Search

By the start of 2020, the novel coronavirus (COVID‐19) had been declared a worldwide pandemic, and because of its infectiousness and severity, several strands of research have focused on combatting its ongoing spread. One potential solution to detecting COVID‐19 rapidly and effectively is by analyzing chest X‐ray images using Deep Learning (DL) models. Convolutional Neural Networks (CNNs) have been presented as particularly efficient techniques for early diagnosis, but most still include limitations. In this study, we propose a novel randomly initialized CNN (RND‐CNN) architecture for the recognition of COVID‐19. This network consists of a set of differently‐sized hidden layers all created from scratch. The performance of this RND‐CNN is evaluated using two public datasets: the COVIDx and the enhanced COVID‐19 datasets. Each of these datasets consists of medical images (X‐rays) in one of three different classes: chests with COVID‐19, with pneumonia, or in a normal state. The proposed RND‐CNN model yields encouraging results for its accuracy in detecting COVID‐19 results, achieving 94% accuracy for the COVIDx dataset and 99% accuracy on the enhanced COVID‐19 dataset. [ABSTRACT FROM AUTHOR]

Wireless sensor networks (WSNs) have recently attracted greater attention worldwide due to their practicality in monitoring, communicating, and reporting specific physical phenomena. The data collected by WSNs is often inaccurate as a result of unavoidable environmental factors, which may include noise, signal weakness, or intrusion attacks depending on the specific situation. Sending high‐noise data has negative effects not just on data accuracy and network reliability, but also regarding the decision‐making processes in the base station. Anomaly detection, or outlier detection, is the process of detecting noisy data amidst the contexts thus described. The literature contains relatively few noise detection techniques in the context of WSNs, particularly for outlier‐detection algorithms applying time series analysis, which considers the effective neighbors to ensure a global‐collaborative detection. Hence, the research presented in this article is intended to design and implement a global outlier‐detection approach, which allows us to find and select appropriate neighbors to ensure an adaptive collaborative detection based on time‐series analysis and entropy techniques. The proposed approach applies a random forest algorithm for identifying the best results. To measure the effectiveness and efficiency of the proposed approach, a comprehensive and real scenario provided by the Intel Berkeley Research Laboratory has been simulated. Noisy data have been injected into the collected data randomly. The results obtained from the experiment then conducted experimentation demonstrate that our approach can detect anomalies with up to 99% accuracy. [ABSTRACT FROM AUTHOR]

Frequent pattern mining (FPM) algorithms are often based on graph isomorphism in order to identify common pattern occurrences. Recent research works, however, have focused on cases in which patterns can differ from their occurrences. Such cases have great potential for the analysis of noisy network data. Most existing FPM algorithms consider differences in edges and their labels, but none of them so far has considered the structural differences of vertices and their labels. Discerning how to identify cases that differ from the initial pattern by any number of vertices, edges, or labels has become the main challenge of recent research works. As a solution, we suggest a novel FMP algorithm named mining frequent approximate patterns (MFAPs) with two central new characteristics. First, we begin by using the inexact matching technique, which allows for structural differences in edge, vertices, and labels. Second, we follow the approximate matching with a focus on mining patterns within the directed graph, as opposed to the more commonly explored case of patterns being mined from the undirected graph. Our results illustrate the effectiveness of this new MFAP algorithm in identifying patterns within an optimized time. [ABSTRACT FROM AUTHOR]

With the emergence of fog computing, new paradigms for data processing and management for IoT devices have been established in the quickly changing world of teaching/learning. This study addresses the complex issues brought about by the infiltration of diverse data sources by investigating novel approaches to strengthen data security and enhance access control mechanisms in fog computing environments. The commonly used cryptographic technique known as CP‐ABE is renowned for providing accurate access control. Unfortunately, current multi‐authority CP‐ABE methods have difficulties when implemented on low‐resource IoT devices. These techniques are not appropriate for resource‐constrained IoT devices since the sizes of the secret key and ciphertext grow in proportion to the number of attributes. In this paper, a novel multi‐authority CP‐ABE approach, called MA‐based CP‐ABE, efficiently tackles these issues by optimizing the length of secret keys and ciphertext. Users' secret keys are always the same size, no matter how many attributes they own. Moreover, MA‐based CP‐ABE ensures that the size of the ciphertext scales linearly with the number of authorities rather than characteristics, which makes it a sensible option for devices with restricted resources. A Generative AI approach has also been integrated along with CP‐ABE to make sure that the IoT data is secure and privacy is maintained. As per the security and experimental analysis, the proposed approach is considered secure and suitable for IoT‐based applications. [ABSTRACT FROM AUTHOR]

