iOS Mobile Application Research Articles

A machine learning approach for skin lesion classification on iOS: implementing and optimizing a convolutional transfer learning model with Create ML

The integration of machine learning (ML) into mobile applications presents unique challenges, particularly in resource-constrained environments such as iOS devices. Skin lesion classification is a critical task in dermatology, where accurate and efficient diagnostic tools can significantly aid in early detection of malignant lesions. This study aims to implement a machine learning-based iOS mobile application and develop a binary classification model for skin lesion images to determine whether a lesion is malignant. The research utilized Create ML to develop a convolutional neural network optimized for iOS, employing a transfer learning approach. A logistic regression model was cascaded with the convolutional neural network N to enhance classification accuracy. The model's performance was assessed through various validation metrics, ensuring its robustness and efficiency within the constraints of mobile hardware. A curated dataset from the International Skin Imaging Collaboration archive was used for training and testing. The model achieved an accuracy of 92%, a precision of 90%, a recall of 93%, and an F1-score of 91% in classifying skin lesions. These metrics validate the model's efficacy in identifying malignant lesions. Data curation involved collecting, labeling, and preparing a dataset from publicly available sources, ensuring the inclusion of diagnostically relevant features. The final model was integrated into an iOS application using Core ML and Vision frameworks. The developed application demonstrates reliable performance in classifying skin lesions with high accuracy on iOS devices. The inclusion of comprehensive performance metrics justifies the efficacy of the proposed approach. Future work will explore enhancements in model architecture and object detection capabilities to further improve diagnostic precision and application usability.

Recurrent Neural Network Based IOS Mobile Applications for Slope Safety Assessment

Recurrent Neural Network Based IOS Mobile Applications for Slope Safety Assessment

MPillBox: An open framework for a smarter pillbox

As the medical and technological fields have improved, there is a growing reliance on technology in the medical field. A considerable issue plaguing patients around the world is the management of medication intake for medications that treat chronic or otherwise serious illnesses. As such, many hospitalizations or even deaths are caused by medication errors. Existing solutions that provide smart pillboxes make many assumptions regarding patients, such as patient due diligence regarding expiration dates, storage atmospheric conditions, medication interactions, and awareness of alerts. mPillBox is introduced and presented as an open framework for making a pillbox smarter. The purpose of mPillBox is to improve user medication adherence and ensure medications remain effective. mPillBox aims to revolutionize existing smart pillboxes by introducing several key features: By attaching itself, via a Raspberry Pi, to any pillbox, mPillBox allows a user to manage a schedule for their medications. Unlike other digital pillboxes, mPillBox allows users to check expiration dates and atmospheric conditions to ensure the efficacy of their medications. mPillBox provides an automated medication interactions checker that informs the user of any interactions for current or future medications. Furthermore, mPillBox relies on Internet of Things devices in the vicinity, such as Chromecast, to automatically alert users. This is managed by a newly proposed mPillBox algorithm. These key features provide the necessary means for ensuring proper medication intake and medication efficacy that are not available in existing smart pillboxes. mPillBox is a low-cost system, with no required subscription fees, that does not require any medical or technical professional to set up, allowing it to be deployed anywhere. An mPillBox prototype was implemented along with an iOS mobile application to allow any user or patient to turn their simple pillbox into a smarter pillbox for managing their medication intake. The results show that mPillBox is a low-cost and user-friendly system that is smarter and more effective than existing smart pillboxes.

Cozie Apple: An iOS mobile and smartwatch application for environmental quality satisfaction and physiological data collection

Collecting feedback from people in indoor and outdoor environments is traditionally challenging and complex to achieve in a reliable, longitudinal, and non-intrusive way. This paper introduces Cozie Apple, an open-source mobile and smartwatch application for iOS devices. This platform allows people to complete a watch-based micro-survey and provide real-time feedback about environmental conditions via their Apple Watch. It leverages the inbuilt sensors of the smartwatch to collect physiological (e.g., heart rate, activity) and environmental (sound level) data. This paper outlines data collected from 48 research participants who used the platform to report perceptions of urban-scale environmental comfort (noise and thermal) and contextual factors such as who they were with and what activity they were doing. The results of 2,400 micro-surveys across various urban settings are illustrated in this paper, showing the variability of noise-related distractions, thermal comfort, and associated context. The results show that participants experienced at least a little noise distraction 58% of the time, with people talking being the most common reason (46%). This effort is novel due to its focus on spatial and temporal scalability and the collection of noise, distraction, and associated contextual information. These data set the stage for larger deployments, deeper analysis, and more helpful prediction models toward better understanding the occupants’ needs and perceptions. These innovations could result in real-time control signals to building systems or nudges for people to change their behavior.

