Applied Informatics

The social appropriation of knowledge (SAK) of a territory is gotten when a society achieves development and applies science, technology and innovation to generate social and economic development.

A Digital Observatory SAK, is a means of using the concepts of visual data analytics (VA) and business intelligence (BI) and based on a proposed conceptual model, seeks to make available to the population and intuitive form, scientific and technological knowledge of a territory.

In this way, it seeks to stimulate the creation and consolidation of spaces for the understanding, reflection and debate of solutions to social, political, cultural and economic problems. Additionally, it is sought that the population can make their own, knowledge such as useful and necessary elements for their benefit and advantage.

This article presents the description of the proposed conceptual model to observe, analyze and monitor the SAK of a territory and how this model is embodied in an interactive web page accessible to the community.

Machine Learning algorithms have many advantages and a great potential for solving complex problems in different domains. However, it is not “magical”. One of its main difficulties lies in recollecting representative data of the domain in order to train the system, otherwise, its efficacy will be seriously compromised. Therefore, a method has been proposed to evaluate the collected data with the assistance of the available domain experts and determine whether it can be used. In this work, the method is applied to evaluate two versions of data gathered on the students’ performance in an undergraduate program course. As a result, it is determined whether they can be used in the training of an Intelligent System that will foretell such performance.

Competitive Intelligence (CI) is a valuable tool that allows organizations to have information relevant to their environment, allowing them to anticipate changes, identify opportunities and focus on innovation. Implement useful methods for the control and systematic monitoring of the impact generated in social networks, is very useful in the context of the CI. This article proposes a methodology designed to process the information obtained about the activity of various Twitter accounts linked to the same institution. The first analysis, based on structured data of the twitters, lets to identify graphically how to find relations between the accounts data over the time. After that, it is presented how Natural Language Processing (NLP) using machine learning techniques could be used to visualize, classify and group the information. The methodology was tested with public data from a university through cloud computing services, so an CI analysis is performed for the institution. As result, we found the identification of crucial discussion topics within the analyzed community is highlighted, as well as the proposal of a control panel for monitoring the various associated accounts.

In today’s world, advertising has become one of the most important aspects of modern life and has impacted society in many ways. We could say, that it has become embedded (even surreptitiously) into the human symbolic universe. On the other hand, social networks play an almost ubiquitous role both in message production and transmission, as well as providing unique insights not readily available through other channels. It is only natural then, to develop strategies capable of automating information retrieval and processing. Our main goal is the construction of an automated process for the constitution of an advertising strategy based on the use of social network data and user provided information. The underlying model considers text mining algorithms along with an innovative content-based decision process constructed in terms of theoretic-semiotic assumptions of pragmatism of Charles Sanders Peirce. We describe a practical application of the proposed methodology in order to obtain the required insights for the future construction of the advertising strategy of an academic institution in Colombia based on Facebook, Twitter and student-surveys as a first step in the development of an automated solution.

Most real-word data can be modeled as heterogeneous information networks (HINs), which are composed of multiple types of nodes and links. Classification for objects in HINs is a fundamental problem with broad applications. However, traditional methods cannot involve in heterogeneous information networks. These approaches could not involve the relatedness between objects and various path semantics. In this paper, we proposed a novel framework called CHIN for classification. It utilizes the relevance measurement on objects to iteratively label objects in HINs. As different meta-path performs different accuracy for classification, the proposed framework incorporates the weights of meta-paths. As our experiments show, CHIN generates more accurate classes than the other classification algorithm, but also provides meaningful weights for meta-paths for classification task.

In this work, we studied the problem of the efficient distribution of insulin, as it is a product of first necessity for the Mexican citizens with diabetes. In contrast to other pharmaceutical products, insulin must be transported with optimal conditions which restrict its distribution time. Similarly, warehousing and production costs must be considered in the supply, storage and distribution decisions given its obsolescence or damage risks. To address this problem, we propose a decision model that integrates distribution within the supply and storage aspects of the insulin supply chain. For this case, we considered variables such as warehousing costs, transportation costs and times, and decisions regarding route and inventory planning. For the development of the integrated decision model, we extended on the capacitated vehicle routing problem (CVRP) model and the Economic Order Quantity (EOQ) model of logistics and supply chain management. When the integrated model was tested on a distribution instance of 100 pharmaceutical retailers, we obtained a more suitable distribution of insulin considering time restrictions and operational warehousing and transportation costs. Thus, the proposed model can be considered for improvement of distribution decisions for other products or retailers in the pharmaceutical industry.

