Mobile Device Applications Research Articles

Exploring convolutional neural networks with transfer learning for diagnosing Lyme disease from skin lesion images

Background and objectiveLyme disease which is one of the most common infectious vector-borne diseases manifests itself in most cases with erythema migrans (EM) skin lesions. Recent studies show that convolutional neural networks (CNNs) perform well to identify skin lesions from images. Lightweight CNN based pre-scanner applications for resource-constrained mobile devices can help users with early diagnosis of Lyme disease and prevent the transition to a severe late form thanks to appropriate antibiotic therapy. Also, resource-intensive CNN based robust computer applications can assist non-expert practitioners with an accurate diagnosis. The main objective of this study is to extensively analyze the effectiveness of CNNs for diagnosing Lyme disease from images and to find out the best CNN architectures considering resource constraints. MethodsFirst, we created an EM dataset with the help of expert dermatologists from Clermont-Ferrand University Hospital Center of France. Second, we benchmarked this dataset for twenty-three CNN architectures customized from VGG, ResNet, DenseNet, MobileNet, Xception, NASNet, and EfficientNet architectures in terms of predictive performance, computational complexity, and statistical significance. Third, to improve the performance of the CNNs, we used custom transfer learning from ImageNet pre-trained models as well as pre-trained the CNNs with the skin lesion dataset HAM10000. Fourth, for model explainability, we utilized Gradient-weighted Class Activation Mapping to visualize the regions of input that are significant to the CNNs for making predictions. Fifth, we provided guidelines for model selection based on predictive performance and computational complexity. ResultsCustomized ResNet50 architecture gave the best classification accuracy of 84.42% ±1.36, AUC of 0.9189±0.0115, precision of 83.1%±2.49, sensitivity of 87.93%±1.47, and specificity of 80.65%±3.59. A lightweight model customized from EfficientNetB0 also performed well with an accuracy of 83.13%±1.2, AUC of 0.9094±0.0129, precision of 82.83%±1.75, sensitivity of 85.21% ±3.91, and specificity of 80.89%±2.95. All the trained models are publicly available at https://dappem.limos.fr/download.html, which can be used by others for transfer learning and building pre-scanners for Lyme disease. ConclusionOur study confirmed the effectiveness of even some lightweight CNNs for building Lyme disease pre-scanner mobile applications to assist people with an initial self-assessment and referring them to expert dermatologist for further diagnosis.

Section2 - Applications of mobile devices in miniaturized analysis

Section2 - Applications of mobile devices in miniaturized analysis

Об одном опыте составления фразеологического словаря, его стилевых аспектах и прикладном значении для перевода

This article studies an experience of making an English-to-Russian and Russian-to-English dictionary of set expressions implemented as an application for mobile devices. Here we elaborate on its basic ideas and requirements used in modern interpreting. Further, we provide key facts about the dictionary, its structure and organization, describe the compilation process including how we established criteria for choosing relevant language units, as well as highlight their analysis method with reference to different sources. Further, considering the stylistic gradation of target-language semantic analogues in relation to source-language units offered in the dictionary, we give a separate emphasis to difficulties experienced when determining the register of set phrases. Additionally, we cover a number of their aspects which may be taken into account to decide on a stylistic category. We identify typical features of some registers and suggest criteria for differentiating between set expressions in terms of their style. Our theoretical observations are accompanied by the comparison of English and Russian units specifying their similarities and differences that were noted when composing the dictionary. Its solutions are considered from the perspective of popular interpreting techniques with regard to set phrases: use of existing target-language analogues, literal translation, and conveyance of connotative equivalents. We also promote experimental approaches that intend to help translators in their work. In conclusion, we summarize the novelties of the dictionary, estimate its user-friendliness and applicability to the practical aspects of translation and interpreting, and make suppositions about its future potential.

