Investigating the Efficacy of Deep Reinforcement Learning Models in Detecting and Mitigating Cyber-attacks: a Novel Approach

S. Phani Praveen; Anuradha Chokka; Pappula Sarala; Rajeswari Nakka; Suresh Babu Chandolu; V. Esther Jyothi

doi:https://doi.org/10.54216/JCIM.140107

International Journal of Neutrosophic Science | 2024

Convergence of Filters on Bornological Vector Spaces and Neutrosophic Filters

In this research, we construct new type of convergence of bornological vector spaces called convergence of filters through using conception bounded sets. As well, we have considered several characteristics of these concepts like Fréchet filter associated with sequence, filter that has a unique limit and ultra-filter which is very useful in the study of neutrosophic topological spaces and neutrosophic filters.

groups

Fatma Al-Basri mail -

Asawer Khdeidan mail

link https://doi.org/10.54216/IJNS.240409

Volume & Issue

Vol. Volume 24 / Iss. Issue 4

Details open_in_new

International Journal of Neutrosophic Science | 2024

A Study on First and Second Order Bipolar Fuzzy Topological Spaces and Crisp Topological Spaces and Analyzing the Connections Between Them

In our previous paper we discussed about the concept of SOBPFS, SOBPFT and its mathematical modelling in medical diagnosis. In this paper, the detailed study about SOBPFT accordance with FOBPFT and crisp topological spaces are analysed and also some natural examples of SOBPFT are provided. In third section, the connections between FOBPFT and SOBPFT under five different cases are discussed. And last section tells that, from a crisp topology τ on X there exists three different SOBPFT denoted by (ω(τ)) ̂, (ω_* (τ)) ̂ and (ω_ε (τ)) ̂ and from a SOBPFT on X there exists three crisp topologies denoted by i(τ ̂_B ), i^* (τ ̂_B ) and i_ε (τ ̂_B ).  

groups

Muthamizhselvi S. mail -

V. M. Vijayalakshmi mail

link https://doi.org/10.54216/IJNS.240410

Volume & Issue

Vol. Volume 24 / Iss. Issue 4

Details open_in_new

International Journal of Neutrosophic Science | 2024

Type-I extension Diophantine neutrosophic interval valued soft set in real life applications for a decision making

We describe certain operations and present the theory of the Type-I extension Diophantine neutrosophic interval valued soft set. Additionally, we go over an algorithm that uses the Type-I soft set model to address the decision-making problem. We present a similarity measure between two Type-I extension Diophantine neutrosophic interval valued soft sets and talk about how it might be used in practical applications. A few exemplary cases are provided to demonstrate their practical application in solving uncertain problems.

groups

Lejo J. Manavalan mail -

Sadeq Damrah mail -

Mutaz M. Abbas Ali mail -

Abdallah Al-Husban mail -

M. Palanikumar mail

link https://doi.org/10.54216/IJNS.240411

Volume & Issue

Vol. Volume 24 / Iss. Issue 4

Details open_in_new

International Journal of Neutrosophic Science | 2024

Enhancing Predictive Accuracy of Insurance Stock Market in Jordan using Hyprid GFS.Thrift Model: A Genetic Fuzzy System-based Fintech Approach

This study focuses on improving the predicting accuracy of the daily ASE's weighted price index of the insurance sector (ICI) using a nonlinear spectral model called maximum overlapping discrete wavelet transform (MODWT) with five mathematical functions, namely, Haar, Daubechies (d4), least square (la8), best localization (bl14), and Coiflet (c6). Using a nonlinear spectral model called maximum overlapping discrete wavelet transform (MODWT) with five mathematical functions—Haar, Daubechies (d4), least square (la8), best localization (bl14), and Coiflet (c6)—this study aims to increase the daily ASE's weighted price index of the insurance sector's (ICI) prediction accuracy. The model utilizes a genetic fuzzy system based on Thrift's methodology (GFS.Thrift). The Amman Stock Exchange (ASE) supplied a dataset with 4,478 observations for the purpose of the study. The dataset represented daily data from January 2, 2006, to March 24, 2024.  The adaptive GFS.THRIFT model was trained with 90% of the dataset, while the remaining 10% was used to test its prediction performance. Multiple egressions and multicollinearity tests were used to select input variables such as standardized foreign direct investment (FDI), standardized value traded (VT) and consumer price index (CPI). Insights from this study indicate that all input variables are positively related to the output variable. Secondly, the proposed model (MODWT-Haar-GFS. Thrift) significantly outperforms other existing models including the GFS. Thrift model.

