User-friendly Application Research Articles

AttributeRank: An Algorithm for Attribute Ranking in Clinical Variable Selection.

Risk difference is a valuable measure of association in epidemiology and healthcare which has the potential to be used in medical and clinical variable selection. In this study, an attribute ranking algorithm, called AttributeRank, was developed to facilitate variable selection from clinical data sets. The algorithm computes the risk difference between a predictor and the response variable to determine the level of importance of a predictor. The performance of the algorithm was compared with some existing variable selection algorithms using five clinical data sets on neonatal birthweight, bacterial survival after treatment, myocardial infarction, breast cancer, and diabetes. The variable subsets selected by AttributeRank yielded the highest average classification accuracy across the data sets, compared to Fisher score, Pearson's correlation, variable importance function, and Chi-Square. AttributeRank proved to be more valuable in attribute ranking of clinical data sets compared to the existing algorithms and should be implemented in a user-friendly application in future research.

IOT based Smart Pothole Detection System using ESP32

This project presents a comprehensive pothole detection and navigation system aimed at improving road safety and reducing vehicle wear and tear. The system utilizes an ESP32 microcontroller, a gyroscope, and a GPS module, integrated into car tires to enable real-time detection of potholes. The gyroscope measures vibrations and deviations caused by uneven road surfaces, while the GPS module pinpoints the exact geographic location of the detected potholes. The system also measures the depth and width of the potholes to provide detailed information. This data is transmitted wirelessly to a central server, where an AI-based algorithm processes it to eliminate duplicate entries and filter out false detections. Once validated, the pothole information is mapped onto a user-friendly mobile application, providing users with real-time updates on road conditions. By allowing users to choose safer and smoother routes with minimal potholes, this system ensures enhanced driving safety, reduced maintenance costs, and a more efficient travel experience. Additionally, the mapped pothole data can serve as valuable feedback for road maintenance authorities to prioritize repairs and improve infrastructure. Key Words: pothole detection, ESP32, gyroscope, GPS, AI, road safety.

Website as a Marketplace for Teleradiology/Telemedicine Solutions

The healthcare industry is rapidly evolving with advancements in technology, especially in telemedicine and teleradiology. These fields enable remote diagnosis and consultation, improving access to healthcare services globally. In this context the main and the primary objective of this project is to create a comprehensive, user-friendly web application that serves as a centralized marketplace for healthcare providers and vendors of teleradiology and telemedicine solutions. The platform will facilitate the buying, selling, and leasing of telemedicine equipment, software, and services, thereby enhancing the efficiency and reach of telehealth services.

Neuropsychiatric symptoms predict rate of change in executive function in Alzheimer's disease and related dementias.

Neuropsychiatric symptoms (NPS) are considered diagnostic and prognostic indicators of dementia and are attributable to neurodegenerative processes. Little is known about the prognostic value of early NPS on executive functioning (EF) decline in Alzheimer's disease and related dementias (ADRD). We examined whether baseline NPS predicted the rate of executive function (EF) decline among older adults with ADRD. Older adults (n = 1625) with cognitive impairment were selected from the National Alzheimer's Coordinating Center database. EF was estimated with a latent factor indicated by scores on Number Span Backward, Letter Fluency, and Trail Making-Part B. A curve of factors (CUFF) latent growth curve model was estimated to examine rate of change over four years. Baseline NPS severity was entered as a predictor in the model to examine its influence on the rate of change in EF over time. The CUFF models exhibited good fit. EF significantly declined over four waves (slope = -.16, p < .001). Initial visit NPS severity predicted decline in EF (slope = .013, p < .001), such that those with greater baseline NPS severity demonstrated a more rapid decline in EF performance over time. Presence of 2 NPS significantly predicted EF decline, and those with medium total NPS severity (NPS score of 2-4) at baseline exhibited a sharper decline in EF. Findings underscore the importance of targeting NPS early across ADRD syndromes to minimize EF decline, offering novel insights into how early NPS treatment may alter cognitive trajectories. We provide an innovative, user-friendly web-based application that may be helpful for personalized treatment planning.

Tagtango: an application to compare single-cell annotations.

