EAI Endorsed Transactions on Scalable Information Systems

Combining Lexical, Host, and Content-based features for Phishing Websites detection using Machine Learning Models

2023-11-20T20:59:52+00:00

In cybersecurity field, identifying and dealing with threats from malicious websites (phishing, spam, and drive-by downloads, for example) is a major concern for the community. Consequently, the need for effective detection methods has become a necessity. Recent advances in Machine Learning (ML) have renewed interest in its application to a variety of cybersecurity challenges. When it comes to detecting phishing URLs, machine learning relies on specific attributes, such as lexical, host, and content based features. The main objective of our work is to propose, implement and evaluate a solution for identifying phishing URLs based on a combination of these feature sets. This paper focuses on using a new balanced dataset, extracting useful features from it, and selecting the optimal features using different feature selection techniques to build and conduct a
comparative performance evaluation of four ML models (SVM, Decision Tree, Random Forest, and XGBoost). Results showed that the XGBoost model outperformed the others models, with an accuracy of 95.70% and a false negatives rate of 1.94%.

Fast Lung Image Segmentation Using Lightweight VAEL-Unet

2024-01-07T01:13:44+00:00

INTRODUCTION: A lightweght lung image segmentation model was explored. It was with fast speed and low resouces consumed while the accuracy was comparable to those SOAT models.

OBJECTIVES: To improve the segmentation accuracy and computational efficiency of the model in extracting lung regions from chest X-ray images, a lightweight segmentation model enhanced with a visual attention mechanism called VAEL-Unet, was proposed.

METHODS: Firstly, the bneck module from the MobileNetV3 network was employed to replace the convolutional and pooling operations at different positions in the U-Net encoder, enabling the model to extract deeper-level features while reducing complexity and parameters. Secondly, an attention module was introduced during feature fusion, where the processed feature maps were sequentially fused with the corresponding positions in the decoder to obtain the segmented image.

RESULTS: On ChestXray, the accuracy of VAEL-Unet improves from 97.37% in the traditional U-Net network to 97.69%, while the F1-score increases by 0.67%, 0.77%, 0.61%, and 1.03% compared to U-Net, SegNet, ResUnet and DeepLabV3+ networks. respectively. On LUNA dataset. the F1-score demonstrates improvements of 0.51%, 0.48%, 0.22% and 0.46%, respectively, while the accuracy has increased from 97.78% in the traditional U-Net model to 98.08% in the VAEL-Unet model. The training time of the VAEL-Unet is much less compared to other models. The number of parameters of VAEL-Unet is only 1.1M, significantly less than 32M of U-Net, 29M of SegNet, 48M of Res-Unet, 5.8M of DeeplabV3+ and 41M of DeepLabV3Plus_ResNet50.

CONCLUSION: These results indicate that VAEL-Unet’s segmentation performance is slightly better than other referenced models while its training time and parameters are much less.

Investigation of Imbalanced Sentiment Analysis in Voice Data: A Comparative Study of Machine Learning Algorithms

2024-01-10T06:45:45+00:00

INTRODUCTION: Language serves as the primary conduit for human expression, extending its reach into various communication mediums like email and text messaging, where emoticons are frequently employed to convey nuanced emotions. In the digital landscape of long-distance communication, the detection and analysis of emotions assume paramount importance. However, this task is inherently challenging due to the subjectivity inherent in emotions, lacking a universal consensus for quantification or categorization.

OBJECTIVES: This research proposes a novel speech recognition model for emotion analysis, leveraging diverse machine learning techniques along with a three-layer feature extraction approach. This research will also through light on the robustness of models on balanced and imbalanced datasets.

METHODS: The proposed three-layered feature extractor uses chroma, MFCC, and Mel method, and passes these features to classifiers like K-Nearest Neighbour, Gradient Boosting, Multi-Layer Perceptron, and Random Forest.

RESULTS: Among the classifiers in the framework, Multi-Layer Perceptron (MLP) emerges as the top-performing model, showcasing remarkable accuracies of 99.64%, 99.43%, and 99.31% in the Balanced TESS Dataset, Imbalanced TESS (Half) Dataset, and Imbalanced TESS (Quarter) Dataset, respectively. K-Nearest Neighbour (KNN) follows closely as the second-best classifier, surpassing MLP's accuracy only in the Imbalanced TESS (Half) Dataset at 99.52%.

CONCLUSION: This research contributes valuable insights into effective emotion recognition through speech, shedding light on the nuances of classification in imbalanced datasets.

A Hybrid CNN Approach for Unknown Attack Detection in Edge-Based IoT Networks

2024-01-18T09:54:36+00:00

INTRODUCTION: In the constantly growing Internet of Things (IoT), device security is crucial. As IoT gadgets pervade our lives, detecting unforeseen assaults is crucial to protecting them. Behavioral analysis, machine learning, and collaborative intelligence may be needed to protect against new dangers. This short discusses the need of detecting unexpected IoT attacks and essential security strategies for these interconnected environments.

