Search Results (1,548)

Smallholder poultry farming contributes enormously to rural livelihoods, food security, and nutrition in South Africa, yet the poultry industry remains constrained by limited participation and low ICT utilisation. This study investigated the socioeconomic and demographic factors influencing decisions and choices of smallholder poultry farmers towards the adoption of ICT and market engagement in Jozini Local Municipality, KwaZulu-Natal. A cross-sectional research design was used to collect primary data from respondents. Data were collected through face-to-face surveys from 162 participants, who were randomly selected. Descriptive statistics were employed to profile the use and extent of ICT, while the multivariate probit model was used to analyse the determinants of ICT adoption and market engagement. The findings revealed that most farmers own ICT tools such as mobile phones (98.15%), which they mainly use for communication purposes (98.77%) rather than for accessing production and market related information. Smallholder characteristics like age, faming experience, marital status, and household size significantly influenced farmers decisions and choices to adopt ICT and participate in markets. The study recommends improving the traditional extension through digital integration and farmer support by means of training on ICT and formal market linkages. These interventions can significantly market participation and profitability in smallholder poultry farming, stabilising rural economic development. Full article

Introduction: The aim of this study was to examine the prevalence of scores indicating depression, anxiety and stress (<95th percentile of the score on each of the domains) among students at the University of Pristina-Kosovska Mitrovica and social and lifestyle characteristics associated with scores indicative of depression, anxiety and stress in this population studying in a post-conflict area. Methods: The cross-sectional study applying the non-probabilistic convenience sampling that included a total of 656 students of nine faculties who were present in the classes during the day of this study at the University of Pristina-Kosovska Mitrovica was conducted during the 2024/2025 school year. Results: A total of 9.3% had a score on the DASS-D scale, indicating severe or extremely severe depression, 19.6% had a score indicating severe or extremely severe anxiety, and 13.9% had a score indicative of severe or extremely severe stress. Our study showed the association of scores indicating depression with living in rural areas, average self-rated health, use of anti-anxiety medications, and mobile phone addiction. Our study showed the association of scores indicating anxiety and average self-rated health, use of anti-anxiety medications, score on social support scale, and score on state impulsivity scale. Our study showed the association of scores indicating stress with female sex, age in years, poor self-rated financial status, average self-rated health, use of anti-anxiety medications, and score on the state impulsivity scale. Conclusions: This study has shown a significant burden of psychological distress among students at the University of Pristina-Kosovska Mitrovica. Full article

Distracted driving is one of the primary causes of road traffic accidents. Behavior recognition technology based on machine vision has emerged as a research hotspot due to its non-contact and high-efficiency nature. To address the challenges of complex lighting conditions in the driver’s cabin, low detection accuracy for small-scale keypoints, and the difficulty in effectively characterizing behavioral features, this paper proposes a distracted driving behavior recognition method based on an improved YOLOv8n-Pose model and multi-feature fusion. First, the original YOLOv8n-Pose model is optimized. A P2 detection layer is added to enhance the feature extraction capabilities for small-scale human keypoints, and the SE attention module is incorporated to improve the model’s robustness under complex lighting conditions. In addition, the loss function is replaced with focal loss to tackle the class imbalance problem, thus forming the YOLOv8n-PSF-Pose keypoint detection network. Subsequently, based on the coordinates of 12 human keypoints extracted by this network, a multi-dimensional feature vector is constructed, which takes joint angles as the core and integrates the relative distances between keypoints and the number of valid keypoints. Finally, a BP neural network is adopted to classify the constructed feature vectors, enabling the accurate recognition of six typical distracted driving behaviors (normal driving, drinking or eating, making phone calls, using mobile phones, operating vehicle infotainment systems, and turning around to fetch items). The experimental results show that the improved YOLOv8n-PSF-Pose model achieves an mAP50 of 93.8% in keypoint detection, which is 6.7 percentage points higher than the original model; the BP classification model based on multi-feature fusion achieves an F1-score of 97.7% in the behavior recognition task, which is significantly better than traditional classifiers such as SVM and random forest, and the image processing speed on the NVIDIA RTX 3090TI reaches a high throughput of 45 FPS. This proves that the proposed method achieves an excellent balance between accuracy and speed. This study provides an effective solution for the real-time and accurate recognition of distracted driving behaviors. Full article