A Brain–Computer Interface (BCI), integrated with the Internet of Medical Things (IoMT) and based on electroencephalogram (EEG) technology, allows users to control external devices by decoding brainwave patterns. Advanced deep learning-based BCIs, especially those utilizing sensorimotor rhythms (SMRs), have emerged as direct brain–device communication facilitators. SMRs involve users imagining limb motions to induce specific brain activity changes in the motor cortex. Despite progress, some users struggle with BCIs due to weak signals, individual variability, and limited task applicability. This study introduces an unsupervised EEG preprocessing pipeline for SMR-based BCIs. It evaluates an EEG dataset recorded during finger movements, employing two cleaning methods: an investigator-dependent pipeline and our proposed unsupervised method. Two distinct feature datasets are generated: one from cleaned EEG data processed into spectrogram images using supervised preprocessing, and another from data cleaned using our proposed unsupervised pipeline. The study extensively assesses five transfer learning convolutional neural network (TL-CNN) models for distinguishing Motor Imagery (MI) from finger movements (Mex) using the generated datasets. A novel probability fusion technique is developed to enhance TL-CNN classification in Mex versus MI finger-pinching actions. Comparative results show that the fusion-based method outperforms other state-of-the-art methods when applied to unsupervised EEG data. Specifically, our proposed approach achieves 97.9% accuracy, 93.4% precision, 95% recall, and an F1-score of 93.2%, demonstrating significant progress in distinguishing MI and Mex activities through the use of our unsupervised pre-processing pipeline and fusion-based CNN method. Our findings demonstrate the potential of our approach to serve as a benchmark for the global interdisciplinary research community and enable the development of future more effective and user-friendly real-time BCI systems. • Near real-time EEG preprocessing and probability-based fusion are proposed. • A novel approach to disentangle MI (mental motor acts) from Mex (motor execution). • Hand Movement Classification using a Fusion of CNN architectures in the IoMT. • 64 EEG channels have been used to perform ERS and ERD analyses. • Experiments show good performances on EEG time series and time–frequency datasets. [ABSTRACT FROM AUTHOR]

In the last decade, there has been a significant surge of interest in machine learning, primarily driven by advancements in deep learning (DL). DL has emerged as a powerful solution to address various challenges in numerous fields, including remote sensing (RS). Graph Deep Learning (GDL), a sub-field of DL, has recently gained increasing attention in the RS community. Tasks in RS requiring detailed information about the relationships between image/scene features are particularly well-suited for GDL. This study examines the notion of GDL and its recent developments in RS-related fields. An extensive survey of the current state-of-the-art in GDL is presented in this paper, with a specific emphasis on five established graph learning techniques: Graph Convolutional Networks (GCNs), Graph Attention Networks (GATs), Graph Recurrent Neural Networks (GRNNs), Graph Auto-encoders (GAEs), and Graph Generative Adversarial Networks (GGANs). A taxonomy is proposed based on the input data type (dynamic or static) or task being considered. Several promising research directions for GDL in RS are suggested in this paper to foster productive collaborations between the two domains. To the best of our knowledge, this study is the first to provide a comprehensive review that focuses on graph deep learning in remote sensing. [ABSTRACT FROM AUTHOR]

The Red Palm Weevil (RPW), also known as the palm weevil, is considered among the world's most damaging insect pests of palms. Current detection techniques include the detection of symptoms of RPW using visual or sound inspection and chemical detection of volatile signatures generated by infested palm trees. However, efficient detection of RPW diseases at an early stage is considered one of the most challenging issues for cultivating date palms. In this paper, an efficient approach to the early detection of RPW is proposed. The proposed approach is based on RPW sound activities being recorded and analyzed. The first step involves the conversion of sound data into images based on a selected set of features. The second step involves the combination of images from the same sound file but computed by different features into a single image. The third step involves the application of different Deep Learning (DL) techniques to classify resulting images into two classes: infested and not infested. Experimental results show good performances of the proposed approach for RPW detection using different DL techniques, namely MobileNetV2, ResNet50V2, ResNet152V2, VGG16, VGG19, DenseNet121, DenseNet201, Xception, and InceptionV3. The proposed approach outperformed existing techniques for public datasets. • Efficient approach for early detection of Red Palm Weevil (RPW). • Recording and analyzing RPW sound activities. • Applying different deep learning techniques to classify palms as infested and not infested. • Monitoring palm farms to detect early signs of RPW infection. • Several experiments are conducted using real-world and public datasets. [ABSTRACT FROM AUTHOR]