My Latent Tuberculosis Treatment - mobile application to assist in adherence to latent tuberculosis treatment

According to the World Health Organization (WHO), latent tuberculosis occurs through latent infection by Mycobacterium tuberculosis without evidence of active tuberculosis (TB) symptoms. As patients don’t develop the same symptoms as active TB, the treatment is abandoned before the end, as it lasts about six months. This leads to significant treatment avoidance, requiring new forms of adherence to latent TB treatment. One of the strategies to help to latent TB treatment is the possibility of using applications for mobile devices, once the use of ICTs to aid in the treatment of LTBI can increase the rate of treatment adherence. Thus, this work aimed to study the creation of a technology that helps the adherence of these patients, being made available an application that is easy to use, intuitive, free and developed in a language for Android phones, which accompany the patient throughout the treatment.

Development and testing of a mobile application for periodontal diagnosis

BackgroundThe new classification of periodontal diseases introduced a new set of rules for periodontal diagnosis. The objective of this study was to develop and test the implementation of a mobile device application for periodontal diagnosis. Material and MethodsAn integral algorithm that included periodontal health / related conditions and periodontitis was developed based on the classification of periodontal diseases of 2018. A mobile application for Android implementing the algorithm was developed using the framework MIT App Inventor. Once the app was debugged for glitches and performance of the algorithm, it was tested with 20 voluntary dental students, postgraduate students of periodontology, and professors in an academic setting. Participants were asked to determine the diagnosis of 10 predetermined clinical cases using two strategies: diagnosis based on knowledge and with the PerioSmart app. The results were tabulated, and the concordance rate was calculated. ResultsIn general, the use of the PerioSmart application had a better concordance rate than diagnosis based on knowledge. In particular, the mobile app was better in determining the type of diagnosis, stage/grade of periodontitis, and with better efficiency. ConclusionsThe mobile device application demonstrated efficiency and good concordance rate and therefore can improve the periodontal diagnosis. Key words:Mobile application, periodontal diagnosis, periodontitis, gingivitis.

Digital tools to support the maintenance of physical activity in people with long-term conditions: A scoping review

ObjectiveThis scoping review aimed to bring together and identify digital tools that support people with one or more long-term conditions to maintain physical activity and describe their components and theoretical underpinnings.MethodsSearches were conducted in Cumulative Index to Nursing and Allied Health Literature, Medline, EMBASE, IEEE Xplore, PsycINFO, Scopus, Google Scholar and clinical trial databases, for studies published between 2009 and 2019, across a range of long-term conditions. Screening and data extraction was undertaken by two independent reviewers and the Preferred Reporting Items for Scoping Reviews guidelines informed the review's conduct and reporting.ResultsA total of 38 results were identified from 34 studies, with the majority randomised controlled trials or protocols, with cardiovascular disease, type 2 diabetes mellitus and obesity the most common long-term conditions. Comorbidities were reported in >50% of studies but did not clearly inform intervention development. Most digital tools were web-browser-based ± wearables/trackers, telerehabilitation tools or gaming devices/components. Mobile device applications and combination short message service/activity trackers/wearables were also identified. Most interventions were supported by a facilitator, often for goal setting/feedback and/or monitoring. Physical activity maintenance outcomes were mostly reported at 9 months or 3 months post-intervention, while theoretical underpinnings were commonly social cognitive theory, the transtheoretical model and the theory of planned behaviour.ConclusionsThis review mapped the literature on a wide range of digital tools and long-term conditions. It identified the increasing use of digital tools, in combination with human support, to help people with long-term conditions, to maintain physical activity, commonly for under a year post-intervention. Clear gaps were the lack of digital tools for multimorbid long-term conditions, longer-term follow-ups, understanding participant's experiences and informs future questions around effectiveness.

