HCovBi-Caps: Hate Speech Detection Using Convolutional and Bi-Directional Gated Recurrent Unit With Capsule Network

Khan, Shakir; Kamal, Ashraf; Fazil, Mohd; Alshara, Mohammed Ali; Sejwal, Vineet Kumar; Alotaibi, Reemiah Muneer; Baig, Abdul Rauf; Alqahtani, Salihah

doi:10.1109/access.2022.3143799

Cited by 58 publications

(18 citation statements)

References 40 publications

(51 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Experimental data show that the FHAN way in this paper has better performance in stock price prediction than other neural network models and LSTM-attention [18]. References [19,20] presented a novel Convolutional, BiGRU, and Capsule network-based deep learning model, HCovBi-Caps, to classify the hate speech, and multichannel CNN modeling is discussed in [21][22][23] and a new multichannel convolution neural network (MCCNN) model is proposed for extracting the relationship.…”

Section: Introductionmentioning

confidence: 93%

Multilayer Graph-Based Deep Learning Approach for Stock Price Prediction

Alshara

2022

Security and Communication Networks

View full text Add to dashboard Cite

Although a strategy for predicting stock prices using relational data has been described recently, no practical way for selecting aggregating various forms of relational data to forecast stock prices has been discovered. The authors present an upgraded multilayer node graph attention network (FHAN) model that incorporates the Fraudar algorithm and provides insight into the interaction between several items. The model, which regards businesses as nodes and interactions as edges, aggregates data from various connection types and adds it to each company’s node representation, which is then automatically fed into the task-specific layer select information. The testing findings indicate that this approach is more accurate in stock price prediction than the currently popular neural network methodology. The experiment compares several distinct neural network algorithms. This approach is more accurate than the previous method when ideal parameters are used. The average rise is around 4%, while the largest increase is 24%.

show abstract

Section: Introductionmentioning

confidence: 93%

Multilayer Graph-Based Deep Learning Approach for Stock Price Prediction

Alshara

2022

Security and Communication Networks

View full text Add to dashboard Cite

show abstract

“…Deep learning, according to [12], was instrumental in the discovery of architectures like the Hierarchical Computing Architecture (HiCH), which, when combined with algorithms like Internet of Things, convolutional neural network (CNN) [13,14], will lead to the development of wireless body area networks (WBAN) for wearable devices. A variety of machine learning algorithms, including KNN ,EM, C5.0, C4.5 and, are used to enhance AI by lling in missing data and building decision trees.…”

Section: Literature Surveymentioning

confidence: 99%

Blockchain Technologies in Healthcare System for Real Time Applications Using IoT and Deep Learning Techniques

Khan

Siddiqui

Albahlal

et al. 2023

Preprint

View full text Add to dashboard Cite

Data transparency, flexible access, immutability, privacy, audit, traceability, data provenance, trust, and security are fundamental issues for modern healthcare data management systems. As a promising new technology, block chain has the potential to enhance healthcare data management functions by boosting data efficiency and guaranteeing trust. The present research looked into the benefits of block chain technology in healthcare and the challenges that have prevented its widespread implementation so far. Healthcare organisations around the world are using a variety of methods to modernise into more effective, coordinated and user-cantered structures. There is an increase in both human effort and security risks when dealing with massive amounts of data, such as reports and images for each individual. Internet of Things (IoT) solutions in healthcare aim to address these problems by enhancing patient care while reducing costs through more effective use of healthcare resources. However, many different types of intrusion can pose serious risks to IoT devices. In some cases, doctors will insist that their patients use only certain labs or pharmacies, regardless of the quality of the services they provide, simply to increase the doctor's bottom line. Because of this, protecting data is essential when discussing the Internet of Things. To solve these problems, Blockchain technology has emerged as the most reliable method for protecting the privacy of control systems in real time. In this paper, we will introduce a CNN-based healthcare data security framework using the blockchain technique by generating the hash of each data point, which will alert all users of the blockchain network to any unauthorised changes to data or breaches in the supply of medicines.

show abstract

“…However, the limitation of their work is that they did not explore more advanced BERT architectures such as robustly optimized BERT pretraining approach (RoBERTa), which has the potential to bolster performance further. Shakir et al 21 has developed an architecture consisting of bidirectional gated recurrent units (BiGRU), which is followed by a convolutional layer and a capsule network. A capsule network helps to incorporate contextual information at different orientations for hate speech detection.…”

Section: Related Workmentioning

confidence: 99%

MetaHate: AI‐based hate speech detection for secured online gaming in metaverse using blockchain

Sanghvi,

Bhavsar,

Hundlani

et al. 2023

Security and Privacy

View full text Add to dashboard Cite

The emergence of Web 3.0, blockchain technology (BC), and artificial intelligence (AI) are transforming multiplayer online gaming in the metaverse. This development has its concerns about safety and inclusivity. Hate speech, in particular, poses a significant threat to the harmony of these online communities. Traditional moderation methods struggle to cope with the immense volume of user‐generated content, necessitating innovative solutions. This article proposes a novel framework, MetaHate, that employs AI and BC to detect and combat hate speech in online gaming environments within the metaverse. Various machine learning (ML) models are applied to analyze Hindi–English code mixed datasets, with gradient boosting proving the most effective, achieving 86.01% accuracy. AI algorithms are instrumental in identifying harmful language patterns, while BC technology ensures transparency and user accountability. Moreover, a BC‐based smart contract is proposed to support the moderation of hate speech in the game chat. Integrating AI and BC can significantly enhance the safety and inclusivity of the metaverse, underscoring the importance of these technologies in the ongoing battle against hate speech and in bolstering user engagement. This research emphasizes the potential of AI and BC synergy in creating a safer metaverse, highlighting the need for continuous refinement and deployment of these technologies.

show abstract

HCovBi-Caps: Hate Speech Detection Using Convolutional and Bi-Directional Gated Recurrent Unit With Capsule Network

Cited by 58 publications

References 40 publications

Multilayer Graph-Based Deep Learning Approach for Stock Price Prediction

Multilayer Graph-Based Deep Learning Approach for Stock Price Prediction

Blockchain Technologies in Healthcare System for Real Time Applications Using IoT and Deep Learning Techniques

MetaHate: AI‐based hate speech detection for secured online gaming in metaverse using blockchain

Contact Info

Product

Resources

About