OBJECTIVES: This research uses the BoT-IoT dataset to create an enhanced IoT intrusion detection system. The goals are to optimize a CNN architecture for effective pattern recognition, address imbalanced data, and evaluate model performance using precision, recall, F1-score, and AUC-ROC measures. Improving IoT ecosystem reliability and security against unknown assaults is the ultimate goal.

METHODS: The proposed methods use the BoT-IoT dataset to create a comprehensive IoT intrusion detection system. This involves tuning a Convolutional Neural Network (CNN) architecture to improve pattern recognition. Oversampling and class weighting address imbalanced data issues.

RESULTS: The comprehensive evaluation of our innovative unknown attack detection method shows promise, suggesting it may be better than existing methods. A high accuracy, precision, recall, and f-measure of 98.23% were attained using an advanced model and feature selection methods. This achievement was achieved by using features designed to identify unknown attacks in the dataset, proving the proposed methodology works.

CONCLUSION: This research presents an improved IoT Intrusion Detection System using the BoT-IoT dataset. The optimised Convolutional Neural Network architecture and imbalanced data handling approaches achieved 98.23% accuracy.

E-GVD: Efficient Software Vulnerability Detection Techniques Based on Graph Neural Network

2024-02-07T02:28:50+00:00

INTRODUCTION: Vulnerability detection is crucial for preventing severe security incidents like hacker attacks, data breaches, and network paralysis. Traditional methods, however, face challenges such as low efficiency and insufficient detail in identifying code vulnerabilities.
OBJECTIVES: This paper introduces E-GVD, an advanced method for source code vulnerability detection, aiming to address the limitations of existing methods. The objective is to enhance the accuracy of function-level vulnerability detection and provide detailed, understandable insights into the vulnerabilities.
METHODS: E-GVD combines Graph Neural Networks (GNNs), which are adept at handling graph-structured data, with residual connections and advanced Programming Language (PL) pre-trained models.
RESULTS: Experiments conducted on the real-world vulnerability dataset CodeXGLUE show that E-GVD significantly outperforms existing baseline methods in detecting vulnerabilities. It achieves a maximum accuracy gain of 4.98%, indicating its effectiveness over traditional methods.
CONCLUSION: E-GVD not only improves the accuracy of vulnerability detection but also contributes by providing fine-grained explanations. These explanations are made possible through an interpretable Machine Learning (ML) model, which aids developers in quickly and efficiently repairing vulnerabilities, thereby enhancing overall software security.

Integrating Metaheuristics and Two-Tiered Classification for Enhanced Fake News Detection with Feature Optimization

2024-02-08T06:35:17+00:00

INTRODUCTION: The challenge of distributing false information continues despite the significant impact of social media on opinions. The suggested framework, which is a metaheuristic method, is presented in this research to detect bogus news. Employing a hybrid metaheuristic RDAVA methodology coupled with Bi-LSTM, the method leverages African Vulture Optimizer and Red Deer Optimizer.

OBJECTIVES: The objective of this study is to assess the effectiveness of the suggested model in identifying false material on social media by employing social network analysis tools to combat disinformation.

METHODS: Employing the data sets from BuzzFeed, FakeNewsNet, and ISOT, the suggested model is implemented on the MATLAB Platform and acquires high accuracy rates of 97% on FakeNewsNet and 98% on BuzzFeed and ISOT. A comparative study with current models demonstrates its superiority.

RESULTS: Outperforming previous models with 98% and 97% accuracy on BuzzFeed/ISOT and FakeNewsNet, respectively, the suggested model shows remarkable performance.

CONCLUSION: The proposed strategy shows promise in addressing the problem of false information on social media in the modern day by effectively countering fake news. Its incorporation of social network analysis methods and metaheuristic methodologies makes it a powerful instrument for identifying false news.

A Self-learning Ability Assessment Method Based on Weight-Optimised Dfferential Evolutionary Algorithm

2024-02-22T02:26:04+00:00

INTRODUCTION: The research on the method of cultivating college students' autonomous ability based on experiential teaching is conducive to college students' change of learning mode and learning thinking, improving the utilisation rate of educational resources, as well as the reform of education.

OBJECTIVES: Addressing the current problems of unquantified analyses, lack of breadth, and insufficient development strategies in the methods used to develop independent learning skills in university students.

METHODS: This paper proposes an intelligent optimisation algorithm for the cultivation of college students' independent learning ability in experiential teaching. Firstly, the characteristics and elements of college students' independent learning are analysed, while the strategy of cultivating college students' independent learning ability in experiential teaching is proposed; then, the weight optimization method of cultivating college students' independent learning ability based on experiential teaching is proposed by using the improved intelligent optimization algorithm; finally, the validity and feasibility of the proposed method are verified through experimental analysis.

RESULTS: The results show that the proposed method has a wider range of culture effects.

