Articles by Carla Taramasco
International Journal of Environmental Research and Public Health, 2022
Epivigila is a Chilean integrated epidemiological surveillance system with more than 17,000,000 C... more Epivigila is a Chilean integrated epidemiological surveillance system with more than 17,000,000 Chilean patient records, making it an essential and unique source of information for the quantitative and qualitative analysis of the COVID-19 pandemic in Chile. Nevertheless, given the extensive volume of data controlled by Epivigila, it is difficult for health professionals to classify vast volumes of data to determine which symptoms and comorbidities are related to infected patients. This paper aims to compare machine learning techniques (such as support-vector machine, decision tree and random forest techniques) to determine whether a patient has COVID-19 or not based on the symptoms and comorbidities reported by Epivigila. From the group of patients with COVID-19, we selected a sample of 10% confirmed patients to execute and evaluate the techniques. We used precision, recall, accuracy, F1-score, and AUC to compare the techniques. The results suggest that the support-vector machine performs better than decision tree and random forest regarding the recall, accuracy, F1-score, and AUC. Machine learning techniques help process and classify large volumes of data more efficiently and effectively, speeding up healthcare decision making.
Frontiers in Applied Mathematics and Statistics, 2022
Linear functional analysis historically founded by Fourier and Legendre played a significant role... more Linear functional analysis historically founded by Fourier and Legendre played a significant role to provide a unified vision of mathematical transformations between vector spaces. The possibility of extending this approach is explored when basis of vector spaces is built Tailored to the Problem Specificity (TPS) and not from the convenience or effectiveness of mathematical calculations. Standardized mathematical transformations, such as Fourier or polynomial transforms, could be extended toward TPS methods, on a basis, which properly encodes specific knowledge about a problem. Transition between methods is illustrated by comparing what happens in conventional Fourier transform with what happened during the development of Jewett Transform, reported in previous articles. The proper use of computational intelligence tools to perform Jewett Transform allowed complexity algorithm optimization, which encourages the search for a general TPS methodology.
Sensors, 2022
The population is aging worldwide, creating new challenges to the quality of life of older adults... more The population is aging worldwide, creating new challenges to the quality of life of older adults and their families. Falls are an increasing but not inevitable threat to older adults. Information technologies provide several solutions to address falls, but smart homes and the most available solutions require expensive and invasive infrastructures. In this study, we propose a novel approach to classify and detect falls of older adults in their homes through low-resolution infrared sensors that are affordable, non-intrusive, do not disturb privacy, and are more acceptable to older adults. Using data collected between 2019 and 2020 with the eHomeseniors platform, we determine activity scores of older adults moving across two rooms in a house and represent an older adult fall through skeletonization. We find that our twofold approach effectively detects activity patterns and precisely identifies falls. Our study provides insights to physicians about the daily activities of their older adults and could potentially help them make decisions in case of abnormal behavior.
IEEE Access, 2021
In the last two decades, studies about using technology for automatic detection of human falls in... more In the last two decades, studies about using technology for automatic detection of human falls increased considerably. The automatic detection of falls allows for quicker aid that is key to increasing the chances of treatment and mitigating the consequences of falls. However, each type of fall has its specificities and determining the correct type of fall can help treat the person who has fallen. Although it is essential to use computational methods to classify falls, there are few studies about that in the literature, especially compared to the studies that propose solutions for fall detection. In this sense, we execute a systematic literature review (SLR) using the (Kitchenham et al., 2009) method to investigate the computational solutions used to classify the different types of falls. We performed a search on Scopus, Web of Science, and PubMed scientific databases looking for computational methods to fall classification in their papers. We use the grounded theory methodology for a more detailed qualitative analysis of the papers. As a result of our search, we selected a total of 36 studies for our review and found two different computational methods for classifying falls. Related to the steps used in each method, we found fourteen different types of sensors, four different techniques for background and foreground extraction of videos, twenty-one techniques for feature extraction, and seven different fall classification strategies. Finally, we also identified fifty-one different types of falls. In conclusion, we believe that the methods and techniques analyzed in our study can help developers to create new and better systems for classification, detection, and prevention of falls and falls database. Besides, we identified gaps that can be explored in future research related to the automatic classification of falls. INDEX TERMS Automated falls, classification algorithms, e-health, falls, falls classification, types of falls.
