Deep Learning in the Recognition of Activities of Daily Living Using Smartwatch Data.

The recognition of human activities (HAR) using wearable device data, such as smartwatches, has gained significant attention in the field of computer science due to its potential to provide insights into individuals' daily activities. This article aims to conduct a comparative study of deep learning techniques for recognizing activities of daily living (ADL). A mapping of HAR techniques was performed, and three techniques were selected for evaluation, along with a dataset. Experiments were conducted using the selected techniques to assess their performance in ADL recognition, employing standardized evaluation metrics, such as accuracy, precision, recall, and F1-score. Among the evaluated techniques, the DeepConvLSTM architecture, consisting of recurrent convolutional layers and a single LSTM layer, achieved the most promising results. These findings suggest that software applications utilizing this architecture can assist smartwatch users in understanding their movement routines more quickly and accurately.

A Study on the Influence of Sensors in Frequency and Time Domains on Context Recognition.

Adaptive AI for context and activity recognition remains a relatively unexplored field due to difficulty in collecting sufficient information to develop supervised models. Additionally, building a dataset for human context activities "in the wild" demands time and human resources, which explains the lack of public datasets available. Some of the available datasets for activity recognition were collected using wearable sensors, since they are less invasive than images and precisely capture a user's movements in time series. However, frequency series contain more information about sensors' signals. In this paper, we investigate the use of feature engineering to improve the performance of a Deep Learning model. Thus, we propose using Fast Fourier Transform algorithms to extract features from frequency series instead of time series. We evaluated our approach on the ExtraSensory and WISDM datasets. The results show that using Fast Fourier Transform algorithms to extract features performed better than using statistics measures to extract features from temporal series. Additionally, we examined the impact of individual sensors on identifying specific labels and proved that incorporating more sensors enhances the model's effectiveness. On the ExtraSensory dataset, the use of frequency features outperformed that of time-domain features by 8.9 p.p., 0.2 p.p., 39.5 p.p., and 0.4 p.p. in Standing, Sitting, Lying Down, and Walking activities, respectively, and on the WISDM dataset, the model performance improved by 1.7 p.p., just by using feature engineering.

Validation of Angle Estimation Based on Body Tracking Data from RGB-D and RGB Cameras for Biomechanical Assessment.

Motion analysis is an area with several applications for health, sports, and entertainment. The high cost of state-of-the-art equipment in the health field makes it unfeasible to apply this technique in the clinics' routines. In this vein, RGB-D and RGB equipment, which have joint tracking tools, are tested with portable and low-cost solutions to enable computational motion analysis. The recent release of Google MediaPipe, a joint inference tracking technique that uses conventional RGB cameras, can be considered a milestone due to its ability to estimate depth coordinates in planar images. In light of this, this work aims to evaluate the measurement of angular variation from RGB-D and RGB sensor data against the Qualisys Tracking Manager gold standard. A total of 60 recordings were performed for each upper and lower limb movement in two different position configurations concerning the sensors. Google's MediaPipe usage obtained close results compared to Kinect V2 sensor in the inherent aspects of absolute error, RMS, and correlation to the gold standard, presenting lower dispersion values and error metrics, which is more positive. In the comparison with equipment commonly used in physical evaluations, MediaPipe had an error within the error range of short- and long-arm goniometers.

Incremental 3D Cuboid Modeling with Drift Compensation.

This paper presents a framework of incremental 3D cuboid modeling by using the mapping results of an RGB-D camera based simultaneous localization and mapping (SLAM) system. This framework is useful in accurately creating cuboid CAD models from a point cloud in an online manner. While performing the RGB-D SLAM, planes are incrementally reconstructed from a point cloud in each frame to create a plane map. Then, cuboids are detected in the plane map by analyzing the positional relationships between the planes, such as orthogonality, convexity, and proximity. Finally, the position, pose, and size of a cuboid are determined by computing the intersection of three perpendicular planes. To suppress the false detection of the cuboids, the cuboid shapes are incrementally updated with sequential measurements to check the uncertainty of the cuboids. In addition, the drift error of the SLAM is compensated by the registration of the cuboids. As an application of our framework, an augmented reality-based interactive cuboid modeling system was developed. In the evaluation at cluttered environments, the precision and recall of the cuboid detection were investigated, compared with a batch-based cuboid detection method, so that the advantages of our proposed method were clarified.

