Search Results (1,639)

Deteriorating road infrastructure is a global concern, especially in low-income countries where financial and technological constraints hinder effective monitoring and maintenance. Traditional methods, like inertial profilers, are expensive and complex, making them unsuitable for large-scale use. This paper explores the integration of cost-effective, scalable smartphone technologies for road surface monitoring. Smartphone sensors, such as accelerometers and gyroscopes, combined with data preprocessing techniques like filtering and reorientation, improve the quality of collected data. Machine learning algorithms, particularly CNNs, are utilized to classify road anomalies, enhancing detection accuracy and system efficiency. The results demonstrate that smartphone-based systems, paired with advanced data processing and machine learning, significantly reduce the cost and complexity of traditional road surveys. Future work could focus on improving sensor calibration, data synchronization, and machine learning models to handle diverse real-world conditions. These advancements will increase the accuracy and scalability of smartphone-based monitoring systems, particularly for urban areas requiring real-time data for rapid maintenance. Full article

This research explores the perspectives of kindergarten through to Grade 12 (K-12) teachers on incorporating information and communication technology (ICT) into the environmental education (EE) curriculum. In the context of the increasing influence of ICT in education, this study examines both the potential enhancements ICT offers to EE and the challenges it poses. Using data from an online survey and an in-person focus group, the investigation addresses the capacity of ICT to promote environmental stewardship and personal growth, alongside concerns regarding technology’s potential to alienate students from nature and the divided opinions among educators regarding optimal technology use. Attention is given to systemic barriers that complicate EE integration and the variability of its implementation in Ontario, Canada, where EE is mandated across K-12 curricula. The findings illuminate educators’ concerns about digital dependencies among their students and the difficulty they face in striking a balance between the use of ICT and non-technical pedagogical approaches when engaging students in environmental lessons. Importantly, study participants identified limited contemporary and timely technological tools to support EE delivery that deemphasize using personal mobile devices (e.g., smartphones and tablets). In response, we recommend three forms of technology (and accompanying lesson ideas) that are affordable, easy to integrate into classrooms, and do not require off-site trips, thereby enhancing accessibility and equity. This study’s implications are aimed at educators, policymakers, and stakeholders seeking to enhance EE delivery within a technologically evolving educational framework and ensure the development of environmentally conscious students. Full article

Smartphones have become a central element in modern society with their widespread adoption driven by technological advancements and their ability to facilitate everyday tasks. A critical feature influencing user satisfaction and smartphone adoption is battery life, as the intensive use of mobile devices can significantly drain battery power. This paper addresses the challenge of predicting smartphone battery consumption using artificial intelligence techniques, specifically deep learning, to optimize energy efficiency. By collecting and analyzing data from mobile devices, such as application usage, screen time, network type, network usage, and battery temperature among others, we developed a predictive model tailored to user-specific behavior. This model identifies the key variables affecting battery consumption and provides personalized energy-saving strategies. Our approach offers a solution for improving battery performance, contributing to more efficient energy management in both hardware and networking terms while adapting to individual usage patterns. The results demonstrate that our approach can significantly predict the battery to anticipate power demands based on user-specific usage. While challenges remain, such as improving the generalizability of the model across different devices, this approach provides a scalable and adaptive method to improve the energy efficiency of smartphones, which will allow efficient management solutions to be suggested, contributing to better battery and network management to improve user experience and device longevity. Full article

In the domain of cybersecurity, cyber threats targeting network devices are very crucial. Because of the exponential growth of wireless devices, such as smartphones and portable devices, cyber risks are becoming increasingly frequent and common with the emergence of new types of threats. This makes the automatic and accurate detection of network-based intrusion very essential. In this work, we propose a network-based intrusion detection system utilizing the comprehensive feature engineering approach combined with boosting machine-learning (ML) models. A TCP/IP-based dataset with 25,192 data samples from different protocols has been utilized in our work. To improve the dataset, we used preprocessing methods such as label encoding, correlation analysis, custom label encoding, and iterative label encoding. To improve the model’s accuracy for prediction, we then used a unique feature engineering methodology that included novel feature scaling and random forest-based feature selection techniques. We used three conventional models (NB, LR, and SVC) and four boosting classifiers (CatBoostGBM, LightGBM, HistGradientBoosting, and XGBoost) for classification. The 10-fold cross-validation methods were employed to train each model. After an assessment using numerous metrics, the best-performing model emerged as XGBoost. With mean metric values of 99.54 ± 0.0007 for accuracy, 99.53 ± 0.0013 for precision, 99.54 ± 0.001 for recall, and an F1-score of 99.53 ± 0.0014, the XGBoost model produced the best performance overall. Additionally, we showed the ROC curve for evaluating the model, which demonstrated that all boosting classifiers obtained a perfect AUC value of one. Our suggested methodologies show effectiveness and accuracy in detecting network intrusions, setting the stage for the model to be used in real time. Our method provides a strong defensive measure against malicious intrusions into network infrastructures while cyber threats keep varying. Full article