Cognitive Reserve alludes to gain, resistance, plasticity and is the functional correlative of ne... more Cognitive Reserve alludes to gain, resistance, plasticity and is the functional correlative of neuroplasticity and a potential protection factor, which could explain why some patients may show the same pathology but quite different clinical manifestations. Among the activities considered as promoters are studies, work, physical and social activities. Although there are surveys or tables that seek to measure these factors and reflect this reserve in an index, this can be a quite reductionist strategy. Given the increasing ageing of the population, added to the active elders paradigm, programs addressed to seniors are carried out; it is important to consider that gains are accumulative and dynamism must be promoted from earlier ages. The sample for this work consisted of 30 seniors (60–87years) from the Region of Valparaíso, Chile. The CRIq was applied to the participants to measure the CR index and no differences were found between men and women. The purpose of this work is to describe the activities that promote reserve, carried out from 18 years onwards by 30 autonomous and cognitively competent seniors. It is held that it is not the type of activity that matters, but rather the frequency and the length of the execution period that turns into advantages for the persons. The data submitted reveal that seniors never failed to frequently execute some of the activities. That is, they had the habit of being active along their whole lives. This mechanism could be considered as a kind of dynamo where the greater input of promoting activities would make possible better conditions of the nervous system, but it does not have an easy storage as it is in continuous use. For this reason, gains depend on the active habit of execution, its early start, diversity of activities and permanence during the whole life span.
Applied Sciences, 2021
The 2019 Coronavirus disease (COVID-19) pandemic is a current challenge for the world’s health sy... more The 2019 Coronavirus disease (COVID-19) pandemic is a current challenge for the world’s health systems aiming to control this disease. From an epidemiological point of view, the control of the incidence of this disease requires an understanding of the influence of the variables describing a population. This research aims to predict the COVID-19 incidence in three risk categories using two types of machine learning models, together with an analysis of the relative importance of the available features in predicting the COVID-19 incidence in the Chilean urban commune of Concepción. The classification results indicate that the ConvLSTM (Convolutional Long Short-Term Memory) classifier performed better than the SVM (Support Vector Machine), with results between 93% and 96% in terms of accuracy (ACC) and F-measure (F1) metrics. In addition, when considering each one of the regional and national features as well as the communal features (DEATHS and MOBILITY), it was observed that at the regional level the CRITICAL BED OCCUPANCY and PATIENTS IN ICU features positively contributed to the performance of the classifiers, while at the national level the features that most impacted the performance of the SVM and ConvLSTM were those related to the type of hospitalization of patients and the use of mechanical ventilators.
Biology, 2021
Among the diverse and important applications that networks currently have is the modeling of infe... more Among the diverse and important applications that networks currently have is the modeling of infectious diseases. Immunization, or the process of protecting nodes in the network, plays a key role in stopping diseases from spreading. Hence the importance of having tools or strategies that allow the solving of this challenge. In this paper, we evaluate the effectiveness of the DIL-Wα ranking in immunizing nodes in an edge-weighted network with 3866 nodes and 6,841,470 edges. The network is obtained from a real database and the spread of COVID-19 was modeled with the classic SIR model. We apply the protection to the network, according to the importance ranking list produced by DIL-Wα, considering different protection budgets. Furthermore, we consider three different values for α; in this way, we compare how the protection performs according to the value of α.
Revista Interamericana de Ambiente y Turismo, 2021
The purpose of this study is to develop a new method that allows calculating the characteristics ... more The purpose of this study is to develop a new method that allows calculating the characteristics of tourist paths, favoring the understanding of visitor behavior. Changes and complexities are considered between a first phase of quasi-random "search" of attractions and tourist sites to visit, and a second phase of direct access to places of interest in the territory. This method is based on the notion of entropy curve, where a low value corresponds to a direct and rapid access to the preselected or recently defined sites, and a high value corresponds to an almost random search for tourist sites showing a more erratic behavior of the tourist. The location in space and time of the high entropy parts of the tourist trajectory would allow making better decisions related to the management of tourism in a given territory.