Mapping urban tree species supports green infrastructure planning. An essential issue refers to the monitoring of exotic species that may become invasive. Street-level imagery provides a complementary perspective to aerial images for species identification that are difficult to distinguish from above. In this context, our study aimed to evaluate deep learning-based object detection and image segmentation approaches to identify a potentially invasive tree species known as Leucaena leucocephala in an urban environment in Brazil, using 422 street-level images acquired from Google Street View (SV) and mobile phones (MPs). Object detection models (YOLOv8 and DETR) and a foundation segmentation model (SAM, zero-shot) were applied to assess how deep learning paradigms perform under heterogeneous urban imaging conditions. YOLOv8 achieved detection performance with mAP50 above 0.83 and recall up to 0.76. DETR showed domain sensitivity, with mAP50 of 0.45 in SV images and 0.84 in MP imagery. For segmentation, SAM zero-shot achieved 0.92 accuracy and 0.93 F1-score in SV images, decreasing to 0.63 accuracy and 0.66 F1-score in MP images. Overall, this study demonstrates that combining detection and segmentation approaches provides complementary information for urban vegetation monitoring, supporting decision-making related to invasive species management and sustainable urban landscape planning. Full article

Cognitive or visual distraction caused by drivers using mobile phones, operating the central console, or conversing with passengers while driving is a significant contributing factor to road traffic accidents. Aiming to solve the problem that existing driving behavior monitoring systems exhibit insufficient recognition accuracy and low real-time detection performance in complex driving environments, this study proposes a dual-flow driver distraction detection model based on Sobel edge detection (DFSED-Model). The model is designed with a collaborative learning framework: the first flow adopts a lightweight pre-trained backbone network to achieve efficient semantic feature extraction. The second flow utilizes Sobel edge detection to extract the driver’s driving contours and enhances the model’s spatial sensitivity to driving movements and hand movements. Through the feature learning process of the first-flow-guided auxiliary branch, collaborative optimization of knowledge transfer and attention focusing is realized, thereby improving the model’s convergence speed and discriminative performance. The proposed model is evaluated on three widely used public datasets: the State Farm Distracted Driver Detection (SFD) dataset, the 100-Driver dataset, and the American University in Cairo Distracted Driver Dataset (AUCDD-V1). Under the premise of maintaining low computational overhead, the accuracy of the DFSED-Model reaches 99.87%, 99.86%, and 95.71%, respectively, which is significantly superior to that of many mainstream models. The results demonstrate that the proposed method achieves a favorable balance between accuracy, parameter count, and efficiency, and possesses strong practical value and deployment potential. Full article

Water supplies contaminated by heavy metals pose a serious threat to human health, especially in areas without access to centralized testing facilities. While copper is a necessary heavy metal in trace levels, high concentrations can have detrimental effects on health, such as oxidative stress, cognitive impairment, and liver damage. Due to their expense, complexity, and reliance on laboratories, conventional detection techniques are accurate but unsuitable for real-time, dispersed deployment. Machine learning offers a potent solution to these constraints by facilitating the automatic, precise, and quick interpretation of complicated sensor data. It makes it possible to make decisions in real time without requiring a large laboratory infrastructure. In this work, a dual-mode optical sensor was developed using the colorimetry and fluorometry images of carbon dots embedded in hydrogels with the Cu²⁺ concentration of 0, 20, 50, 100, 200, and 500 μM. Data augmentation was used to expand the RGB picture dataset for each modality, and these data were interpolated to provide responses at 1 µM intervals (0–500 µM). We trained a comprehensive set of supervised machine learning models, including Logistic Regression, Support Vector Machines, Random Forest, and XGBoost, to categorize water samples into five risk-informed quality levels. The system achieved classification accuracies exceeding 96%. Furthermore, we built a simple user interface to make the system practically deployable in mobile phone. Together, these results demonstrate a scalable, interpretable, cost-effective, and quick solution for real-time water quality monitoring in resource-constrained environments. Since the proposed method focuses on classifying concentration ranges rather than precise quantification, a formal limit of detection (LOD) was not calculated; instead, the lowest concentration in the experimental dataset serves as the minimum detectable level. Full article