Locomotive syndrome (LS) refers to a condition where individuals face challenges in performing activities of daily living. Early detection of such deterioration is crucial to reduce the need for nursing care. The Geriatric Locomotive Function Scale (GLFS-25), a 25-question assessment, has been proposed for categorizing individuals into different stages of LS. However, its subjectivity has prompted interest in technology-based quantitative assessments. In this study, we utilized machine learning and an instrumented five-time sit-to-stand test (FTSTS) to assess LS stages. Younger and older participants were recruited, with older individuals classified into LS stages 0–2 based on their GLFS-25 scores. Equipped with a single inertial measurement unit at the pelvis level, participants performed the FTSTS. Using acceleration data, 144 features were extracted, and seven distinct machine learning models were developed using the features. Remarkably, the multilayer perceptron (MLP) model demonstrated superior performance. Following data augmentation and principal component analysis (PCA), the MLP+PCA model achieved an accuracy of 0.9, a precision of 0.92, a recall of 0.9, and an F1 score of 0.91. This underscores the efficacy of the approach for LS assessment. This study lays the foundation for the future development of a remote LS assessment system using commonplace devices like smartphones. Full article

Smartphones equipped with highly integrated sensors are increasingly being recognized as powerful tools for rapid on-site testing. Here, we propose a low-cost, portable, and highly multiplexed smartphone-based spectrometer capable of collecting three types of spectra—transmission, reflection, and fluorescence—by simply replacing the optical fiber attached to the housing. Spectral analysis is performed directly on the smartphone using a custom-developed app. Furthermore, we introduce a high signal-to-noise ratio (SNR) caffeine detection scheme that leverages aspirin and salicylic acid as fluorescent probes, allowing for the rapid and straightforward detection of caffeine in various samples. The fluorescence quenching of the probes was found to be linearly related to the caffeine concentration (0–200 μM), and the recoveries of the commercially available caffeine-containing samples were in the range of 98.0333–105.6000%, with a limit of detection (LOD) of 2.58 μM. The reliability and stability of the on-site assay using the smartphone spectrometer were verified. More importantly, this spectrometer demonstrates great potential as a versatile device for use outside of laboratory settings by enabling different operating modes tailored to various scenarios. Full article

Globally, 77% of the elderly aged 65 and above suffer from multiple chronic ailments, according to recent research. However, several barriers within the healthcare system in the developing world hinder the adoption of home-based patient management, hence the need for the IoMT, whose application raises security concerns, particularly in authentication. Several authentication techniques have been proposed; however, they lack a balance of security and usability. This paper proposes a Naive Bayes based adaptive user authentication app that calculates the risk associated with a login attempt on an Android device for elderly users, using their health conditions, risk score, and available authenticators. This authentication technique guided by the MAPE-K_HMT framework makes use of embedded smartphone sensors. Results indicate a 100% and 98.6% accuracy in usable-security metrics, while cross-validation and normalization results also support the accuracy, efficiency, effectiveness, and usability of our model with room for scaling it up without computational costs and generalizing it beyond SSA. The post-deployment evaluation also confirms that users found the app usable and secure. A few areas need further refinement to improve the accuracy, usability, security, and acceptance but the model shows potential to improve users’ compliance with IoMT security, thereby promoting the attainment of SDG3. Full article

Background: Cardiovascular diseases (CVDs) are the leading causes of death globally. Managing risk factors and preventing atherosclerosis and its progress, especially with lifestyle changes, are highly important. Smartphone-based mobile health (mHealth) strategies allow easily accessible assistance for healthy nutrition. This study aimed to assess the acceptance and outline the needs and demands for a nutritional mHealth tool by analyzing the desired characteristics. Methods: A cross-sectional study was conducted between August 2022 and September 2023 targeting 398 individuals with atherosclerosis. Acceptance, needs, and demands regarding mHealth, sociodemographic, medical, psychometric, and electronic health (eHealth) data were assessed. Multiple hierarchical regression analyses were conducted to determine the predictors of acceptance. Results: High acceptance for nutritional mHealth was reported by 88.4% (n = 274). Significant predictors of acceptance were age (β = −0.01, p = 0.002), diabetes (β = 0.20, p = 0.041), depressive symptoms (β = −0.02, p = 0.017), digital confidence (β = 0.17, p = 0.001), Internet anxiety (β = −0.18, p = 0.004), and the Unified Theory of Acceptance and Use of Technology (UTAUT) predictors effort expectancy (β = 0.23, p < 0.001) and social influence (β = 0.53, p < 0.001). Preferences included handheld devices, permanent use (86.5%), and weekly (44.5%) new content of 10 to 30 min (79%). Conclusions: These results summarize the patients’ preferences for individualized mHealth tools to ensure their effectiveness. Especially regarding the secondary prevention of CVDs, mHealth can be a helpful resource. The high acceptance rate and specific preferences outlined in this study form a strong basis for the development of mHealth tools with a focus on nutritional support in patients with CVDs. Full article

