Trustworthy-Based Authentication Model with Intrusion Detection for IoT-Enabled Networks with Deep Learning Algorithm

M.; Jayanthi; Suganthi; M.  Jamuna; S.

doi:https://doi.org/10.54216/JCIM.140214

Fusion: Practice and Applications | 2024

A New Method for Intelligent Multimedia Compression Based on Discrete Hartley Matrix

Multimedia data (video, audio, images) require storage space and transmission bandwidth when sent through social media networking. Despite rapid advances in the capabilities of digital communication systems, the high data size and data transfer bandwidth continue to exceed the capabilities of available technology, especially among social media users. The recent growth of multimedia-based web applications such as WhatsApp, Telegram, and Messenger has created a need for more efficient ways to compress media data. This is because the transmission speed of networks for multimedia data is relatively slow. In addition, there is a specific size for sending files via email or social networks, because much high-definition multimedia information can reach the Giga Byte size. Moreover, most smart cameras have high imaging resolution, which increases the bit rate of multimedia files of video, audio, and image.  Therefore, the goal of data compression is to represent media (video, audio, images, etc.) as accurately as possible with the minimum number of bits (bit rate). Traditional data compression methods are complex for users. They require a high processing power for media data. This shows that most of the existing algorithms have loss in data during the process of compressing and decompressing data, with a high bitrate for media data (video, audio, and image). Therefore, this work describes a new method for media compression systems by discrete Hartley matrix (128) to get a high speed and low bit rate for compressing multimedia data. Finally, the results show that the proposed algorithm has a high-performance speed with a low bit rate for compression data, without losing any part of data (video, sound, and image). Furthermore, the majority of users of social media are satisfied with the data compression interactive system, with high performance and effectiveness in compressing multimedia data. This, in turn, will make it easier for users to easily send their files of video, audio, and images via social media networks.

groups

Noor Mezher Sahab mail -

Qusay Abboodi Ali mail

link https://doi.org/10.54216/FPA.160207

Volume & Issue

Vol. Volume 16 / Iss. Issue 2

Details open_in_new

International Journal of Neutrosophic Science | 2025

Neutrosophic Sets in Big Data Analytics: A Novel Approach for Feature Selection and Classification

Big Data Analytics are said to help in transforming huge amounts of raw data towards valuable information that can be used, but there are formidable challenges in feature selection and classification due to the complexity and high dimensionality of the data. Traditional methods are usually too weak to handle the built-in uncertainty, imprecision, and inconsistency within big data and they often fail to perform well. This paper aims to induce the new methodology on these problems using the sets of neutrosophic in dealing with more flexible and nuanced data analysis. The key contributions to the current approach proposed are threefold. First, generalization of the classical set through extension of the notions of truth, indeterminacy, and falsity by allowing representations of uncertainty in data. The second combines a powerful process for selecting features based upon neutrosophic set theory that is optimal by genetic algorithms and advances a step further by applying these features in training and validating the classification models across a set of different domains. Therefore, the major aim from this study is to increase accuracy and reliability in feature selection and classification in big data analytics. This methodology has been implemented and tested over datasets of the following types: healthcare, finance, social media, and more. Results have proved great improvement against conventional performance metrics, for example, the classification accuracy with an SVM classifier over the Cleveland Heart Disease dataset increases from 83.5% to 87.2%, and of a Random Forest classifier over a financial dataset from 76.4% to 81.9%. For instance, the accuracy of social media sentiment analysis changed to 82.7% from 78.3%. All these findings establish that the neutrosophic set-based method holds good advantages in addressing the limitations of classical alternatives. The proposed approach of neutrosophism, through an explicit model, enhances performances in classifications and, at the same time, augments overall robustness and reliability in big data analytic. The importance of this study lies in establishing the groundwork for further research and practical applications, thus indicating possible further development in this field.

