This paper proposes a novel approach for predicting serverless workloads using machine learning techniques. The research highlights the importance of accurate workload prediction in serverless computing and provides v...
详细信息
Collaborative filtering is a widely adopted technique in the field of recommender systems, aiming to predict users' preferences based on their historical interactions with items. Traditional collaborative filterin...
详细信息
ISBN:
(纸本)9798350348910
Collaborative filtering is a widely adopted technique in the field of recommender systems, aiming to predict users' preferences based on their historical interactions with items. Traditional collaborative filtering methods often face challenges when dealing with cross-domain recommendation scenarios, where user-item interactions are scattered across multiple domains and data sparsity is prevalent. This research paper proposes a novel Graph Neural Network (GNN) approach for Cross-Domain Collaborative Filtering Recommendations to address these issues. The proposed approach leverages the expressive power of GNNs to capture complex and non-linear patterns in user-item interactions while incorporating cross-domain knowledge. The proposed research paper models the recommendation system as a heterogeneous graph, where users and items are represented as nodes, and the interactions between users and items, as well as the relations between domains, are represented as edges. To train the GNN model, mean squared error loss function is used, which jointly optimizes for domain-specific recommendation performance while encouraging knowledge sharing across multiple domains. Experimental results demonstrate the supremacy of the GNN-based method compared to state-of-the-art collaborative filtering techniques, especially in situations where the cold start problem is a major concern. The GNN-based cross-domain collaborative filtering approach not only outperforms traditional collaborative filtering methods but also exhibits robustness in handling heterogeneous and sparse data across multiple domains. The ability to incorporate cross-domain knowledge makes the proposed model a valuable tool for building recommendation systems in complex and diverse environments. In conclusion, this research presents a comprehensive investigation of the application of Graph Neural Networks to cross-domain collaborative filtering recommendations. The results highlight the effectiveness and versatility of
Multilevel thresholding plays a crucial role in image processing, with extensive applications in object detection, machine vision, medical imaging, and traffic control systems. It entails the partitioning of an image ...
详细信息
This paper presents PhishURLDetect: a lightweight security framework for detecting phishing URLs based on fine-tuned Large Language Models (LLMs). It utilizes a proprietary corpus comprising 573,880 phishing and benig...
详细信息
This paper put forward an embedded scheme to execute image watermarking in light of the discrete wavelet transform (DWT), singular value decomposition (SVD) and Charge System Search (CSS) method. In the proposed schem...
详细信息
Aim: Recent advances in Artificial Intelligence (AI) and the addition of Deep Learning (DL) have made it possible to analyse both real-time and historical data from the Internet of Things (IoT). Recently, IoT technolo...
详细信息
Electroencephalography (EEG) signals are often utilized to study cognitive processes and brain diseases. The non-stationary and non-linear nature of EEG signals makes their analysis difficult. A deep learning framewor...
详细信息
The advent of the Internet of Things (IoT) has transformed the way devices communicate, with an ever-increasing need for seamless interoperability and energy-efficient communication. This paper presents a unified omni...
详细信息
The adoption of Hypertext Transfer Protocol v3 (HTTP/3 or H3) is on the rise. In this context, we analyze the security vulnerabilities of H3, specifically with the QUIC protocol, and the associated challenges they pos...
详细信息
The Internet of Things(IoT)has been growing over the past few years due to its flexibility and ease of use in real-time *** IoT's foremost task is ensuring that there is proper communication among different types ...
详细信息
The Internet of Things(IoT)has been growing over the past few years due to its flexibility and ease of use in real-time *** IoT's foremost task is ensuring that there is proper communication among different types of applications and devices,and that the application layer protocols fulfill this ***,as the number of applications grows,it is necessary to modify or enhance the application layer protocols according to specific IoT applications,allowing specific issues to be addressed,such as dynamic adaption to network conditions and ***,several IoT application layer protocols have been enhanced and modified according to application ***,no existing survey articles focus on these *** this article,we survey traditional and recent advances in IoT application layer protocols,as well as relevant real-time applications and their adapted application layer protocols for improving *** changing the nature of protocols for each application is unrealistic,machine learning offers means of making protocols intelligent and is able to adapt *** this context,we focus on providing open challenges to drive IoT application layer protocols in such a direction.
暂无评论