Distributed denial-of-service (DDoS) attacks persistently proliferate, impacting individuals and Internet Service Providers (ISPs). Deep learning (DL) models are paving the way to address these challenges and the dynamic nature of potential threats. Traditional detection systems, relying on signature-based techniques, are susceptible to next-generation malware. Integrating DL approaches in cloud-edge/federated servers enhances the resilience of these systems. In the Internet of Things (IoT) and autonomous networks, DL, particularly federated learning, has gained prominence for attack detection. Unlike conventional models (centralized and localized DL), federated learning does not require access to users’ private data for attack detection. This approach is gaining much interest in academia and industry due to its deployment on local and global cloud-edge models. Recent advancements in DL enable training a quality cloud-edge model across various users (collaborators) without exchanging personal information. Federated learning, emphasizing privacy preservation at the cloud-edge terminal, holds significant potential for facilitating privacy-aware learning among collaborators. This paper addresses: (1) The deployment of an optimized deep neural network for network traffic classification. (2) The coordination of federated server model parameters with training across devices in IoT domains. A federated flowchart is proposed for training and aggregating local model updates. (3) The generation of a global model at the cloud-edge terminal after multiple rounds between domains and servers. (4) Experimental validation on the BoT-IoT dataset demonstrates that the federated learning model can reliably detect attacks with efficient classification, privacy, and confidentiality. Additionally, it requires minimal memory space for storing training data, resulting in minimal network delay. Consequently, the proposed framework outperforms both centralized and localized DL models, achieving superior performance. [ABSTRACT FROM AUTHOR]

Land cover change (LCC) models aim to track spatiotemporal changes made in land cover. In most cases, LCC models contain uncertainties in their main components (i.e., input parameters and model structure). These uncertainties propagate through the modeling system, which generates uncertainties in the model outputs. The aim of this manuscript is to propose an approach to reduce uncertainty of LCC prediction models. The main objective of the proposed approach is to apply a sensitivity analysis method, based on belief function theory, to determine parameters and structures that have a high contribution in the variability of the predictions of the LCC model. Our approach is applied to four common LCC models (i.e., DINAMICA, SLEUTH, CA-MARKOV, and LCM). Results show that uncertainty of the model parameters and structure has meaningful impacts on the final decisions of LCC models. Ignoring this uncertainty can lead to erroneous decision about land changes. Therefore, the presented approach is very useful to identify the most relevant uncertainty sources that need to be processed to improve the accuracy of LCC models. The applicability and effectiveness of the proposed approach are demonstrated through a case study based on the Cairo region. Results show that 13% of the agriculture and 3.8% of the desert lands in 2014 would be converted to urban areas in 2025. [ABSTRACT FROM AUTHOR]

Applications of remote sensing (RS) data cover several fields such as: cartography, surveillance, land-use planning, archaeology, environmental studies, resources management, etc. However, the amount of RS data has grown considerably due to the increase of aerial and satellite sensors. With this continuous increase, the necessity of having automated tools for the interpretation and analysis of RS big data is clearly obvious. The manual interpretation becomes a time consuming and expensive task. In this paper, a novel tool for interpreting and analyzing RS big data is described. The proposed system allows knowledge gathering for decision support in RS fields. It helps users easily make decisions in many fields related to RS by providing descriptive, predictive and prescriptive analytics. The paper outlines the design and development of a framework based on three steps: RS data acquisition, modeling, and analysis & interpretation. The performance of the proposed system has been demonstrated through three models: clustering, decision tree and association rules. Results show that the proposed tool can provide efficient decision support (descriptive and predictive) which can be adapted to several RS users’ requests. Additionally, assessing these results show good performances of the developed tool. [ABSTRACT FROM AUTHOR]

Correction to: Complex & Intelligent Systems https://doi.org/10.1007/s40747-022-00767-w In the original article, there is a citation for the retracted article https://link.springer.com/article/10.1007/s10916-018-1045-z that will be removed. The original article can be found online at https://doi.org/10.1007/s40747-022-00767-w. [Extracted from the article]