Devices to measure calf raise test outcomes: A narrative review.

The calf raise test (CRT) is commonly administered without a device in clinics to measure triceps surae muscle function. To standardise and objectively quantify outcomes, researchers use research-grade or customised CRT devices. To incorporate evidence-based practice and apply testing devices effectively in clinics, it is essential to understand their design, applicability, psychometric properties, strengths, and limitations. Therefore, this review identifies, summarises, and critically appraises the CRT devices used in science. Four electronic databases were searched in April 2022. Studies that used devices to measure unilateral CRT outcomes (i.e., number of repetitions, work, height) were included. Thirty-five studies met inclusion, from which seven CRT devices were identified. Linear encoder (n=18) was the most commonly used device, followed by laboratory equipment (n=6) (three-dimensional motion capture and force plate). These measured the three CRT outcomes. Other devices used were electrogoniometer, Häggmark and Liedberg light beam device, Ankle Measure for Endurance and Strength (AMES), Haberometer, and custom-made. Devices were mostly used in healthy populations or Achilles tendon pathologies. AMES, Haberometer, and custom-made devices were the most clinician-friendly, but only quantified repetitions were completed. In late 2022, a computer vision mobile application appeared in the literature and offered clinicians a low-cost, research-grade alternative. This review details seven devices used to measure CRT outcomes. The linear encoder is the most common in research and quantifies all three CRT outcomes. Recent advances in computer-vision provide a low-cost research-grade alternative to clinicians and researchers via a n iOS mobile application.

IOS mobile malware analysis: a state-of-the-art

In earlier years, most malware attacks were against Android smartphones. Unfortunately, for the past few years, the trend has shifted towards attacks against the Apple iOS smartphone. Consequently, an in-depth analysis of the malware and iOS architecture is important to identify the best mitigation solution against malware exploitation. Hence, this paper presents a state-of-the-art deep analysis of malware against iOS smartphones. This includes comprehensive studies of malware architecture involving payload, propagation, operating algorithm, infection, and activation with underlying integration with a phylogenetic concept. Phylogenetic, borrowed from the biology field, can identify any evolution of the origin of the malware involved. To support this deep analysis of malware, a preliminary study was conducted using 12 malware samples, by focusing on social media and online banking. This took place in a controlled laboratory using hybrid analysis. The result showed that there is a way to identify the evolution of malware and as a result, a model has been developed. Based on the evaluation, 4% of mobile applications matched the patterns developed in this model. This proves that the model developed in this paper can detect any possible security exploitation related to social media and online banking for iOS mobile applications. This work can be used as guidance for other researchers working on similar interests in the future.

Assuring quality in assisted reproduction laboratories: assessing the performance of ART Compass - a digital art staff management platform.

Staff management is the most cited ART/IVF laboratory inspection deficiency. Small ART/IVF clinics may be challenged to perform these activities by low staff volume; similarly, large ART/IVF networks may be challenged by high staff volume and large datasets. Here, we sought to investigate the performance of an automated, digital platform solution to manage this necessary task. The ART Compass (ARTC) digital staff management platform was used to assess the clinical decision-making of ART laboratory staff. The survey modules presented standardized instructions to technologists and measured inter- and intra-technologist variability for subjective "clinical decision-making" type questions. Internal and external comparisons were achieved by providing technologists two answers: (1) a comparison to their own lab director and (2) to the most popular response collectively provided by all lab director level accounts. The platform is hosted on HIPAA compliant Amazon web servers, accessible via web browser and mobile applications for iOS (Apple) and Android mobile devices. Here, we investigated the performance of a digital staff management platform for single embryologist IVF practices and for three IVF lab networks (sites A, B, C) from 2020 to 2022. Embryology dish preparation survey results show variance among respondents in the following: PPE use, media volume, timing of oil overlay, and timing of moving prepared dishes to incubators. Surveying the perceived Gardner score and terms in use for early blastocysts reveals a lack of standardization of terminology and fair to poor agreement. We observed moderate inter-technologist agreement for ICM and TE grade (0.47 and 0.52, respectively). Lastly, the clinical decision of choice to freeze or discard an embryo revealed that agreement to freeze was highest for the top-quality embryos, and that some embryos can be highly contested, evenly split between choice to freeze or discard. We conclude that a digital platform is a novel and effective tool to automate, routinely monitor, and assure quality for staff-related parameters in ART and IVF laboratories. Use of a digital platform can increase regulatory compliance and provide actionable insight for quality assurance in both single embryologist practices and for large networks. Furthermore, clinical decision-making can be augmented with artificial intelligence integration.