Applicability of a motor rehabilitation system in stroke victims / Aplicabilidade de um sistema de reabilitação motora em pacientes pós-acidente vascular encefálico

Abstract Introduction: The recovery of stroke patients is long and boring due to the repetitive nature of the exercises used and the length of treatment. Thus, we started using virtual reality as an alternative and, because of its advantages, health professionals are adapting video games for physical therapy. However, there are some limitations, such as the fact that games are designed for entertainment and not for therapeutic purposes. Objective: In order to mitigate gaps in assistive devices for physical therapy, this study describes the development and applicability of a computer support system for motor rehabilitation - Ikapp - in stroke victims. Methods: Twenty-seven stroke patients filled out a socioeconomic questionnaire, tested Ikapp during five minutes and answered a usability and satisfaction questionnaire about handling the tool. The chi-square test was used to analyze any association between sociodemographic factors and the features of the system. Results: The Ikapp system can be an excellent device to assist neurological rehabilitation of stroke patients, as participants questionnaires showed that 85.2% were satisfied in regard to motivation and inclusion of Ikapp in physiotherapy and 77.8% relative to ease of interaction with the tool. Conclusion: The Ikapp system proved to be an easy-to-use and accessible computer support system for patients with functional limitations.

Resumo Introdução: A recuperação de indivíduos pós-Acidente Vascular Encefálico (AVE) tem se mostrado longa e monótona devido ao caráter repetitivo dos exercícios utilizados na clínica e aos anos de tratamento. Logo, tem-se utilizado a Realidade Virtual (RV) como uma alternativa e diante de suas vantagens, profissionais de saúde vêm adaptando vídeo games à fisioterapia. No entanto, existem algumas limitações, como a do fato de estes vídeo games terem sido desenvolvidos para diversão e não serem apropriados para uso terapêutico. Objetivo: Em busca de atenuar lacunas existentes em dispositivos adaptados à fisioterapia, este estudo descreve o desenvolvimento e a aplicabilidade de um sistema computacional de suporte a reabilitação motora - Ikapp - em pacientes pós-AVE. Métodos: 27 pacientes pós-AVE preencheram um questionário socioeconômico, testaram o Ikapp durante 5 min e responderam a um questionário de usabilidade e satisfação sobre o manuseio da ferramenta. Para analisar a associação de fatores sociodemográficos com funcionalidades do sistema, o teste qui quadrado (Exato de Fisher) foi utilizado. Resultados: O Ikapp pode ser uma excelente ferramenta de auxílio à reabilitação neurológica de pacientes pós-AVE, visto que seus testes evidenciaram 85,2% de satisfação no que diz respeito à motivação e inclusão no processo fisioterápico e 77,8% em relação à facilidade de interação com a ferramenta. Conclusão: O Ikapp mostrou ser um sistema computacional de fácil aplicação e acessível a pacientes com diferentes limitações funcionais.

MirrARbilitation: A clinically-related gesture recognition interactive tool for an AR rehabilitation system.

BACKGROUND AND OBJECTIVE: Interactive systems for rehabilitation have been widely investigated for motivational purposes. However, more attention should be given to the manner in which user movements are recognized and categorized. This paper aims to evaluate the efficacy of using a clinically-related gesture recognition tool, based on the international biomechanical standards (ISB) for the reporting of human joint motion, for the development of an interactive augmented reality (AR) rehabilitation system -mirrARbilitation. METHODS: This work presents an AR rehabilitation system based on ISB standards, which enables the system to interact and to be configured according to therapeutic needs. The Kinect(TM) skeleton tracking technology was exploited and a new movement recognition method was developed to recognize and classify biomechanical movements. Further, our mirrARbilitation system provides exercise instructions while simultaneously motivating the patient. The system was evaluated on a cohort of 33 patients, physiotherapists, and software developers when performing shoulder abduction therapy exercises. Tests were performed in three moments: (i) users performed the exercise until they feel tired without the help of the system, (ii) the same however using the mirrARbilitation for motivation and guidance, and (iii) users performed the exercise again without the system. Users performing the movement without the help of the system worked as baseline reference. RESULTS: We demonstrated that the percentage of correct exercises, measured by the movement analysis method we developed, improved from 69.02% to 93.73% when users interacted with the mirrARbilitation. The number of exercise repetitions also improved from 34.06 to 66.09 signifying that our system increased motivation of the users. The system also prevented the users from performing the exercises in a completely wrong manner. Finally, with the help of our system the users' worst result was performing 73.68% of the rehabilitation movements correctly. Besides the engagement, these results suggest that the use of biomechanical standards to recognize movements is valuable in guiding users during rehabilitation exercises. CONCLUSION: The proposed system proved to be efficient by improving the user engagement and exercise performance outcomes. The results also suggest that the use of biomechanical standards to recognize movements is valuable in guiding users during rehabilitation exercises.

