Large language models (LLMs) are increasingly utilized for complex tasks requiring longer context lengths, with some models supporting up to 128K or 1M tokens. This trend, however, presents significant challenges in i...
详细信息
Student feedback improves the quality of the teaching and learning process. If the feedback is summarized, it is easier to understand. Despite the fact that many lecturers collect feedback from students, it is not sum...
详细信息
An efficient technique for preserving user privacy of users while publishing data is anonymization. Banks, Social Network service providers and hospitals are examples of data owners/stakeholders who anonymize their cu...
An efficient technique for preserving user privacy of users while publishing data is anonymization. Banks, Social Network service providers and hospitals are examples of data owners/stakeholders who anonymize their customers' data before releasing it in order to protect users' privacy. However, trustworthy information consumers still value anonymous data. Numerous anonymization models and techniques have been developed for releasing data while preserving user privacy. These models/algorithms de-identify user data, which is typically presented as graphs. Giving clear perspectives on the entire information privacy field, including recent anonymization research, tabular and SN data, is crucial. In this article, we proposed an approach for anonymization to address privacy issues in social networks specifically addressing semantic similarity attacks. Far as we are aware, our proposed technique is capable of resolving the issues of semantic similarity between sensitive attributes efficiently. The results of the proposed approach have been evaluated using the dataset of around 6000 users of a real-time social network viz. Twitter. Evaluation metrics of APL (Average Path Length) show that our technique can protect privacy and also maintain the utility of data while publishing it for public use.
Smart grid technology increases reliability, security, and efficiency of the electrical grids. However, its strong dependencies on digital communication technology bring up new vulnerabilities that need to be consider...
详细信息
The essence of this work presented is the conception and construction of a unique model. This model harnesses the power of Natural Language Processing (NLP) and Recurrent Neural Networks (RNN) to decipher the sentimen...
详细信息
Manufacturing lines are subject to continual change as components inevitably wear down over time, necessitating replacement. Often, the exact original parts may no longer be readily available, or an upgrade to integra...
Manufacturing lines are subject to continual change as components inevitably wear down over time, necessitating replacement. Often, the exact original parts may no longer be readily available, or an upgrade to integrate new technology becomes desirable. The crux of these scenarios lies in swiftly and seamlessly incorporating these changes, minimizing disruption to the existing processes. To address this, we put forward a concept utilizing a digital twin, complemented by an open-source industrial IoT framework. This combination facilitates both software and hardware loop integration, paving the way for efficient co-engineering development with existing legacy systems. Through this approach, we enable swift technological integration, keeping the manufacturing process agile and up-to-date.
On social media, words and phrases express people's opinions about companies, services, governments, and events. The objective of sentiment analysis in the discipline of natural language processing is to extract p...
详细信息
On social media, words and phrases express people's opinions about companies, services, governments, and events. The objective of sentiment analysis in the discipline of natural language processing is to extract positive or negative polarities from social media text. The exponential growth of demands for businesses and governments motivates academics to complete sentiment analysis study. For sentiment analysis, we have proposed various machine learning algorithms like Logistic Regression (LR), Support Vector Machine (SVM), K-Nearest Neighbor (K-NN) and ensemble learning like Random Forest (RF), Gradient Boosting (GB), Voting Classifier (VC), XGBoost Classifier (XGBC), ADABoost Classifier (ADABC), Bagging Classifier (BC). Then the accuracy of each algorithm is compared and the result was quite good with GB. The accuracy of 94.99% is obtained with gradient descent.
With computers' growth, network-based technology, including advanced communication features, Internet of Things (IoT), automation, and upcoming fifth generation (5G) mobile technology, network security has become ...
详细信息
ISBN:
(纸本)9781665435598
With computers' growth, network-based technology, including advanced communication features, Internet of Things (IoT), automation, and upcoming fifth generation (5G) mobile technology, network security has become challenging to secure applications, systems, and networks. Rapid increase of network devices has created many new attacks and therefore presented significant difficulties for network security to identify threats correctly. Intrusion detection systems (IDSs) guarantee the network's confidentiality, integrity, and availability by monitoring network traffic and blocking any potential intrusions. Despite significant research efforts, IDS still confronts many difficulties in increasing detection efficiency and decreasing false alarm rates. Intrusion detection systems are using machine learning and deep learning-based IDS to identify intrusions throughout the network as quickly as possible. This paper identifies the idea of IDS and the following details the taxonomy developed based on the prominent Machine Learning (ML) and Deep Learning (DL) methods used in NIDS system design. An in-dept. analysis of NIDS-based papers is discussed to outline the benefits and weaknesses of the various options. New technology, including ML and DL, and current advances in these NIDS technologies are described with the methodology, assessment metrics, and dataset selections. Through highlighting the existing research difficulties with the longterm scope of the NIDS study to improve machine learning and deep learning-based NIDS. Many novel techniques are using to deal with Intrusion detection systems. However, most are not quick enough to adapt to cyber security defense systems' dynamic and complex nature as the threats surface is growing exponentially with different devices' interfaces. This paper proposes a review of various Intrusion detection system (IDS) capabilities and assets using deep learning techniques. It also suggests a novel idea to automatically adapt the network intru
Past few years researchers have focused on using the attention and transformer model to access image insights and provide deep descriptions for an input image. Although these methods have shown greater improvementsove...
详细信息
ISBN:
(纸本)9798350333855
Past few years researchers have focused on using the attention and transformer model to access image insights and provide deep descriptions for an input image. Although these methods have shown greater improvementsover the regular methodology of using recurrent neural networks. But still, it is under the great influence of the gradient vanishing issue. Our way of tackling this issue is to minimize the use of gradient-intensive task and replace it with distance-mapping tasks. This means that our model predicts the output on the basis of “Euclidian Distance”. To accomplish this first we use pretrained neural network to extract features and then use K Nearest neighbor to cluster image with similar features together. Here the model is used to gather low level object information to generate relevant caption so that model can work on the top efficiency and also the generated caption is natural. To fulfill this requirement, we make use for our feature extractor model and clustering model to find the closest resembling image to our query image and return its most relevant captions
In the modern manufacturing industry, collaborative architectures are growing in popularity. We propose an Industry 5.0 value-driven manufacturing process automation ecosystem in which each edge automation system is b...
In the modern manufacturing industry, collaborative architectures are growing in popularity. We propose an Industry 5.0 value-driven manufacturing process automation ecosystem in which each edge automation system is based on a local cloud and has a service-oriented architecture. Additionally, we integrate cloud-based collaborative learning (CCL) across building energy management, logistic robot management, production line management, and human worker Aide local clouds to facilitate shared learning and collaborate in generating manufacturing workflows. Consequently, the workflow management system generates the most effective and Industry 5.0-driven workflow recipes. In addition to managing energy for a sustainable climate and executing a cost-effective, optimized, and resilient manufacturing process, this work ensures the well-being of human workers. This work has significant implications for future work, as the ecosystem can be deployed and tested for any industrial use case.
暂无评论