Comparison of hybrid and native iOS mobile application development technologies


 
 
 Mobile applications dedicated to iOS can be developed natively or hybrid. The subject of this paper is to compare these technologies on the example of a created mobile application. The performance of both technologies, the structure of projects, as well as resource consumption on the example of four smartphones operating under iOS, has been examined. Considering the performance analysis, the compilation time of the application, reading and writing data from the cloud database, as well as the time of sorting the read data was examined. On the test devices, it was checked how intense is the use of the system. The obtained results confirm that producing a mobile application in native technology is more perfor- mance efficient.
 
 

Selçuk weather station and web-mobile applications

In this paper, a system for reading meteorological data like temperature, humidity, air pressure, wind speed, wind direction, and rainfall at regular intervals, deployed in Selçuk University Alaeddin Keykubat Campus. The system also provides real-time images and video time-lapses of the campus sky. These data are made available to university people via a website and mobile applications for both iOS and Android. The website and mobile applications provide a clear experience for the users, also explaining the icons and terms used on the website. Users can access the system archive in graphical ways.

Deployment of a Mobile Application Using a Novel Deep Neural Network and Advanced Pre-Trained Models for the Identification of Brain Tumours

ABSTRACT Medical image processing is significant in clinical diagnosis and treatment. However, the traditional approach for examining these images has hit its performance limit, and requires a considerable amount of time and effort. In addition, the misdiagnosis of brain tumour types from these images can hinder patients from receiving proper medical treatment and can diminish their chances of survival. The emerging deep learning technique has shown good results in classification problems. In the current study, existing transfer learning models and a novel model were applied to classify augmented magnetic resonance images (n = 12,256 images). These methods were used to identify three different kinds of brain tumours from the images: meningioma, glioma, and pituitary tumours. Accuracies of 83.30%, 79.54%, 81.83%, 82.49%, 85.21%, and 91.73% were obtained using ADAM optimizers for VGG-16, VGG-19, Inception V3, Xception, Mobile net, and the proposed Lightweight Sequential net, respectively. Furthermore, we achieved accuracies of 50.45%, 60.24%, 57.85%, 61.98%, 75.14%, and 84.82% while using the SGDM optimizer for the aforementioned deep neural networks, respectively. We also developed an Android and IOS mobile application using the novel deep neural network and a flutter framework. The mobile application was tested using brain tumour images collected from SRM hospital and an accuracy of 82.5% was obtained. The untrained data of 155 images collected from hospital were used to validate this application. In terms of execution speed, the proposed architecture surpassed the existing pre-trained models. Thus, when compared to approximately similar approaches, our newly developed network outperformed them.

Mental health in smart cities: The role of technology during COVID-19 pandemic

COVID-19 has changed the daily lives of citizens around the world and exposed the vulnerability of life and the functioning of cities. The pandemic has forced citizens to adapt to new models of remote work during quarantine and access to smart technology-based services. The article aims to assess citizens' perceptions of the technological solutions provided by smart cities and, in particular, the municipality of Paphos before and after the Covid-19 pandemic, as well as to evaluate their impact on citizens' mental health. The results of the study contribute to the understanding of the mental health benefits for citizens living in smart cities compared to people living in low-tech areas, revealing the potential positive effects of smart technologies, as well as the change in people's digital decision-making before and after the pandemic

Video-Assisted Clinical Care for Remote Management of COVID-19

Due to the COVID-19 pandemic, the need for biomedical monitoring devices has increased for collecting vital signs from patients virtually. This paper will discuss developing an iOS mobile application that will ingest video frames in real-time to provide oxygen saturation and heart rate values. We provide two techniques for capturing data using 1) face monitoring under natural light and 2) fingertip monitoring using the iPhone’s flashlight. We observed an average Root Mean Squared Error (RMSE) of 3.6 for heart rate estimation using fingertip recordings and 13.25 using face recordings. For oxygen saturation, we obtained the RMSE for each class between SpO2 values 94 - 99%. The lowest RMSE provided from our application was 0.26 for fingertip recording and 0.22 for face recording at SpO2 level 96%. The highest RMSE was 6.34 for fingertip recording and 6.56 for face recording at SpO2 level 99%. These preliminary models will be further enhanced through a clinical study with UC Davis Health as we collect data from participants with respiratory diseases.