Background: Difficult intubation is an important clinical problem faced by anesthesiologists and is one of the most important causes of anesthesia-related morbidity. According to various sources, the frequency of encountering a difficult airway is stated as 1–4%. Aim: We thought that difficult tracheal intubation could be predicted by photographic analysis using artificial intelligence. Methods: Sixteen photographs were taken in the preoperative period in the sitting and lying positions anteriorly, laterally, with the mouth open, with the mouth closed, with the neck straight, and with the neck extended. Intubations performed without intervention for the first time were considered easy. Intubations with external tracheal intervention and with more than one attempt were evaluated as medium. Intubations requiring more than three attempts; intubation with stylets, fiberoptic bronchoscopes, or video laryngoscopes; or cases in which patients could not be intubated and provided airway with a laryngeal mask were considered difficult. Results: In our study, the CNN (convolutional neural network) model performed well overall, with the best results generally obtained using batch sizes of 32 and 128 and learning rates ranging from 0.1 to 0.001. Conclusions: The prominent aspects of our study are that it can be conducted with an easily accessible mobile phone, can be performed at the bedside, and is successful in predicting difficult intubation. The sensitivity of methods currently used to assess difficult airways is generally low, and the likelihood of clinicians successfully identifying this condition using available information varies widely; thus far, there is no gold standard for prediction. We believe that our study will bring a different perspective to estimating the difficulty of intubation, which occupies a very important place in anesthesia practice. Full article

(1) Background: The local divergence exponent (LDE) is a sensitive measure of walking stability deterioration and risk of falling in older adults. We aim to determine the validity the LDE measured using a mobile phone and to assess its ability to discriminate between healthy young and older adults; (2) Methods: 20 older adults (76.4 ± 4.6 years) and 20 young adults (29.1 ± 6.5 yrs) walked for 6 min on a 20-m walkway while wearing a research-grade inertial measurement unit (IMU) and a mobile phone placed on the sternum to record 3D acceleration data. The LDE was calculated using data from both devices for 3D, vertical (VT), mediolateral (ML), anteroposterior (AP), and norm (N) accelerations. ICC (3,1) was used to determine the validity of the mobile phone’s LDE. Mann–Whitney U tests were used to determine age-group discriminability of LDE measures; (3) Results: LDEs demonstrated excellent absolute agreement between the wearable IMU and mobile phone (ICC = 0.844). Mobile phone-derived LDEs demonstrated excellent validity relative to the wearable IMU (ICC > 0.75). No significant age-related differences in LDE were observed; wearable or mobile sensors (both p > 0.05); (4) Conclusions: LDEs measures obtained with a mobile phone are valid. No age group differences were identified. Full article

Background: The impact of screen time is having serious adverse effects on people’s lives. Unfortunately, early childhood is the most vulnerable stage in the lifespan, and most children are using television, computers, parents’ and mothers’ mobile phones, or tablets, for longer than recommended. For this reason, the interest of the education community in proposing programs for reducing screen time has grown, which could be of interest for families and professionals in early childhood development and care for children adhering to a healthy lifestyle. For this reason, the objective of this study is to compile programs including families that have tried to reduce preschool-aged children’s time in front of screens. Method: The search strategy is designed based on the PICOS framework. A review was conducted in three databases (PubMed, Web of Science, and ProQuest Central) on 11 October 2024, following the PRISMA guidelines. The systematic review is registered in PROSPERO. Results: A total of 287 articles were initially found, and 15 met all inclusion criteria. Conclusions: The results reveal that programs based on training parents in addition to performing games with children have positive effects for reducing screen time in children up to six years old, even in a specific population. Full article