CONCLUSION: Addressing the problem of poor generalisation in the development of independent learning skills among university students.

Research on Credit Risk Prediction Method of Blockchain Applied to Supply Chain Finance

2024-03-05T01:39:15+00:00

INTRODUCTION: From the perspective of blockchain, it establishes a credit risk evaluation index system for supply chain finance applicable to blockchain, constructs an accurate credit risk prediction model, and provides a reliable guarantee for the research of credit risk in supply chain finance.

OBJECTIVES: To address the inefficiency of the current credit risk prediction and evaluation model for supply chain finance.

METHODS: This paper proposes a combined blockchain supply chain financial credit risk prediction and evaluation method based on kernel principal component analysis and intelligent optimisation algorithm to improve Deep Echo State Network. Firstly, the evaluation system is constructed by describing the supply chain financial credit risk prediction and evaluation problem based on blockchain technology, analysing the evaluation indexes, and constructing the evaluation system; then, the parameters of DeepESN network are optimized by combining the kernel principal component analysis method with the JSO algorithm to construct the credit risk prediction and evaluation model of supply chain finance; finally, the effectiveness, robustness, and real-time performance of the proposed method are verified by simulation experiment analysis.

RESULTS: The results show that the proposed method improves the prediction efficiency of the prediction model.

CONCLUSION: The problems of insufficient scientific construction of index system and poor efficiency of risk prediction model of B2B E-commerce transaction size prediction method are effectively solved.

A Solution to Graph Coloring Problem Using Genetic Algorithm

2024-03-15T13:25:27+00:00

INTRODUCTION: The Graph Coloring Problem (GCP) involves coloring the vertices of a graph in such a way that no two adjacent vertices share the same color while using the minimum number of colors possible.

OBJECTIVES: The main objective of the study is While keeping the constraint that no two neighbouring vertices have the same colour, the goal is to reduce the number of colours needed to colour a graph's vertices. It further investigate how various techniques impact the execution time as the number of nodes in the graph increases.

METHODS: In this paper, we propose a novel method of implementing a Genetic Algorithm (GA) to address the GCP.

RESULTS: When the solution is implemented on a highly specified Google Cloud instance, we likewise see a significant increase in performance. The parallel execution on Google Cloud shows significantly faster execution times than both the serial implementation and the parallel execution on a local workstation. This exemplifies the benefits of cloud computing for computational heavy jobs like GCP.

CONCLUSION: This study illustrates that a promising solution to the Graph Coloring Problem is provided by Genetic Algorithms. Although the GA-based approach does not provide an optimal result, it frequently produces excellent approximations in a reasonable length of time for a variety of real-world situations.

DTT: A Dual-domain Transformer model for Network Intrusion Detection

2024-03-17T12:30:26+00:00

With the rapid evolution of network technologies, network attacks have become increasingly intricate and threatening. The escalating frequency of network intrusions has exerted a profound influence on both industrial settings and everyday activities. This underscores the urgent necessity for robust methods to detect malicious network traffic. While intrusion detection techniques employing Temporal Convolutional Networks (TCN) and Transformer architectures have exhibited commendable classification efficacy, most are confined to the temporal domain. These methods frequently fall short of encompassing the entirety of the frequency spectrum inherent in network data, thereby resulting in information loss. To mitigate this constraint, we present DTT, a novel dual-domain intrusion detection model that amalgamates TCN and Transformer architectures. DTT adeptly captures both high-frequency and low-frequency information, thereby facilitating the simultaneous extraction of local and global features. Specifically, we introduce a dual-domain feature extraction (DFE) block within the model. This block effectively extracts global frequency information and local temporal features through distinct branches, ensuring a comprehensive representation of the data. Moreover, we introduce an input encoding mechanism to transform the input into a format suitable for model training. Experiments conducted on two distinct datasets address concerns regarding data duplication and diverse attack types, respectively. Comparative experiments with recent intrusion detection models unequivocally demonstrate the superior performance of the proposed DTT model.

Evaluating Performance of Conversational Bot Using Seq2Seq Model and Attention Mechanism

2024-03-18T15:08:59+00:00

The Chat-Bot utilizes Sequence-to-Sequence Model with the Attention Mechanism, in order to interpret and address user inputs effectively. The whole model consists of Data gathering, Data preprocessing, Seq2seq Model, Training and Tuning. Data preprocessing involves cleaning of any irrelevant data, before converting them into the numerical format. The Seq2Seq Model is comprised of two components: an Encoder and a Decoder. Both Encoder and Decoder along with the Attention Mechanism allow dialogue management, which empowers the Model to answer the user in the most accurate and relevant manner. The output generated by the Bot is in the Natural Language only. Once the building of the Seq2Seq Model is completed, training of the model takes place in which the model is fed with the preprocessed data, during training it tries to minimize the loss function between the predicted output and the ground truth output. Performance is computed using metrics such as perplexity, BLEU score, and ROUGE score on a held-out validation set. In order to meet non-functional requirements, our system needs to maintain a response time of under one second with an accuracy target exceeding 90%.

