The paper addresses solutions based on machine learning methods to problems emerging at the withdrawal of statistical information about flows for real time classification of traffic in SDN networks. The solution is ba...
详细信息
ISBN:
(纸本)9783030392161;9783030392154
The paper addresses solutions based on machine learning methods to problems emerging at the withdrawal of statistical information about flows for real time classification of traffic in SDN networks. The solution is based on P4 switch with a specially designed for it system of memory organization allowing to store only the essential data about each flow per packet. Three ways of flow identification were discovered during the research. The method allows to avoid additional load both on the network between switches and SDN controller and the controller itself thanks to preliminary real time processing of data at the switch. The approach allows to avoid extension of delay of the controller response in the process of traffic flows classification. The theoretical foundation received experimental validation. Methodology is developed for defining optimal parameters of the switch. Optimal parameters for the switch planned for further research have been defined experimentally.
Time Series (TS) clustering is one of the most effervescent research fields due to the Big Data and the IoT explosion. The problem gets more challenging if we consider the multivariate TS. In the field of Business and...
详细信息
ISBN:
(纸本)9783030200558;9783030200541
Time Series (TS) clustering is one of the most effervescent research fields due to the Big Data and the IoT explosion. The problem gets more challenging if we consider the multivariate TS. In the field of Business and Management, multivariate TS are becoming more and more interesting as they allow to match events the co-occur in time but that is hardly noticeable. In this study, Recurrent Neural Networks and transfer learning have been used to analyze each example, measuring similarities between variables. All the results are finally aggregated to create an adjacency matrix that allows extracting the groups. Proof-of-concept experimentation has been included, showing that the solution might be valid after several improvements.
The main objective of intrusion detection systems (IDS) is to discover the dynamic and the virulent form of network traffic that simply changes according to the characteristics of the network. The IDS methodology repr...
详细信息
ISBN:
(纸本)9789811500299;9789811500282
The main objective of intrusion detection systems (IDS) is to discover the dynamic and the virulent form of network traffic that simply changes according to the characteristics of the network. The IDS methodology represents a prominent developing area in the field of computer network technology and its security. Different form of IDS has been developed working on distinctive approaches. One such kind of approach where it is used is the machine learning mechanism. In the proposed methodology, an experiment is applied on the data set named as KDD-99, including its subclasses such as denial of service (DOS), other types of attacks and the class without any form of attack. Depending upon the machine learning algorithms various distinct forms of IDS have been developed which further checks the optimization-based potential features in connectionwith the neural network classifier for the various forms of IDS-based attacks. This approach provides a comparative study between theANNand the optimizer-basedANNtechnology. The experimental analysis shows the convolution neural network with SVM show effective analysis providing accurate forms of IDS, thereby improving its detection based on individual class along with maintaining its results fundamentally.
Analyses of human action forces is a standard function of current digital human models. However, research has been indicating that this feature needs to be improved as it lacks accuracy. Muscle-torque based modeling c...
详细信息
ISBN:
(纸本)9783030202163;9783030202156
Analyses of human action forces is a standard function of current digital human models. However, research has been indicating that this feature needs to be improved as it lacks accuracy. Muscle-torque based modeling can be used to calculate action forces. Because it is not efficient to measure torques in all spatial directions, different calculating approaches have been developed. The question is which one is the best to calculate action forces? In this paper, we will therefor explain four different calculations - a spherical, linear, independent and fluid approach. To compare their quality, a study based on 366 measurements of maximum torques has been conducted. Results show that the spherical approach predicts maximum muscle torques to about 1.7% accuracy. The fluid approach increases the accuracy significantly (R-2 0.9), but needs more input data. Hence, a mix using both approaches is proposed as the best solution to calculate action forces in digital human models.
Recently, the government of United Arab of Emirates (UAE) is focusing on Artificial Intelligence (AI) strategy for future projects that will serve various sectors. Health care sector is one of the significant sectors ...