Online Bus Monitoring and Reservation Application (OBMRA) for GL Trans Agency

Online bus tracking and reservation applications an application for mobile devices that functions on a centralized network. The software application "Online bus monitoring and reservation application” provides a bus transportation system, the opportunity to book seats, the cancellation of tickets, and a variety of inquiries needing prompt and swift reservations. Online bus reservation and monitoring apps are intended to facilitate the management and computerization of traditional databases and the booking, tracking, and monitoring of buses and travel. It allows workers to check ticket availability and make reservations for specific clients. It maintains all user data, including bus, reservation, booking, and customer data.

A tecnologia e a depressão: um aplicativo como ferramenta para cuidado em saúde

The aim was to develop an application for mobile devices as an instrument to support family and close friends of depressed people with potential risk of self-extermination. Applied research of technological production aimed at developing an application for a mobile device that provides information on risk factors for suicidal acts and guidelines applied. The application, developed by the adapted Scrum method, informs the possible manifestations and behaviors of the person at risk, through information provided by the user, through a platform in the chat format, mediated by a virtual agent. The application developed for the use of family members or people close to those with depression and risk of self-extermination can provide access to education for the population and families regarding the manifestations suggestive of the unfavorable evolution of depression. Therefore, it is necessary to carry out a detailed study with the evaluation of experts to analyze its quality and usability. It is expected that this application can reach a standard of excellence in meeting the needs of users as an instructive and updated tool, based on evidence, offering quality assistance and harm mitigation.

Approximate or accurate? Efficacy of daily use of weather and air quality mobile applications for pollen allergy sufferers?

Nowadays, technology permeates every aspect of human activity, from the professional to the recreational side, and the recent pandemic crisis has only amplified a clearly defined trend. Through portable devices, people play, work, and get information. The immediacy of information and of many aspects of our life is a condition that, once acquired, is difficult to give up. However, immediate information must also be correct, and not all issues can easily be simplified to the point of being understandable in the absence of basic theoretical notions to a large audience. This aspect is particularly relevant when dealing with issues related to human health and the communication problems encountered in recent months concerning the spread of SARS-CoV-2, and the vaccination campaign is there to prove it. With the intent of clarifying the advantages and disadvantages of fast and accessible information, in this article, some of the most widespread applications for mobile devices, dedicated to pollen allergens, air quality, parks, gardens, and green areas, were examined. A widespread lack of clarity on the sources of the data and on the criteria used to formulate synthetic judgments-that often confuse the final users-was noted.

Development and content validation of a mobile application for monitoring latent tuberculosis treatment.

ABSTRACTBackground: Non-compliance with latent tuberculosis infection (LTBI) treatment is a reality. The objective of this study was to develop and validate an mobile device application for monitoring the treatment of LTBI. Methods: We defined the requirements, elaborated on the application's conceptual map, generated implementation and prototyping alternatives, and validated content. Results: Feedback on the validity of content were: “usefulness, consistency, clarity, objectivity, vocabulary, and precision” from professionals, and “clarity” from patients. Conclusions: The application proved to be easy to understand, according to the assessment of both professionals and people undergoing treatment for LTBI.

Multitouch Pressure Sensing With Soft Optical Time-of-Flight Sensors

This article reports on optical time-of-flight (ToF) as a detection mode for soft optical deformation sensors. In this work, low-cost miniature light detection and ranging (LiDAR) chips recently developed for consumer mobile device applications perform real-time optical reflectometry at cm scales in soft optical waveguide networks. Our methods complement existing work by capturing spatial information that is lost with amplitude-only measurements. We demonstrate its application in a multitouch button system capable of extracting displacement values from soft optical switches with average error in the range of 100–200 microns on 1.75 mm of the switch travel. Because making reliable electronic connections to soft materials is a challenging task, we focus on minimizing connector count. In a tracking application, we find the centroid of an object on a three-point supported plate using three optical pressure switches connected to a single LiDAR sensor.