Motor Rehabilitation Using Kinect: A Systematic Review.

BACKGROUND: Interactive systems are being developed with the intention to help in the engagement of patients on various therapies. Amid the recent technological advances, Kinect™ from Microsoft (Redmond, WA) has helped pave the way on how user interaction technology facilitates and complements many clinical applications. In order to examine the actual status of Kinect developments for rehabilitation, this article presents a systematic review of articles that involve interactive, evaluative, and technical advances related to motor rehabilitation. MATERIALS AND METHODS: Systematic research was performed in the IEEE Xplore and PubMed databases using the key word combination "Kinect AND rehabilitation" with the following inclusion criteria: (1) English language, (2) page number >4, (3) Kinect system for assistive interaction or clinical evaluation, or (4) Kinect system for improvement or evaluation of the sensor tracking or movement recognition. Quality assessment was performed by QualSyst standards. RESULTS: In total, 109 articles were found in the database research, from which 31 were included in the review: 13 were focused on the development of assistive systems for rehabilitation, 3 in evaluation, 3 in the applicability category, 7 on validation of Kinect anatomic and clinical evaluation, and 5 on improvement techniques. Quality analysis of all included articles is also presented with their respective QualSyst checklist scores. CONCLUSIONS: Research and development possibilities and future works with the Kinect for rehabilitation application are extensive. Methodological improvements when performing studies on this area need to be further investigated.

Desenvolvimento e aprimoramento de um sistema computacional- Ikapp- de suporte a reabilitação motora / Development and improvement of a computational system- Ikapp- to support motor rehabilitation

A aplicabilidade das Tecnologias Interativas (TIs) na área de saúde, em particular na reabilitação motora, tem sido uma alternativa clínica usada com intuito de estimular maior engajamento do paciente ao seu processo de recuperação que por vezes é extenuante. O presente estudo descreve uma ferramenta tecnológica -Ikapp- de suporte a reabilitação motora. Ferramenta essa que busca ampliar as possibilidades dos dispositivos comerciais já existentes no contexto clínico. Sessenta (60) voluntários foram convidados a interagir com as interfaces do setup e do jogo do Ikapp com objetivo de examinar a funcionalidade, grau de aceitação, demandas e limitações para aprimoramentos. Os resultados do presente estudo demonstram altos índices de satisfação pelos participantes. Além disso, os resultados demonstraram que o Ikapp é uma ferramenta que agrega valores terapêuticos à ludicidade e motivação de acordo com a perspectiva dos participantes.

The applicability of Interactive Technologies (ITs) in the health area, especially in motor rehabilitation, has been a therapeutic alternative used aiming to encourage a greater patient engagement in their recovery process that is sometimes lengthy. The present study describes the technological tool (Ikapp) to support motor rehabilitation, which aims to expand the possibility of the commercial devices that is already used in clinical practice. Sixty (60) volunteers were invited to interact with the setup and game interfaces of Ikapp aiming to examine their features, the degree of acceptance, demands and limitations to the enhancement. The results of present study showed high levels of satisfaction for the participants. Furthermore, the results demonstrated that the Ikapp is a tool that adds value to therapeutic playfulness and motivation according to the participant' perspective.

User satisfaction through empathy and orientation in three-dimensional worlds.

This paper describes a methodology for navigation and exploration assistance intended to enhance user satisfaction when exploring three-dimensional virtual environments. The complexity of such environments often makes navigation and information retrieval difficult, making it necessary to add assistance components to the world in order to turn it easier to manipulate. This methodology uses three-dimensional "intelligent" avatars as interactive guides, along with information-based navigation strategies. The intelligence of the avatars is represented through physical features, behaviors, and knowledge about the user and the environment. These components establish the avatar's architecture. Content personalization according to the user's interest, navigation assistance according to the desired content, and avatar guides that make the virtual place more realistic and pleasant are proposed in order to involve users. A three-dimensional model of the Guggenheim Museum Bilbao, in Spain, is presented as a prototype for the validation of this methodology. In the museum, the guide is represented as a fish that, according to the user's preferences, assumes gender and age. The avatar swims through the museum, following navigation routes that lead through exhibitions previously chosen by the visitor.