Background/Objectives: Nomophobia, the irrational fear of being without a mobile phone, is increasingly prevalent among university students and has emerged as a concerning form of digital dependence. Among nursing students, this condition is particularly relevant due to the emotional demands and cognitive challenges of healthcare education. Nomophobia has been linked with adverse psychological outcomes, sleep disturbances, and impaired academic and clinical performance. However, existing evidence remains fragmented and lacks an integrated conceptual synthesis. This review aimed to synthesize current evidence on the prevalence, correlates, and outcomes of nomophobia among nursing students. Methods: An integrative review was conducted following Whittemore and Knafl’s methodology and PRISMA guidelines. A systematic search was performed in PubMed, CINAHL, PsycINFO, PsycArticles, and Medline (between 2015 and 2025), supplemented by Google Scholar. Cross-sectional studies and literature focusing on nomophobia in nursing students were included. The primary studies and selected review articles were considered when no overlap with the included primary evidence was identified. Methodological quality appraisal was assessed using validated tools (QuADS and JBI). Results: Twenty-two studies were included (19 cross-sectional and 3 reviews). Four thematic areas emerged: prevalence and severity (50–90% moderate to severe); psychological correlates (anxiety, depression, stress, insomnia, alexithymia, fear of missing out); academic and cognitive outcomes (impaired performance, procrastination, reduced decision-making); and behavioural predictors (excessive smartphone use and emotional dysregulation). The Nomophobia Questionnaire (NMP-Q) was the most frequently used instrument. Conclusions: Nomophobia represents a relevant dimension of the mind–technology relationship in nursing education, with implications for students’ mental health, academic engagement, and clinical readiness. Addressing nomophobia may support healthier learning environments and contribute to the development of emotionally competent and safe future healthcare professionals. However, significant gaps remain, particularly regarding longitudinal evidence and intervention-based approaches. Full article

This study identifies and explains road safety behavior patterns in Colombia using explainable artificial intelligence (XAI). Based on 9232 records and 38 variables from the Territorial Survey of Road Safety Behavior, the CRISP-DM methodology was applied, including data cleaning, normalization, encoding, and feature selection. XGBoost, Random Forest, Bagging, and AdaBoost models were evaluated, incorporating three domain-specific indices: Distraction Index (DI), Risky Road Interaction Index (RRI), and Normative Compliance Index (NCI). AdaBoost achieved the best overall balance (Precision = 0.78; Recall = 0.75; F1-score = 0.77), simultaneously reducing false positives and false negatives. SHAP analysis revealed that environmental and infrastructure factors (lighting, traffic signals, intersections, congestion, perceived crime) explain more variance than self-reported behaviors (mobile phone use, alcohol consumption, speeding). The complementary indices indicated above-average distraction levels, high exposure to risky interactions, and low compliance in specific segments. These findings enable the prioritization of targeted interventions (improvements in lighting and crossings, focused enforcement, and educational campaigns) and support operation with thresholds adjusted to error costs, providing traceable decision support for public road safety policies. Overall, the proposed approach integrates prediction and explainability to enable actionable decisions and continuous monitoring aimed at reducing traffic accidents. Full article

