Titlebook: Intelligent Systems; 11th Brazilian Confe João Carlos Xavier-Junior,Ricardo Araújo Rios Conference proceedings 2022 The Editor(s) (if appli

tattle

,Using BERT to Predict the Brazilian Stock Market,nt in news with the following approaches: (1) lexicons; or (2) machine learning algorithms. However, both strategies are subject to errors introduced by human factors. While the lexical approach needs a specific dictionary for the financial domain, algorithms based on machine learning need a databas

expeditious

,Human Action Recognition Based on 2D Poses and Skeleton Joints,e been studied and several researches have emerged using videos as objects of study. One of them is human action recognition, which seeks to identify in a given video what actions the people present in it are performing, whether for recreational purposes or for monitoring public places for people’s

机构

HALO

,When Less May Be More: Exploring Similarity to Improve Experience Replay,he total accumulated rewards in the long run. COMPER uses temporal difference learning with predicted target values for sets of similar transitions and a new experience replay approach based on two memories of transitions. We present an assessment of two possible neural network architectures for the

FLAX

,Human Identification Based on Gait and Soft Biometrics,en approached in many works over the last decades, that resulted in state-of-art methods based on biometric features such as fingerprint, iris and face. Despite the great development in this area, there are still many challenges to overcome, and this present work aims to present an approach to one o

alcohol-abuse

衰弱的心

,Combining Neural Networks and a Color Classifier for Fire Detection,ection can bring great improvements to security systems and prevent many losses. Effective fire detection systems help fire situations to have lesser consequences than they could have by signaling as quickly as possible the experts. This paper proposes a combination of modern image classification mo

表状态

反复拉紧

,A Probabilistically-Oriented Analysis of the Performance of ASR Systems for Brazilian Radios and TVin the last few years. Several state-of-art results were achieved by open-source end-to-end models, such as the Kaldi toolkit and the Wav2vec 2.0. Alternative commercial tools are also available, including the Google and Microsoft speech to text APIs and the Audimus System of VoiceInteraction. We an

直言不讳

,A Reward Function Using Image Processing for a Deep Reinforcement Learning Approach Applied to the ears. Most researches advocate for learning through high-dimensional sensory inputs (i.e. images) as observations in order to simulate scenarios that more closely approach reality. Though, when using these video game environments, the common practice is to provide the agent a reward signal calculate