Time-Constrained Service Handoff for Mobile Edge Computing in 5G

Many mobile device applications require low end-to-end latency to edge computing infrastructure when offloading their computation tasks in order to achieve real-time perception and cognition for users. User mobility brings significant challenges in providing low-latency offloading due to the limited coverage area of cloudlets. Virtual machine (VM)/container handoff is a promising solution to seamlessly transfer services from one cloudlet to another to maintain low latency as users move. However, an inefficient path planning for the handoff can result in system congestion and consequently poor quality of service (QoS). The situation can even worsen by selfish users who intentionally lie about their true parameters to achieve better service at the cost of degrading the whole system's performance. To fill this research gap, we propose an Online Service Handoff Mechanism (OSHM) to provide an efficient path dynamically for transferring VM/container from the current serving cloudlet to a nearby cloudlet at the destination of a mobile user. Our proposed path planning algorithm is based on a label correction methodology, leading to polynomial time complexity. OSHM is accompanied by our proposed payment determination function to discourage misreporting of unknown parameters. We discuss the theoretical properties of our proposed mechanism in implementing a system equilibrium and ensuring truthfulness. We also perform a comprehensive assessment through extensive experiments which show the efficiency of OSHM in terms of workload, handoff time, consumed energy, and other metrics compared to several benchmarks. Experimental results show that OSHM outperforms other algorithms, reducing at least 61% in average workload, 33% in average handoff time, and 29% in average energy consumption.

M-Learning and Learning Autonomy - Needs Analysis and Suggested Model

In this 4.0 era, where technology has been a part of our daily lives, the integration of smart devices into education is an indispensable movement that we are striving for. Hence, the application of mobile devices into learning, M-learning is becoming a trendy approach and a quality assurance’s measurement for almost every academic institution. Technology makes education available for students almost anywhere, anytime, and offers unlimited access to learning resources. Furthermore, M-learning is also reported to have a positive impact on students’ learning autonomy. Hence, this paper aims at validating possibilities to amplify this aspect of M-learning and suggesting an appropriate M-learning model at Nguyen Tat Thanh university (NTTU). The paper investigates students’ needs, requirements, ability to adapt to the new trend of M-learning plus the external elements affecting their learning autonomy to come up with the learning model. Surveys were collected from students in the Faculty of Foreign Languages and analyzed using a qualitative method to provide educators and teachers at NTTU with insightful information and careful preparation before launching new approaches to M-learning.

An Interactive Information System That Supports an Augmented Reality Game in the Context of Game-Based Learning

Mobile augmented reality applications are gaining prominence in education, but there is a need to design appropriate and enjoyable games to be used in educational contexts such as classrooms. This paper presents an interactive information system designed to support the implementation of an augmented reality application in the context of game-based learning. PlanetarySystemGO includes a location-based mobile augmented reality game designed to promote learning about the celestial bodies and planetary systems of the Universe, and a web application that interacts with the mobile device application. Besides face-to-face classes, this resource can also be used in online classes, which is very useful in social isolation situations as the ones caused by the COVID-19 pandemic. Furthermore, it is the inclusion of the web application, with a back-office, in the information system that makes it possible to include curricula contents according to the grade level of students. Moreover, it is intended that teachers use the information system to include the contents they find appropriate to the grade level they teach. Therefore, it is crucial to provide their professional development to be able to use this resource. In this regard, a pilot study was conducted with teachers who participated in a STEM professional development programme in order to assess if the system is appropriate to be used by them. It is concluded that teachers found this resource relevant to motivate students to learn, and also acknowledged that the web application facilitated the introduction of appropriate curricula contents and also was useful to assess student performance during the game. Teachers need support, however, to implement these types of technologies which are not familiar to them. The necessary support can be provided through collaboration among the researchers and teachers in their schools. Besides engaging students to learn about celestial bodies, it is concluded that the information system can be used by teachers to introduce appropriate curricula contents and to be implemented in class.

A Clinical Risk Model for Surgical Site Infection Following Pediatric Spine Deformity Surgery.

