A major challenge in detecting anomalies in dataset is the need for labeled data to train and validate models. In this paper, we analyze a novel approach that use the Long Short-Term Memory (LSTM) to identify attacks in an imbalanced dataset. Importantly, our models are trained exclusively on examples from the normal class. The LSTM is specifically trained to recognize the typical traffic patterns in normal data and to create a compressed representation of the input data. With a focus on real-time detection, this paper illuminates the path to a new era of proactive network security, where dynamic, context-aware anomaly detection stands as the vanguard against the ever-evolving landscape of cyberattacks. With a commitment to achieving more than 99

Sentiment analysis (SA) identifies sentiments in text, reviews, tweets, audio, images, and videos. Sentiment integrates emotion and thinking, with emotions being temporary while sentiments last longer. Emotion recognition and sentiment polarity analysis are gaining popularity in natural language processing due to their ability to mine social media data. This study applies machine learning (ML) classifiers such as random forest, logistic regression, support vector machine, and decision tree to classify text and speech as positive, negative, or neutral. Additionally, it explores available sentiment analysis tools and introduces the audio text emotion and sentiment analyser (ATESA). ATESA leverages ensemble-oriented classification techniques using deep learning, specifically bidirectional long-short-term memory recurrent neural networks (Bi-LSTM-RNN). It processes text, Twitter data, and speech converted into text. Experimental results show that ATESA achieves 92% accuracy, outperforming other algorithms.

The Pending Interest Table (PIT) in Named Data Networking (NDN) plays a crucial role by storing state information of requests within the router, enabling efficient data packet routing back to the requester. However, this mechanism is vulnerable to Interest Flooding Attacks (IFA), where an attacker sends a large number of malicious requests to overwhelm the PIT, disrupting network performance. Previous research primarily focused on offline detection of IFA using selected features and machine learning techniques. In this work, we build on these findings by deploying a trained Artificial Neural Network (ANN) classifier on each NDN router for real-time, online detection of IFA. Additionally, we introduce a novel traceback-based mitigation strategy activated upon detection, significantly improving the network’s resilience against such attacks. Our proposed method demonstrates superior performance in terms of satisfaction ratio and throughput for legitimate consumers compared to existing approach.

This research paper explores the transformative potential of integrating Internet of Things (IoT) devices into smart home technologies, ushering in a new era of energy-efficient living. Focusing on energy optimization, the paper examines the intricate network of interconnected devices shaping efficient residential ecosystems. Beginning with an investigates specific devices such as smart thermostats and intelligent lighting systems. Through meticulous analysis of user behavior, it unveils how these devices influence and mold household energy consumption. Spotlighting data analytics, the paper reveals the power of information processing for personalized, efficient energy management. Addressing challenges like privacy and interoperability, it proposes innovative solutions for seamless IoT integration. The research concludes with an environmental assessment, emphasizing the symbiotic relationship between IoT and smart homes in fostering a sustainable and eco-friendly future.

Network security plays an important role in an increasingly related society. For the safety and security of information system, detection of network traffic attacks is crucial. This research work focuses on the use of Support Vector Machines (SVM) algorithm as a machine learning tool for the detection of network traffic attacks. SVM is a flexible and adaptable classification algorithm that has shown its fruitfulness in multiple domains, including network security. This paper elaborates the utilization of SVM to observe between normal and malicious network traffic patterns. In this paper, we prepare multiple categories of network attacks, such as Denial-of-Service (DoS), User-to-Root (U2R), and Remote-to-Local (R2L) attacks. For training and evaluation purpose, KDD Cup 99 dataset is used. Several number of performance metrics, like accuracy, precision, recall, as well as F1-score, are also used to evaluate the correctness of the SVM-based intrusion detection system. The results illustrate the capability of SVM in detection of network traffic, attaining high accuracy rates while accurately solving the issues of complex attack patterns where the F1-Score for the Linear kernal and RBF 96.65 and 99.24 respectively. In addition to this, the research also highlights the significance of feature engineering along with hyperparameter engaged in develop SVM models for specified network security. In the end, this study highlights the usefulness of SVM as an essential tool in network security to identify network traffic attacks.

