and acts as a proof of concept for the use of machine learning for the assessment of the insulation performance of shallow floor system under the guidance of BS EN 1363-1:2012. A Support Vector Machine machine learning algorithm is adopted in this work. The required processes that were needed for the development of the expert system include the stages of data acquisition, exploratory data analysis, choice of machine learning algorithm, model training, tuning, and validation. This expert system is useful for practitioners to rapidly assess the feasibility of different construction details at early stages of the design process. [ABSTRACT FROM AUTHOR]

Wireless Rechargeable Sensor Networks based on wireless energy transmission successfully solve the problem of node death caused by energy shortage in traditional wireless sensor networks. Existing studies on joint energy replenishment and data collection have planned charging path first and then perform data collection. This approach does not effectively extend network life and improve network performance in data collection. In this paper, we jointly consider the impact of energy replenishment and data collection on network performance and use the Least Squares Support Vector Machine based regression prediction with dynamically changing energy consumption rate and data generation rate of sensor nodes. To solve the above problem, we propose a multi-objective path planning model for joint energy replenishment and data collection with the optimization objectives of maximizing the remaining lifetime of sensor nodes, maximizing the data collection of MC, and minimizing the amount of data loss. The conventional exact algorithm is difficult to solve the path planning problem, so heuristic algorithms have gradually become the main algorithm to solve the problem. Based on discrete fireworks algorithm and co-evolutionary algorithm, we present a grid-based multi-objective cooperation fireworks algorithm. Simulation results show that the proposed algorithm performs better in convergence and diversity. In terms of the average remaining lifetime of sensor nodes, the proposed algorithm is 0.43%, 0.52%, 1.97%, and 0.81% higher than MPACO, MODFA, NSGA-II, and SPEA-II, respectively. Similarly, the target value of solutions in data collection increased by 1.87%, 1.22%, 4.49%, and 2.10%, respectively. [ABSTRACT FROM AUTHOR]

To solve the problem that the traditional hyperspectral image classification method cannot effectively distinguish the boundary of objects with a single scale feature, which leads to low classification accuracy, this paper introduces the idea of guided filtering into hyperspectral image classification, and then proposes a multi-scale guided feature extraction and classification (MGFEC) algorithm for hyperspectral images. Firstly, the principal component analysis theory is used to reduce the dimension of hyperspectral image data. Then, guided filtering algorithm is used to achieve multi-scale spatial structure extraction of hyperspectral image by setting different sizes of filtering windows, so as to retain more edge details. Finally, the extracted multi-scale features are input into the support vector machine classifier for classification. Several practical hyperspectral image datasets were used to verify the experiment, and compared with other spectral feature extraction algorithms. The experimental results show that the multi-scale features extracted by the MGFEC algorithm proposed in this paper are more accurate than those extracted by only using spectral information, which leads to the improvement of the final classification accuracy. This fully shows that the proposed method is not only effective, but also suitable for processing different hyperspectral image data. [ABSTRACT FROM AUTHOR]

A software defect report is a bug in the software system that developers and users submit to the software defect library during software development and maintenance. Managing a software defect report that is overwhelming is a challenging task. The traditional method is manual identification, which is time-consuming and laborious and delays the repair of important software defects. Based on the above background, the purpose of this paper is to study the software defect prediction (SDP) model based on LASSO–SVM. In this paper, the problem of poor prediction accuracy of most SDP models is proposed. A SDP model combining minimum absolute value compression and selection method and support vector machine algorithm is proposed. Firstly, the feature selection ability of the minimum absolute value compression and selection method is used to reduce the dimension of the original data set, and the data set not related to SDP is removed. Then, the optimal value of SVM is obtained by using the parameter optimization ability of cross-validation algorithm. Finally, the SDP is completed by the nonlinear computing ability of SVM. The accuracy of simulation results is 93.25% and 66.67%, recall rate is 78.04%, and f-metric is 72.72%. The results show that the proposed defect prediction model has higher prediction accuracy than the traditional defect prediction model, and the prediction speed is faster. [ABSTRACT FROM AUTHOR]

The K-nearest neighbor-weighted multi-class twin support vector machine (KWMTSVM) is an effective multi-classification algorithm which utilizes the local information of all training samples. However, it is easily affected by the noises and outliers owing to the use of the hinge loss function. That is because the outlier will obtain a huge loss and become the support vector, which will shift the separating hyperplane inappropriately. To reduce the negative influence of outliers, we use the ramp loss function to replace the hinge loss function in KWMTSVM and propose a novel sparse and robust multi-classification algorithm named ramp loss K-nearest neighbor-weighted multi-class twin support vector machine (RKWMTSVM) in this paper. Firstly, the proposed RKWMTSVM restricts the loss of outlier to a fixed value, thus the negative influence on the construction of hyperplane is suppressed and the classification performance is further improved. Secondly, since outliers will not become support vectors, the RKWMTSVM is a sparser algorithm, especially compared with KWMTSVM. Thirdly, because RKWMTSVM is a non-differentiable non-convex optimization problem, we use the concave–convex procedure (CCCP) to solve it. In each iteration of CCCP, the proposed RKWMTSVM solves a series of KWMTSVM-like problems. That also means RKWMTSVM inherits the merits of KWMTSVM, namely, it can exploit the local information of intra-class to improve the generalization ability and use inter-class information to remove the redundant constraints and accelerate the solution process. In the end, the clipping dual coordinate descent (clipDCD) algorithm is employed into our RKWMTSVM to further speed up the computational speed. We do numerical experiments on twenty-four benchmark datasets. The experimental results verify the validity and effectiveness of our algorithm. [ABSTRACT FROM AUTHOR]