Intra-urban commuting plays a fundamental role in shaping urban spatial structure and daily mobility patterns. Existing studies have largely explained commuting flows using attribute-based or distance-centred approaches. Such approaches overlook the interdependent and relational nature of commuting within complex urban systems. This study constructs a subdistrict-level commuting network using anonymised mobile phone signalling data from Hangzhou, China, and a valued exponential random graph model (valued ERGM) to examine how commuting flows are generated through the interaction of network self-organization, local job-housing conditions, and multi-dimensional proximity. The results reveal strong endogenous dependence exemplified by reciprocal commuting ties. Employment agglomeration and public rental housing provision are associated with stronger integration of subdistricts within the commuting network, while high housing prices and certain residential amenities are associated with reduced inter-subdistrict commuting. Beyond geographic distance, metro connectivity, administrative affiliation, and social interaction are significantly associated with commuting flows. This study advances a relational explanation of intra-urban commuting and demonstrates the methodological value of valued ERGMs for analysing weighted urban flow networks. The findings have implications for integrated transport, housing, and governance strategies, particularly transit-oriented development, cross-jurisdictional coordination, and the strategic siting of affordable housing, aimed at promoting more locally embedded and sustainable urban mobility. Full article

This study focuses on the instantaneous effects of fast charging technologies, in terms of the daily operation of mobile devices, and specifically on the trade-off between fast charge and discharge efficiency. A controlled experimental layout is used, containing three smart devices, iPhone 17 Pro, iPad 11 Air and MacBook Pro, and four variations in chargers. The research monitored important values like the voltage, current, power and thermal behavior of the selected devices. These comparative results showed that high-speed charging at 67 Watts causes peak temperatures in the battery to be 41.5 °C, which is significantly higher compared to charging under standard protocols of 20 W, with values of 33.1 °C. This thermal stress forces the battery outside of its optimum operating window and consequently increases the internal resistance of the battery which results in a reduction of about 5% of the subsequent discharge runtime. Although fast charging offers a rapid energy replenishment, the thermal penalty incurred by the fast charging process reduces the battery’s short-term utility, suggesting that standard charging is the best option to maximize the single-cycle duration. Full article

Extant literature captures the benefits and risks concerning young adults’ use of digital technologies and platforms, but it does not unilaterally recognize the drivers of problematic digital behavior. Those drivers might differ across dimensions of young adults’ digital lives, their socioeconomic backgrounds, and other demographic determinants. In this study, we analyze the determinants of addictive digital behavior of economics and business students from a Southeast European (SEE) sample of 372 participants. We measure digital addictive behavior regarding Internet use, with a focus on mobile phones, using established psychological scales. Our results show that age is generally associated with lower problematic digital behavior (significant in the full sample), while female students report higher PRIUSS-3 scores than male students. Higher ICT proficiency is associated with lower PRIUSS-3 and MPPUS-10 scores. Daily screen time is associated with higher MPPUS-10 scores, but it does not significantly predict PRIUSS-3 in the multivariable model. The empirical results can be used to frame the higher education policies and targeted interventions in the SEE region. Full article

Background and Objectives: To evaluate the clinical performance of a smartphone-based sound amplification device (SBSAD) compared to a conventional personal sound amplification product (PSAP) in older adults with mild-to-moderate sensorineural hearing loss (SNHL), ad-dressing the need for accessible alternatives given the low adoption of traditional hearing aids. Materials and Methods: Forty-nine participants (mean age 68 years) with mild-to-moderate SNHL underwent audiometric testing and subjective evaluation under three conditions: unaided, aided with a commercial PSAP, and aided with an SBSAD (iPhone with wireless earbuds). Primary outcomes included functional gain in sound field thresholds and user ratings of sound quality and acceptability via a custom questionnaire. Results: Both devices yielded significant threshold improvements compared to the unaided condition (p < 0.001). Mean functional gain was 16.0 dB for the PSAP and 15.3 dB for the SBSAD, with no statistically significant difference (p > 0.5). Subjective ratings for sound quality, comfort, cosmetic acceptability, and future willingness to use were comparable between devices (all p > 0.05). Conclusions: The SBSAD performed equivalently to a traditional PSAP in improving audibility and user satisfaction. Smartphone-based technologies offer a viable, accessible mobile health solution to bridge the gap for older adults who lack conventional hearing aids. Full article