ABSTRACT. In this article, we present a system that allows monitoring the energy consumption of electric loads in the residential sector. The system consists of sensor nodes that are responsible for monitoring both current and voltage and send them to a database hosted on a Raspbian server through an IoT communication protocol. The monitored data can be visualized in an IoT interface by graphs of the daily, weekly and monthly energy consumption developed through Atom and complements such as Highcharts. Additionally, reports can be generated with the total kilowatt-hours consumed at the end of the month and the total cost for the service. An important feature of the prototype is that by means of remote management it allows activating or deactivating the passage of energy towards the loads connected to the system. In this way, it is possible to have an adequate control of energy consumption in the home in order to promote energy efficiency and decrease expenses for the payment of electric service.

ABSTRACT. Data driven government has become significant in the quest for quality service delivery in the public sector. Countries all over the world are now using Information Communication Technologies (ICTs) to enhance the quality of their governance. ICTs have been found to improve efficiency and effectiveness of public administration and enhance citizen’s access to government services, hence, improvement of the quality of governance. The increasing development of ICTs however, presents new and emerging threats for government to contend with. The issue of cybercrime has become a critical factor in digital government practice in recent times. The internet which provides free access to information has also led to the abuse of technology in perpetrating crimes capable of undermining a nation’s security. This study examines the implications of cybercrimes on the implementation digital government in Nigeria’s public sector. The paper makes use of qualitative secondary data gathered from publications of peer reviewed journals and international bodies, books, internet materials to interrogate the implication of cybercrimes in Nigeria’s quest for digital government adoption. Data gathered were analysed through a systematic literature review with the Routine Activity theory serving as the theoretical framework. Findings of the study reveal the great threat that the increasing spate of cybercrimes pose for digital government implementation in the Nigeria public sector. The paper argues for a data driven government in Nigeria and the political will for its implementation and as well, a vigorous public awareness campaign and decisive application of cyber laws in the country.

ABSTRACT. Nowadays, in a highly-globalized world, the understanding of causes and consequences involved in the migration phenomena, and also the prediction of migration flows are important for development of national public policies and for urban resource planning. The high complexity of human im/emigration movements can not only be explained by economic causes but rather by the interaction among multiple additional factors (demographic, social, linguistic, among others). The application of Machine Learning techniques and Data Visualization models on high volumes of raw data from countries can provide good insight to understand how indicators from countries are related to migration causes, and also to make visible the migration flows between the sending and receiving countries. This paper describes a tool which includes supervised classification and visualization methods to analyze country indicators and aim to discover the connections among these attributes and the migration movements.

ABSTRACT. The growing use of mobile devices for supporting teaching - learning processes and their use in storing academic contents on virtual platforms, requires that systems oriented to the mobile learning consider the learning context of students. One of the biggest challenges during the construction of these systems is the modeling of the context and the possibility of including ontology-based approaches in order to structure in a better way the information. Thus, this paper presents a mobile learning system that uses a network of ontologies which allows the representation of the contextual dimensions of a teaching - learning environment (e.g., location, time, user profiles and knowledge areas). Moreover, it is possible to take advantage of the use of semantic search (keywords) and route algorithms applied to ontological models due to their expressiveness and extensible architecture. This study looks for providing students and teachers with personalized and relevant academic information in their current context of study. Finally, the system was empirically evaluated in a real academic context. The results show favorable perceptions from the participants about its usefulness. These results were obtained by means of the statistical tool ANOVA, and show a positive influence on the academic performance of the students.