A Web-Based Augmented Reality System

2024-03-20T10:58:56+00:00

Web-based augmented reality (AR) systems have many use cases and opportunities in Product Visualisation, Education and Training, Advertising and Marketing, Navigation and Wayfinding, Virtual Try-On, Interactive Storey Telling, Museums and Cultural Heritage, Training and Simulation, Gamification and more. As such, this research paper, A Web-Based Augmented Reality System, will explore these technologies and their use cases in the form of a literature review and several examples utilising the likes of Vectary, Blippar, Model Viewer and World Cast AR. The purpose of which, is to demonstrate a level of understanding of these virtual technologies, to develop them and to develop their future with practical use cases.

Image Quality Assessment of Multi-Satellite Pan-Sharpening Approach: A Case Study using Sentinel-2 Synthetic Panchromatic Image and Landsat-8

2024-03-21T10:22:43+00:00

INTRODUCTION: The satellite's physical and technical capabilities limit high spectral and spatial resolution image acquisition. In Remote Sensing (RS), when high spatial and spectral resolution data is essential for specific Geographic Information System (GIS) applications, Pan Sharpening (PanS) becomes imperative in obtaining such data.

OBJECTIVES: Study aims to enhance the spatial resolution of the multispectral Landsat-8 (L8) images using a synthetic panchromatic band generated by averaging four fine-resolution bands in the Sentinel-2 (S2) images.

METHODS: Evaluation of the proposed multi-satellite PanS approach, three different PanS techniques, Smoothed Filter Intensity Modulation (SFIM), Gram-Schmidt (GS), and High Pass Filter Additive (HPFA) are used for two different study areas. The techniques' effectiveness was evaluated using well-known Image Quality Assessment Metrics (IQAM) such as Root Mean Square Error (RMSE), Correlation Coefficient (CC), Erreur Relative Globale Adimensionnelle de Synthèse (ERGAS), and Relative Average Spectral Error (RASE). This study leveraged the GEE platform for datasets and implementation.

RESULTS: The promising values were provided by the GS technique, followed by the SFIM technique, whereas the HPFA technique produced the lowest quantitative result.

CONCLUSION: In this study, the spectral bands of the MS image’s performance show apparent variation with respect to that of the different PanS techniques used.

Quantum Deep Neural Network Based Classification of Attack Vectors on the Ethereum Blockchain

2024-03-27T15:30:48+00:00

INTRODUCTION: The implementation of robust security protocols is imperative in light of the exponential growth of blockchain-based platforms such as Ethereum. The importance of developing more effective strategies to detect and counter potential attacks is growing in tandem with the sophistication of the methods employed by attackers. In this study, we present a novel approach that leverages quantum computing to identify and predict attack vectors on the Ethereum blockchain.

OBJECTIVES: The primary objective of this study is to suggest an innovative methodology for enhancing the security of Ethereum by leveraging quantum computing. The purpose of this study is to demonstrate that QRBM and QDN are efficient in identifying and predicting security flaws in blockchain transactions.

METHODS: We combined methods from quantum computing with social network research approaches. An enormous dataset containing both genuine Ethereum transactions and a carefully chosen spectrum of malicious activity indicative of popular attack vectors was used to train our model, the QRBM. Thanks to the dataset, the QRBM was able to learn to distinguish between typical and out-of-the-ordinary activities.

RESULTS: In comparison to more conventional deep learning models, the QRBM showed substantially better accuracy when it came to identifying transaction behaviours. The model's improved scalability and efficiency were made possible by its quantum nature, which is defined by features like entanglement and superposition. Specifically, the QRBM handled non-informative inputs better and solved problems faster.

CONCLUSION: This study paves the way for further investigation into quantum-enhanced cybersecurity measures and highlights the promise of quantum neural networks in strengthening the security of blockchain technology. According to our research, quantum computing has the potential to be an essential tool in creating Ethereum-style blockchain security systems that are more advanced, efficient, and resilient.

Smart Contracts for Ensuring Data Integrity in Cloud Storage with Blockchain

2024-04-04T09:07:47+00:00

INTRODUCTION: Data integrity protection has become a significant priority for both consumers and organizations as cloud storage alternatives have multiplied since they provide scalable solutions for individuals and organizations alike. Traditional cloud storage systems need to find new ways to increase security because they are prone to data modification and unauthorized access thus causing data breaches.

OBJECTIVES: The main objective of this study is to review usage of smart contracts and blockchain technology to ensure data integrity in cloud storage.

METHODS: . Case studies, performance evaluations, and a thorough literature review are all used to demonstrate the effectiveness of the suggested system.

RESULTS: This research has unveiled a revolutionary approach that capitalizes on the fusion of smart contracts and cloud storage, fortified by blockchain technology.