groups

Azmi Shawkat Abdulbaqi mail -

Ahmed Dheyaa Radhi mail -

Lateef Abd Zaid Qudr mail -

Harshavardhan Reddy Penubadi mail -

Ravi Sekhar mail -

Pritesh Shah mail -

Mrinal Bachute mail -

Jamal Fadhil Tawfeq mail -

Hassan muwafaq Gheni mail

link https://doi.org/10.54216/IJNS.250138

Volume & Issue

Vol. Volume 25 / Iss. Issue 1

Details open_in_new

International Journal of Neutrosophic Science | 2024

Efforts of Neutrosophic Logic in Medical Image Processing and Analysis

Medical image processing is indispensable for correct diagnosis and planning of treatment. However, it is susceptible to many errors due to noise, artifacts, and the variability innate in anatomical structures themselves. Traditional image analysis methods hence suffer from these complexities in the images themselves and lead to probable inaccuracies in image analysis. This paper probes into the role of neutrosophic logic in the domain of medical image processing to seek better handling of these problems. The main objectives of the work were to optimize the noise reduction, image segmentation, feature extraction, and classification using the special capabilities of neutrosophic logic directed toward handling uncertainty and indeterminacy. Contributions The contributions of this study are multifaceted: it contributes by introducing detailed support for applying neutrosophic logic in a number of medical image processing tasks and integrates neutrosophic logic with prior techniques and evaluates their performance with traditional methods. The experimental results in the study are complete and demonstrate significant improvements in key metrics. For example, applying neutrosophic logic in noise reduction increased the peak signal-to-noise ratio of MRI images from 25 dB to 35 dB. In some segmentation tasks, the Dice coefficient for liver CT scans increased from 0.85 to 0.92. It increases the accuracy of feature extraction in breast cancer detection from 88% to 95%, while integrating neutrosophic logic with convolutional neural networks improves the accuracy in retinal image classification from 92% to 97%. All these results underline the strong role that neutrosophic logic can play in enhancing accuracy, robustness, and reliability in the processing of medical images. The result of the study concludes that neutrosophic logic not only improves the current limitations but also holds great promise for handling uncertainty in many medical fields, opening a promising way for future advancements in the field of medical imaging and health applications.

groups

Azmi Shawkat Abdulbaqi mail -

Bourair Al-Attar mail -

Lateef Abd Zaid Qudr mail -

Harshavardhan Reddy Penubadi mail -

Ravi Sekhar mail -

Pritesh Shah mail -

Sushma Parihar mail -

Sushmitha Kallam mail -

Jamal Fadhil Tawfeq mail -

Hassan muwafaq Gheni mail

link https://doi.org/10.54216/IJNS.240428

Volume & Issue

Vol. Volume 24 / Iss. Issue 4

Details open_in_new

International Journal of Neutrosophic Science | 2024

Some results on approximation in neutrosophic normed space

Neutrosophic normed linear spaces are the main significant notion in the study of classical functional analysis under a neutrosophic environment to handle indeterminate and inconsistent information. Where the neutrosophic norm function assigns to each vector in the linear space a neutrosophic number, which is a number with a truth, indeterminacy, and falsity component. The main aim of this work is to study and discuss the important properties of proximinality of specific sets and new results for a large class in neutrosophic normed space. Moreover, we show some results closely related proximainality of classes to the normed construction in the space. Also, we prove achieved for generalized sets in neutrosophic normed space, most marks on convexity and Cheby-shevity classes are considered.

groups

Alaa Adnan Auad mail -

Mohammed A. Hilal mail

link https://doi.org/10.54216/IJNS.240429

Volume & Issue

Vol. Volume 24 / Iss. Issue 4

Details open_in_new

International Journal of Neutrosophic Science | 2024

IDLTM-DMT: Intelligent Deep Learning based Trust Management with Decision Making Tool for Healthcare Internet of Things and Big Data Environment with Neutrosophic Set Analysis

Over the last few years development of Internet of Things (IoT) devices and communication technologies have resulted in the massive generation of health-related data. In the context of healthcare, IoT offers several advantages, including being able to observe patients very closely and using data for analytics. A major challenging issue that exists in the usage of IoT and big data in the medical field is security. As healthcare data is highly vulnerable and becomes a target for attacks, there are significant privacy issues related to the usage of big data analytics. Besides, implementing new data analysis tools and strategies for handling big data decision-making is a major issue. The capability to examine this amount of data is a significant aspect of big data in health care.  For resolving these issues, this paper presents a new intelligent deep learning-based trust management with decision making tool (IDLTM-DMT) for IoT healthcare big data environments, incorporating Neutrosophic Set Analysis (NSA). The proposed IDLTM-DMT model enables IoT devices to gather healthcare data. The IDLTM-DMT model involves a DL based bidirectional long short-term memory (BiLSTM) model for vulnerability detection and thereby identifies the malicious traffic in the Network. Hadoop MapReduce is used for handling big data and a decision-making tool using Deep Stacked Auto Encoder (DSAE) is used for the classification of diseases that exist in big data. To optimize the DSAE model's hyperparameters and improve classification performance, the Sandpiper Optimization (SPO) Algorithm is employed. Neutrosophic Set Analysis is integrated to manage the indeterminacy and inconsistency of the data, enhancing the decision-making process. Extensive experimental analysis is conducted on the EEG Eye State Dataset, with results analyzed using various performance measures. The findings indicate that the proposed method achieves improved accuracy compared to existing methods, demonstrating the effectiveness of incorporating Neutrosophic Set Analysis in IoT healthcare big data environments.

