Evaluating the performance of machine learning algorithms for network intrusion detection systems in the internet of things infrastructure

As numerous Internet-of-Things (IoT) devices are deploying on a daily basis, network intrusion detection systems (NIDS) are among the most critical tools to ensure the protection and security of networks against malicious cyberattacks. This paper employs four machine learning algorithms: XGBoost, random forest, decision tree, and gradient boosting, and evaluates their performance in NIDS, considering the accuracy, precision, recall, and F-score. The comparative analysis conducted using the CICIDS2017 dataset reveals that the XGBoost performs better than the other algorithms reaching the predicted accuracy of 99.6% in detecting cyberattacks. XGBoost-based attack detectors also have the largest weighted metrics of F1-score, precision, and recall. The paper also studies the effect of class imbalance and the size of the normal and attack classes. The small numbers of some attacks in training datasets mislead the classifier to bias towards the majority classes resulting in a bottleneck to improving macro recall and macro F1 score. The results assist the network engineers in choosing the most effective machine learning-based NIDS to ensure network security for today’s growing IoT network traffic.

Geometric Approach to Optimal Path Problem with Uncertain Arc Lengths

In this paper, the problem of finding the shortest paths, one of the most important problems in science and technology has been geometrically studied. Shortest path algorithm has been generalized to the shortest cycles in each homotopy class on a surface with arbitrary topology, using the universal covering space notion in the algebraic topology. Then, a general algorithm has been presented to compute the shortest cycles (geometrically rather than combinatorial) in each homotopy class. The algorithm can handle surface meshes with the desired topology, with or without boundary. It also provides a fundamental framework for other algorithms based on universal coverage space due to the capacity and flexibility of the framework.

Statistical adjustment of the parameters of multi-objective optimization problems with design expert method

Optimization methods in which one single criterion is considered cannot provide a comprehensive solution to various decision- making algorithms because they cannot consider the interchange of conflicting goals that sometimes conflict with one another. Multi-objective opti-mization is a suitable solution to this obstacle. Given the importance of multi-objective optimization problems in engineering and technology, adjusting the parameters of these types of problems will, in addition to the decision-making accuracy, facilitate the analysis of the results and makes it more applicable. For this purpose, multi-objective optimization using experimental design methods has been developed which can solve these problems by considering different objectives simultaneously. Mathematical modelling for the setting of the parameters of the considered problem with all the statistical details related to their prediction and optimization have been studied.

Circular Gabor wavelet algorithm for fingerprint liveness detection

Biometrics usage is growing daily and fingerprint-based recognition system is among the most effective and popular methods of personality identification. The conventional fingerprint sensor functions on total internal reflectance (TIR), which is a method that captures the external features of the finger that is presented to it. Hence, this opens it up to spoof attacks. Liveness detection is an anti-spoofing approach that has the potentials to identify physiological features in fingerprints. It has been demonstrated that spoof fingerprint made of gelatin, gummy and play-doh can easily deceive sensor. Therefore, the security of such sensor is not guaranteed. Here, we established a secure and robust fake-spoof fingerprint identification algorithm using Circular Gabor Wavelet for texture segmentation of the captured images. The samples were exposed to feature extraction processing using circular Gabor wavelet algorithm developed for texture segmentations. The result was evaluated using FAR which measures if a user presented is accepted under a false claimed identity. The FAR result was 0.03125 with an accuracy of 99.968% which showed distinct difference between live and spoof fingerprint.

A Survey about various Generations of Lexical Analyzer

Lexical analysis helps the interactivity and visualization for active learning that can improve difficult concepts in automata. This study gives a view on different lexical analyzer generators that has been implemented for different purposes in finite automata. It also intends to give a general idea on the lexical analyzer process, which will cover the automata model that is used in the various reviews. Some concepts that will be described are finite automata model, regular expression and other related components. Also, the advantages and disadvantages of lexical analyzer will be discussed.

An augmented reality system to enhance facial expressions recognision in autistic children

In the past decade, Augmented Reality (AR) has been applied in several professional practice areas, including but not limited to autism therapy. AR supplies virtual information to the visual perceptions of users, giving the user new tools to ensure that knowledge for many processes and in many environments are comprehended efficiently. Usually, AR applications depend on virtual reality headset (VR-box) to overlay virtual objects and text on the surrounding environment of the user.People with autism spectrum condition (ASC) especially children are often found lacking in social interaction, including facial expres-sion and understanding of other minds which make social communication more difficult for them. This paper aims to use AR system to assist children with (ASC) in better understanding facial expressions by overlaying suggested 3d objects over the physical environment. Results of AR treatment found higher engagement and more effective compare to a non-AR system.This paper utilizes Vuforia to create an AR environment for the treatment of children with ASC. Vuforia is a software development kit that provides AR capabilities to smartphone devices.

A comparative study of particle swarm optimization and genetic algorithm

This paper provides an introduction and a comparison of two widely used evolutionary computation algorithms: Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) based on the previous studies and researches. It describes Genetic Algorithm basic functionalities including various steps such as selection, crossover, and mutation.

Geometric Modelling of the Thinning by Cell Complexes

Motivation: Thinning is an extremely active area of research because of its primary role in reducing the amount of information that must be processed by algorithms for pattern recognition. Most thinning algorithms are supposed to be topology-preserving, although an accurate statement of what this means is usually left unanswered.Results: The objective of this article is the presentation of a general topology via the concepts of homotopy theory to preserve the thinning. The proposed method can be applied to any decomposition of non-structural cells of the object, given that the cells have a fixed structure.

Breaking through unravel problems in ERP implementation using agile

Demand for the industry to enhance competitive advantage. For that, the industry is required to make a breaking through in order to enhance the organizational performance. This is a reason for addressing the inefficiencies in managing people, processes, organizations, and technology. One of the efforts in improving organization performance is the development in the field of Information Systems as an effort to improve the agility of the organization. ERP system is one solution that can be employed in order to improve organization performance. However, in reality, industrial companies face problems in ERP implementation. This is a challenge to solve the problems of implementing an ERP system for industry. In this opportunity, researchers intend to conduct a re-search to identify the problems of factors in the ERP implementation, namely by proposing agile methods as one of the new methodologies in the effort to solve the problems in the ERP implementation for an industry. The results of this study will result in an agile model of implementing ERP for improving the capacity of ERP systems. This study idea is to analyze the agile method as a solution alternative to make changes for the ERP implementation success. This study is using Structural Equation Modeling as a quantitative data analysis approach of an industry as a case study.

Taxonomy of bio-inspired optimization algorithms

Bio-Inspired optimization algorithms are inspired from principles of natural biological evolution and distributed collective of a living organism such as (insects, animal, …. etc.) for obtaining the optimal possible solutions for hard and complex optimization problems. In computer science Bio-Inspired optimization algorithms have been broadly used because of their exhibits extremely diverse, robust, dynamic, complex and fascinating phenomenon as compared to other existing classical techniques.This paper presents an overview study on the taxonomy of bio-inspired optimization algorithms according to the biological field that are inspired from and the areas where these algorithms have been successfully applied