Applied Sciences, 2021
Fake news, viruses on computer systems or infectious diseases on communities are some of the prob... more Fake news, viruses on computer systems or infectious diseases on communities are some of the problems that are addressed by researchers dedicated to study complex networks. The immunization process is the solution to these challenges and hence the importance of obtaining immunization strategies that control these spreads. In this paper, we evaluate the effectiveness of the DIL-Wα ranking in the immunization of nodes that are attacked by an infectious disease that spreads on an edge-weighted graph using a graph-based SIR model. The experimentation was done on real and scale-free networks and the results illustrate the benefits of this ranking.
Symmetry, 2021
Establishing a node importance ranking is a problem that has attracted the attention of many rese... more Establishing a node importance ranking is a problem that has attracted the attention of many researchers in recent decades. For unweighted networks where the edges do not have any attached weight, many proposals have been presented, considering local or global information of the networks. On the contrary, it occurs in undirected edge-weighted networks, where the proposals to address this problem have been more scarce. In this paper, a ranking method of node importance for undirected and edge-weighted is provided, generalizing the measure of line importance (DIL) based on the centrality degree proposed by Opsahl. The experimentation was done on five real networks and the results illustrate the benefits of our proposal.
International Journal of Environmental Research and Public Health, 2021
The understanding of infectious diseases is a priority in the field of public health. This has ge... more The understanding of infectious diseases is a priority in the field of public health. This has generated the inclusion of several disciplines and tools that allow for analyzing the dissemination of infectious diseases. The aim of this manuscript is to model the spreading of a disease in a population that is registered in a database. From this database, we obtain an edge-weighted graph. The spreading was modeled with the classic SIR model. The model proposed with edge-weighted graph allows for identifying the most important variables in the dissemination of epidemics. Moreover, a deterministic approximation is provided. With database COVID-19 from a city in Chile, we analyzed our model with relationship variables between people. We obtained a graph with 3866 vertices and 6,841,470 edges. We fitted the curve of the real data and we have done some simulations on the obtained graph. Our model is adjusted to the spread of the disease. The model proposed with edge-weighted graph allows for identifying the most important variables in the dissemination of epidemics, in this case with real data of COVID-19. This valuable information allows us to also include/understand the networks of dissemination of epidemics diseases as well as the implementation of preventive measures of public health. These findings are important in COVID-19’s pandemic context.
IEEE Access, 2021
Many governments worldwide are engaging into digital transformation initiatives to improve effici... more Many governments worldwide are engaging into digital transformation initiatives to improve efficiency, effectiveness, cost, and transparency. Collaborative e-government processes offer a way to overcome the typical integration and interoperability issues of existing isolated e-government solutions. A study was conducted to help e-government modelers and architects to know current approaches to modeling collaborative e-government processes that consider integration and interoperability. The research questions are: Which kind of representations (architecture, framework, ontology, meta-model, model or process) are used to model these processes? Which concerns (cost, value, citizen, technology, organization) do they focus on? How do they address collaborative processes concepts (interoperability and collaboration)? This article describes the design, execution and results of a Systematic Literature Review (SLR) that gathered primary studies from well-known scientific literature databases, and organized them with a novel literature classification schema consisting of model type, model focus, collaboration scheme, and interoperability level. The initial search found 326 publications, of which duplicates removal and exclusion criteria application left only 52 for detailed analysis. Key findings are: literature for this topic proposes Frameworks and (general) Models, but not metamodels or ontologies; most addressed focus has shifted from Technology and Organization, towards Citizen; collaboration studies have shifted from Open Participation towards Data Transparency; and most work that addresses interoperability remains focused on Technical aspects with a smattering of Semantics and Organizational aspects. These findings reinforce the need for proposals that address the problem of collaborative e-government processes as something that lives at the junction of egovernment, software architecture description, collaborative work, and interoperability.