The insulating strength of an air gap is an important basis for external insulation design of power transmission and transformation project, and both gap structure and meteorological conditions have a great influence on the breakdown voltage of air gap. The temperature, humidity and other meteorological conditions in the actual operating environment of power transmission and transformation projects may change greatly with time, so presently, there is no better method to calculate the breakdown voltage of air gaps in various meteorological conditions. In this paper, a prediction model for positive switching impulse breakdown voltage of rod-plane air gap based on extremely randomized trees is proposed. All samples are divided into training set and test set by Self-Organizing Mapping neural network and stratified sampling method. In the test set, the predicted breakdown voltage results of rod-plane air gap based on decision trees, random forest, extremely randomized trees and support vector machine are compared, with reference to the rectification results of atmospheric correction method. The result shows that the maximum absolute relative error of the model is 4.3% and the mean absolute percentage error is 1.6%. Then, the importance of features of import variables is calculated with the trained extremely randomized trees model. Finally, the breakdown voltage of rod-plane air gap in correspondence to different gap distances in four extreme meteorological conditions is calculated with the model. The method can provide reference for calculation of the breakdown voltage of air gap in various meteorological conditions. [ABSTRACT FROM AUTHOR]

Fuzzy support vector machine and their variants are prominent classification techniques that reduce the adverse effects of noises and outliers as compare to classical support vector machine. However, in these methods, only the distance between the training pattern and the class center is considered, and hence, the edge support vectors cannot be distinguished from noises and outliers properly. These limitations are overcome by intuitionistic fuzzy-based support vector machine which allocate two parameters (membership and non-membership degrees) to each pattern of a dataset and hence define score number based on the importance of a pattern. In this paper, an intuitionistic fuzzy proximal support vector machine for multi-category classification problems is proposed. The method significantly reduces the impacts of noises and outliers present in the dataset by assigning the intuitionistic fuzzy score function to each training point based on its location and surroundings. Moreover, the method is computationally efficient as the robust classifiers are obtained by solving the system of linear equations instead of large size quadratic programming problems. In the proposed method, using polynomial and Gaussian kernels, the hyperplanes are also developed in the feature space. The geometrical advantages of the suggested method over the existing techniques are ascertained using the simulated two-dimensional artificial dataset having three target classes. Further, extensive experimental studies on ten UCI benchmark datasets have been performed which demonstrate that the proposed algorithm predicts more precisely about future data as comparison to some well-established algorithms. Figures are also illustrated by varying different parameters involved in the model which confirms the performance of the method over the existing algorithms. Moreover, the analysis of the predictive behavior of the proposed approach is done using the Friedman test, a nonparametric alternative to the analysis of variance test at 5 % significance level. Further, the proposed method has also been applied to image classification and gesture-phase segmentation problems which confirms the efficiency and handling capabilities of the proposed algorithm in practical applications. [ABSTRACT FROM AUTHOR]

An intrusion detection system is a security system that aims to detect sabotage and intrusions on networks to inform experts of the attack and abuse of the network. Different classification methods have been used in the intrusion detection systems such as fuzzy, genetic algorithms, decision trees, artificial neural networks, and support vector machines. Moreover, ensemble classifiers have shown more robust and effective performance for various tasks in the field. In this paper, we adopt ensemble models in order to improve the performance of intrusion detection and, at the same time, decrease the false alarm rate. We use kNN for multi-class classification, as well as SVM to approach the classification problem in normal-based detection. In order to combine multiple outputs, we use the Dempster–Shafer method in which there is the possibility of explicit retrieval of uncertainty. Moreover, we utilize deep learning for extracting features to train the samples, selected by the sample selection algorithm based on ensemble margin. We compare our results with state-of-the-art methods on benchmarking datasets such as UNSW-NB15, CICIDS2017, and NSL-KDD. Our proposed method indicates the superiority in terms of prominent metrics Accuracy, Precision, Recall, and F-measure. [ABSTRACT FROM AUTHOR]

