The huge increase in information published on the web, and its users has led to the emergence of notifications systems (Web syndication), such as the Publish/Subscribe system (Pub/sub) that helps the user to track information managed by the information collectors (RSS (Really Simple Syndication)) in real time. For pertinent use of the information issue from large data streams (Big Data) that currently exist on the net, the development of new filtering systems is mandatory. Several algorithms have been developed to meet this end. In this work we propose a new algorithm for indexing structures that will allow us to develop efficient and intelligent systems.
The progress in information distribute on the network, and its users has drive to the evolution of notification systems (Web syndication), such as the Publish/Subscribe system (Pub/sub) that aid the user to trace information managed by the information collectors RSS1 in real time. For relevant use of the information issue from large data streams (Big Data) that currently exist on the net, the improvement of new filtering systems is necessary. Different algorithms have been developed to meet this end. In this work, we propose a new algorithm for indexing structures that will allow us to develop efficient systems.
1 November 2024 in Indonesian Journal of Electrical Engineering and Computer Science
In the domain of smart health devices, the accurate detection of physical indicators levels plays a crucial role in enhancing safety and well-being. This paper introduces a cross device federated learning framework using hybrid deep learning model. Specifically, the paper presents a comprehensive comparison of different combination of long short-term memory (LSTM), gated recurrent unit (GRU), convolutional neural network (CNN), random forest (RF), and extreme gradient boosting (XGBoost), in order to forecast stress levels by utilizing time series information derived from wearable smart gadgets. The LSTM-RF model demonstrated the highest level of accuracy, achieving 93.53% for user 1, 99.40% for user 2, and 97.88% for user 3. Similarly, the LSTM-XGBoost model yielded favorable outcomes, with accuracy rates of 85.88%, 98.55%, and 92.02% for users 1, 2, and 3, respectively. These findings highlight the efficacy of federated learning and the utilization of hybrid models in stress detection. Unlike traditional centralized learning paradigms, the presented federated approach ensures privacy preservation and reduces data transmission requirements by processing data locally on Edge devices.