详细信息
ISBN:
(纸本)9783030311292;9783030311285
Recently, the government of United Arab of Emirates (UAE) is focusing on Artificial Intelligence (AI) strategy for future projects that will serve various sectors. Health care sector is one of the significant sectors they are focusing on and the planned (AI) projects of it is aiming to minimize chronic and early prediction of dangerous diseases affecting human beings. Nevertheless, project success depends on the adoption and acceptance by the physicians, nurses, decision makers and patients. The main purpose of this paper is to explore out the critical success factors assist in implementing artificial intelligence projects in the health sector. Besides, the founded gap for this topic was explored as there is no enough sharing of multiple success factors that assist in implementing artificial intelligence projects in the health sector precisely. A modified proposed model for this research was developed by using the extended TAM model and the most widely used factors. Data of this study was collected through survey from employees working in the health and IT sectors in UAE and total number of participants is 53 employees. The outcome of this questionnaire illustrated that managerial, organizational, operational and IT infrastructure factors have a positive impact on (AI) projects perceived ease of use and perceived usefulness.
With the arrival of the era of the big data, the power energy conservation has attracted much attention. The smart grid technology is a deep integration of the traditional power technology and the information, and the...
详细信息
ISBN:
(纸本)9783030152352;9783030152345
With the arrival of the era of the big data, the power energy conservation has attracted much attention. The smart grid technology is a deep integration of the traditional power technology and the information, and the control and automation technology. By collecting a large amount of the data in the power generation, transmission, distribution, the power consumption and dispatching, marketing and other links, we can conduct the in-depth analysis and mining of the big data information to guide the decision-making and optimization in all links, in order to improve the efficiency of the power enterprises, enhance the stability of the power grid operation, better meet the needs of the power customers, and further ensure the efficiency of the urban power energy conservation.
In this work we analyse MALDI mass spectrometry imaging data for thyroid cancer samples. Such a data, containing information about spatial distribution of proteins/peptides, makes possible to make a virtual analysis h...
详细信息
ISBN:
(纸本)9783030298852;9783030298845
In this work we analyse MALDI mass spectrometry imaging data for thyroid cancer samples. Such a data, containing information about spatial distribution of proteins/peptides, makes possible to make a virtual analysis how a technique of fine needle aspiration (FNA) biopsy, a routine diagnosis procedure for thyroid, influences the outcome i.e. a set of discriminative features between cancerous and normal tissue. We hypothesised that an impure dataset (consisting of normal cell contaminated cancer samples) would be beneficial in the terms of stable feature selection. We compared several methods of predictor selection on different datasets to perform an in-depth feature ranking stability analysis for thyroid cancer mass spectrometry data. Furthermore we examined the impact of sample contamination level on the selection.
This article presents the mechanisms for processing fuzzy expert estimates in network models for project management. The distribution of the probability function of the execution time is proposed. This function allows...
详细信息
ISBN:
(纸本)9783030264741
This article presents the mechanisms for processing fuzzy expert estimates in network models for project management. The distribution of the probability function of the execution time is proposed. This function allows us to build a beta-distribution of a random variable over the entire domain of its definition for a combination of approximate points and interval expert estimates. This article describes also the approximation of linguistic estimates by using fuzzy triangular and trapezoidal numbers. It is based on the construction of the membership function of a fuzzy triangular number, accounting for its scale. The proposed approach makes it possible to obtain more accurate prediction estimates for making informed decisions during informational uncertainty.
We propose a one-dimensional blood flow model taking into account muscle pump, external contraction and autoregulation. This model is used to study two effects: blood flow during running and the impact of enhanced ext...
详细信息
ISBN:
(纸本)9783030350482;9783030350475
We propose a one-dimensional blood flow model taking into account muscle pump, external contraction and autoregulation. This model is used to study two effects: blood flow during running and the impact of enhanced external counterpulsation on the coronary blood flow on the basis of patient-specific data. On the basis of mathematical modelling we observe optimal stride frequency, which maximizes venous return.
The problem of adaptive estimation for measurement noise covariance matrix in Kalman filter is analytically solved based on accurate observations obtained irregularly. The results of numerical modeling are provided. T...
详细信息
ISBN:
(纸本)9783030500979
The problem of adaptive estimation for measurement noise covariance matrix in Kalman filter is analytically solved based on accurate observations obtained irregularly. The results of numerical modeling are provided. These results illustrate the key advantages of state vector stochastic estimation algorithm based on proposed approach in comparison to conventional one.
暂无评论