In this article, we present tagtango, an innovative R package and web application designed for robust and intuitive comparison of single-cell clusters and annotations. It offers an interactive platform that simplifies the exploration of differences and similarities among different clustering and annotation methods. Leveraging single-cell data analysis and different visualizations, it allows researchers to dissect the underlying biological differences across groups. tagtango is a user-friendly application that is portable and works seamlessly across multiple operating systems. tagtango is freely available at https://github.com/bernibra/tagtango as an R package as well as an online web service at https://tagtango.unil.ch. Supplementary data are available at Bioinformatics online.

DIABETES PREDICTION MACHINE LEARNING-BASED DIABETES PREDICTION APP USING RANDOM FOREST ALGORITHM

Diabetes is a chronic metabolic condition that causes increased blood glucose levels in millions of people worldwide. Early detection and quick action are critical for controlling this illness and preventing consequences. This work describes creating a user-friendly smartphone application for diabetes prediction using the Random Forest algorithm, a powerful machine-learning technique. The software uses user-provided information, such as age, body mass index (BMI), blood pressure, and glucose levels, to forecast the chance of acquiring diabetes. The Random Forest model was trained on a large dataset of medical records and achieved an astounding 88% accuracy on the test set. The app, created using Python and Figma, a cross-platform framework, has an intuitive and user-friendly design that allows users to enter personal information and obtain immediate forecasts. The app is a useful screening tool, allowing people to estimate their risk of getting diabetes and receive necessary medical assistance as soon as possible. The successful implementation of this diabetes prediction software highlights machine learning algorithms' potential to improve preventive healthcare and promote early intervention for chronic diseases.

Blockchain-Based E-Voting System: A Decentralized Approach on the Ethereum Private Network

The e-voting system, which is based on blockchain technology, greatly improves the security, transparency, and integrity of electronic voting. This is achieved by using a decentralized ledger system that distributes the recording of votes, allows for public verification, and maintains voter anonymity through cryptographic methods. This resilient method guarantees that once a vote is submitted, it is securely recorded and cannot be changed without the agreement of network members, thereby protecting the integrity of elections. Built on the private Go Ethereum (Geth) network, this study implements an e-voting system that features validator nodes for transaction verification, user-friendly mobile applications for voter interaction, and comprehensive smart contract capabilities that define the voting process rules. The mobile application guides users from launching the app and authenticating their identity to selecting candidates and securely recording their votes, ensuring seamless connectivity to the blockchain and incorporating essential verification steps. Furthermore, the implementation process includes meticulous setup of Ethereum nodes, smart contract development, and thorough testing for functionality, performance, and security. The evaluation focuses on aspects like maintaining data transparency, user authentication, and resilience against unauthorized access, demonstrating high user satisfaction with the app's performance. Ultimately, this blockchain-based system addresses modern electoral challenges, ensuring a secure, transparent, and reliable voting experience that fosters trust among all stakeholders involved.

Digitalization of Services through Mekari KlikPajak: Analysis of Public Private Partnerships

Digitalization in the field of tax administration needs more attention, where modern society today requires efficient and effective tax services, especially in Indonesia which uses a self-assessment tax system. Although it is the government's obligation to provide services according to the needs of the community, along with the development of approaches to improving the performance of public administration, the concept of public-private partnership has developed. One form of public-private partnership in tax administration services is Mekari Klik Pajak. This application is a digital application developed by a technology company to assist taxpayers in carrying out their tax obligations in a more practical, transparent, and in accordance with applicable provisions. This research article aims to analyze how the implementation of public-private partnerships in Mekari Klik Pajak can help accelerate the process of digitizing tax administration in Indonesia. The results of the analysis show that the implementation of public-private partnerships with Mekari makes it possible to reduce the burden on the government in the technical process, as well as develop user-friendly applications that make it easier for taxpayers, both individuals and companies, to fulfill their tax obligations. Applications such as Mekari Klik Pajak provide features that can be accessed anytime and anywhere, reducing geographical and time barriers that often occur in conventional tax systems.