This paper introduces a novel semicircular distribution obtained by applying the quadratic rank transmutation map to the stereographic semicircular exponential distribution, referred to as the transmuted stereographic semicircular exponential distribution (TSSCED). This newly proposed distribution exhibits enhanced flexibility compared to the baseline stereographic semicircular exponential distribution (SSCEXP). We conduct a comprehensive analysis of the model's properties and demonstrate its efficacy in data modeling through the application to a real dataset. [ABSTRACT FROM AUTHOR]

Until now, clinicians are not able to evaluate the Psychogenic Non-Epileptic Seizures (PNES) from the rest-electroencephalography (EEG) readout. No EEG marker can help differentiate PNES cases from healthy subjects. In this paper, we have investigated the power spectrum density (PSD), in resting-state EEGs, to evaluate the abnormalities in PNES affected brains. Additionally, we have used functional connectivity tools, such as phase lag index (PLI), and graph-derived metrics to better observe the integration of distributed information of regular and synchronized multi-scale communication within and across inter-regional brain areas. We proved the utility of our method after enrolling a cohort study of 20 age- and gender-matched PNES and 19 healthy control (HC) subjects. In this work, three classification models, namely support vector machine (SVM), linear discriminant analysis (LDA), and Multilayer perceptron (MLP), have been employed to model the relationship between the functional connectivity features (rest-HC versus rest-PNES). The best performance for the discrimination of participants was obtained using the MLP classifier, reporting a precision of 85.73%, a recall of 86.57%, an F1-score of 78.98%, and, finally, an accuracy of 91.02%. In conclusion, our results hypothesized two main aspects. The first is an intrinsic organization of functional brain networks that reflects a dysfunctional level of integration across brain regions, which can provide new insights into the pathophysiological mechanisms of PNES. The second is that functional connectivity features and MLP could be a promising method to classify rest-EEG data of PNES form healthy controls subjects. [ABSTRACT FROM AUTHOR]

Lung cancer emerges as a major factor in cancer-related fatalities in the current generation, and it is predicted to continue having a long-term impact. Detecting symptoms early becomes crucial for effective treatment, underscoring innovative therapy's necessity. Many researchers have conducted extensive work in this area, yet challenges such as high false-positive rates and achieving high accuracy in detection continue to complicate accurate diagnosis. In this research, we aim to develop an ecologically considerate lung cancer therapy prototype model that maximizes resource utilization by leveraging recent advancements in computational intelligence. We also propose an Internet of Medical Things (IoMT)-based, consumer-focused integrated framework to implement the suggested approach, providing patients with appropriate care. Our proposed method employs Logistic Regression, MLP Classifier, Gaussian NB Classifier, and Intelligent Feature Selection using K-Means and Fuzzy Logic to enhance detection procedures in lung cancer dataset. Additionally, ensemble learning is incorporated through a voting classifier. The proposed model's effectiveness is improved through hyperparameter tuning via grid search. The proposed model's performance is demonstrated through comparative analysis with existing NB, J48, and SVM approaches, achieving a 98.50% accuracy rate. The efficiency gains from this approach have the potential to save a significant amount of time and cost. This study underscores the potential of computational intelligence and IoMT in developing effective, resource-efficient lung cancer therapies. [ABSTRACT FROM AUTHOR]

Simple Summary: Skin diseases can be serious, and early detection is key to effective treatment. Unfortunately, the quality of images used to diagnose these diseases often suffers due to interference from hair, making accurate diagnosis challenging. This research introduces a novel technology, the DM–AHR, a self-supervised conditional diffusion model designed specifically to generate clear, hairless images for better skin disease diagnosis. Our work not only presents a new, advanced model that expertly identifies and removes hair from dermoscopic images but also introduces a specialized dataset, DERMAHAIR, to further research and improve diagnostic processes. The enhancements in image quality provided by DM–AHR significantly improve the accuracy of skin disease diagnoses, and it promises to be a valuable tool in medical imaging. Accurate skin diagnosis through end-user applications is important for early detection and cure of severe skin diseases. However, the low quality of dermoscopic images hampers this mission, especially with the presence of hair on these kinds of images. This paper introduces DM–AHR, a novel, self-supervised conditional diffusion model designed specifically for the automatic generation of hairless dermoscopic images to improve the quality of skin diagnosis applications. The current research contributes in three significant ways to the field of dermatologic imaging. First, we develop a customized diffusion model that adeptly differentiates between hair and skin features. Second, we pioneer a novel self-supervised learning strategy that is specifically tailored to optimize performance for hairless imaging. Third, we introduce a new dataset, named DERMAHAIR (DERMatologic Automatic HAIR Removal Dataset), that is designed to advance and benchmark research in this specialized domain. These contributions significantly enhance the clarity of dermoscopic images, improving the accuracy of skin diagnosis procedures. We elaborate on the architecture of DM–AHR and demonstrate its effective performance in removing hair while preserving critical details of skin lesions. Our results show an enhancement in the accuracy of skin lesion analysis when compared to existing techniques. Given its robust performance, DM–AHR holds considerable promise for broader application in medical image enhancement. [ABSTRACT FROM AUTHOR]