Desktop clouds offer cloud computing services on desktops, simultaneously with users in interactive sessions. Users can affect the virtual machines execution for several reasons. For example, a user can turn-off or reboot the physical machine, or a user can execute demanding applications. A global snapshot of a distributed system is a fault tolerance strategy. In a previous work, we developed the Desktop Cloud Global Snapshot, which obtains the state of the whole system. In case of failure, it is possible to go back to the stored state and resume execution from that point. To recover the system from a global snapshot, we can use the same physical machines or others, if necessary. For this solution it is essential to have a file management system. As global snapshots are created, the number of files that must be handled grows making their management more complex. This article presents the Global Snapshot File Tracker, a software tool that is responsible for maintaining the record of the files that form the state of each virtual machine from its snapshots, and determining what files are required to replicate the state of the virtual machine if it is necessary to resume its execution on another host. The paper includes the background, the problem statement, the proposed solution, the developed solution, and the functionality and evaluation.

This paper presents a web system named TBDiagnostic for data acquisition, analysis and diagnosis of pulmonary tuberculosis. With the help of an artificial intelligence model, which generates a prediction of the diagnosis of tuberculosis, the system allows the user to generate a fast and accurate diagnosis of a person with symptoms of tuberculosis. The system allows to storage patient records and generate reports on these records. This system could help physicians who treat the disease especially in health centers and hospitals with limited infrastructure and data as it is the case of developing countries.

The Integrating the Healthcare Enterprise (IHE) advocates for the integration of distributed and heterogeneous health information systems. This is achieved through the development of standards that specify protocols through which the integrated systems can communicate as profiles. In Namibia, healthcare services are extended to communities through community health workers (CHW). Most CHW are sent to the field to educate and raise awareness of diseases in the communities. However, there is no platform for them to communicate the disease surveillance information to the regional and Head offices in real-time. The IHE, through its Information Technology Infrastructure Technical Framework Volume 2b Transaction B provides a Cross-Gateway Patient Discovery (XCPD) profile that can support the means to locate communities which hold patient-relevant health data as well as the translation of patient identifiers across communities that hold similar patient data. The XCPD profile can be adapted to support communication between the CHW, the DHIS-2 in the Ministry of Health and Social Services (MoHSS) and silo HIS in the regional hospitals, for them to share and also to exchange information within a health information exchange ecosystem. At the present moment, the DHIS-2 and the silo health information systems work in isolation simply because these HIS are heterogeneous, they are not interfaced and also not distributed. The study sought to develop a framework to enable the semantic interoperability of the DHIS-2, silo systems and CHWs for data semantic interoperability so that they can exchange disease-surveillance information.

The advent of imaging methods in medicine has yielded new diagnosing dynamics inside hospitals. Since imaging allows the inspection with few or no intrusiveness, there is a remarked intention in producing medical verdicts from the radiology data by implementing computational algorithms and, therefore preclude the use of the long-lasting analytics that involve manual segmentation or often painful procedures such as histology. Currently, troves of medical-imaging data are stored in the picture archiving and communication system (PACS) – the standard imaging database –. The massive storage is initially created and maintained obeying to the legal regulations, but the resulting repository holds unbeatable conditions to apply artificial intelligence and derive conclusions from hidden patterns, a new mechanism never envisaged before. However, the same regulations that enabled the creation of the medical imaging repository have precluded the quantifications from images stored in PACS.

This paper presents a strategy that empowers PACS so that analytical procedures can run without violating confidentiality policies or creating security breaches. The platform supports unlimited analytical procedures, and, as a prof of concept, the problem of accurately measuring the maximum head circumference in pediatrics is solved and presented.

The design of virtual scenarios and organic models, through the use of virtual reality with the inclusion of photorealism, with all these components can develop a process of handling reactions to phobias that generates an immersive experience similar to reality, obtaining as a result an alternative treatment to arachnophobia, this contribution of help can be partial or total, since it will depend on the time of use. To verify the states of improvement in the users that are submitted to the test of the application, guidelines will be provided to continue the research using a set of technological tools for the area of phobia treatment, as well as the connection of virtual reality in other branches of medicine.