ABSTRACT. This article evaluates the usability of an interactive virtual reality system for the recovery of hand and wrist mobility by means of the LeapMotion device and the Unity3D graphics engine. Through the programmed interfaces, the proposed VR system allows the patient to correctly complete established medical protocols via exercise routines with audio and video feedback. The usability evaluation of the VR system was carried out using the VRUSE model in an experiment. This model was utilized to design a survey consisting of 10 items, where each item represents a model factor. The survey was applied in the experiment in which 30 patients participated. The obtained results showed that the VRUSE factors of the proposed VR system for rehabilitation are significantly related to its overall use, with factor correlation values lower than 0,005. Patients participating in the experiment consider that the interactive virtual reality-based system for upper limb rehabilitation is usable. Additionally, it was proved that the rehabilitation environments programmed in the Unity 3D graphics engine allows patients to comply precisely with the established medical protocols, driving them to a progressive movement recovery of the affected limb.

ABSTRACT. We present the integration of deep learning approach for autonomous robot KUKA YouBot navigation in human rescue applications. The incorporation of deep learning approach was carried out through the combination among Robot Operating System, Python software, Open Source Computer Vision Library and internet of things. The Robot Operating System with Hydro medusa distribution provides the managing of odometry, kinematics and path planning nodes. The combination of all nodes allows the simulation of the autonomous robot navigation by using Gazebo and provides the implementation of the algorithms in simulated and real platforms. Python software improves the communication tasks taking advantage of data processing tools in the deep learning process. Then, Open Source Computer Vision Library allows the integration of the deep learning approach by using the Single Shot Detector algorithm which provides robustness in velocity and precision which mainly allows the human detection by using a trained neuronal network. The integration of Robot Operating System, Python software, Open Source Computer Vision Library, and internet of things is a promising architecture for providing smart autonomous navigation capability not only for human rescue, but also for applications like: social robots, precision farming, industry and so on.

ABSTRACT. Fuzzy Cognitive Maps (FCMs) and current developments in Machine Learning have been contributing in capturing human behaviors through data and learning models, which focus on predicting, interpreting or identifying behavioral patterns on systems and their relationships. In recent years seasonal diseases caused by vectors that transport viral pathogens in tropical regions, such as the Aedes Aegypti mosquito, have caused noticeable impacts both on public health and country’s economies in Latin America. This work proposes a model for early prognosis based on FCMs for making a risk assessment of potential presence of Dengue fever in a specific region of the Ecuadoran coast. The FCM is used as a knowledge representation strategy for the cause-effect relationships; and, learning models for gaining the identification of the underlying cause of symptoms. The model aims to improve the chances of proper diagnosis of seasonal diseases, which can impact not only on the prescription and correct treatments, but also on taking actions for preventing the spread of the fever with impact in the economy of the country.

ABSTRACT. ITC and E-government platforms are crucial to gather and mining data in order to develop strategies to ensure gender equality. We propose multiple methods from soft- computing to perform an analysis over gender equality data. A database of the evolution of anti-discrimination laws and gender equality regulations for 50 years (1960-2010), is codified to match a three-state neural network. The performance of the network is checked for such patterns. Clustering analysis is performed to group countries with similar behavior around the world. Finally, the evolution of gender equality laws world- wide is described and predicted using exponential smoothing. The results show that in gender evolution, equality is far from being reached, especially in North Africa which continue with significant regulatory deficiencies. Otherwise changes (mostly for better) are to be expected, mainly in South America.

ABSTRACT. Deep learning constitute a promising alternative when it comes to providing algorithms that process a big quantity of data and input variables coming from cognitive cities. But the use of deep learning technologies in the cognitive cities domain started only a few years ago; in that regard, there are still many issues that need to be addressed and not enough literature has been developed. This work provides a novel classification framework of cognitive cities using deep learning algorithms that is based in current surveys for known domains such as machine learning and smart cities, but adds the perspective of efficiency, sustainability and resilience that cognitive cities aim to solve.