IEEE Access, 2021
Microservice-based systems promote agility and rapid business development. Some features, such as... more Microservice-based systems promote agility and rapid business development. Some features, such as fast time-to-market, scalability and optimal response times, have encouraged stakeholders to get more involved in the development and implementation of microservices architectures in order to translate their business vision into the implementation of the architecture. Although some techniques allow the inclusion of the stakeholders' perspective in the design of microservice architectures, few proposals consider such perspectives in the selection and evaluation of technologies that implement microservice architectures. Indeed, the qualities that characterize microservice-based systems strongly depend on the suitable selection of technologies, such as application frameworks and platforms. This article proposes a collaborative technique that includes stakeholders and software architects in the selection and evaluation of application frameworks and platforms to implement microservice-based systems. We evaluated the technique in an industrial case of design and implementation of an Ambient-Assisted Living (AAL) system, which combines microservice architecture and Internet-of-Medical-Things (IoMT) sensors. The case results indicate that the proposed technique supported stakeholders in the pragmatic evaluation of alternative technological solutions. Additionally, it allowed the implementation of an AAL system that satisfies the quality specifications of stakeholders and end-users. This initial study suggests that actively including stakeholders in the implementation of microservice-based systems allows architects to make design decisions that better consider stakeholders viewpoints as well as managing their expectations.
IEEE Access, 2020
Clinical software is a fundamental tool for supporting healthcare systems because it improves the... more Clinical software is a fundamental tool for supporting healthcare systems because it improves the quality of patient care and automatizes the most frequently performed clinical tasks. Nevertheless, since health systems include various components, such as supplies, transportation, laboratories, and interoperability, eliciting the most critical requirements for understanding the problem that the clinical software must solve is quite a complex task. Indeed, the requirement elicitation process may directly determine the success or failure of the clinical software. In this article, we present the D&I framework, a methodology that uses dissemination and implementation strategies to recommend guidelines for the elicitation of clinical software requirements. The objective of this framework is to support software developers in the identification of key requirements with the goal of more holistically understanding the problem to be solved by the clinical software. We evaluated the D&I framework with a real case study related to a bed management system. We employed a usability instrument with 50 clinicians to evaluate tasks in software modules that represent clinical priorities defined by stakeholders. The results indicate that the perception of usability by end users is acceptable, suggesting that the evaluated tasks satisfy the established clinical priorities. The D&I framework provides a starting point for research and discussion about the contribution of dissemination and implementation strategies to the body of knowledge about requirement engineering.
Neural Computing and Applications, 2020
Human behavior is manly addressed by emotions. One of the most accepted models that represent emo... more Human behavior is manly addressed by emotions. One of the most accepted models that represent emotions is known as the circumplex model. This model organizes emotions into points on a bidimensional plane: valence and arousal. Despite the importance of the emotion recognition, there are limited initiatives that seek to classify emotions easily in an uncontrolled environment. In this work, we present the architecture and the design of an extensible software which allows recognizing and classifying emotions by using a low-cost EEG. The proposed software implements an emotion classifier although a support vector machines (SVM) are boosted with an autonomous bio-inspired approach. The contribution was experimentally evaluated by taking a set of well-known validated EEG Databases for Emotion Recognition. Computational experiments show promising results. Using our proposal for EEG emotion classification, we reach an accuracy close to 95%. The results obtained confirm that our approach is able to overcome to a commonly used SVM classifier and that the proposed software can be useful in real environments.
Currently, one of the main challenges for information systems in healthcare is focused on support... more Currently, one of the main challenges for information systems in healthcare is focused on support for health professionals regarding disease classifications. This work presents an innovative method for a recommendation system for the diagnosis of breast cancer using patient medical histories. In this proposal, techniques of natural language processing (NLP) were implemented on real datasets: one comprised 160, 560 medical histories of anonymous patients from a hospital in Chile for the following categories: breast cancer, cysts and nodules, other cancer, breast cancer surgeries and other diagnoses; and the other dataset was obtained from the MIMIC III dataset. With the application of word-embedding techniques, such as word2vec's skip-gram and BERT, and machine learning techniques, a recommendation system as a tool to support the physician's decision-making was implemented. The obtained results demonstrate that using word embeddings can define a good-quality recommendation system. The results of 20 experiments with 5-fold cross-validation for anamnesis written in Spanish yielded an F1 of 0.980 ± 0.0014 on the classification of 'cancer' versus 'not cancer' and 0.986 ± 0.0014 for 'breast cancer' versus 'other cancer'. Similar results were obtained with the MIMIC III dataset.