groups

C K Marigowda mail -

Thriveni J mail -

Gowrishankar S mail

link https://doi.org/10.54216/IJNS.240430

Volume & Issue

Vol. Volume 24 / Iss. Issue 4

Details open_in_new

International Journal of Advances in Applied Computational Intelligence | 2025

An Effective Workload Prediction with Rnn-Lstm For Efficient Resource Autoscaling In Private Cloud Environments

The research focuses on an accurate workload prediction approach for auto-scaling resources in the Private Cloud using improved Time-Series models. Although many factors still result in dynamic workloads of cloud systems, an accurate forecast becomes vital for service quality and cost. The chapter discusses a Proactive Prediction Engine (PPE) framework using Auto Regressive Integrated Moving Average (ARIMA) and Recurrent Neural Network Long Short-Term, to forecast CPU utilization. Real-time datasets of OpenStack private cloud and Amazon AWS were used for experimental evaluation. The analyses show that the RNN_LSTM model performs far better than ARIMA by reducing the MAE and RMSE values by roughly 40 percent in each set. This has further reinforced that RNN_LSTM can model non-linearity and handle correlation issues in the workload data. Automated scaling of the instances with the Open Stack based on the predicted CPU load is made possible by the integration of RNN_LSTM prediction with OpenStack, supported by Terraform. This strategy reduces times of service outages and enables the efficient use of resources in the network. Regarding accuracy and automation, the proposed method can be a relevant solution for workload management for private cloud infrastructure. In this respect, the results support the implementation of deep learning-based predictive models to optimize the performance of autoscaling.

groups

Narek Badjajian mail -

Sandy Montajab Hazzouri mail

link https://doi.org/10.54216/IJAACI.070105

Volume & Issue

Vol. Volume 7 / Iss. Issue 1

Details open_in_new

Journal of Cybersecurity and Information Management | 2024

Advanced Cyber Attack Detection Using Generative Adversarial Networks and NLP

A key difficulty in the ever-changing cybersecurity scene is the detection of sophisticated cyber-attacks. Because new threats are so much more sophisticated and difficult to detect, traditional tactics typically fail. A new technique to improving cyber-attack detection skills is explored in this study. It uses Generative Adversarial Networks (GANs) and Natural Language Processing (NLP). Using GANs' realistic data generation capabilities, possible attack paths are simulated, creating a strong dataset for training detection systems. At the same time, natural language processing (NLP) methods are used to decipher the mountain of textual information produced by cyberspace, including incident reports, communication patterns, and logs.  Our approach is based on building a fake dataset using GANs that mimics the features of advanced cyberattacks. A detection model is then trained using this dataset. Simultaneously, we improve the detection model's capacity to spot intricate and nuanced assault patterns by processing and analysing text-based data using natural language processing approaches. We use a benchmark cybersecurity dataset to test the integrated method. The experimental findings show that our GAN-NLP based detection system outperforms existing systems, which have an average accuracy of 85.3%, by a wide margin. It achieves a recall of 93.2%, precision of 92.5%, and accuracy of 94.7%. These findings prove that GANs and NLP work well together to identify complex cyberattacks. Finally, GANs and NLP together provide a potent instrument for better cyber-attack detection. A scalable solution that can adapt to the ever-changing nature of cyber threats is offered by this integrated approach, which also increases detection accuracy and efficiency. Improving the models and investigating their use in a real-world cybersecurity setting will be the primary goals of future research.

groups

P. Ramya mail -

Himagiri Chandra Guntupalli mail

link https://doi.org/10.54216/JCIM.140211

Volume & Issue

Vol. Volume 14 / Iss. Issue 2

Details open_in_new

Journal of Cybersecurity and Information Management | 2024

Optimized Group-Centric Data Routing in Heterogeneous Wireless Sensor Networks for Enhanced Energy Efficiency