In this paper, the load forecasting model is established to increase the precision of meteorological impacts, temperature, short-term power load forecasting, working and holiday factors by considering the power load. Further, IGA-LS-SVM is proposed which is a short-term power load forecasting technique based on AI algorithm. And to increase the forecast accuracy and generalization capability of LS-SVM, we applied the adopted mutation probability and new coding technology to the parameter optimization of LS-SVM. The temperature, load, weather state, working and holiday days be taken as prediction model as input, and load value was predicted output. We selected the sample data from meteorological information and historical load of a city in Yunnan province. By results, the prediction verifies the good prediction effect when associated with existing BP algorithm and the proposed IGA- LS-SVM algorithm yields a value 0.8274 more significant than all others, which is appropriate for short-term power load prediction. [ABSTRACT FROM AUTHOR]

With the rapid development of computer technology, data collection becomes easier, and data object presents more complex. Data analysis method based on machine learning is an important, active, and multi-disciplinarily research field. Support vector machine (SVM) is one of the most powerful and fast classification models. The main challenges SVM faces are the selection of feature subset and the setting of kernel parameters. To improve the performance of SVM, a metaheuristic algorithm is used to optimize them simultaneously. This paper first proposes a novel classification model called IBMO-SVM, which hybridizes an improved barnacle mating optimizer (IBMO) with SVM. Three strategies, including Gaussian mutation, logistic model, and refraction-learning, are used to improve the performance of BMO from different perspectives. Through 23 classical benchmark functions, the impact of control parameters and the effectiveness of introduced strategies are analyzed. The convergence accuracy and stability are the main gains, and exploration and exploitation phases are more properly balanced. We apply IBMO-SVM to 20 real-world datasets, including 4 extremely high-dimensional datasets. Experimental results are compared with 6 state-of-the-art methods in the literature. The final statistical results show that the proposed IBMO-SVM achieves a better performance than the standard BMO-SVM and other compared methods, especially on high-dimensional datasets. In addition, the proposed model also shows significant superiority compared with 4 other classifiers. [ABSTRACT FROM AUTHOR]

Features subset selection was commonly used in data mining and artificial intelligence techniques to produce a model with a minimal set of features that enhances the performance of the classifier. The essential motive for selecting features is to avoid the problem of a number of dimensions trap. This paper introduces a new technique of selection of features dependent on the modified of binary teaching–learning-based optimization and the suggested method called MBTLBO. This algorithm (teaching learning-based optimization TLBO) is one of the present metaheuristic that is been widely utilized to a several of intractable optimization issues in recent times. Such algorithm has been combined with supervised data mining technique (support vector machine) for the implementation of feature subset selection problem in binary identification. The collection of specific risk features with the rheumatic disease was implemented. The findings revealed that the new approach (MBTLBO) increases the accuracy of classification. [ABSTRACT FROM AUTHOR]

The decision making of a suitable heating, ventilating and air conditioning system's set-point temperature is an energy and environmental challenge in our society. In the present paper, a general framework to define such temperature based on a dynamic adaptive comfort algorithm is proposed. Due to the fact that the thermal comfort of the occupants of a building has different ranges of acceptability, this method is applied to learn such comfort temperature with respect to the running mean temperature and therefore to decide the suitable range of indoor temperature. It is demonstrated that this solution allows to dynamically build an adaptive comfort algorithm, an algorithm based on the human being's thermal adaptability, without applying the traditional theory. The proposed methodology based on the K-Nearest-Neighbour algorithm was tested and compared with data from an experimental thermal comfort field study carried out in a mixed mode building in the south-western area of Spain and with the Support Vector Machine method. The results show that K-Nearest-Neighbour algorithm represents the pattern of thermal comfort data better than the traditional solution and that it is a suitable method to learn the thermal comfort area of a building and to define the set-point temperature for a heating, ventilating and air-conditioning system. [ABSTRACT FROM AUTHOR]

Mobile edge computing (MEC) is an emerging technology recognized as an effective solution to guarantee the Quality of Service for computation-intensive and latency-critical traffics. In MEC system, the mobile computing, network control and storage functions are deployed by the servers at the network edges (e.g., base station and access points). One of the key issue in designing the MEC system is how to allocate finite computational resources to multi-users. In contrast with previous works, in this paper we solve this issue by combining the real-time traffic classification and CPU scheduling. Specifically, a support vector machine based multi-class classifier is adopted, the parameter tunning and cross-validation are designed in the first place. Since the traffic of same class has similar delay budget and characteristics (e.g. inter-arrival time, packet length), the CPU scheduler could efficiently scheduling the traffic based on the classification results. In the second place, with the consideration of both traffic delay budget and signal baseband processing cost, a preemptive earliest deadline first (EDF) algorithm is deployed for the CPU scheduling. Furthermore, an admission control algorithm that could get rid off the domino effect of the EDF is also given. The simulation results show that, by our proposed scheduling algorithm, the classification accuracy for specific traffic class could be over 82 percent, meanwhile the throughput is much higher than the existing scheduling algorithms. [ABSTRACT FROM AUTHOR]