Review on Mobile Application Development Based on Flutter Platform

Abstract: Covid-19 pandemic has made mobile applications very popular. There is a huge competition between many mobile application development frameworks available in the market. In today’s world ease of development is the thing all developers are seeing for and flutter has come with the required platform to support development of applications for both iOS and Android platforms, consequently decreasing the cost and complexity of application creation across both platforms. Flutter is the crossplatform mobile application development open-source SDK tool for developing high-performance and more reliable mobile applications for iOS and Android operating systems. This paper has been undertaken to indicate the benefits of using flutter over other app development platforms. Keywords: Cross-Platform Mobile Application, Flutter, Dart, GetX State Management, Firebase

A Mobile App for Wound Localization Using Deep Learning

We present an automated wound localizer from 2D wound and ulcer images using a deep neural network as the first step towards building an automatic and complete wound diagnostic system. The wound localizer is developed using the YOLOv3 model, which is then turned into an iOS mobile application. The developed localizer can detect the wound and its surrounding tissues and isolate the localized wounded region from images, which would help future processing such as wound segmentation and classification due to the removal of unnecessary regions from wound images. For Mobile App development with video processing, a lighter version of YOLOv3 named tiny-YOLOv3 has been used. The model is trained and tested on our image dataset collaborating with AZH Wound and Vascular Center, Milwaukee, Wisconsin. The YOLOv3 model is compared with the SSD model in our developed dataset (AZH wound database, available at https://github.com/uwm-bigdata/wound_localization), showing that YOLOv3 gives an mAP value of 93.9%, which is much better than the SSD model (86.4%). The robustness and reliability of these models are also tested on a publicly available dataset named Medetec, which shows very good performance. Finally, a bigger dataset (BMAZHM Wound Database) is created, and the developed model is retrained with the new dataset to achieve a very high mAP of 97.3%.

Water and Air Quality Monitoring System based on the Internet of Things

Environmental pollution is a global issue that occurs at this time. It is caused by various human activities that produce pollutants that endanger their lives. By utilizing current technology, it is possible to design a Water and Air Quality Monitoring System based on the Internet of Things to monitor air and water quality quickly and in real-time in the surrounding environment. The users can access this system via the web and Android / IOS mobile applications that display the data obtained by the sensor in the form of real-time graphics of water and air conditions. In addition, this system consists of several sensor nodes in charge of providing field data regarding the parameters used as the basis for assessing water and air quality according to the applicable standards in Indonesia. Sensors for water using a Turbidity Sensor, DS18B20 Sensor, PH Sensor, DHT 11, and TDS (Total Dissolved Solids) Sensor. Sensors for air consist of the DHT11 sensor, the MQ-7sensor, the MQ-135 sensor, and the dust sensor GP2Y1010AU0F.

Reference intervals and values for fecal cortisol, aldosterone, and the ratio of cortisol to dehydroepiandrosterone metabolites in four species of cetaceans.

The goal of the current study was to create reference intervals and values for several common and one potential novel physiological indicators of animal welfare for four species of cetaceans. The subjects included 189 bottlenose dolphins (Tursiops truncatus), 27 Indo-Pacific bottlenose dolphins (Tursiops aduncus), eight Pacific white-sided dolphins (Lagenorhynchus obliquidens), and 13 beluga whales (Delphinapterus leucas) at Alliance of Marine Mammal Parks and Aquariums and/or Association of Zoos and Aquariums accredited facilities. During two sampling time periods between July and November of 2018 and between January and April of 2019, fecal samples were collected weekly for five weeks from all animals. Samples were processed and analyzed using enzyme immunoassay for fecal cortisol, aldosterone, and dehydroepiandrosterone (DHEA) metabolites. Linear mixed models were used to examine demographic and time factors impacting hormone metabolite concentrations. Age, sex, and time of year were all significant predictors for some of the models (p < 0.01). An iOS mobile application ZooPhysioTrak was created for easy access to species-specific reference intervals and values accounting for significant predictors. For facilities without access to this application, additional reference intervals and values were constructed without accounting for significant predictors. Information gained from this study and the use of the application can provide reference intervals and values to make informed management decisions for cetaceans in zoological facilities.