Today we live in a world full of digital content. Digitalization is growing and the use of cyber-physical systems too. A cyber-physical systems (CPS) is a system that integrates both physical and virtual capabilities which communicates via a network. Attributes of CPSs includes real-time, fault-tolerance, security, safety, scalability, reliability, distributed, adaptability and heterogeneity. Hence, security for CPS is very crucial due to the nature of CPS and the interaction with the physical world. Therefore, the use of effective security mechanisms is crucial. Moreover, we have to ensure that we build these systems in a way that they meet the CPS specific requirements and to adapt the security mechanism accordingly, since the security threats of CPSs differ from classical software. This paper analyzes the security threats of cyber-physical systems, presents countermeasure to these threats and propose a security based reference architecture for cyber-physical systems. Furthermore, the architecture is applied on a case study of smart home to validate the proposed architecture. The proposed security based reference architecture is a good start to focus on this important aspect of security for CPS and great contribution to the research community.

A number of solutions were advanced for problems of delays and overcrowdings of networks such as caches and proxies. The purpose of caches and proxies was to bring information closer to the users by serving user requests as if there were originating servers. Later, other challenges evolved as a consequence of caches and proxies for the Internet content distribution and services. Web caches are situated between Web servers (or originating servers) and clients in order to fulfils HTTP propagated requests instead of the servers. The distinct features of Web caches is storage of copies of objected requested lately which are used quickly fulfils the requests without the need to transfer object from the distant original server. Though, caches can be classified into browser cache, client-side cache and server-side cache. Nowadays, several CDNs (such as Akamai and DigitalIsland) are faced with imminent storage congestion and management. This paper offered best media access controls architecture for the CDNs for improved quality of service, integrity and content sharing.

Information Security (IS) Risk Assessment is a main part of risk analysis; it helps organizations make decisions to protect their Information Technology (IT) services and underlying IT assets from potentially adverse events. How to do assessment in this context, however, is not a well defined task. Some approaches provide guidelines but leave analysts to define how to implement them, leading to different mechanisms to identify input data, different procedures to process those inputs, and different results as a consequence. To address this problem, we present a semiautomatic procedure, based on data systematically obtained from modern IT Service Management (ITSM) tools used by IT staff to handle IT services’ assets and configurations. We argue that these tools handle actual data that may be used to collect inputs for a IS risk assessment procedure, thus reducing subjective values. We evaluated the procedure in a real case study and found that our approach actually reduces variability of some results. We also identified areas that must be addressed in future work.

This study seeks to develop an automated solar-powered irrigation system. This will provide a cost-effective solution to the traditional irrigation method. This project is aimed at designing a system that harnesses solar energy for smart irrigation and allows for more efficient way to conserve water on the farmland. The system developed is portable and is designed to be adaptable to existing water system. The system incorporates wireless communication technology established using NRF module. For easy operations, the system can be controlled via an Android app-enabled with Bluetooth network. The user experience allows selection of either manual control for scheduled irrigation or automatic control using wireless sensors.

Currently, there are different trends in terms of education. Some of these trends require the support of information technologies. For example, since some years ago, the flipped classroom educational model has been presented, which is a strategy that reverses the traditional learning model through instructional content developed by students. Flipped classroom is directly related to blended learning, which is a methodology that combines the traditional classroom learning environment with the use of online digital material. Moreover, blended learning requires both students and teachers, who communicate in presence and virtual manners. This paper presents a Virtual Learning Environment (VLE) as a technological tool for the development of learning activities and language teaching with the flipped classroom model in the blended learning education program. This VLE allows highlighting the importance of monitoring and feedback to the student from the collected data. Likewise, the VLE allows highlighting the importance of the teacher as the main actor behind the operation of the software. Finally, the VLE articulates the methodological proposal allowing the virtual work and the classroom class.

The concept of educational games is to aid students in understanding various subjects in an interactive and engaging environment. Subjects like mathematics have continued to pose a challenge to many secondary school students in developing countries like Nigeria as seen from recent low performance in the Senior Secondary Certificate Examination (SSCE). Lack of interest is one of the key factors that contribute to the low performance hence there is need for a system that can help to improve student’s interest in mathematics and subsequently their rate of success. The goal of this study is thus to develop an educational game software to help stimulate students’ interest in mathematics and to also help them in understanding and improving their performance in the subject. The game was created by leveraging on the Unity game engine platform and the programming language used for development was C#.