AI-Based Hate Speech Detection in Albanian Social Media: New Dataset and Mobile Web Application Integration

This paper aims to advance AI-based hate speech (HS) detection in the Albanian language, which is resource-limited in natural language processing (NLP). Addressing the challenge of limited data, we developed a human-annotated dataset of over 11,000 comments, carefully curated from various Albanian social media platforms, containing a substantial number of HS instances. The dataset was annotated using a detailed two-layer taxonomy to capture the complex dimensions of HS. To ensure high-quality annotations, three expert annotators applied a majority voting system, achieving a substantial Fleiss’s kappa coefficient of 0.62, underscoring the reliability and consistency of the annotations. We conducted a comparative analysis of several machine learning (ML) algorithms, including support vector machine (SVM), Naïve Bayes (NB), XGBoost, and random forest (RF), paired with various text vectorisation techniques and pre-processing methods. In binary classification, the NB model with term frequencyinverse document frequency (TF-IDF) vectorization achieved the highest performance, with an F1 score of 0.80. For multiclass classification, XGBoost outperformed other models, achieving an F1 score of 0.77. Interestingly, our experiments revealed that pre-processing steps generally reduced model performance, suggesting that raw text inputs work better for the Albanian language. Through error analysis using local interpretable model-agnostic explanations (LIME), we identified key challenges, such as polysemy and irony, which contributed to misclassifications. To demonstrate the practical applicability of our work, we developed a user-friendly mobile web application based on the best-performing model, providing realtime HS detection with the potential for integration into social media platforms.

Innovative Web Design of Mobile Applications for Travel Planning: Improving the Quality of User Experience

The purpose of the study is to analyze and create a web design for a travel application that will provide effective and convenient user interaction with a digital resource. The research method: general scientific methods of analysis and synthesis (to analyze the current state of the problem and existing Ukrainian applications for travel planning), modeling method (development of a goal tree and a functional model of the problem) and prototyping method (development of a prototype of a web application for travel, taking into account modern design solutions and UX/UI approaches). The scientific novelty is the development of the most innovative and modern web application design that will meet modern user requirements and ensure effective customer interaction with the application. Conclusions. Developing a web design for a travel application that will meet modern user requirements and ensure effective interaction with a digital resource is a key component of a successful product on the market. The paper examines the current state of use of mobile travel applications, identifies their positive and negative characteristics. The practical significance of the obtained results lies in the development of a travel application interface that will provide the functions of route planning and planning, recommendations for places to visit, hotel and transport booking, organization of group trips, joint route planning with other users, obtaining detailed information about events and activities, organizing excursions, sharing tips and experiences with other users. The study results can be used to develop an intuitive, convenient and functional application interface that meets the needs of users in planning and organizing travel. The results of the study can be used to develop an intuitive, user-friendly and functional application interface. This will help to increase user satisfaction and the effectiveness of their interaction with the application in the process of planning and organizing travel.

Implementation of integrated IoT-based monitoring system to improve clean water services at KP-SPAMS Tirta Jatisari

The Tirta Jatisari Water Supply and Sanitation Management Group (KP-SPAMS) faced challenges ensuring transparency in water usage and efficiency in billing due to the limitations of conventional water meters. These meters lacked real-time monitoring capabilities, hindering leak detection and leading to billing inaccuracies. To address this, an Internet of Things (IoT)-based monitoring system integrated with a web application was implemented to improve transparency and operational efficiency. The methodology involved needs analysis and system design, IoT device development, installation of flow meter sensors, development of a user-friendly web application for both KP-SPAMS managers and consumers, and comprehensive system training and socialization. Results demonstrated improved billing accuracy and speed, along with real-time water usage monitoring for both KP-SPAMS and consumers, facilitating timely leak detection. The implementation successfully increased consumer satisfaction and fostered the development of technologically adept human resources.