groups

Jamil J. Jaber mail -

Anwar Al-Gasaymeh mail -

Maha Shehadeh mail -

Asma S. Alzwi mail

link https://doi.org/10.54216/IJNS.240412

Volume & Issue

Vol. Volume 24 / Iss. Issue 4

Details open_in_new

Journal of Intelligent Systems and Internet of Things | 2024

Fractal Dimension on CBCT Images and Modular Neural Networks to Identify Reduced Bone Mineral Density in Women

This paper provides two different methods to diagnose osteoporosis in women; the first method is the fractal analysis evaluated by CBCT at two bone locations (the mandible and the second cervical vertebrae) to see if there is any correlation between the two. At the same time, the second method is deep convolutional neural networks (DCNNs). One hundred eighty-eight patients' mandibular CBCT images were used, and DCNN models based on the ResNet-101 framework were employed. Dual X-ray absorptiometry of the hip and lumbar spine revealed that 139 of the 188 postmenopausal women tested had osteoporosis, whereas 49 had average bone mineral density. The second cervical vertebra and the mandible were selected as locations of interest for FD analysis on the CBCT images. Measurement accuracy, both within and between observers' agreements, and correlations between two data sets were all calculated. To evaluate osteoporosis, we used a segmented, three-phase approach. Stage 1 was devoted to the identification of mandibular bone slices. In Stage 2, the coordinates for the mandible's cross-sectional views were established, and Stage 3 calculated the thickness of the mandible bone, emphasizing osteoporotic variations.  The average FD values within the interest area of the mandible were significantly lower in people with osteoporosis than in those with average bone mineral density. At the same time, the two groups had no significant difference in FD values at the second cervical vertebra. For the mandibular site, areas beneath the curve were 0.644 (P = 0.008), while the area under the curve for the vertebral site was 0.531 (P = 0.720). DCNN training in the first stage yielded an astounding 98.85% training accuracy, the second stage decreased L1 loss to a meager 1.02 pixels, and the bone thickness computation method used in the last stage had a mean squared error of 0. 8377. We concluded that FD was underutilized even though it distinguished between women with normal BMD and those with osteoporosis in the mandibular area. Additionally, even with small mandibular CBCT datasets, the results show the value of a modular transfer learning approach for osteoporosis detection.

groups

Eman Shawky Mira mail -

Ahmed Mohamed Saaduddin Sapri mail -

Taseer Bashir mail -

Khalid Hassan mail -

Abdulhameed Saeed Alghamdi mail -

Yousef Almasaabi mail -

Nagham Talal Maddah mail -

Hind F. Kayal mail -

El-Sayed M. El-Kenawy mail -

Mohamed Saber mail

link https://doi.org/10.54216/JISIoT.130111

Volume & Issue

Vol. Volume 13 / Iss. Issue 1

Details open_in_new

International Journal of Neutrosophic Science | 2024

A Study on Decision Making and Teaching Competency: Processing Self Perception and Cognitive Schema through Neutrosophic Science