Despite tremendous efforts, the incidence of surgical site infection (SSI) following the surgical treatment of pediatric spinal deformity remains a concern. Although previous studies have reported some risk factors for SSI, these studies have been limited by not being able to investigate multiple risk factors at the same time. The aim of the present study was to evaluate a wide range of preoperative and intraoperative factors in predicting SSI and to develop and validate a prediction model that quantifies the risk of SSI for individual pediatric spinal deformity patients. Pediatric patients with spinal deformity who underwent primary, revision, or definitive spinal fusion at 1 of 7 institutions were included. Candidate predictors were known preoperatively and were not modifiable in most cases; these included 31 patient, 12 surgical, and 4 hospital factors. The Centers for Disease Control and Prevention definition of SSI within 90 days of surgery was utilized. Following multiple imputation and multicollinearity testing, predictor selection was conducted with use of logistic regression to develop multiple models. The data set was randomly split into training and testing sets, and fivefold cross-validation was performed to compare discrimination, calibration, and overfitting of each model and to determine the final model. A risk probability calculator and a mobile device application were developed from the model in order to calculate the probability of SSI in individual patients. A total of 3,092 spinal deformity surgeries were included, in which there were 132 cases of SSI (4.3%). The final model achieved adequate discrimination (area under the receiver operating characteristic curve: 0.76), as well as calibration and no overfitting. Predictors included in the model were nonambulatory status, neuromuscular etiology, pelvic instrumentation, procedure time ≥7 hours, American Society of Anesthesiologists grade >2, revision procedure, hospital spine surgical cases <100/year, abnormal hemoglobin level, and overweight or obese body mass index. The risk probability calculator encompassing patient, surgical, and hospital factors developed in the present study predicts the probability of 90-day SSI in pediatric spinal deformity surgery. This validated calculator can be utilized to improve informed consent and shared decision-making and may allow the deployment of additional resources and strategies selectively in high-risk patients. Prognostic Level III. See Instructions for Authors for a complete description of levels of evidence.

Content Analysis of Mobile Device Applications for Artistic Creation for Children between 4 and 12 Years of Age

This article presents the results of the content analysis of 32 painting and drawing mobile applications aimed at children between 4 and 12 years old. The characteristics of the artistic dimension were studied, such as the possibilities of drawing, color, and experimentation, as well as the characteristics of the technical dimension related to the visual design of the interface, usability, and adaptability to users. The results collected show that mobile apps offer tools that have great potential for artistic and creative development, but also reveal certain limitations and problems in the quality of the graphic tools and interface design. One of the central problems of the interfaces of these apps is related to decontextualization and the lack of attention to the diversity and the heterogeneity of users in that age group.

The method of vicinity minutiae decomposition with higher level graphs for fingerprint verification

The subject matter of the paper is the development of fingerprint local structures based on the new method of the minutia vicinity decomposition (MVD) for the solution to the task of fingerprint verification. It is an essential task because it is produced attempts to introduce biometric technology in different areas of social and state life: criminology, access control system, mobile device applications, banking. The goal is to develop real number vectors that can respond to criteria for biometric template protection schemes such as irreversibility with the corresponding accuracy of equal error rate (EER). The problem to be solved is the problem of accuracy in the case of verification because there are false minutiae, disappearing of truth minutiae and there are also linear and angular deformations. The method is the new method of MVD that used the level of graphs with many a point from 7 to 3. This scheme of decomposition is shown in this paper; such a variant of decomposition is never used in science articles. The following results were obtained: description of a new method for fingerprint verification. The new metric for creating vectors of real numbers were suggested – a minimal path for points in the graphs. Also, the algorithm for finding out minimal paths for points was proposed in the graphs because the classic algorithm has a problem in some cases with many points being 6. These problems are crossing and excluding arcs are in the path. The way of sorting out such problems was suggested and examples are given for several points are 20. Results of false rejection rate (FRR), false acceptance rate (FAR), EER are shown in the paper. In this paper, the level of EER is 33 % with full search. 78400 false and 1400 true tests were conducted. The method does not use such metrics as distances and angles, which are used in the classical method of MVD and will be used in future papers. This result is shown for total coincidences of real number, not a similarity that it is used at verifications. It is a good result in this case because the result from the method index-of-max is 40 %.