An AIoT-based Air Quality Monitoring System for Real-time PM2.5 Prediction in Urban Environments

This study aimed to develop an air quality monitoring and forecasting system focusing on PM2.5 using a combination of AI of Things (AIoT) technology. The system was designed to provide warnings of PM2.5 levels through a mobile application. Air pollution, particularly PM2.5, is a significant health concern globally, with Southeast Asia being heavily affected. Bangkok, Thailand, experiences high PM2.5 concentrations during cool weather. Existing research explores short-term PM2.5 prediction using AIoT. Still, there is a need for improved software, hardware, and ML algorithms for user-friendly mobile applications with real-time data access and health advisories. The system was installed on a building next to a main road in Bangkok. It collected data on PM2.5. The Air Quality Index (AQI) was used to categorize PM2.5 levels and their health impacts. Time series analysis with moving averages and the Random Forest algorithm were employed in advance for PM2.5 forecasting. A mobile application was developed to provide a user interface and data visualization. The MARF (Moving Average and Random Forest) model emerged as a success, achieving higher accuracy (average of 92.59%) for 1-hour advance forecasts compared to the Moving Average (MA) model (average of 84.16%). The developed system demonstrates the potential of AIoT for accurate PM2.5 monitoring and forecasting. Future research could explore more advanced ML algorithms and integrate additional environmental factors for enhanced forecasting accuracy.

Development of an Energy Harvesting Automated Punching Bag

Abstract—Experience the future of fitness with our innovative automated power generating wall-mounted punching bag. This advanced system revolutionizes traditional workouts by incorporating customizable punch combinations, LED-guided targets, and real-time performance tracking. Users can seamlessly adjust punch settings with a simple knob, while dynamic LED lights guide them through targeted combinations, enhancing training effectiveness and refining technique. Embedded sensors accurately measure punching force and track workout progress, providing insightful feedback via a user-friendly mobile application. Detailed analytics and calorie expenditure data empower users to monitor their fitness journey effectively, while the bag harnesses kinetic energy to contribute to sustainable power generation. This interdisciplinary project merges cutting-edge technology with principles of electrical, electronics, and mechanical engineering, showcasing ingenuity and versatility. Join us in redefining fitness with a sustainable, interactive, and informative workout experience tailored to the needs of enthusiasts and athletes alike.

A Statistical Approach for Identifying the Best Combination of Normalization and Imputation Methods for Label-Free Proteomics Expression Data.

Label-free proteomics expression data sets often exhibit data heterogeneity and missing values, necessitating the development of effective normalization and imputation methods. The selection of appropriate normalization and imputation methods is inherently data-specific, and choosing the optimal approach from the available options is critical for ensuring robust downstream analysis. This study aimed to identify the most suitable combination of these methods for quality control and accurate identification of differentially expressed proteins. In this study, we developed nine combinations by integrating three normalization methods, locally weighted linear regression (LOESS), variance stabilization normalization (VSN), and robust linear regression (RLR) with three imputation methods: k-nearest neighbors (k-NN), local least-squares (LLS), and singular value decomposition (SVD). We utilized statistical measures, including the pooled coefficient of variation (PCV), pooled estimate of variance (PEV), and pooled median absolute deviation (PMAD), to assess intragroup and intergroup variation. The combinations yielding the lowest values corresponding to each statistical measure were chosen as the data set's suitable normalization and imputation methods. The performance of this approach was tested using two spiked-in standard label-free proteomics benchmark data sets. The identified combinations returned a low NRMSE and showed better performance in identifying spiked-in proteins. The developed approach can be accessed through the R package named 'lfproQC' and a user-friendly Shiny web application (https://dabiniasri.shinyapps.io/lfproQC and http://omics.icar.gov.in/lfproQC), making it a valuable resource for researchers looking to apply this method to their data sets.

SpatialGE is a User-Friendly Web Application that Facilitates Spatial Transcriptomics Data Analysis.

Spatial transcriptomics (ST) is a powerful tool for understanding tissue biology and disease mechanisms. However, the advanced data analysis and programming skills required can hinder researchers from realizing of the full potential of ST. To address this, we developed spatialGE, a web application that simplifies the analysis of ST data. The application spatialGE provided a user-friendly interface that guides users without programming expertise through various analysis pipelines, including quality control, normalization, domain detection, phenotyping, and multiple spatial analyses. It also enabled comparative analysis among samples and supported various ST technologies. The utility of spatialGE was demonstrated through its application in studying the tumor microenvironment of two data sets: 10X Visium samples from a cohort of melanoma metastasis and Nanostring CosMx fields of vision from a cohort of Merkel cell carcinoma samples. These results support the ability of spatialGE to identify spatial gene expression patterns that provide valuable insights into the tumor microenvironment and highlight its utility in democratizing ST data analysis for the wider scientific community.