CONCLUSION: This theoretical analysis demonstrate that smart contracts offer a dependable and scalable mechanism for maintaining data integrity in cloud storage, opening up a promising area for further research and practical application.

IoT Protocols: Connecting Devices in Smart Environments

2024-04-06T13:51:43+00:00

The study delves into the implications of various IoT protocols on communication efficiency and energy consumption within smart environments. The RVRR (routing via respective reducer) protocol emerges as a standout performer, showcasing notable advantages over other conventional protocols. Specifically, the results demonstrate a substantial reduction in communication costs with RVRR, exhibiting improvements of 22.72%, 43.46%, and 49.04% when compared to ILP, SDN-Smart, and R-Drain, respectively. excels in data transmission, achieving commendable reductions in Round-Trip Time (RTT) and enhancing overall energy efficiency. It registers an 18.80% decrease in energy consumption compared to ILP, 28.65% compared to SDN-Smart, and a significant 37% reduction when compared to R-Drain. This suggests that RVRR is adept at optimizing resource usage (routing via respective reducer )and minimizing energy consumption, crucial aspects in the context of IoT applications. The study reveals that RVRR contributes to an extended network lifespan, outperforming other protocols by substantial margins. It showcases a 19.45% improvement over ILP, 39.16% over SDN-Smart, and an impressive 54.60% over R-Drain. This underscores the sustainability and longevity benefits offered by RVRR (routing via respective reducer), making it a promising protocol for efficient and enduring IoT applications within smart environments.

A hybrid intrusion detection system with K-means and CNN+LSTM

2024-04-07T02:52:04+00:00

Intrusion detection system (IDS) plays an important role as it provides an efficient mechanism to prevent or mitigate cyberattacks. With the recent advancement of artificial intelligence (AI), there have been many deep learning methods for intrusion anomaly detection to improve network security. In this research, we present a novel hybrid framework called KCLSTM, combining the K-means clustering algorithm with convolutional neural network (CNN) and long short-term memory (LSTM) architecture for the binary classification of intrusion detection systems. Extensive experiments are conducted to evaluate the performance of the proposed model on the well-known NSL-KDD dataset in terms of accuracy, precision, recall, F1-score, detection rate (DR), and false alarm rate (FAR). The results are compared with traditional machine learning approaches and deep learning methods. The proposed model demonstrates superior performance in terms of accuracy, DR, and F1-score, showcasing its effectiveness in identifying network intrusions accurately while minimizing false positives.

Improving Mobile Ad hoc Networks through an investigation of AODV, DSR, and MP-OLSR Routing Protocols

2024-04-08T14:40:27+00:00

Mobile Ad Hoc Networks (MANETs) pose a dynamically organized wireless network, posing a challenge to establishing quality of service (QoS) due to limitations in bandwidth and the ever-changing network topology. These networks are created by assembling nodes systematically, lacking a central infrastructure, and dynamically linking devices such as mobile phones and tablets. Nodes employ diverse methods for service delivery, all while giving priority to network performance. The effectiveness of protocols is crucial in determining the most efficient paths between source and destination nodes, ensuring the timely delivery of messages. Collaborative agreements with MANETs improve accessibility, allow for partial packet delivery and manage network load, ultimately minimizing delays and contributing to exceptional carrier performance. This article conducts a comparative analysis of simulation parameters for AODV, DSR, and MP-OLSR protocols to explore QoS limitations associated with different routing protocols. The study primarily focuses on evaluating various quality metrics for service improvement, assessing protocol performance. Simulation results underscore the DSR protocol's 80% superior throughput compared to AODV and MP-OLSR. However, in terms of delay and packet delivery ratio, the hybrid protocol outperforms both AODV and DSR protocols. These findings provide a distinct perspective for testing the compliance services of MANETs.

Real-Time 3D Routing Optimization for Unmanned Aerial Vehicle using Machine Learning

2024-04-09T08:21:49+00:00

In the realm of Unmanned Aerial Vehicles (UAVs) for civilian applications, the surge in demand has underscored the need for sophisticated technologies. The integration of Unmanned Aerial Systems (UAS) with Artificial Intelligence (AI) has become paramount to address challenges in urban environments, particularly those involving obstacle collision risks. These UAVs are equipped with advanced sensor arrays, incorporating LiDAR and computer vision technologies. The AI algorithm undergoes comprehensive training on an embedded machine, fostering the development of a robust spatial perception model. This model enables the UAV to interpret and navigate through the intricate urban landscape with a human-like understanding of its surroundings. During mission execution, the AI-driven perception system detects and localizes objects, ensuring real-time awareness. This study proposes an innovative real-time three-dimensional (3D) path planner designed to optimize UAV trajectories through obstacle-laden environments. The path planner leverages a heuristic A* algorithm, a widely recognized search algorithm in artificial intelligence. A distinguishing feature of this proposed path planner is its ability to operate without the need to store frontier nodes in memory, diverging from conventional A* implementations. Instead, it relies on relative object positions obtained from the perception system, employing advanced techniques in simultaneous localization and mapping (SLAM). This approach ensures the generation of collision-free paths, enhancing the UAV's navigational efficiency. Moreover, the proposed path planner undergoes rigorous validation through Software-In-The-Loop (SITL) simulations in constrained environments, leveraging high-fidelity UAV dynamics models. Preliminary real flight tests are conducted to assess the real-world applicability of the system, considering factors such as wind disturbances and dynamic obstacles. The results showcase the path planner's effectiveness in providing swift and accurate guidance, thereby establishing its viability for real-time UAV missions in complex urban scenarios.

