Silvio Priem-Mendes

This work presents a data-driven framework for early detection of polymer melt instability in industrial injection moulding using Long Short-Term Memory (LSTM) time-series models. The study uses six months of continuous production data comprising approximately 280,000 injection cycles collected from a fully operational thermoplastic injection line. Because melt behaviour evolves gradually and conventional threshold-based monitoring often fails to capture these transitions, the proposed approach models temporal patterns in torque, pressure, temperature, and rheology to identify drift conditions that precede quality degradation. A physically informed labelling strategy enables supervised learning even with sparse defect annotations by defining volatile zones as short time windows preceding operator-identified non-conforming parts, allowing the model to recognise instability windows minutes before defects emerge. The framework is designed for deployment on standard machine signals without requiring additional sensors, supporting proactive process adjustments, improved stability, and reduced scrap in injection moulding environments. These findings demonstrate the potential of temporal deep-learning models to enhance real-time monitoring and contribute to more robust and adaptive manufacturing operations.

The increasing concern for road safety has driven the development of advanced driver behavior analysis systems. This study presents a comprehensive review of various techniques to detect unsafe driving behaviors, with a particular emphasis on using smartphone sensors. By leveraging data from accelerometers, gyroscopes, and GPS, these methods allow for the detection of aggressive driving patterns, which may result from factors such as driver distraction or drowsiness. Modern sensor technology plays a crucial role in real-time monitoring and has significant potential to enhance vehicle safety systems. A Long Short-Term Memory (LSTM) network combined with a Conv1D layer was trained to analyze driving patterns using a sliding window technique. As technology continues evolving, its application in driver behavior analysis holds great promise for reducing traffic accidents and improving driving habits. Furthermore, the ability to gather and analyze large amounts of data from drivers in various conditions opens new opportunities for more personalized and adaptive safety solutions. This research offers insights into the future direction of driver monitoring systems and the growing impact of mobile and sensor-based solutions in transportation safety.

This 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.

Human errors are probably the main cause of car accidents, and this type of vehicle is one of the most dangerous forms of transport for people. The danger comes from the fact that on public roads there are simultaneously different types of actors (drivers, pedestrians or cyclists) and many objects that change their position over time, making difficult to predict their immediate movements. The intelligent transport system (ITS-G5) standard specifies the European communication technologies and protocols to assist public road users, providing them with relevant information. The scientific community is developing ITS-G5 applications for various purposes, among which is the increasing of pedestrian safety. This paper describes the developed work to implement an ITS-G5 prototype that aims at the increasing of pedestrian and driver safety in the vicinity of a pedestrian crosswalk by sending ITS-G5 decentralized environmental notification messages (DENM) to the vehicles. These messages are analyzed, and if they are relevant, they are presented to the driver through a car’s onboard infotainment system. This alert allows the driver to take safety precautions to prevent accidents. The implemented prototype was tested in a controlled environment pedestrian crosswalk. The results showed the capacity of the prototype for detecting pedestrians, suitable message sending, the reception and processing on a vehicle onboard unit (OBU) module and its presentation on the car onboard infotainment system.

Determining the indoor location is usually performed by using several sensors. Some of these sensors are fixed to a known location and either transmit or receive information that allows other sensors to estimate their own locations. The estimation of the location can use information such as the time-of-arrival of the transmitted signals, or the received signal strength, among others. Major problems of indoor location include the interferences caused by the many obstacles in such cases, causing among others the signal multipath problem and the variation of the signal strength due to the many transmission media in the path from the emitter to the receiver. In this paper, the creation and usage of perfect sequences that eliminate the signal multipath problem are presented. It also shows the influence of the positioning of the fixed sensors to the precision of the location estimation. Finally, genetic algorithms were used for searching the optimal location of these fixed sensors, therefore minimizing the location estimation error.

The radio network design (RND) is an NP-hard optimization problem which consists of the maximization of the coverage of a given area while minimizing the base station deployment. Solving RND problems efficiently is relevant to many fields of application and has a direct impact in the engineering, telecommunication, scientific, and industrial areas. Numerous works can be found in the literature dealing with the RND problem, although they all suffer from the same shortfall: a noncomparable efficiency. Therefore, the aim of this paper is twofold: first, to offer a reliable RND comparison base reference in order to cover a wide algorithmic spectrum, and, second, to offer a comprehensible insight into accurate comparisons of efficiency, reliability, and swiftness of the different techniques applied to solve the RND problem. In order to achieve the first aim we propose a canonical RND problem formulation driven by two main directives: technology independence and a normalized comparison criterion. Following this, we have included an exhaustive behavior comparison between 14 different techniques. Finally, this paper indicates algorithmic trends and different patterns that can be observed through this analysis.