Loading...
2 results
Search Results
Now showing 1 - 2 of 2
- Stability and performance analysis of the Open Box Transport ProtocolPublication . Loureiro, Paulo; Monteiro, EdmundoIn this paper we study the stability of the Open Box Transport Protocol (OBP), an explicit congestion control protocol that provides information to the end systems about the current state of the network path. To support the study we deduced the OBP transfer function, which modulates the OBP behavior at equilibrium. In the stability evaluation we use Bode and Nyquist diagrams. The OBP stability characteristics, discussed in this work, are only related with the equilibrium phase, in other words when all the network capacity is in use. The results show that the OBP is stable for the tested scenarios and the transfer function does not have unstable poles. We also present an evaluation process that helps to identify the OBP performance. We show that the OBP reaches high utilization of the bottleneck channel and has fairness skills.
- Driving Behavior Classification Using a ConvLSTMPublication . Pingo, Alberto; Castro, João; Loureiro, Paulo; Mendes, Silvio; Bernardino, Anabela; Miragaia, Rolando; Husyeva, IrynaThis work explores the classification of driving behaviors using a hybrid deep learning model that combines Convolutional Neural Networks (CNNs) with Long Short-Term Memory (LSTM) networks (ConvLSTM). Sensor data are collected from a smartphone application and undergo a preprocessing pipeline, including data normalization, labeling, and feature extraction, to enhance the model’s performance. By capturing temporal and spatial dependencies within driving patterns, the proposed ConvLSTM model effectively differentiates between normal and aggressive driving behaviors. The model is trained and evaluated against traditional stacked LSTM and Bidirectional LSTM (BiLSTM) architectures, demonstrating superior accuracy and robustness. Experimental results confirm that the preprocessing techniques improve classification performance, ensuring high reliability in driving behavior recognition. The novelty of this work lies in a simple data preprocessing methodology combined with the specific application scenario. By enhancing data quality before feeding it into the AI model, we improve classification accuracy and robustness. The proposed framework not only optimizes model performance but also demonstrates practical feasibility, making it a strong candidate for real-world deployment.