In linear e-Learning management systems, also referred to as Learning Management Systems (LMS), content is presented to the learners in the same way irrespective of their different learning styles, educational, social and historical background, their interests and learning abilities. In education recommender-based adaptive systems, learning is personalized and differentiated, taking into consideration the students’ different attributes. Adaptivity is automatic adjustment of the content provided to learners to suit their individual attributes. Personalisation is the ability to provide content and services that are tailored to individuals based on knowledge about their preferences and behavior. This research applies pedagogical foundations of teaching and learning in identifying learner attributes to go into an educational recommender-based adaptive system. Through a literature review, 40 attributes of personalized/differentiated learning were identified. A user-centric approach was adopted to prioritise the attributes in order to identify the 10 top attributes. This was done by using the Multi-Attribute Utility Theory (MAUT). The 40 attributes of personalised learning initially fed into questionnaires for students. From a population of 1203 students from a higher education college called EDU-REC, for the purpose of this research and to preserve anonymity of the college, a sample of 200 students was purposively selected for the research on the basis of their familiarity with the college’s eLearning system, and 103 students responded to the questionnaire representing a response rate of 52%. From the responses of the students, the following top ten (10) attributes were identified for inclusion in an educational recommender platform: culture, emotional/mental state, socialisation, motivation, learning preferences, prior knowledge, educational background, learning/cognitive style, and navigation and learning goals.

In the world today, smartphones are evolving every day and with this evolution, security becomes a big issue. Security is an important aspect of the human existence and in a world, with inadequate security, it becomes an issue for the safety of the smartphone users. One of the biggest security threats to smartphones is the issue of malware. The study carried out a survey on malware detection techniques towards identifying gaps, and to provide the basis for improving and effective measure for unknown android malware. The results showed that machine learning is a more promising approach with higher detection accuracy. Upcoming researchers should look into deep learning approach with the use of a large dataset in order to achieve a better accuracy.

Based on the literature, it is possible to build voice recognition systems by using voice synthesizers and voice command controls. In addition, phonemes recognition can be made by implementing algorithms already created for this kinds of tasks. Nevertheless, phonemes recognition might generate some errors, when the implementation of such algorithms is unsuitable. Then, the possibility to perform phonemes recognition based on open source APIs arises. In the work presented in this paper, we used open source APIs for voice commands recognition. Thus, we propose an architecture that allows the construction of a system for phonemes recognition and voice synthesizers. The results have been implemented and validated in order to illustrate the reliability of the proposed architecture.

A company’s ability to be mobile is the capability to transact anytime, anywhere, Mobile information and communication technologies (ICT) ability to transform businesses is attributed to the dynamic capabilities (DCs) of ICT. In response to changing technologies and as a means to gain profits, organizations use DC, which is a catalyst of the business ability to design and adjust resources. As such DCs effect is also felt on resource base affording the organization competitive advantage. In this qualitative Namibian case study, the DCs of mobile ICT were closely analyzed as a means to investigate the usage of DCs of mobile ICT by Namibian Small and Medium Enterprises (SME), and how it can enhance SME transformation and strategies used for its adoption. The analysis of this study was conducted using the Theory of Dynamic Capabilities. For this study 40 SMEs were identified by means of convenience sampling and one employee per SME by means of purposive sampling. The collection of data was primarily through interviews and questionnaires subsequently the data was coded. The results showed that although some SMEs in Namibia use technology, there is still a significant number that is oblivious to the advantages that DCs of mobile ICT can offer. The researcher therefore recommends that governing bodies of Namibian SMEs enforce policies that facilitate the adoption of mobile ICT and sponsor local SMEs as conduit for economic advancement; that owners of SMEs adopt mobile ICT as a means to gain competitive advantage; that SMEs with existing mobile ICT infrastructure should look into ways of adopting diverse DCs of mobile ICT thus creating a better environment for faster service delivery; that SMEs should adopt the culture of ICT training to enable employees to effectively use mobile ICT; that in order to reduce software costs SMEs should opt for open source applications; and that as means to gain visibility and increase customer base SMEs should make use of mobile technology to market their services and products.

A real-world reconstruction from a computer graphics tool is one of the main issues in two different communities: robotics and artificial intelligence, both of them under different points of view such as computer science, perception and machine vision. A real scene can be reconstructed by generating of point clouds with the help of depth sensors, rotational elements and mathematical transformations according to the mechanical design. This paper presents the development of a three-dimensional laser range finder based on a two-dimensional laser scanner Hokuyo URG-04LX-UG01 and a step motor. The design and kinematic model of the system to generate 3D point clouds are presented with an experimental acquisition algorithm implemented on Robotic Operative System ROS in Python language. The quality of the generated reconstruction is improved with a calibration algorithm based on a model parameter optimization from a reference surface, the results from the calibrated model were compared with a commercial low-cost device. The concurrent application of the system permits the viewing of the scene from different perspectives. The output files can be easily visualized with Python or MATLAB and used for surface reconstruction, scene classification or mapping. In this way, typical robotic tasks can be realized, highlighting autonomous navigation, collision avoidance, grasp calculation and handling of objects.

