Search Results (137)

Bank loan prediction (BLP) analyzes the financial records of individuals to conclude possible loan status. Financial records always contain confidential information. Hence, privacy is significant in the BLP system. This research aims to generate a privacy-preserving automated BLP scheme. To achieve this, differential privacy (DP) is combined with machine learning (ML). Using a benchmark dataset, the proposed method analyzes two different DP techniques, namely Laplacian and Gaussian, with five different ML models: Random Forest (RF), Extreme Gradient Boosting (XGBoost), Adaptive Boosting (AdaBoost), Logistic Regression (LR), and Categorical Boosting (CatBoost). Each of the DP techniques is evaluated by varying distinct privacy parameters with 10-fold cross-validation, and from the outcome analysis, optimal parameters are nominated to balance privacy and security. The analysis indicates that applying the Laplacian mechanism with a DP budget of 2 and the RF model achieves the highest accuracy of 62.31%. For the Gaussian method, the best accuracy of 81.25% is attained by the CatBoost model in privacy budget 1.5. Additionally, the proposed method uses explainable artificial intelligence (XAI) to show the conclusion capability of DP-integrated ML models. The proposed research shows an efficient method for automated BLP while preserving the privacy of personal financial information and, thus, mitigating vulnerability to scams and fraud. Full article

The use of product and service brands by popular movie characters has long been a powerful marketing tool, boosting brand awareness and enhancing brand image. Product placement—the appearance of brands in films—not only increases visibility but also provides vital financial support for film production, particularly in big-budget blockbusters. However, an interesting question arises: to what extent do filmmakers and brands align brand values with the personalities of film characters? Is the goal solely to maximize exposure, or is there a conscious effort to create authentic pairings that resonate with audiences? This study examines the appearance of product and service brands in the Marvel Cinematic Universe, focusing specifically on two main characters: Iron Man (Tony Stark) and Captain America (Steve Rogers). We analyzed 11 Marvel Studios films released between 2008 and 2019, documenting brand appearances and evaluating their alignment with the characters’ personalities. By applying personality typology models (Aaker, Mark and Pearson, MBTI, NERIS Type Explorer), we developed detailed profiles of both the movie characters and the associated brands. The findings reveal that while brand placements are extensive, there is often a deliberate effort to pair them with characters in ways that reinforce authenticity and strengthen audience connections. This benefits filmmakers, audiences, and brands alike by enhancing credibility and fostering emotional engagement. Full article

The COVID-19 pandemic and the subsequent hard lockdown in South Africa, implemented in March 2020, significantly disrupted disability and rehabilitation services. Persons with disabilities experienced limited access to essential Orthotic and Prosthetic services, particularly in rural provinces such as the Eastern Cape. This study aimed to explore how Medical Orthotists and Prosthetists reconfigured their services during and after the pandemic to inform disability-inclusive emergency responses. A descriptive qualitative study was conducted with 12 Medical Orthotists and Prosthetists practicing in the public sector in the Eastern Cape. Semi-structured interviews were conducted via MS Teams, and the data were analysed by using thematic analysis to identify key themes related to service disruptions and adaptations. Four main themes emerged: (1) disrupted access to Orthotic and Prosthetic services, (2) backlogs and limited services, (3) safety measures and adaptation control, and (4) lingering challenges and gaps. Service delivery was hindered by halted outreach clinics, limited access to materials, budget reallocations, and the deprioritisation of rehabilitation services. This study highlights the challenges faced by Medical Orthotists and Prosthetists in maintaining the functionality of Orthotic and Prosthetic services during the pandemic. These findings emphasise the need for disability-inclusive policies and strategies to ensure the continuity of rehabilitation services during emergencies. Full article