The objective of this research is to examine the decision-making processes of teachers and explore their self-assessments of teaching competency levels based on the competency indicators proposed by the Ministry of National Education (MoNE) in Turkey. The study adopts a constructivist perspective, offering a fresh look at the cognitive levels of teachers and their decision-making mechanisms. Additionally, it integrates neutrosophic science principles to address the uncertainties and indeterminacies present in teachers' self-evaluation and decision-making processes. Data were gathered using the "General Competencies for Teaching Profession (GCTP)" scale, which was developed according to the competencies defined by the MoNE. This new scale, featuring 15 Likert-type items, was validated and tested for reliability before being administered to a sample of 320 volunteering teachers from various disciplines in Turkey. The scale measures data within the "Professional skills" domain and captures teachers' self-perceived competency beliefs related to their professional skills, considering factors such as years of teaching experience, gender, subjects taught, and the type of school (primary or secondary) where they are employed. SPSS 16.0 was used for data analysis and to obtain descriptive statistics for the item results. The analysis revealed that primary school teachers scored higher on the GCTP scale compared to high school teachers. By incorporating neutrosophic science, the study effectively navigates the uncertainties in assessing teaching competencies, offering a more nuanced understanding of the factors that influence teachers' decision-making processes.

groups

Saziye Yaman mail

link https://doi.org/10.54216/IJNS.240413

Volume & Issue

Vol. Volume 24 / Iss. Issue 4

Details open_in_new

International Journal of Wireless and Ad Hoc Communication | 2024

Hybrid Metaheuristics with Deep Learning Assisted Intrusion Detection on Cyber-Physical Smart Grid Environment

Smart grids (SGs) offer can ensure that users with a continuous power supply, decreased line losses, improved renewable output and storing, user participation in current electricity, and demand-side responsiveness. The development of cyberphysical SG (CPSG) systems has transformed the standard power grid by allowing bi-directional energy flow among utilities and users. But, because of increased data change among consumers, it is presented a major problem to the firewall systems for the transmission networks at either cyber or physical planes. Intrusion Detection Systems (IDSs) can role an essential play in maintaining SGs systems against cyber threats by generating a second wall of defense, complementing conventional preventive security procedures (for instance, authorization, encryption, and authentication). Therefore, this article concentrates on the design and development of Hybrid Metaheuristics with Deep Learning Assisted Intrusion Detection in a Cyber-Physical Smart Grid (HMDL-IDCPSG) infrastructure. The major objective of the HMDL-IDCPSG system provides the effectual recognition of the intrusions using feature selection and classification processes in the CPSG infrastructure. In the presented HMDL-IDCPSG method, a binary dragonfly algorithm with the hybrid directed differential operator (BDA‐DDO) algorithm could be implemented for the feature selection (FS) method. Besides, attention-based bi-directional long short-term memory (ABiLSTM) algorithm could be carried out for the recognition and classification of the intrusions. At last, the sparrow search algorithm (SSA) can be exploited for highest chosen the hyperparameter values of the ABiLSTM algorithm which supports in achieving a better solution. For demonstrating the greater outcome of the HMDL-IDCPSG technique, a comprehensive simulation value can be executed. The obtained results reported the supremacy of the HMDL-IDCPSG methodology with other existing approaches

groups

Manal M. Nasir mail -

Salim M. Hebrisha mail

link https://doi.org/10.54216/IJWAC.080206

Volume & Issue

Vol. Volume 8 / Iss. Issue 2

Details open_in_new

International Journal of Wireless and Ad Hoc Communication | 2024

Improving Network Security using Tunicate Swarm Algorithm with Stacked Deep Learning Model on IoT Environment

The Internet of Things (IoT) represents important security vulnerabilities, increasing difficulties in cyberattacks. Attackers employ these vulnerabilities to establish distributed denial-of-service (DDoS) attacks, compromising availability and causing financial losses to digital platforms. Newly, numerous Machine Learning (ML) and Deep Learning (DL) approaches have been presented for the identification of botnet attacks in IoT networks. By analyzing the patterns of communication and behavior of IoT devices, DL algorithms will be differentiated between malicious and normal activity, therefore supporting the earlier detection and avoidance of botnet attacks. This is essential to protect the integrity and security of IoT systems that can be increasingly vulnerable to botnet-driven attacks because of their limited security measures and often large-scale applications. In this aspect, this study designs an innovative tunicate swarm algorithm with stacked deep learning for botnet detection (TSASDL-BD) technique for IoT platforms. The purpose of the TSASDL-BD technique is to recognize the botnets and achieve maximum network security. In the TSASDL-BD technique, the TSA is applied for the effectual feature selection process, which aids in reducing the dimensionality problem. For botnet detection, the TSASDL-BD technique makes use of the stacked long short-term memory gated recurrent unit (SLSTM-GRU) model. Finally, the artificial humming algorithm (AHA) can be used for the optimal selection of the hyperparameter values of the SLSTM+GRU system. The outcome analysis of the TSASDL-BD method on the benchmark database takes place. The extensive outcomes stated that the TSASDL-BD approach gains maximum detection results over other algorithms with respect of different measures