ABSTRACT. When mapping burned areas, the use of indexes such as: NDVI, NDII, SAVI, GEMI and IAQ (BAI) allow the classification of vegetation status, of which the IAQ index has been designed to clearer identification of areas affected by fires. Another alternative is the multitemporal analysis, which detects changes from one image already classified to another, corresponding to the same surface on different dates. The common denominator applies both techniques separately in order to take advantage of the characteristics of a classified image. Therefore, the current study aims to combine multi-temporality and different indexes to integrate both characteristics and facilitate the identification of burned areas. The study area is located in southern Chile with the corresponding dates from January 15 to 30, 2017, where fires consumed much of the endemic forestation of the area. The methodology applied has been based on obtaining and correcting Landsat 8 satellite images prior and after the event. Following this, the different indexes have been calculated to apply the change detection. Thereafter, the results have been integrated to make a multitemporal RGB combination of the new bands where, in the red quill corresponds to the indexes before the event, the green quill to the indexes after the event and the blue quill to the multitemporal difference. As a result of the multi-temporal index combinations, the outstanding index is the SAVI-Multitemporal, which allows 93% visual discrimination of the areas affected by the fires, unlike the SAVI, BAI, GEMI, BAI indexes -Multitemporal and GEMI-Multitemporal with a percentage of discrimination of about 73.33%, 66.67%, 80%, 20% and 86.67%, respectively. Finally, we identified that 157,116,173 hectares of forest have been affected by the fires that occurred in Chile in the studied time period.

ABSTRACT. Nowadays, mobile devices have become one of the most useful instruments used by a person on its regular life, mainly due to the importance and the necessity of its tools. In that context, the mobile devices store the user’s personal information and even more data, becoming a personal tracker for daily activities, thus providing important information about the user. Derived from this gathering of information, many tools are available for use on mobile devices, with the restrain that each tool only provides isolated information about a specific application or activity. Therefore, the present work proposes a tool that could potentially aid investigators through the presentation of a complete report and timeline of the activities that were performed on the device, said report incorporates the information provided by many sources into an unique set of data. Also, with the aid of an example, the steps to use the proposed tool are shown.

ABSTRACT. This paper presents the implementation of a fully portable and autonomous low-cost GSM/GPRS network based on SDR (Software Defined Radio). This solution uses a Raspberry Pi platform and a Blade-RF module as hardware components, and YateBTS as software component. The proposed solution by leveraging the growing capabilities in terms of processing and memory of low-power consumption platforms such as Raspberry Pi platforms, and the flexibility of an SDR platform (Blade-RF and YateBTS), implements a reconfigurable communications system able to provide voice, messages and data services. The implemented network using open-source technologies, can be deployed in standalone mode or as part of an existing telecommunication infrastructure in realistic communication environments. Due to features such as: portability, energy autonomy, light weight, fast deployment and reconfigurability, the developed system can be applied in a variety of fields. Among the different application areas, relevant use cases are: communications services in emergency or natural disasters scenarios and relief services in search and rescue missions. In order to analyze the performance of the system, measures to to assess the voice services, text messages and data services are carried out. Results reveal that this autonomous communications infrastructure is suitable for a rapid deployment of a complete mobile communication system, with low power consumption and a low-cost of investment and maintenance.

ABSTRACT. Testing accessibility in educational and informational resources is an excellent challenge for accessibility experts. At present, there are no adequate tools and methods to evaluate the accessibility of multimedia resources, which makes the type of video resource not accessible to all users, especially for users with disabilities. There are millions of multimedia resources on the web, among them those of video type that we used as educational and informative resources in teaching-learning processes. However, its creators are not worried about implementing accessibility to make them more inclusive. This article proposes a combined method between the photosensitive epilepsy analysis tool and the manual evaluation with the Website Accessibility Conformance Evaluation Methodology 1.0 to generate more accessible videos. In this research, we apply as a case study to 10 video-type resources of Latin American universities according to the Webometrics ranking. This case study can serve as a starting point for future research related to accessibility in video-type resources.