Blockchain technology stands as a revolutionary force poised to reshape numerous sectors, including finance, supply chain management, healthcare, and beyond. Within the sphere of micro-economies, where conventional financial infrastructures often falter, blockchain emerges as a beacon of promise. This paper delves into the transformative potential of blockchain in empowering micro-economies, offering insights into its decentralized solutions and their capacity to uplift individuals and communities at the grassroots level. Through the examination of case studies and existing literature, this abstract elucidates the benefits, challenges, and future prospects of blockchain technology in fostering inclusive economic growth and fostering financial independence for marginalized communities.

Recently, technology like Blockchain is gaining attention all over the world today, because it provides a secure, decentralized framework for all types of commercial interactions. When choosing the optimal blockchain platform, one needs to consider its usefulness, adaptability, and compatibility with existing software. Because novice software engineers and developers are not experts in every discipline, they should seek advice from outside experts or educate themselves. As the number of decision-makers, choices, and criteria grows, the decision-making process becomes increasingly complicated. The success of Bitcoin has spiked the demand for blockchain-based solutions in different domains in the sector such as health, education, energy, etc. Organizations, researchers, government bodies, etc. are moving towards more secure and accountable technology to build trust and reliability. In this paper, we introduce a model for the prediction of blockchain development platforms (Hyperledger, Ethereum, Corda, Stellar, Bitcoin, etc.). The proposed work utilizes multiple data sets based on blockchain development platforms and applies various traditional Machine Learning classification techniques. The obtained results show that models like Decision Tree and Random Forest have outperformed other traditional classification models concerning multiple data sets with 100

With the expansion of network traffic and the increasing experiences of cyber threats, the need for flexible as well as systematic network traffic attack detection systems has become foremost. Conventional signature-based methods often struggle to identify novel or previously unknown attacks, making it essential to explore alternative techniques for enhancing network security. This research presents a novel approach for enhancing network traffic attack detection using K-means clustering, a popular unsupervised machine learning algorithm. The proposed system employs K-means clustering to group network traffic data into clusters based on their similarity. By identifying anomalous patterns within these clusters, the system can effectively detect network attacks. The approach is evaluated using a real-world network traffic dataset, and the results demonstrate its effectiveness in improving the accuracy and efficiency of attack detection. Additionally, the approach shows promise in the detection of zero-day attacks, thus enhancing network security in the face of evolving threats. This research contributes to the field of network security by offering a data-driven and proactive approach to attack detection that can adapt to emerging threats and minimize false positives.

Network traffic analysis plays a crucial role in detecting and mitigating security threats in modern computer networks. In this study, we employ machine learning techniques, specifically Gradient Boosting, Linear Discriminant Analysis (LDA), and Support Vector Machines (SVMs), to analyze network traffic data from the KDD Cup dataset. The KDD Cup dataset contains a large volume of network traffic data, including various features such as duration, protocol type, service, and flag, among others. We first preprocess the dataset by removing redundant rows and converting categorical variables to factors. We then split the dataset into training and testing sets and perform feature scaling to ensure uniformity across features. For our analysis, we utilize Gradient Boosting, a powerful ensemble learning technique, to iteratively train weak learners to correct the errors of the previous models. Additionally, we employ Linear Discriminant Analysis to find the linear combination of features that best separates the classes, and SVMs with both linear and Radial Basis Function (RBF) kernels for classification. We evaluate the performance of each model using standard metrics such as accuracy, precision, recall, and F1-score. Furthermore, we visualize the loss percentage over iterations for Gradient Boosting to gain insights into the optimization process. Our results demonstrate the effectiveness of Gradient Boosting, LDA, and SVMs in accurately classifying network traffic instances. The models show promising performance in distinguishing between normal and malicious network activity, highlighting their potential for enhancing network security in real-world applications.

In the realm of Convolutional Image Transformation Networks (CITN), this study addresses the critical need for robust anomaly detection. The motivation stems from the escalating importance of reliable image classification models in various domains, where identifying anomalies is paramount. Grounded in this context, our hypothesis posits that an enhanced convolutional network can effectively discern anomalies within images. Leveraging innovative methods, we augment traditional Convolutional Neural Networks with specialized transformation techniques. Through extensive experimentation and evaluation, our results demonstrate the model’s superior performance in detecting anomalies, surpassing existing benchmarks. This research contributes a novel approach to bolstering image transformation networks for anomaly detection, offering valuable insights for applications in diverse fields. In conclusion, the proposed methodology showcases promising strides in advancing the capabilities of CITN for heightened anomaly detection accuracy.