Exploring the Impact of Mismatch Conditions, Noisy Backgrounds, and Speaker Health on Convolutional Autoencoder-Based Speaker Recognition System with Limited Dataset

2024-04-09T12:04:44+00:00

This paper presents a novel approach to enhance the success rate and accuracy of speaker recognition and identification systems. The methodology involves employing data augmentation techniques to enrich a small dataset with audio recordings from five speakers, covering both male and female voices. Python programming language is utilized for data processing, and a convolutional autoencoder is chosen as the model. Spectrograms are used to convert speech signals into images, serving as input for training the autoencoder. The developed speaker recognition system is compared against traditional systems relying on the MFCC feature extraction technique. In addition to addressing the challenges of a small dataset, the paper explores the impact of a "mismatch condition" by using different time durations of the audio signal during both training and testing phases. Through experiments involving various activation and loss functions, the optimal pair for the small dataset is identified, resulting in a high success rate of 92.4% in matched conditions. Traditionally, Mel-Frequency Cepstral Coefficients (MFCC) have been widely used for this purpose. However, the COVID-19 pandemic has drawn attention to the virus's impact on the human body, particularly on areas relevant to speech, such as the chest, throat, vocal cords, and related regions. COVID-19 symptoms, such as coughing, breathing difficulties, and throat swelling, raise questions about the influence of the virus on MFCC, pitch, jitter, and shimmer features. Therefore, this research aims to investigate and understand the potential effects of COVID-19 on these crucial features, contributing valuable insights to the development of robust speaker recognition systems.

Manifesto of Deep Learning Architecture for Aspect Level Sentiment Analysis to extract customer criticism

2024-04-09T12:56:19+00:00

Sentiment analysis, a critical task in natural language processing, aims to automatically identify and classify the sentiment expressed in textual data. Aspect-level sentiment analysis focuses on determining sentiment at a more granular level, targeting specific aspects or features within a piece of text. In this paper, we explore various techniques for sentiment analysis, including traditional machine learning approaches and state-of-the-art deep learning models. Additionally, deep learning techniques has been utilized to identifying and extracting specific aspects from text, addressing aspect-level ambiguity, and capturing nuanced sentiments for each aspect. These datasets are valuable for conducting aspect-level sentiment analysis. In this article, we explore a language model based on pre-trained deep neural networks. This model can analyze sequences of text to classify sentiments as positive, negative, or neutral without explicit human labeling. To evaluate these models, data from Twitter's US airlines sentiment database was utilized. Experiments on this dataset reveal that the BERT, RoBERTA and DistilBERT model outperforms than the ML based model in accuracy and is more efficient in terms of training time. Notably, our findings showcase significant advancements over previous state-of-the-art methods that rely on supervised feature learning, bridging existing gaps in sentiment analysis methodologies. Our findings shed light on the advancements and challenges in sentiment analysis, offering insights for future research directions and practical applications in areas such as customer feedback analysis, social media monitoring, and opinion mining.

Development of Standards for Metadata Documentation in Citizen Science Projects

2024-04-09T13:31:03+00:00

Introduction: Citizen science has generated large volumes of data contributed by citizens in the last decade. However, the lack of standardization in metadata threatens the interoperability and reuse of information.

Objective: The objective was to develop a proposal for standards to document metadata in citizen science projects in order to improve interoperability and data reuse.

Methods: A literature review was conducted that characterized the challenges in metadata documentation. Likewise, it analyzed previous experiences with standards such as Darwin Core and Dublin Core.

Results: The review showed a high heterogeneity in the documentation, making interoperability difficult. The analyzes showed that standards facilitate the flow of information when they cover basic needs.

Conclusions: It was concluded that standardizing metadata is essential to harness the potential of citizen science. The initial proposal, consisting of flexible norms focused on critical aspects, sought to establish bases for a collaborative debate considering the changing needs of this community.

Integrative Resource Management in Multi Cloud Computing: A DRL Based Approach for multi-objective Optimization

2024-04-10T08:34:29+00:00

INTRODUCTION: The multi-data canter architecture is being investigated as a significant development in meeting the increasing demands of modern applications and services. The study provides a toolset for creating and managing virtual machines (VMs) and physical hosts (PMs) in a virtualized cloud environment, as well as for simulating various scenarios based on real-world cloud usage trends.