ABSTRACT. During the last five years, the sharing economy has emerged as one of the main business models to offer goods and services. Indeed, delivery and transportation are industries for which “sharing” has had one of the biggest impacts, with companies such as: Uber, Lyft or Cabify. However, like in any traditional company, human resource management is an issue for sharing economy firms. Our work aims to infer patterns regarding the performance of human resources in this context. We used unsupervised classification techniques over employee records from a delivery company that uses a sharing economy business model. We propose an automatic and scalable frame- work to discover efficient groups of workers, using features from logistic, geographical and temporal information. Although previous similar works have presented promising results, unlike them, we do not use demographic information about the employees. Our results suggest that deliveries per day, the kilometers covered by the worker and the companies that occupy a delivery agent are important features to determine outstanding workers. The framework proposed can turn into a key point to keep the exponential growth of these kind of companies during the time.

ABSTRACT. Analyzing large amount of geolocated digital transactions made by city residents, one can depict the temporal rhythms of a city. Temporal behavior emerges by aggregating a large amount of data at the intracity level, where we compare sales patterns in different days of the week and at different hours of the day. We get hold of an anonymized dataset of 600K records and aggregate information at neighborhood social level of the city looking for crime indicators, such as thefts, kidnappings, rapes and homicides. Our proposal is aimed at representing these crime rates based on a popularity metric of the neighborhoods of a city defined by the digital transactions made in each one of them. Finally, we obtained excellent correlations for the thefts and kidnappings rates, with a Pearson correlation coefficients of 0.66 and 0.57, respectively, considering one week of the month as our time window and 23h00 as the best hour. This contribution could help to discover crime hostpots based on the sales patters of a neighborhood in a given time.

ABSTRACT. This research proposes the design of a wearable device for acquisition of cardiac signals in real time. The signals are acquired by means of electrodes, in addition they are processed and treated by means of instrumentation amplifiers. This information is sent through the IEEE 802.11 (Wi-Fi) protocol to a database. The electrocardiographic signals and the heart rate are displayed in a web environment which allow to analyze the P, Q, R, S, T and U waves of a normal electrocardiogram. This system was tested on 10 people of different ages in the range of 20 to 50 years. The tests show a system effectiveness of 90% compared with a certified medical device. The design of this portable system offers great comfort and mobility for patients. In addition, it helps practitioners to continuously rate people with heart diseases as well as prepare adequate medical treatments.

ABSTRACT. The use of information technologies in the health domain started decades ago; nevertheless, there are still many issues that need to be addressed. Health Recommender Systems(HRSs) constitute a promising alternative when it comes to providing tools to assist doctors in the diagnosis of diseases, as well as to help patients with recommendations in regards of how to keep their wellness. This work provides insights about the methods and techniques used in the design and development of HRSs, focusing on the types of the recommendations these systems provide and the data representations they employ to build their knowledge base. For this effect, a number of articles published between January 2006 and August 2018, from five different scientific databases, were retrieved. After an examination and selectio nof publications, 249 articles were categorized by means of a classification framework which was built upon related works and the content of the studies analyzed. Furthermore, the results of the classification are presented and major findings are outlined and discussed.

ABSTRACT. The aim of this work is to provide a computational method of calculation of parameters to analyze the exfoliative cytology of the cervix or Papanicolaou (PAP). The parameters calculated are those currently used to diagnose cervical uterine cancer, checked by a cytologist through visual examination of a PAP sample, under a microscope. The aim is to determine the risk of cancer, based on the calculation of parameters of the cell nucleus of the sample, such as its size and shape. It is suggested that a low-cost automated system implements a 4-stage process: (1) to obtain a digital image as from a cytological sample; (2) pre- processing it, implementing mathematical operations; (3) to apply an edge detection algorithm to segment the image, separating and identifying the cells from the rest of the sample; (4) to identify a cell nuclei, classify and measure it, to determine whether it corresponds to a healthy or sick nuclei. This process made possible to detect and measure the nucleus of a sample with an efficiency level of more than 96%. This validates the possibility of automating the process of anomaly detection to prevent the cervical cancer, given that it involves great benefits for the patient.