This article presents the parallel implementation, using a graphical processing unit (GPU), of a Sequential Monte Carlo Method, which is a sophisticated model estimation technique based on simulations, also known as Particle Filter. The particle filter is applied to the localization of a simulated Ackerman mobile robot with a simplified kinematic model. The inputs for the model are the linear displacement of the car and the steering angle, subject to additive white Gaussian noise disturbances. The car model integrates a simulated GPS and a compass which also present Gaussian noise. The program was designed using a client/server architecture, considering that the energy constraints of embedded systems used in mobile robotics favor the separation of the tasks of visualization and localization. The client is a web program responsible for the task of visualization, developed in HTML5 using JS and AJAX, and the server implements the particle filter algorithm using the libraries CUDA and Thrust, improving considerably the performance time of the particle filter. The performance is approximately 9 times faster in GPU over CPU in the tested architecture. This opens the possibility to embed this type in simulations in real-time systems.

The present paper proposes the approach of locomotion in mammals to be applied in articulated robotics. This is achieved using Central Pattern Generators by amplitude modulation of oscillatory signals to communicate the angle of rotation of each of the joints that are involved in a specific type of locomotion. Performing simulations to determine viability by frequency and amplitude, a better response was found in the amplitude modulation. A series of locomotion data with dogs were compiled and used as a reference for the amplitude modulation of the differential equation systems that replicate the Central Pattern Generators of the articulations of the quadrupedal robot. Recurrent neural networks in continuous time were used to represent the CPG. The angle was modulated as a function of the amplitude of the cyclic signal produced by the Central Pattern Generators allowing to manage the setpoints (angles) for a given articulation, between 0° and 90°. Other works, although related to Central Pattern Generators, and some focused on reproducing the model, none of them deals with the construction of modulated signals that represent joint angles based on data obtained from biomechanical studies of locomotion by quadrupeds. A distributed autonomous control architecture based on modular and hierarchical Central Pattern Generators, organized in two layers, that simultaneously synchronizes and executes the movement of each joint from each leg, and for the total movement production is proposed.

Small and medium enterprises (SMEs) represent one of the main forces in economic development and employment generation. It is expected that these SMEs can turn towards new manufacturing paradigms such as Industry 4.0 to ensure their competitiveness in a future market. Nevertheless, these companies regard Industry 4.0 more as a challenge rather than a chance or as enabler for new value added opportunities. For this reason, in this article a literature review of Industry 4.0 officials reports and standards is carried out, in order to define a step by step the procedure of manufacturing resources migration towards Industry 4.0 by means of digital retrofitting, specifying both hardware and software requirements, the systems structure and required technology mapping for the Industry 4.0 implementation over traditional manufacturing resources. The main objective is to obtain the benefits of applying the Industry 4.0 paradigm without incurring in huge investments and provide technologic tools to SMEs that allow them to participate in globalized markets. Finally, the proposed methodology is applied in the retrofitting of a CNC machine given as result an industry 4.0 component ready to be integrated on a high-level application.

Currently, there are a lot of enterprises around the world dedicated to the same business e.g. banking, academy, trading, etc. All of those enterprises require specific information systems; however, information systems in the same business have several similar or equal features. Consequently, it is possible to create one information system for one specific business reusing components developed previously in another information system of the same specific business. Since enterprises from the same business are different, their information systems are different (e.g., academic institutions). In this paper, we present an approach to offer the capability to reuse software components that have been created for solving some specific processes. So, for this approach, it is necessary to have some core components and several auxiliary components. Based on this set of components, it is possible to combine them in order to get a functional information system for one specific enterprise in one specific business.

Nowadays, companies have moved from offering a single product for all their clients, to offer different customized for each one. These companies provide Configuration Systems where a user can decide and discard which features she wants in her final product. However, although almost all of these systems support individual decisions, usually they do not offer an special support for decisions made by multiple users for the same product. This paper introduces Multi-SPLOT, a web-based Configuration System that supports simultaneous decisions from multiple users. This system uses off-the-shelf solvers to determine if these decisions are not conflicting among them, and to propose solutions when the decisions of an user conflict with decisions of the others. This paper shows the design of the solution and details of its implementation using Angular, Firebase and the optimization library in Google App Script.