Background/Objectives: Weight management is directly linked to cancer recurrence and survival, but unfortunately, nutritional oncology counseling is not typically covered by insurance, creating a disparity for patients without nutritional education and food access. Novel ways of imparting personalized nutrition advice are needed to address this issue. Large language models (LLMs) offer a promising path toward tailoring dietary advice to individual patients. This study aimed to assess the capacity of LLMs to offer personalized dietary advice to patients with breast cancer. Methods: Thirty-one prompt templates were designed to evaluate dietary recommendations generated by ChatGPT and Gemini with variations within eight categorical variables: cancer stage, comorbidity, location, culture, age, dietary guideline, budget, and store. Seven prompts were selected for four board-certified oncology dietitians to also respond to. Responses were evaluated based on nutritional content and qualitative observations. A quantitative comparison of the calories and macronutrients of the LLM- and dietitian-generated meal plans via the Acceptable Macronutrient Distribution Ranges and United States Department of Agriculture’s estimated calorie needs was performed. Conclusions: The LLMs generated personalized grocery lists and meal plans adapting to location, culture, and budget but not age, disease stage, comorbidities, or dietary guidelines. Gemini provided more comprehensive responses, including visuals and specific prices. While the dietitian-generated diets offered more adherent total daily calorie contents to the United States Department of Agriculture’s estimated calorie needs, ChatGPT and Gemini offered more adherent macronutrient ratios to the Acceptable Macronutrient Distribution Range. Overall, the meal plans were not significantly different between the LLMs and dietitians. LLMs can provide personalized dietary advice to cancer patients who may lack access to this care. Grocery lists and meal plans generated by LLMs are applicable to patients with variable food access, socioeconomic means, and cultural preferences and can be a tool to increase health equity. Full article

Advances in telecommunications and artificial intelligence (AI) are reshaping modern educational spaces. Drawing upon diverse resources, this systematic literature review examines how these new advances including 5G, Internet of Things (IoT), and AI-based analytics can transform conventional classrooms into adaptive, secure, and highly interactive environments. Real-time data collection and personalized feedback systems are found to significantly enhance engagement and accessibility for diverse learner populations. Furthermore, emerging security architectures, such as zero-trust frameworks and AI-driven intrusion detection, mitigate cyber threats and strengthen data confidentiality. Nevertheless, it is found that broader adoption is limited due to practical hurdles, which include budget allocation, professional development, and regulatory compliance. In response, strategic recommendations are provided to guide the planning and implementation of intelligent telecommunications in different educational contexts while noting the need for responsible data governance and equitable access. By illustrating how AI-assisted connectivity can enhance personalized instruction while safeguarding learner privacy, this study offers a forward-looking perspective on modern pedagogical approaches which can balance technological innovation with ethical considerations. Full article

Spike neural networks (SNNs) perform excellently in various domains. However, SNNs based on differential privacy (DP) protocols introduce uniform noise to the gradient parameters, which may affect the trade-off between model efficiency and personal privacy. Therefore, the adaptive differential private SNN (ADPSNN) is proposed in this work. It dynamically adjusts the privacy budget based on the correlations between the output spikes and labels. In addition, the noise is added to the gradient parameters according to the privacy budget. The ADPSNN is tested on four datasets with different spiking neurons including leaky integrated-and-firing (LIF) and integrate-and-fire (IF) models. Experimental results show that the LIF neuron model provides superior utility on the MNIST (accuracy 99.56%) and Fashion-MNIST (accuracy 92.26%) datasets, while the IF neuron model performs well on the CIFAR10 (accuracy 90.67%) and CIFAR100 (accuracy 66.10%) datasets. Compared to existing methods, the accuracy of ADPSNN is improved by 0.09% to 3.1%. The ADPSNN has many potential applications, such as image classification, health care, and intelligent driving. Full article

Climate change is one of the problems that affects the climate, natural disasters, and lives, economies, and industries around the world. Since the main cause is the combustion of fossil fuels, the transportation sector is a significant factor in causing these problems. Therefore, many countries, including Thailand, have policies to promote the increased use of electric vehicles. However, past measures have focused mostly on promoting the use of personal electric vehicles. For public transportation, buses are a major part of creating pollution and the problems of particulate matter with a diameter of less than 2.5-micron (PM 2.5), which is another major problem in Thailand because Thailand has many old buses. However, pushing transport operators to switch from internal combustion engine (ICE) buses to electric buses requires a large budget. Therefore, the conversion of old ICE buses into electric buses is one approach that can help promote the use of electric buses to become more possible. Another issue that makes transport operators afraid to switch from ICE buses to electric buses is the shortage of maintenance personnel. Therefore, this action research focuses on creating knowledge and practical skills related to electric vehicle modification and maintenance in the education sector. From the results of this practical research, the researcher was able to modify the old ICE bus into an electric bus and passed the test according to the research objectives. Full article