Applied Sciences, 2020
During the last years, highly-recognized computational intelligence techniques have been proposed... more During the last years, highly-recognized computational intelligence techniques have been proposed to treat classification problems. These automatic learning approaches lead to the most recent researches because they exhibit outstanding results. Nevertheless, to achieve this performance, artificial learning methods firstly require fine tuning of their parameters and then they need to work with the best-generated model. This process usually needs an expert user for supervising the algorithm's performance. In this paper, we propose an optimized Extreme Learning Machine by using the Bat Algorithm, which boosts the training phase of the machine learning method to increase the accuracy, and decreasing or keeping the loss in the learning phase. To evaluate our proposal, we use the Parkinson's Disease audio dataset taken from UCI Machine Learning Repository. Parkinson's disease is a neurodegenerative disorder that affects over 10 million people. Although its diagnosis is through motor symptoms, it is possible to evidence the disorder through variations in the speech using machine learning techniques. Results suggest that using the bio-inspired optimization algorithm for adjusting the parameters of the Extreme Learning Machine is a real alternative for improving its performance. During the validation phase, the classification process for Parkinson's Disease achieves a maximum accuracy of 96.74% and a minimum loss of 3.27%.
IEEE Access, 2020
Telehealth systems deliver remote care of elderly and physically less able patients as well as re... more Telehealth systems deliver remote care of elderly and physically less able patients as well as remote surgeries, treatments, and diagnoses. In this regard, several systemic properties must be satisfied (such as security) in order to ensure the functionality of Telehealth systems. Although existing studies discuss different security episodes that involve Telehealth systems, it is difficult to have a clear standpoint about which are the most reported security issues and which solutions have been proposed. Furthermore, since Telehealth systems are composed of several software systems, it is not clear which critical areas of Software Engineering are relevant to develop secure Telehealth systems. This article reports a systematic mapping study (SMS) whose purpose is to detect, organize, and characterize security issues in Telehealth systems. Based on the SMS results, we examine how Software Engineering may help to develop secure Telehealth systems. From over a thousand studies, we distinguished and classified 41 primary studies. Results show that (i) four security classifications (attacks, vulnerabilities, weaknesses, and threats) concentrate the most reported security issues; (ii) three security strategies (detect attacks, stop or mitigate attacks and react to attacks) characterize security issues, and (iii) the most relevant research themes are related to insecure data transmission and privacy. The SMS's findings suggest that software design, requirements, and models are key areas to develop secure Telehealth systems.
Journal of Medical Systems, 2020
The world population ageing is on the rise, which has led to an increase in the demand for medica... more The world population ageing is on the rise, which has led to an increase in the demand for medical care due to diseases and symptoms prevalent in health centers. One of the most prevalent symptoms prevalent in older adults is falls, which affect one-third of patients each year and often result in serious injuries that can lead to death. This paper describes the design of a fall detection system for elderly households living alone using very low resolution thermal sensor arrays. The algorithms implemented were LSTM, GRU, and Bi-LSTM; the last one mentioned being that which obtained the best results at 93% in accuracy. The results obtained aim to be a valuable tool for accident prevention for those patients that use it and for clinicians who manage the data.
Revista Interamericana de Ambiente y Turismo, 2020
The purpose of this study is to develop a new method that allows calculating the characteristics ... more The purpose of this study is to develop a new method that allows calculating the characteristics of tourist paths, favoring the understanding of visitor behavior. Changes and complexities are considered between a first phase of quasi-random "search" of attractions and tourist sites to visit, and a second phase of direct access to places of interest in the territory. This method is based on the notion of entropy curve, where a low value corresponds to a direct and rapid access to the preselected or recently defined sites, and a high value corresponds to an almost random search for tourist sites showing a more erratic behavior of the tourist. The location in space and time of the high entropy parts of the tourist trajectory would allow making better decisions related to the management of tourism in a given territory.
Uploads
Articles by Carla Taramasco