Abstract Violence recognition is challenging because it can be presented in very different forms. For example, it can be present in an image by a person hitting another person or present in audio by a person being rude to another. Thus, audio and video are essential features to be analysed. In the audio approach, speech processing, music, and ambient sound are some of the main points of this problem since finding similarities and differences between these domains is necessary. Human activity can be classified into four different categories in the video approach, depending on the complexity and the number of body parts involved in the action. Examples of Human activity categories are considered: gestures, actions, interactions and activities. Recognizing human actions in the video becomes a challenge with this varied set of human activities. Furthermore, in the last years, the growth of deep learning techniques applied to this area has been enormous, and the reason is that their results surpass traditional signal processing on a large scale. This article is based on audio and video signals inside a vehicle to detect violence. Furthermore, the architecture used was ResNet model with Mel‐spectrogram methodology for audio signals. The proposed method for video signal representation was RGB, which applied four different models: C2D, I3D, X3D, and Flow‐Gated. Finally, multimodal fusion was applied at the end of the process.

Inductive transfer learning is widespread in computer vision applications. However, in natural language processing (NLP) applications is still an under-explored area. The most common transfer learning method in NLP is the use of pre-trained word embeddings. The Universal Language Model Fine-Tuning (ULMFiT) is a recent approach which proposes to train a language model and transfer its knowledge to a final classifier. During the classification step, ULMFiT uses a max and average pooling layer to select the useful information of an embedding sequence. We propose to replace max and average pooling layers with a soft attention mechanism. The goal is to learn the most important information of the embedding sequence rather than assuming that they are max and average values. We evaluate the proposed approach in six datasets and achieve the best performance in all of them against literature approaches.

This work investigates the use of Multi-layered Perceptron Networks (MLP) for attack detection, using the Arduino embedded system as a case study. This paper also investigates techniques to reduce the computational cost of ANN (Artificial Neural Networks), taking into account the low cost and low consumption requirements in order to ensure the feasibility of its implementation. As a result, we evaluated the MLP networks using metrics such as accuracy, precision, and coverage, as well as the classifier performance running on Arduino through time measurements (microseconds).

The development of mobile applications focused on user's health monitoring is a recent trend. Over time, people expect applications that provide even more efficient and interactive services. In this paper, we propose a smart-health application to smartphones that evaluates the physical performance of a subject from the reading data such as the body mass index (BMI), daily steps and heart beats. Fuzzy logic and first-order logic are used to accomplish the task.

Computational efforts for Alternative and Augmented Communication (AAC) must deal with two important issues, that slow down their spread: (1) the need for specific hardware and software in order to engage each different disability and (2) the different communication languages. This paper presents the PickNClick, a hardware/software apparatus that allows for ample AAC in Brazil. The PickNClick consists of a word and sentence prediction tool for Portuguese language to help people with cerebral palsy, in particular, spastic quadriplegic children. Experiments conducted presented good values concerning KSR metric and showed the software applicability cerebral palsy and spastic quadriplegic volunteer.