Using Telemedicine to Provide Education for the Symptomatic Patient with Chronic Respiratory Disease.

Technology-enabled learning, using computers, smartphones, and tablets, to educate patients on their respiratory disease and management has grown over the last decade. This shift has been accelerated by the global COVID-19 pandemic and the need to socially distance for public health. Thirteen recently published papers examined experience, knowledge, skills and attitude acquisition, behaviour change, and impact on health outcomes of patient education using technology (websites and mobile device applications) for people with chronic respiratory disease. Technology-enabled patient education that includes relevant information, with activities that encourage the patient to interact with the digital platform, appears to lead to better patient experience and may increase learning and behaviour change with improved quality of life. Developing online relationships with healthcare providers, lower digital capabilities, and poor access to a computer/smartphone/tablet, appear to be barriers that need to be overcome for equity in access. Maintaining the principles of quality educational design, ensuring interactive experiences for patient involvement in the educational activities, patient co-design, healthcare professionals connecting with experts in the field of technology-enabled learning for development of education models, and ongoing research lead to the best patient outcomes in technology-enabled education for respiratory disease.

MeLOD

In the last few years, many applications for mobile devices have been developed to support learning experiences both in formal and informal contexts. One of the main limits of these applications concerns the development of learning materials suitable for mobile learning contexts. In fact, learning content must be usually prepared in advance by teachers and maintained during the whole lifespan of the application. In this paper, we present MeLOD, a mobile learning environment, which exploits the huge amount of dataset in the Linked Open Data (LOD) cloud to overcome the previous issue, and provides contextualized and continuously updated information based on students’ location. The position of the student sent by the mobile device is used to interlink Geonames DBpedia and Europeana datasets to provide information about all the interesting cultural heritage sites close to the student. Moreover, students social activities like voting and commenting are used to enhance the knowledge base of the environment and to provide recommendations for next students’ visits.

The Effectiveness of Mobile Device-Based Digital Interventions on the Risk Factors of Diabetes Mellitus Control in the Industrial Revolution 4.0

ABSTRACTBackground: Diabetes mellitus is a chronic disease which if not done properly, can cause microvascular and macrovascular disorders. Indicators of the accuracy of diabetes management in this scientific article include education, self-management (improving diet, increasing physical activity, and self-efficacy), and monitoring of HbA1c levels. Mobile devices have the potential as a tool for diabetes mellitus management in the era of the industrial revolution 4.0.Purpose: to provide the latest information regarding the effectiveness of using mobile devices in controlling risk factors for diabetes mellitus.Method: This study is a literature review study. The electronic databases used are Google Scholar, Science Direct, and Directory of Access Journals (DOAJ). Inclusion criteria: original research, a journal of at least 80% indexed by Sinta (Indonesian journal) and indexed by Scopus (international journal), published year 2010-2020, intervention using a mobile device, has an output of HbA1c levels, self management (diet, physical activity, and self efficacy), and the level of knowledge. Exclusion criteria: reference with secondary data.Result: This study used 16 scientific articles. A number of 12 studies (75%) reported the use of mobile device applications in controlling risk factors for diabetes mellitus had significant measurement results in controlling HbA1c levels in 10 studies (83%) and 2 studies were not significant (17%). Outcomes in the form of self-management were reported by 9 studies with details of the significant results of dietary improvement in 5 studies (83%), increased physical activity in 5 studies (63%), and self-efficacy in 4 studies (67%). The increase in knowledge was reported by 4 studies with significant results (100%).Conclusion: Mobile device-based digital intervention is quite effective in controlling diabetes mellitus risk factors to control HbA1c levels, increasing self-management (improving diet, increasing physical activity, and self-efficacy) and knowledge.