Wireless Sensor Networks (WSNs) are increasingly being utilized in environments where human presence is limited or dangerous. The main goal is to enhance the data processing capabilities of these components to extend the overall lifespan of the design. Researchers have explored conventional energy-saving methods to address the energy constraints of sensor nodes. However, it became clear that traditional routing methods, specifically those based on packet grouping, were inadequate. The proposed system, known as Optimized Group-Centric Data Routing (OGC-DR), introduces an efficient method of data routing by utilizing the concept of grouping nodal points. This approach enhances data routing management by differentiating between routing within a nodal group and routing between adjacent nodal groups. Group Heading Nodes (GHN) are assigned to each group of sensory nodes according to fitness criteria. The implementation of a tree-based routing structure improves data routing by creating a "meeting-zone" and strategically selecting intermediary nodes between the source and destination node. To improve data privacy, a sender and receiver engage in an asymmetric secret-key exchange at nodal points. Data is then directed to its ultimate destination via predetermined intermediary nodes and Group Heading Nodes. Simulations of the proposed method indicate several advantages, such as lower end-to-end delays, reduced energy consumption, higher active node count, and enhanced packet delivery rates. Furthermore, it improves data privacy for all communication within the sensory architecture.

groups

P. Muthusamy mail -

A. Rajan mail -

R. Praveena mail -

Sundara Rajulu Navaneethakrishnan mail -

T. R. Ganesh Babu mail -

K. Sakthi Murugan mail

link https://doi.org/10.54216/JCIM.140212

Volume & Issue

Vol. Volume 14 / Iss. Issue 2

Details open_in_new

Journal of Cybersecurity and Information Management | 2024

Integrating Quantum Computing and NLP for Advanced Cyber Threat Detection

The exponential growth of digital data and the increasing sophistication of cyber threats demand more advanced methods for threat analysis. This paper explores the integration of quantum computing and natural language processing (NLP) to enhance cyber threat analysis. Traditional computing methods struggle to keep up with the scale and complexity of modern cyber threats, but quantum computing offers a promising avenue for accelerated data processing, while NLP provides sophisticated tools for interpreting and understanding human language, crucial for analysing threat intelligence. Our proposed framework leverages quantum algorithms for rapid anomaly detection and advanced NLP techniques for precise threat identification and analysis. The methodology includes data collection from diverse sources, pre-processing for normalization, quantum-assisted data processing using Grover's search and Quantum Approximate Optimization Algorithm (QAOA), NLP analysis with transformers and BERT-based models, and integration of findings to build comprehensive threat profiles. Experimental results demonstrate significant improvements: quantum algorithms reduced data processing time by up to 50%, NLP models achieved 92% accuracy in threat identification, and the false positive rate was reduced by 30%. These findings indicate a promising direction for next-generation cybersecurity solutions, enabling more proactive and efficient threat mitigation. Future work will focus on refining quantum algorithms, enhancing NLP models, and expanding the framework for real-time threat detection capabilities.

groups

P. Ramya mail -

R. Anitha mail -

J. Rajalakshmi mail -

R. Dineshkumar mail

link https://doi.org/10.54216/JCIM.140213

Volume & Issue

Vol. Volume 14 / Iss. Issue 2

Details open_in_new

Journal of Cybersecurity and Information Management | 2024

Trustworthy-Based Authentication Model with Intrusion Detection for IoT-Enabled Networks with Deep Learning Algorithm

In the burgeoning field of the Internet of Things (IoT), ensuring secure and trustworthy communication between devices is paramount. This paper proposes a novel Trustworthy-Based Authentication Model (TBAM) integrated with Intrusion Detection Systems (IDS) leveraging deep learning algorithms to secure IoT-enabled networks. The proposed model addresses the dual challenges of authenticating legitimate devices and detecting malicious intrusions. Specifically, we employ a Convolutional Neural Network (CNN) to analyse network traffic patterns for intrusion detection, leveraging its prowess in feature extraction and classification. Additionally, a Long Short-Term Memory (LSTM) network is utilized for continuous monitoring and anomaly detection, capturing temporal dependencies in data flows that are indicative of potential security threats. The authentication mechanism integrates a trust evaluation system that assigns trust scores to devices based on their behaviour, enhancing the model's capability to distinguish between trusted and malicious entities. Our extensive experiments on real-world IoT datasets demonstrate that the TBAM significantly outperforms traditional security models in terms of detection accuracy, false-positive rate, and computational efficiency. Specifically, our model achieves a detection accuracy of 98.7%, a false-positive rate of 1.2%, and a processing time reduction of 30% compared to baseline models. This work contributes a robust, scalable, and efficient solution to the pressing security concerns in IoT networks, paving the way for more secure and reliable IoT applications.

groups

M. Rajendiran mail -

Jayanthi .E mail -

Suganthi .R mail -

M. Jamuna Rani mail -

S. Vimalnath mail

link https://doi.org/10.54216/JCIM.140214

Volume & Issue

Vol. Volume 14 / Iss. Issue 2

Details open_in_new