OBJECTIVES: To propose an optimized resource management model using the Enhanced Flower Pollination algorithm in a heterogeneous environment.

METHODS: The combination of Q-learning with flower pollination raises the bar in resource allocation and job scheduling. The combination of these advanced methodologies enables our solution to handle complicated and dynamic scheduling settings quickly, making it suited for a wide range of practical applications. The algorithm finds the most promising option by using Q-values to drive the pollination process, enhancing efficiency and efficacy in discovering optimal solutions. An extensive testing using simulation on various datasets simulating real-world scenarios consistently demonstrates the suggested method's higher performance.

RESULTS: In the end, the implementation is done on AWS clouds; the proposed methodology shows the excellent performance by improving energy efficiency, Co2 Reduction and cost having multi-cloud environment

CONCLUSION: The comprehensive results and evaluations of the proposed work demonstrate its effectiveness in achieving the desired goals. Through extensive experimentation on diverse datasets representing various real-world scenarios, the proposed work consistently outperforms existing state-of-the-art algorithms.

Enhancing Privacy Measures in Healthcare within Cyber-Physical Systems through Cryptographic Solutions

2024-04-11T08:21:54+00:00

INTRODUCTION: The foundation of cybersecurity is privacy, standardization, and interoperability—all of which are essential for compatibility, system integration, and the protection of user data. In order to better understand the complex interrelationships among privacy, standards, and interoperability in cybersecurity, this article explains their definitions, significance, difficulties, and advantages.

OBJECTIVES: The purpose of this article is to examine the relationship between privacy, standards, and interoperability in cybersecurity, with a focus on how these factors might improve cybersecurity policy and protect user privacy.

METHODS: This paper thoroughly examines privacy, standards, and interoperability in cybersecurity using methods from social network analysis. It combines current concepts and literature to reveal the complex processes at work.

RESULTS: The results highlight how important interoperability and standardization are to bolstering cybersecurity defences and preserving user privacy. Effective communication and cooperation across a variety of technologies are facilitated by adherence to standards and compatible systems.

CONCLUSION: Strong cybersecurity plans must prioritize interoperability and standardization. These steps strengthen resilience and promote coordinated incident response, which is especially important for industries like healthcare that depend on defined procedures to maintain operational security.

Sentinel Shield: Leveraging ConvLSTM and Elephant Herd Optimization for Advanced Network Intrusion Detection

2024-04-11T10:45:45+00:00

Given the escalating intricacy of network environments and the rising level of sophistication in cyber threats, there is an urgent requirement for resilient and effective network intrusion detection systems (NIDS). This document presents an innovative NIDS approach that utilizes Convolutional Long Short-Term Memory (ConvLSTM) networks and Elephant Herd Optimization (EHO) to achieve precise and timely intrusion detection. Our proposed model combines the strengths of ConvLSTM, which can effectively capture spatiotemporal dependencies in network traffic data, and EHO, which allow the model to focus on relevant information while filtering out noise. To achieve this, we first preprocess network traffic data into sequential form and use ConvLSTM layers to learn both spatial and temporal features. Subsequently, we introduce Elephant Herd Optimization that dynamically assigns different weights to different parts of the input data, emphasizing the regions most likely to contain malicious activity. To evaluate the effectiveness of our approach, we conducted extensive experiments on publicly available network intrusion CICIDS2017 Dataset. The experimental results demonstrate the efficacy of the proposed approach (Accuracy = 99.98%), underscoring its potential to revolutionize modern network intrusion detection and proactively safeguard digital assets.

A New Hybrid COA-OOA Based Task Scheduling and Fuzzy Logic Approach to Increase Fault Tolerance in Cloud Computing

2024-05-16T10:27:20+00:00

INTRODUCTION: Technology is made available to customers worldwide through a distributed computing architecture called cloud computing. In the cloud paradigm, there is a risk of single-point failures, in order to prevent errors and gain confidence from consumers in their cloud services, one problem facing cloud providers is efficiently scheduling tasks.

OBJECTIVES: High availability and fault tolerance must be offered to clients by these services. Fuzzy logic and hybrid COA-OOA are used in this study proposed fault-tolerant work scheduling algorithm. Jobs given by users and virtual machines are considered as input for this proposed approach.

METHODS: The given tasks are initially scheduled utilizing the FIFO order. Then, it is rescheduled utilizing the Hybrid Coati Optimization Algorithm (COA) - Osprey Optimization Algorithm (OOA) for scheduling the task based on priority.

RESULTS: This scheduled job is assigned to the VM for further execution. If the jobs are not executed successfully, then fault tolerant mechanism is carried out. Faults are recognized by employing fuzzy logic in this proposed approach. CONCLUSION: This proposed approach attains 62 sec response time, 61 sec of makespan and 98% success rate. Thus, this proposed approach is the best choice for efficient task scheduling with fault tolerant mechanism.