Site reliability engineering for IOS mobile application in small-medium scale industries

Software reliability is one and only the standard used to calculate the excellence of a software system. In this situation, we suggest a method to forecast software reliability in the primary creation of any process growth phases since from the designing stage only. Software mobile application has remained a significant tool in our lifetime, and several small-medium scale software progress companies capitalize the substantial resources to mark accessible prospects. The landscape of mobile atmospheres varies as of server environments owing to various issues, by means of the net, liveliness, battery-operated, and compatibility. Estimating and forecasting mobile application reliability remain the actual contests as of the variety of the mobile situations in which the applications are used, and the absence of widely available fault data. In addition, error information is optionally given in to the end-users. Hence, in what way to estimate reliability of mobile software application has remained more and more significant. In this paper, site reliability engineering (SRE) for mobile application is proposed for the reliability of software and is taken as a case study. Their failure is copied back to the exact features of mobile application is useful and powerful.

A product quality impacts of a mobile software product line: an empirical study

BackgroundThe software product lines (SPL) enable development teams to fully address a systematic reuse of shared assets to deliver a family of similar software products. Mobile applications are an obvious candidate for employing an SPL approach. This paper presents our research outcomes, based on empirical data from an industry-level development project. Two development teams were confronted with the same functionalities set to be delivered through a family of native mobile applications for Android and iOS.MethodsEmpirical data was gathered before, during and after a year of full-time development. The data demonstrate the impact of a SPL approach by comparing the SPL and non-SPL multiple edition development. One family of products (Android apps) was developed using an SPL approach, while another (iOS apps), functionally the same, was developed without employing an SPL approach. The project generated a volume of raw and aggregated empirical data to support our research questions.ResultsThe paper reports a positive impact of an SPL approach on product quality (internal and external) and feature output per week. As data shows, it also increases the delivery of functionalities (240% in 6 more editions), while investing the same amount of effort needed for a single-edition development. As a result of system-supported separation of development and production code, developers had a high confidence in further development. On the other hand, the second team delivered less new functionalities, only two new application editions, and lower software quality than the team that manages multi-edition development by employing an SPL approach.

What’s on the Horizon? An In-Depth Forensic Analysis of Android and iOS Applications

In the digital forensics discipline, the lack of comprehensive research that addresses investigative challenges and opportunities for newer mobile Operating Systems (OSs) such as Android and iOS keeps continuing. These two OSs are currently widely operated by millions of smartphones and used by millions of users; therefore, forensic investigators need to be prepared to analyze these OSs during an investigation giving consideration to mobile app updates. The current research efforts focus on the forensic analysis of individual applications of certain OSs. In this study, we conducted a detailed forensic investigation of both Android and iOS OSs to (1) elucidate their structures for investigators, (2) identify pertinent forensic artifacts, (3) highlight any privacy and security concerns in popular applications present on both OSs, and (4) validate the forensic investigation on the selected tools for reproducibility and verification purposes. This work aims to analyze 27 Android and 33 iOS mobile applications comprehensively.

Development of mobile application for Malay translated hadith search engine

This paper presents the development of mobile application for Malay Translated Hadith search engine. Limitations of current Hadith web application are the design is to optimize its usage on desktop computer but not on mobile devices, which requires simple and user friendly interface. Besides that, web application also needs internet connection to use. Due to increase usage of mobile application among mobile phone users, many existing web applications have moved to mobile based applications to cater for increasing numbers of mobile users. In this study, a mobile application for Android and iOS mobile application has been developed using Flutter framework, a hybrid mobile application framework. A Malay Translated hadith search engine mobile application can easily assist those who are seeking knowledge to learn more about certain topics in hadith, a second source of Islamic knowledge. This mobile application has search and directory features for users to browse the 2028 Sahih Bukhari hadith collection. Users can enter their query using search features to find selected hadith in Malay language. Queries will be processed for searching relevant hadith and display the results to the user. Evaluation using Recall and Precision shows that on the average Recall is 73% and Precision is 33%. Functionality testing is also conducted to test against the functional requirements or specifications. Results shows all requirements are successfully tested.