Multi-Agent Communication System with Chatbots

Memon, Zojan; Jalbani, Akhtar Hussain; Shaikh, Mohsin; Memon, Rafia Naz; Ali, Ahmed S.

doi:10.22581/muet1982.1803.19

Cited by 15 publications

(12 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine learning is recently being explored in research for effective and efficient applications in the field of information security [35,36]. In fact, security is always one of the top concerns in the development of automated communication systems [37]. Intrusion detection is one of the major domains under cyber security, and machine learning is being actively applied and tested in this area to get fruitful results [38].…”

Section: Discussionmentioning

confidence: 99%

Machine Learning Classification of Port Scanning and DDoS Attacks: A Comparative Analysis

Aamir

Rizvi

Hashmani

et al. 2021

Mehran Univ. res. j. eng. technol.

View full text Add to dashboard Cite

Cyber security is one of the major concerns of today’s connected world. For all the platforms of today’s communication technology such as wired, wireless, local and remote access, the hackers are present to corrupt the system functionalities, circumvent the security measures and steal sensitive information. Amongst many techniques of hackers, port scanning and Distributed Denial of Service (DDoS) attacks are very common. In this paper, the benefits of machine learning are taken into consideration for classification of port scanning and DDoS attacks in a mix of normal and attack traffic. Different machine learning algorithms are trained and tested on a recently published benchmark dataset (CICIDS2017) to identify the best performing algorithms on the data which contains more recent vectors of port scanning and DDoS attacks. The classification results show that all the variants of discriminant analysis and Support Vector Machine (SVM) provide good testing accuracy i.e. more than 90%. According to a subjective rating criterion mentioned in this paper, 9 algorithms from a set of machine learning experiments receive the highest rating (good) as they provide more than 85% classification (testing) accuracy out of 22 total algorithms. This comparative analysis is further extended to observe training performance of machine learning models through k-fold cross validation, Area Under Curve (AUC) analysis of the Receiver Operating Characteristic (ROC) curves, and dimensionality reduction using the Principal Component Analysis (PCA). To the best of our knowledge, a comprehensive comparison of various machine learning algorithms on CICIDS2017 dataset is found to be deficient for port scanning and DDoS attacks while considering such recent features of attack.

show abstract

Section: Discussionmentioning

confidence: 99%

Machine Learning Classification of Port Scanning and DDoS Attacks: A Comparative Analysis

Aamir

Rizvi

Hashmani

et al. 2021

Mehran Univ. res. j. eng. technol.

View full text Add to dashboard Cite

show abstract

“…In this case, if the teacher is a single agent, then in the system of communicative-simulation tools can be used at once several technical agents. That said, a current chatbot has the obligatory three-component educational design -database, input processing (natural speech), knowledge reorganization/replication option, and integral unit (Memon et al 2018). The presence of these features allows for multi-agent communication using multiple chatbots and multiple users.…”

Section: Neuro Didactic Potential Of Communicative-simulation Program...mentioning

confidence: 99%

Neuropedagogy of Communication-Imitation Opportunities for the Ukrainian English Teacher

Savchenko,

Prystai,

Hulych

et al. 2023

BRAIN

View full text Add to dashboard Cite

The article tells about the problems of motivation, specificity and effectiveness of using chatbots by Ukrainian humanities students when studying English and, based on the analysis of sociological data, provides new recommendations for the English language teacher. The purpose of the article is to define the problem of using new communicative-simulation opportunities of today's chatbots "from the inside", i.e. from the point of view of personal motivation of the participants of the educational process. This allowed us to understand the more general and invariant neuro-pedagogical mechanisms of the stimulation anthropomorphic environment and tools in English language learning. The authors used sociological, statistical, modeling-predictive pedagogical methods in order to outline the real picture of students' use of chatbots in English studies on the basis of existing neuroscience theories and real student priorities and to provide general methodological recommendations for modeling communicative-simulation technology in linguistic pedagogy. The main result of the article is to objectify the real neuropsychological picture of students' motivation in English-language communication in chatbots, as well as to present five-component gradation of scenarios for chatbots use by students with different levels of academic knowledge, personal pretensions and self-organization abilities. The theoretical conclusions of the article consist in: a) confirmation and further development of already existing provisions on the use of simulation technologies; b) essays on Ukrainian specifics of using chatbots in English language learning in the context of the neuro-pedagogical approach; c) proving the thesis that English-language chatbots are used outside educational plans and are mostly an optional, spontaneous or personal intension tool in learning a foreign language.

show abstract

“…Another field of use for reactive compensators is industry. The industrial business sector adopts passive solutions because they provide control over the power factor [2,3,30,31]. In this field, passive systems often differ essentially in the method of switching chokes and capacitors.…”

Section: Introductionmentioning

confidence: 99%

Compensation of Budeanu’s Reactive and Complemented Reactive Currents in Extended Budeanu Theory in 3-Phase 4-Wire Systems Powered by Symmetrical Nonsinusoidal Voltage Source

Sołjan,

Popławski,

Kurkowski

et al. 2024

Energies

View full text Add to dashboard Cite

The result of continuous efforts in the development of power theory, Budeanu’s power theory was successfully extended. The mathematical description that has been proposed is based on another concept, namely the Currents’ Physical Components (CPC) theory. With CPC theory, it was possible to describe, in the original Budeanu theory, the components of the load current, including the Budeanu distortion current. The Budeanu distortion current can have a maximum of five components associated with different physical phenomena and related to the equivalent parameters of the load. This article discusses passive compensation, which provides compensation for the Budeanu reactive current and the Budeanu complemented reactive current due to the known equivalent load parameters associated with the reactance elements. In addition, the article refers to a very important aspect when determining the parameters of a passive compensator, i.e., choosing parameters in such a way that the compensator simultaneously compensates for the reactive current and the unbalanced current. The article presents five methods relating to the determination of compensator parameters. Two methods are related to the reactive current compensation only for the first harmonic without affecting the unbalanced current. The next three methods relate to the compensation of the Budeanu reactive current and the consideration of the unbalanced current. Calculations and simulations were performed for all five methods, the results of which are presented and analyzed in this publication. The Matlab/Simulink R2023a environment was used as the calculation and simulation software.

show abstract

Multi-Agent Communication System with Chatbots

Cited by 15 publications

References 0 publications

Machine Learning Classification of Port Scanning and DDoS Attacks: A Comparative Analysis

Machine Learning Classification of Port Scanning and DDoS Attacks: A Comparative Analysis

Neuropedagogy of Communication-Imitation Opportunities for the Ukrainian English Teacher

Compensation of Budeanu’s Reactive and Complemented Reactive Currents in Extended Budeanu Theory in 3-Phase 4-Wire Systems Powered by Symmetrical Nonsinusoidal Voltage Source

Contact Info

Product

Resources

About