Comprehensive Review of Advanced Machine Learning Techniques for Detecting and Mitigating Zero-Day Exploits

2024-05-19T00:59:54+00:00

This paper provides an in-depth examination of the latest machine learning (ML) methodologies applied to the detection and mitigation of zero-day exploits, which represent a critical vulnerability in cybersecurity. We discuss the evolution of machine learning techniques from basic statistical models to sophisticated deep learning frameworks and evaluate their effectiveness in identifying and addressing zero-day threats. The integration of ML with other cybersecurity mechanisms to develop adaptive, robust defense systems is also explored, alongside challenges such as data scarcity, false positives, and the constant arms race against cyber attackers. Special attention is given to innovative strategies that enhance real-time response and prediction capabilities. This review aims to synthesize current trends and anticipate future developments in machine learning technologies to better equip researchers, cybersecurity professionals, and policymakers in their ongoing battle against zero-day exploits.

Blockchain based Quantum Resistant Signature Algorithm for Data Integrity Verification in Cloud and Internet of Everything

2024-03-20T15:28:04+00:00

INTRODUCTION: The processing and storage capacities of the Internet of Everything (IoE) platform are restricted, but the cloud can readily provide efficient computing resources and scalable storage. The Internet of Everything (IoE) has expanded its capabilities recently by employing cloud resources in multiple ways. Cloud service providers (CSP) offer storage resources where extra data can be stored. These methods can be used to store user data over the CSP while maintaining data integrity and security. The secure storage of data is jeopardized by concerns like malicious system damage, even though the CSP's storage devices are highly centralized. Substantial security advancements have been made recently as a result of using blockchain technology to protect data transported to networks. In addition, the system's inclusive efficacy is enhanced, which lowers costs in comparison to earlier systems.

OBJECTIVES: The main objective of the study is to a blockchain-based data integrity verification scheme is presented to provide greater scalability and utilization of cloud resources while preventing data from entering the cloud from being corrupted.

METHODS: In this paper, we propose a novel method of implementing blockchain in order to enhance the security of data stores in cloud.

RESULTS: The simulations indicate that the proposed approach is more effective in terms of data security and data integrity. Furthermore, the comparative investigation demonstrated that the purported methodology is far more effective and competent than prevailing methodologies.

CONCLUSIONS: The model evaluations demonstrated that the proposed approach is quite effective in data security.

Truculent Post Analysis for Hindi Text

2024-04-04T14:51:36+00:00

INTRODUCTION: With the rise of social media platforms, the prevalence of truculent posts has become a major concern. These posts, which exhibit anger, aggression, or rudeness, not only foster a hostile environment but also have the potential to stir up harm and violence.

OBJECTIVES: It is essential to create efficient algorithms for detecting virulent posts so that they can recognise and delete such content from social media sites automatically. In order to improve accuracy and efficiency, this study evaluates the state-of-the-art in truculent post detection techniques and suggests a unique method that combines deep learning and natural language processing. The major goal of the proposed methodology is to successfully regulate hostile social media posts by keeping an eye on them.

METHODS: In order to effectively identify the class labels and create a deep-learning method, we concentrated on comprehending the negation words, sarcasm, and irony using the LSTM model. We used multilingual BERT to produce precise word embedding and deliver semantic data. The phrases were also thoroughly tokenized, taking into consideration the Hindi language, thanks to the assistance of the Indic NLP library.

RESULTS: The F1 scores for the various classes are given in the "Proposed approach” as follows: 84.22 for non-hostile, 49.26 for hostile, 68.69 for hatred, 49.81 for fake, and 39.92 for offensive

CONCLUSION: We focused on understanding the negation words, sarcasm and irony using the LSTM model, to classify the class labels accurately and build a deep-learning strategy.

Machine learning as a teaching strategy education: A review

2024-04-09T13:27:04+00:00

In this article, we present a systematic review of the literature that explores the impact of Machine Learning as a teaching strategy in the educational field. Machine Learning, a branch of artificial intelligence, has gained relevance in teaching and learning due to its ability to personalize education and improve instructional effectiveness. The systematic review focuses on identifying studies investigating how Machine Learning has been used in educational settings. Through a thorough analysis, its impact on various areas related to teaching and learning, including student performance, knowledge retention, and curricular adaptability, is examined. The findings of this review indicate that Machine Learning has proven to be an effective strategy for tailoring instruction to individual student needs. As a result, engagement and academic performance are significantly improved. Furthermore, the review underscores the importance of future research. This future research will enable a deeper understanding of how Machine Learning can optimize education and address current challenges and emerging opportunities in this evolving field. This systematic review provides valuable information for educators, curriculum designers, and educational policymakers. It also emphasizes the continuing need to explore the potential of Machine Learning to enhance teaching and learning in the digital age of the 21st century.