• A distributed deep learning-based approach to classify big remote sensing images. • Satellite image classification based on distributed Convolutional-Neural-Networks. • Two steps: (1) preparing the training dataset and (2) a parallel-data training. • Experiments are conducted on a real dataset and show highly classification accuracy. • Experiments show high classification accuracy and faster speed compared with current state-of-the-art methods. Developments in remote sensing technology have led to a continuous increase in the volume of remote-sensing data, which can be qualified as big remote sensing data. A wide range of potential applications is using these data including land cover classification, regional planning, catastrophe prediction and management, and climate-change estimation. Big remote sensing data are characterized by different types of resolutions (radiometric, spatial, spectral, and temporal), modes of imaging, and sensor types, and this range of options often makes the process of analyzing and interpreting such data more difficult. In this paper, which is the first study of its kind, we propose a novel distributed deep learning-based approach for the classification of big remote sensing images. Specifically, we propose Distributed Convolutional-Neural-Networks for handling RS image classification (RS-DCNN). The first step is to prepare the training dataset for RS-DCNN. Then, to ensure a data-parallel training on the top of the Apache Spark framework, a pixel-based convolutional-neural-network model across the big data cluster is performed using BigDL. Experiments are conducted on a real dataset covering many regions of Saudi Arabia and the results demonstrate high classification accuracy at a faster speed than other state-of-the-art classification methods. [ABSTRACT FROM AUTHOR]

This paper reviews big data and Internet of Things (IoT)-based applications in smart environments. The aim is to identify key areas of application, current trends, data architectures, and ongoing challenges in these fields. To the best of our knowledge, this is a first systematic review of its kind, that reviews academic documents published in peer-reviewed venues from 2011 to 2019, based on a four-step selection process of identification, screening, eligibility, and inclusion for the selection process. In order to examine these documents, a systematic review was conducted and six main research questions were answered. The results indicate that the integration of big data and IoT technologies creates exciting opportunities for real-world smart environment applications for monitoring, protection, and improvement of natural resources. The fields that have been investigated in this survey include smart environment monitoring, smart farming/agriculture, smart metering, and smart disaster alerts. We conclude by summarizing the methods most commonly used in big data and IoT, which we posit to serve as a starting point for future multi-disciplinary research in smart cities and environments. [ABSTRACT FROM AUTHOR]

The rapid growth of urban populations worldwide imposes new challenges on citizens' daily lives, including environmental pollution, public security, road congestion, etc. New technologies have been developed to manage this rapid growth by developing smarter cities. Integrating the Internet of Things (IoT) in citizens' lives enables the innovation of new intelligent services and applications that serve sectors around the city, including healthcare, surveillance, agriculture, etc. IoT devices and sensors generate large amounts of data that can be analyzed to gain valuable information and insights that help to enhance citizens' quality of life. Deep Learning (DL), a new area of Artificial Intelligence (AI), has recently demonstrated the potential for increasing the efficiency and performance of IoT big data analytics. In this survey, we provide a review of the literature regarding the use of IoT and DL to develop smart cities. We begin by defining the IoT and listing the characteristics of IoT-generated big data. Then, we present the different computing infrastructures used for IoT big data analytics, which include cloud, fog, and edge computing. After that, we survey popular DL models and review the recent research that employs both IoT and DL to develop smart applications and services for smart cities. Finally, we outline the current challenges and issues faced during the development of smart city services. [ABSTRACT FROM AUTHOR]