Pedestrian distraction poses significant risks at signalized intersections, especially in populated urban areas. This study investigates the primary causes of pedestrian distraction to determine the contributing factors affecting crossing behavior. Data were collected from ten signalized intersections by conducting in-person interviews, performing real-time observation, and reviewing video recordings. The study used binary logistic regression and Heuristic Bin analysis to examine different levels of distraction among pedestrians. Three major types of pedestrian distractions were identified: visual, auditory, and cognitive distractions. From the regression analysis, two models were developed to predict moderate and high levels of distraction based on factors such as age, intersection location, walking behavior, use of electronic devices, and awareness of traffic signals. The results indicated that smartphone usage and earphones were the predominant sources of distraction. Pedestrians walking in pairs demonstrated higher levels of distraction than those walking alone or in groups. Heuristic Bins analysis revealed that females were slightly more distracted than males while walking alone, in pairs, or in a group. Pedestrians also tended to be more distracted when they were walking in pairs than when walking alone or in groups. Full article

Wearable technology has advanced significantly, offering real-time monitoring of athletes’ physiological parameters and optimizing training and recovery strategies. Recent developments focus on biosensor devices capable of monitoring biochemical parameters in addition to physiological ones. These devices employ noninvasive methods such as sweat analysis, which reveals critical biomarkers like glucose, lactate, electrolytes, pH, and cortisol. These biomarkers provide valuable insights into an athlete’s energy use, hydration status, muscle function, and stress levels. Current technologies utilize both electrochemical and colorimetric methods for sweat analysis, with electrochemical methods providing higher precision despite potential signal interference. Wearable devices such as epidermal patches, temporary tattoos, and fabric-based sensors are preferred for their flexibility and unobtrusive nature compared to more rigid conventional wearables. Such devices leverage advanced materials and transmit real-time data to computers, tablets, or smartphones. These data would aid coaches and sports medical personnel in monitoring athletes’ health, optimizing diets, and developing training plans to enhance performance and reduce injuries. Full article

“Smart” devices, such as contemporary smartphones and PDAs (Personal Digital Assistance), play a significant role in our daily live, be it for navigation or location-based services (LBSs). In this paper, the use of Ultra-Wide Band (UWB) and Wireless Fidelity (Wi-Fi) based on RTT (Round-Trip Time) measurements is investigated for pedestrian user localization. For this purpose, several scenarios are designed either using real observation or simulated data. In addition, the localization of user groups within a neighborhood based on collaborative navigation (CP) is investigated and analyzed. An analysis of the performance of these techniques for ranging the positioning estimation using different fusion algorithms is assessed. The methodology applied for CP leverages the hybrid nature of the range measurements obtained by UWB and Wi-Fi RTT systems. The proposed approach stands out due to its originality in two main aspects: (1) it focuses on developing and evaluating suitable models for correcting range errors in RF-based TWR (Two-Way Ranging) technologies, and (2) it emphasizes the development of a robust CP engine for groups of pedestrians. The results obtained demonstrate that a performance improvement with respect to position trueness for UWB and Wi-Fi RTT cases of the order of 74% and 54%, respectively, is achieved due to the integration of these techniques. The proposed localization algorithm based on a P2I/P2P (Peer-to-Infrastructure/Peer-to-Peer) configuration provides a potential improvement in position trueness up to 10% for continuous anchor availability, i.e., UWB known nodes or Wi-Fi access points (APs). Its full potential is evident for short-duration events of complete anchor loss (P2P-only), where an improvement of up to 53% in position trueness is achieved. Overall, the performance metrics estimated based on the extensive evaluation campaigns demonstrate the effectiveness of the proposed methodologies. Full article