Representing DNA for machine learning algorithms: A primer on one-hot, binary, and integer encodings.

This short paper presents an educational approach to teaching three popular methods for encoding DNA sequences: one-hot encoding, binary encoding, and integer encoding. Aimed at bioinformatics and computational biology students, our learning intervention focuses on developing practical skills in implementing these essential techniques for efficient representation and analysis of genetic data. The primary goal of this study is to enhance students' understanding and practical application of DNA encoding methods, which are crucial for various computational analyses in bioinformatics. Our intervention consists of three key components: (1) a conceptual framework that contextualizes these encoding methods within broader bioinformatics applications, (2) an interactive Jupyter Notebook with Python code examples (https://github.com/yashmgupta/Representing-DNA/tree/main), and (3) a user-friendly Streamlit application for visualizing encoded sequences (https://dnaencoding.streamlit.app/) that also enables students to input their own DNA sequences and visualize the different encoding methods, further enhancing their understanding and practical experience. By combining conceptual overview with practical coding and visualization tools, our approach provides a comprehensive foundation for students to leverage these key DNA sequence encoding methods in their future work. This study contributes to bioinformatics education by offering effective, hands-on learning resources that bridge the gap between theoretical knowledge and practical application in DNA sequence analysis, preparing students for advanced research and data analysis projects in the field.

Ownership of contactless data in urban transportation systems

This paper examines the landscape of contactless transport payment systems in developing countries, focusing on data ownership, regulatory challenges, advantages, disadvantages, and implications. It explores the roles of city authorities, contractors, and consumers in managing and utilising data generated through these systems, emphasising the need for robust cybersecurity measures and comprehensive regulatory frameworks. Despite offering enhanced convenience and operational efficiencies, these systems present challenges such as cybersecurity risks, adoption barriers, and ethical concerns over data commercialisation. Plans include integrating these systems with international travel apps, developing user-friendly applications, and enhancing security protocols. The paper highlights the theoretical contributions and opportunities for future research, urging further exploration into regulatory effectiveness, consumer behaviour, technological advancements, ethical dilemmas, regional comparisons, and long-term impacts on urban mobility.

Prediction of early lung adenocarcinoma spread through air spaces by machine learning radiomics: a cross-center cohort study.

Sublobar resection is suitable for peripheral stage I lung adenocarcinoma (LUAD). However, if tumor spread through air spaces (STAS) present, the lobectomy will be considered for a survival benefit. Therefore, STAS status guide peripheral stage I LUAD surgical approach. This study aimed to identify radiological features associated with STAS in peripheral stage I LUAD and to develop a predictive machine learning (ML) model using radiomics to improve surgical decision-making for thoracic surgeons. We conducted a retrospective analysis of patients who underwent surgical treatment for lung tumors from January 2022 to December 2023, focusing on clinical peripheral stage I LUAD. High-resolution computed tomography (CT) scans were used to extract 1,581 radiomics features. Least absolute shrinkage and selection operator (LASSO) regression was applied to select the most relevant features for predicting STAS, reducing model overfitting and enhancing predictability. Ten ML algorithms were evaluated using performance metrics such as area under the receiver operating characteristic curve (AUROC), accuracy, recall, F1-score, and Matthews Correlation Coefficient (MCC) after a 10-fold cross-validation process. SHapley Additive exPlanations (SHAP) values were calculated to provide interpretability and illustrate the contribution of individual features to the model's predictions. Additionally, a user-friendly web application was developed to enable clinicians to use these predictive models in real-time for assessing the risk of STAS. The study identified significant associations between STAS and radiological features, including the longest diameter, consolidation-to-tumor ratio (CTR), and the presence of spiculation. The Random Forest (RF) model for 3-mm peritumoral extensions demonstrated strong predictive performance, with a Recall_Mean of 0.717, Accuracy_Mean of 0.891, F1-Score_Mean of 0.758, MCC_Mean of 0.708, and an AUROC_Mean of 0.944. SHAP analyses highlighted the influential radiomics features, enhancing our understanding of the model's decision-making process. The RF model, employing specific intratumoral and 3-mm peritumoral radiomics features, was highly effective in predicting STAS in peripheral stage I LUAD. This model is recommended for clinical use to optimize surgical strategies for LUAD patients, supported by a real-time web application for STAS risk assessment.