Aerial photography involves capturing images from aircraft and other flying objects, including Unmanned Aerial Vehicles (UAV). Aerial images are used in many fields and can contain sensitive information that requires secure processing. We proposed an innovative new cryptosystem for the processing of aerial images utilizing a chaos-based private key block cipher method so that the images are secure even on untrusted cloud servers. The proposed cryptosystem is based on a hybrid technique combining the Mersenne Twister (MT), Deoxyribonucleic Acid (DNA), and Chaotic Dynamical Rossler System (MT-DNA-Chaos) methods. The combination of MT with the four nucleotides and chaos sequencing creates an enhanced level of security for the proposed algorithm. The system is tested at three separate phases. The combined effects of the three levels improve the overall efficiency of the randomness of data. The proposed method is computationally agile, and offered more security than existing cryptosystems. To assess, this new system is examined against different statistical tests such as adjacent pixels correlation analysis, histogram consistency analyses and its variance, visual strength analysis, information randomness and uncertainty analysis, pixel inconsistency analysis, pixels similitude analyses, average difference, and maximum difference. These tests confirmed its validity for real-time communication purposes. [ABSTRACT FROM AUTHOR]

Life-saving decisions in vehicular ad hoc networks (VANETs) depend on the availability of highly accurate, up-to-date, and reliable data exchanged by neighboring vehicles. However, spreading inaccurate, unreliable, and false data by intruders create traffic illusions that may cause loss of lives and assets. Although several solutions for misbehavior detection have been proposed to address these issues, those solutions lack adequate representation and the adaptability to vehicular context. The use of predefined static thresholds and lack of comprehensive context representation have rendered the existing solutions limited to specific scenarios and attack types, which impedes their generalizability. This paper addresses these limitations by proposing an ensemble-based hybrid context-aware misbehavior detection system (EHCA-MDS) model. EHCA-MDS has been developed in four phases, as follows. The static thresholds have been replaced by dynamic ones created on the fly by analyzing the spatial and temporal properties of the mobility information collected from neighboring vehicles. Kalman filter-based algorithms were used to collect the mobility information of neighboring vehicles. Three sets of features were then derived, each of which has a different perspective, namely data consistency, data plausibility, and vehicle behavior. These features were used to construct a dynamic context reference using the Hampel filter. The Hampel-based z-score was used to evaluate the vehicles based on their behavioral activities, data consistency, and plausibility. For comprehensive features representation, multifaceted, non-parametric-based statistical classifiers were constructed and updated online using a Hampel filter-based algorithm. For accurate representation, the output of the statistical classifiers, vehicles' scores, context reference parameters, and the derived features were used as input to an ensemble learning-based algorithm. Such representation helps to identify the misbehaving vehicles more effectively. The proposed EHCA-MDS model was evaluated in the presence of different types of misbehaving vehicles under different context scenarios through extensive simulations, utilizing a real-world traffic dataset. The results show that the accuracy and robustness of the proposed EHCA-MDS under different vehicular dynamic context scenarios were higher than existing solutions, which confirms its feasibility and effectiveness to improve the performance of VANET critical applications. [ABSTRACT FROM AUTHOR]

Computer networks face vulnerability to numerous attacks, which pose significant threats to our data security and the freedom of communication. This paper introduces a novel intrusion detection technique that diverges from traditional methods by leveraging Recurrent Neural Networks (RNNs) for both data preprocessing and feature extraction. The proposed process is based on the following steps: (1) training the data using RNNs, (2) extracting features from their hidden layers, and (3) applying various classification algorithms. This methodology offers significant advantages and greatly differs from existing intrusion detection practices. The effectiveness of our method is demonstrated through trials on the Network Security Laboratory (NSL) and Canadian Institute for Cybersecurity (CIC) 2017 datasets, where the application of RNNs for intrusion detection shows substantial practical implications. Specifically, we achieved accuracy scores of 99.6% with Decision Tree, Random Forest, and CatBoost classifiers on the NSL dataset, and 99.8% and 99.9%, respectively, on the CIC 2017 dataset. By reversing the conventional sequence of training data with RNNs and then extracting features before applying classification algorithms, our approach provides a major shift in intrusion detection methodologies. This modification in the pipeline underscores the benefits of utilizing RNNs for feature extraction and data preprocessing, meeting the critical need to safeguard data security and communication freedom against ever-evolving network threats. [ABSTRACT FROM AUTHOR]