Medical thermography is a non-invasive technique that allows the measurement of the temperature of the human body surface, exploiting the heat emitted by the body through the skin in the form of infrared electromagnetic radiation. Recently, smartphone-based thermography (ST) has drawn considerable attention. This scoping review (SR) aims to describe its current applications and reliability based on currently available research findings, also taking into account the medico-legal implications linked to its use. A search of the sources was conducted on multiple databases (PubMed, Scopus, Cochrane, Lilacs, Google Scholar). Based on a set of eligibility criteria, all articles deemed useful were included in the SR. Collected data, processed with descriptive statistics, are then discussed. From the initial 241 results, after duplicate removal and full-text reading based on inclusion/exclusion criteria, 20 articles were classified according to the main characteristics and indications and outcomes are highlighted based on clinical evidence. The most frequently documented fields of ST are wound care management and vascular surgery. Other disciplines are less explored (dentistry, ophthalmology, otorhinolaryngology, orthopedics, etc.). Practicality, operational simplicity and affordability of mobile thermographic devices are the chief strengths of this technology. Comparative studies with traditional thermal imaging methods are poor in terms of the number of patients analyzed but this technology showed high sensitivity and accuracy in the large number of patients enrolled in observational studies, encouraging the development of further operational protocols in all medical specialties. Gaining a deeper understanding of such techniques will also help settle the medico-legal issues which may arise from the clinical implementation of ST, thus appraising its reliability and safety from that perspective as well. Full article

Human activity recognition (HAR) in real-world settings has gained significance due to the growth of Internet of Things (IoT) devices such as smartphones and smartwatches. Nonetheless, limitations such as fluctuating environmental conditions and intricate behavioral patterns have impacted the accuracy of the current procedures. This research introduces an innovative methodology employing a modified deep residual network, called 1D-ResNeXt, for IoT-enabled HAR in uncontrolled environments. We developed a comprehensive network that utilizes feature fusion and a multi-kernel block approach. The residual connections and the split–transform–merge technique mitigate the accuracy degradation and reduce the parameter number. We assessed our suggested model on three available datasets, mHealth, MotionSense, and Wild-SHARD, utilizing accuracy metrics, cross-entropy loss, and F1 score. The findings indicated substantial enhancements in proficiency in recognition, attaining 99.97% on mHealth, 98.77% on MotionSense, and 97.59% on Wild-SHARD, surpassing contemporary methodologies. Significantly, our model attained these outcomes with considerably fewer parameters (24,130–26,118) than other models, several of which exceeded 700,000 parameters. The 1D-ResNeXt model demonstrated outstanding effectiveness under various ambient circumstances, tackling a significant obstacle in practical HAR applications. The findings indicate that our modified deep residual network presents a viable approach for improving the dependability and usability of IoT-based HAR systems in dynamic, uncontrolled situations while preserving the computational effectiveness essential for IoT devices. The results significantly impact multiple sectors, including healthcare surveillance, intelligent residences, and customized assistive devices. Full article

Today, many businesses use near-field communications (NFC) payment solutions, which allow them to receive payments from customers quickly and smoothly. However, this technology comes with cyber security risks which must be analyzed and mitigated. This study explores the cyber risks associated with NFC transactions and examines strategies for mitigating these risks, focusing on payment devices. This paper provides an overview of NFC technology, related security vulnerabilities, privacy concerns, and fraudulent activities. It then investigates payment devices such as smartphones, contactless cards, and wearables, highlighting their features and vulnerabilities. The study also examines encryption, authentication, tokenization, biometric authentication, and fraud detection methods as risk mitigation strategies. The paper synthesizes theoretical frameworks to provide insights into NFC transaction security and offers stakeholder recommendations. Full article

Artificial intelligence has significant applications in computer vision studies for cultural heritage. In this research field, visual inspection of historical buildings and the digitization of heritage using machine learning models stand out. However, the literature still lacks datasets for the classification and identification of Brazilian religious buildings using deep learning, particularly with images from the historic town of Ouro Preto. It is noteworthy that Ouro Preto was the first Brazilian World Heritage Site recognized by UNESCO in 1980. In this context, this paper aims to address this gap by proposing a new image dataset, termed ImageOP: The Image Dataset with Religious Buildings in the World Heritage Town of Ouro Preto for Deep Learning Classification. This new dataset comprises 1613 images of facades from 32 religious monuments in the historic town of Ouro Preto, categorized into five classes: fronton (pediment), door, window, tower, and church. The experiments to validate the ImageOP dataset were conducted in two stages: simulations and computer vision using smartphones. Furthermore, two deep learning structures (MobileNet V2 and EfficientNet B0) were evaluated using Edge Impulse software. MobileNet V2 and EfficientNet B0 are architectures of convolutional neural networks designed for computer vision applications aiming at low computational cost, real-time classification on mobile devices. The results indicated that the models utilizing EfficientNet achieved the best outcomes in the simulations, with accuracy = $94.5\%$, precision = $96.0\%$, recall = $96.0\%$, and F-score = $96.0\%$. Additionally, superior accuracy values were obtained in detecting the five classes: fronton ($96.4\%$), church ($97.1\%$), window ($89.2\%$), door ($94.7\%$), and tower ($95.4\%$). The results from the experiments with computer vision and smartphones reinforced the effectiveness of the proposed dataset, showing an average accuracy of $88.0\%$ in detecting building elements across nine religious monuments tested for real-time mobile device application. The dataset is available in the Mendeley Data repository. Full article