groups

Abedallah Z. Abualkishik mail -

Rasha Almajed mail

link https://doi.org/10.54216/IJWAC.080207

Volume & Issue

Vol. Volume 8 / Iss. Issue 2

Details open_in_new

International Journal of Neutrosophic Science | 2024

On Neutrosophic Truncation

Neutrosophic have found their place in neutrosophic studies due to the prevalence of indeterminacy in the world. We present the novel notion of neutrosophic truncated distribution, which is highly significant in analyzing events that involve the exclusion of certain data from the original dataset, particularly where there is a presence of indeterminacy in data. Unsure or ambiguous information, which is disregarded in classical logic, is incorporated within neutrosophic logic due to its focus on both certain and uncertain data. In this paper, the approach of neutrosophic truncation, and truncated distribution of neutrosophic random variable have been introduced, in addition to deriving some of its properties. And other cases discussed neutrosophic truncation depends on the neutrosophic probability function, a classical probability function, and studies neutrosophic probability and neutrosophic interval together. It studies the neutrosophic left truncated and neutrosophic right truncated. Some illustrative examples and statistical properties such as the cumulative function, the moment generating function, the order statistic, and the rth moment are presented.             

groups

Kawther F. Alhasan mail

link https://doi.org/10.54216/IJNS.240414

Volume & Issue

Vol. Volume 24 / Iss. Issue 4

Details open_in_new

Journal of Cybersecurity and Information Management | 2024

Investigating the Efficacy of Deep Reinforcement Learning Models in Detecting and Mitigating Cyber-attacks: a Novel Approach

Ordinary defence components like rule-based firewalls and mark based detection are not staying aware of the always expanding intricacy and frequency of cyber security dangers. The reason for this work is to explore the way that deep reinforcement learning (DRL), a subfield of artificial intelligence famous for its viability in handling testing decision-production situations, may be utilized to improve cyber security conventions. To mimic and balance threatening cyber-attacks, we present a system that utilizes deep reinforcement learning (DRL). We propose a specialist based model that can learn and adjust ceaselessly in powerful network security situations. In light of the present status of the network and the rewards it gets for its decisions, the specialist concludes what the best game-plans are. Specifically, we utilize the policy gradient (PG)- based double deep Q-network (DDQN) model and trial on three different datasets: NSL-KDD, CIC-IDS, and AWID. Our review demonstrates the way that DRL can really further develop the detection after-effects of cyber-attacks. Utilizing the policy gradient DDQN model on different datasets, we find prominent upgrades in cyber security conventions. Specific boundary modifications upgrade the viability of our philosophy much more, displaying empowering results on different datasets. This exploration features the potential of deep reinforcement learning (DRL) as a successful instrument in the field of cyber security. Our examination progresses detection techniques and gives a versatile arrangement that can be applied to an assortment of cyber security worries by giving areas of strength for a to demonstrating and relieving cyber dangers.

groups

S. Phani Praveen mail -

Anuradha Chokka mail -

Pappula Sarala mail -

Rajeswari Nakka mail -

Suresh Babu Chandolu mail -

V. Esther Jyothi mail

link https://doi.org/10.54216/JCIM.140107

Volume & Issue

Vol. Volume 14 / Iss. Issue 1

Details open_in_new