Browsing by Author "Luiz, Luiz Eduardo"
Now showing 1 - 5 of 5
Results Per Page
Sort Options
- An AI-based object detection approach for robotic competitionsPublication . Pilarski, Leonardo; Luiz, Luiz Eduardo; Braun, João; Nakano, Alberto Yoshiro; Pinto, Vítor H.; Costa, Paulo Gomes da; Lima, JoséArtificial Intelligence has been introduced in many applications, namely in artificial vision-based systems with object detection tasks. This paper presents an object localization system with a motivation to use it in autonomous mobile robots at robotics competitions. The system aims to allow robots to accomplish their tasks more efficiently. Object detection is performed using a camera and artificial intelligence based on the YOLOv4 Tiny detection model. An algorithm was developed that uses the data from the system to estimate the parameters of location, distance, and orientation based on the pinhole camera model and trigonometric modelling. It can be used in smart identification procedures of objects. Practical tests and results are presented, constantly locating the objects and with errors between 0.16 and 3.8 cm, concluding that the object localization system is adequate for autonomous mobile robots.
- Development of a analog acquisition and conditioning circuit of surface electromyogram and electrocardiogram signalsPublication . Luiz, Luiz Eduardo; Teixeira, João Paulo; Coutinho, Fábio R.The use of wearable devices to monitor vital signs has become something usual, at the same time, here are an increasing demand in improving signal accuracy with a low power consumption. This work presents a conditioning circuit for electrocardiogram and surface electromyogram signals in a reliable way alongside filter and gain modules developed on the area of interest of such signals. At the end, the results obtained are presented, showing the conditioning capability of the circuit, leaving the proof of behaviour in real-life situations to be proven.
- ECG and sEMG Conditioning and Wireless Transmission with a Biosignal Acquisition BoardPublication . Luiz, Luiz Eduardo; Coutinho, Fábio R.; Teixeira, João PauloThe market for Wearable Health Monitoring Systems (WHMS) has grown together with the demand for devices that offer greater medical reliability and lower cost. This study introduces a wearable system comprising conditioning blocks for electrocardiogram and surface electromyogram signals, an analog-to-digital converter, and wireless data transmission capabilities. These features have been implemented reliably in accordance with the specific requirements of these signals, as well as complying with patient safety directives and ensuring the quality of the resulting signal, allowing it to be used as a data collector for subsequent software implementation. To evaluate its performance, this system is compared against commercially available wearable devices, and the expected outcomes are examined. The obtained results are then presented, showcasing the system’s capabilities and leading to a positive conclusion. As future work, there is a focus on enhancing the user interface and implement digital processing in the result for use in pathology recognition software with greater accuracy.
- History of Technological Evolution in the Brazilian Judiciary System and the Application of Artificial IntelligencePublication . Cabrera, Beatriz M.; Luiz, Luiz Eduardo; Cavalcante, Diogo L.; Teixeira, João PauloArtificial Intelligence systems have been increasingly developing, demonstrating new forms of implementation and utilization, being employed in many sectors. In this regard, aiming to keep up with social development and enhance the development of procedural acts, the Brazilian Judiciary System has been seeking to implement new forms of technology over the years. Although gradually, an evolution can be observed in the sector, such as options that circumvent the use of physical documents and a departure from conducting all acts in person. This has led to the implementation and development of Artificial Intelligence systems within the judiciary, aiming to further improve the Brazilian judicial system. Therefore, this present work seeks to provide a historical overview of the advancements that have occurred in the Brazilian Judiciary System regarding its technological evolution, describing the initial modifications as well as the current applications of Artificial Intelligence. Additionally, it presents their objectives and capabilities. Thus, in conclusion, this paper demonstrates that the progress made over the years is immeasurable, and the application of Artificial Intelligence systems in the Brazilian Judiciary System is already becoming consolidated, with the potential for even greater growth in the coming years.
- Is football unpredictable? Predicting matches using neural networksPublication . Luiz, Luiz Eduardo; Fialho, Gabriel Pinto; Teixeira, João PauloThe growing sports betting market works on the premise that sports are unpredictable, making it more likely to be wrong than right, as the user has to choose between win, draw, or lose. So could football, the world’s most popular sport, be predictable? This article studies this question using deep neural networks to predict the outcome of football matches using publicly available data. Data from 24,760 matches from 13 leagues over 2 to 10 years were used as input for the neural network and to generate a state-of-the-art validated feature, the pi-rating, and the parameters proposed in this work, such as relative attack, defence, and mid power. The data were pre-processed to improve the network’s interpretation and deal with missing or inconsistent data. With the validated pi-rating, data organisation methods were evaluated to find the most fitting option for this prediction system. The final network has four layers with 100, 80, 5, and 3 neurons, respectively, applying the dropout technique to reduce overfitting errors. The results showed that the most influential features are the proposed relative defending, playmaking, and midfield power, and the home team goal expectancy features, surpassing the pi-rating. Finally, the proposed model obtained an accuracy of 52.8% in 2589 matches, reaching 80.3% in specific situations. These results prove that football can be predictable and that some leagues are more predictable than others.