Data-Driven Augmented Reality for Scout Password Recognition in Interactive Learning Environment

Scout password is an essential component of scout science, used for communication through secret codes. Learning scout passwords has traditionally relied on conventional methods, where coaches provide material and exercises during weekly meetings. Due to infrequent practice opportunities, this approach often limits students' ability to engage deeply with the material. To address these challenges, this research introduces a data-driven augmented reality (AR) application designed to enhance the learning experience by making scout password recognition more interactive and accessible. The proposed tool leverages AR technology to provide real-time visualization of movements and auditory cues, creating an immersive and engaging learning environment. By integrating data-driven insights into the AR application, the learning process is tailored to individual student needs, ensuring effective understanding and retention of scout codes. The development process follows the Multimedia Life Cycle methodology, providing a structured and iterative approach to creating a user-friendly and impactful application. This innovative AR-based tool aims to transform traditional scout learning methods, offering students a more dynamic and interactive way to master scout password communication while addressing the limitations of conventional teaching practices.

Construction, validation, and visualization of a web-based nomogram to predict survival in male breast cancer patients with second primary prostate cancer.

The advancement of early detection and treatment has brought about a significant concern for male breast cancer (MBC) survivors-the emergence of a second primary malignancy (SPM) poses a grave threat to their lives. Among them, second primary prostate cancer (spPCa) holds particular significance. This study aimed to investigate the impact of spPCa on the prognosis of MBC patients. We performed a retrospective analysis using information from the Surveillance, Epidemiology, and End Results (SEER) database to investigate individuals diagnosed with MBC who also experienced an SPM between 2000 and 2020. Propensity score matching (PSM) was employed to balance the baseline characteristics of individuals with spPCa and those with second primary non-prostate cancer (non-PCa). The impact of spPCa on participant survival was assessed using the Kaplan-Meier method. Furthermore, two nomograms were developed, based on univariate and multifactor Cox regression analyses, to predict overall survival (OS) and cancer-specific survival (CSS). The capacity of the nomograms was evaluated using the concordance index (C-index), calibration curve, receiver operating characteristic (ROC) analysis, and decision curve analysis (DCA). Additionally, a risk stratification system was devised, taking into account the cumulative score of each patient in the nomogram. This study enrolled a total of 885 MBC patients who experienced an SPM, of which 265 (29.9%) were diagnosed with spPCa. Through PSM, 257 pairs of eligible participants were selected. Survival analysis revealed that patients with prostate cancer (PCa) as an SPM have longer OS and CSS compared to those with other types of cancer as an SPM. The participants were randomly divided into a training set and a validation set in a ratio of 7:3. The Cox proportional hazards model was utilized to assess the risk factors associated with survival outcomes. Two nomograms were developed to forecast the 3-, 5-, 8-, and 10-year OS and CSS of male patients who had breast cancer and SPM. The two nomograms exhibited excellent performance in terms of the C-index, ROC curves, calibration plots, and DCA curves, demonstrating their exceptional clinical discriminative ability and predictive utility. In the risk stratification system predicated on the total score of the nomogram, patients deemed high-risk exhibited diminished OS and CSS. Additionally, we created user-friendly web applications to enhance the accessibility of the nomogram in clinical practices, which can be accessed at https://mbcpre.shinyapps.io/DynNomapp_OS/ for OS and https://mbcpre.shinyapps.io/DynNomapp_CSS/ for CSS. MBC patients with spPCa exhibit a more favorable prognosis than those with other SPMs. The two nomograms we constructed could accurately forecast the OS and CSS for MBC patients with spPCa. Patients whose nomograms are stratified as high-risk should gain additional attention. Our nomograms may aid clinicians in personalizing treatment strategies and supporting clinical decisions.