Today, technology has become a basic necessity for every individual in society. There were times when the internet was used only to send digital mail. We never imagined that technology would be at the tip of our fingers someday, with no long queues and no waiting times. The solution is just a few clicks away on your smartphone. The COVID-19 pandemic outbreak pushed many services online, and the need for an online voting mechanism became the need of the hour. Blockchain innovation is an approach to putting away information that makes it troublesome or difficult to change, switch, or delude the system. It eliminates the need for third-party approval by making the transaction between two parties. The existing electronic voting (e-voting) system failed to build trust among voters due to several security vulnerabilities. We offer a different model that addresses the shortcomings of both the electronic and traditional voting systems with the use of blockchain technology. It will make the voting mechanism more secure and impenetrable to tampering. In this article, we provide an improved environment for unbiased voting. The Ethereum platform is utilized along with Ganache and Metamask to set up a local blockchain network and transaction records.

According to today’s social environment, implementing a secure digital system is a challenging task; a traditional voting system (i.e., ballot system) does not offer ambiguity regarding the counting of electoral votes. Voting frauds may fail because of many reasons like pooling booth fraud, and fake voter IDs, so to solve this problem, we need a secured digital voting system, and the best solution implemented is Blockchain. This technique conquers all the problems of the traditional voting system. And this technology is used to provide a highly secure, decentralized, and provide P2P network to verify, process, and record all persons. This opens all possibilities to construct a secure network as well as a decentralized system that does not need third-party involvement. To the best of our knowledge, this is the first attempt to implement blockchain NEAR protocol for digital voting systems. In this paper, our main aim is to build a secure digital voting system based on this blockchain protocol which offers the privacy of a person, security, flexibility, and fairness of the current voting scheme. It also decreases the cost of hosting a countrywide election.

Predicting Bitcoin price is a universal research area as it attains significance in predicting the market way of its rate so that, investors could procure profits. Concurrently, with the evolution of Machine Learning (ML), researchers attempted to use ML based algorithms for forecasting the Bitcoin price. However, these researches have resulted in inefficient prediction due to error rate. For alleviating such pitfalls, this study intends to forecast the Bitcoin price by comparing its deviations pre and post Covid using suitable ML algorithms. To achieve this, the study proposes Auto Regressive Integrated Moving Average (ARIMA) with Optimized Genetic Algorithm (OGA). In this case, ARIMA model is considered as it possess the innate ability in capturing standard temporal reliances which is distinct to time-series data. Further, hyperparameters are selected by GA based on the fitness function. Based on this, hyperparameter tuning is performed which assist to improvise the model performance. For determining if there exists any deviations in Bitcoin price (pre and post Covid), Augmented Dickey Fuller (ADF) test is considered. Further, comparative analysis is regarded in accordance with performance metrics to validate the performance of the proposed system which proves its effectiveness in predicting Bitcoin price.

Artificial intelligence and Blockchain are two of the most important forces driving innovation today. At the point when Blockchain and AI join their assets, this gives a more significant investigation of the viability of the details of the agreement, and the work processes it manages. Consequently, the requirement for human investigation, intercession and check, is enormously diminished. Man-made intelligence alludes to the capacity of machines to grasp, think, and learn likewise to people, demonstrating the chance of utilizing PCs to mimic human knowledge. A smart contract is computer code running on a blockchain that contains a set of norms by which the smart contract’s parties’ consent to communication between one another. Examining AI integration with smart contracts that are enabled by blockchain in the enhancing finance system operations is the main objective of this endeavor. AI is added to well-established smart contracts, their efficiency increases exponentially. This article presumes that AI and blockchain enabled smart contract will have an enormous effect in future for Finance industry and Digital trading.

SDN has dramatically changed the landscape of the current network paradigm by regulating the network through software in the control plane, called a controller. However, owing to scalability issues in WAN, multiple controllers are deployed for better management of the network. In this paper, we first design the mathematical model for the Controller Placement Problem (CPP) and Reliable CPP (RCPP). While solving CPP and RCPP, we are trying to minimize the total average latency and take the capacity of the controller, and load on the switch as constraints. Afterward, we simulated our proposed approach Varna Based Optimization (VBO), and compared it with other traditional population-based heuristic algorithms such as PSO, TLBO, Jaya, BOA, and WOA. It has been observed and found that VBO provides better results in comparison to others in most of the cases. In order to establish the validity of simulation results, we have deployed the results obtained from simulation over a real and operational emulation-based setup created via ONOS controller and mininet. The emulation results exhibit the same behaviour as simulation.