Motorcycles are a prominent contributor to most fatalities arising from traffic incidents, primarily due to drivers’ failure to adhere to traffic laws. Notably, differences in traffic violation frequency between urban and rural motorcyclists can be ascribed to variations in law enforcement practices and security budget allocations between these areas. This study aims to identify the key determinants influencing the frequency of traffic violations across these distinct geographical regions. The investigation incorporates independent variables such as personal demographics (including gender and age), driving experience, and attitudes toward traffic regulations. The analysis involved the formulation and examination of two separate logit models, each corresponding to urban and non-urban characteristics. The outcomes of a transferability test highlighted distinct disparities between the two models, with the rural model demonstrating a higher number of significant variables. In both models, certain variables consistently influenced the frequency of traffic violations. Lower violation frequencies were associated with factors such as specific age ranges, frequency of driving, and possession of a driver’s license. The insights derived from this study were leveraged to formulate policy recommendations to curb traffic violations among motorcyclists, contributing to enhancing overall traffic safety. Full article

Federated learning (FL) enables privacy-preserving collaborative model training across edge devices without exposing raw user data, but it is vulnerable to privacy leakage through shared model updates, making differential privacy (DP) essential. Existing DP-based FL methods, such as fixed-noise DP, suffer from excessive noise injection and inefficient privacy budget allocation, which degrade model accuracy. To address these limitations, we propose an adaptive differential privacy mechanism that dynamically adjusts the noise based on gradient sensitivity, optimizing the privacy–accuracy trade-off, along with a hierarchical privacy budget management strategy to minimize cumulative privacy loss. We also incorporate communication-efficient techniques like gradient sparsification and quantization to reduce bandwidth usage without sacrificing privacy guarantees. Experimental results on three real-world datasets showed that our adaptive DP-FL method improved accuracy by up to 8.1%, reduced privacy loss by 38%, and lowered communication overhead by 15–18%. While promising, our method’s robustness against advanced privacy attacks and its scalability in real-world edge environments are areas for future exploration, highlighting the need for further validation in practical FL applications such as personalized recommendation and privacy-sensitive user behavior modeling. Full article

Inflammatory bowel disease (IBD) management stands at the cusp of a transformative era, with recent breakthroughs heralding a paradigm shift in treatment strategies. Traditionally, IBD therapeutics revolved around immunosuppressants, but the landscape has evolved significantly. Recent approvals of etrasimod, upadacitinib, mirikizumab, and risankizumab have introduced novel mechanisms of action, offering renewed hope for IBD patients. These medications represent a departure from the status quo, breaking years of therapeutic stagnation. Precision medicine, involving Artificial Intelligence, is a pivotal aspect of this evolution, tailoring treatments based on genetic profiles, disease characteristics, and individual responses. This approach optimizes treatment efficacy, and paves the way for personalized care. Yet, the rising cost of IBD therapies, notably biologics, poses challenges, impacting healthcare budgets and patient access. Ongoing research strives to assess cost-effectiveness, guiding policy decisions to ensure equitable access to advanced treatments. Looking ahead, the future of IBD management holds great promise. Emerging therapies, precision medicine, and ongoing research into novel targets promise to reshape the IBD treatment landscape. As these advances continue to unfold, IBD patients can anticipate a brighter future, one marked by more effective, personalized, and accessible treatments. Full article

Tourism refers to the activity of traveling for pleasure, recreation, or leisure purposes. It encompasses a wide range of activities and experiences, from sightseeing to cultural exploration. In today’s digital age, tourists often organize their excursions independently by utilizing information available on websites. However, due to constraints in designing customized tour routes such as travel time and budget, many still require assistance with vacation planning to optimize their experiences. Therefore, this paper proposes an algorithm for personalized tourism planning that considers tourists’ preferences. For instance, the algorithm can recommend places to visit and suggest activities based on tourist requirements. The proposed algorithm utilizes an extended model of the team orienteering problem with time windows (TOPTW) to account for mandatory locations and activities at each site. It offers trip planning that includes a set of locations and activities designed to maximize the overall score accumulated from visiting these locations. To solve the proposed model, the Adaptive Neighborhood Simulated Annealing (ANSA) algorithm is applied. ANSA is an enhanced version of the well-known Simulated Annealing algorithm (SA), providing an adaptive mechanism to manage the probability of selecting neighborhood moves during the SA search process. The computational results demonstrate that ANSA performs well in solving benchmark problems. Furthermore, a real-world attractive location in Tak Province, Thailand, is used as the case study in this paper to illustrate the effectiveness of the proposed model. Full article

Background: The global rise in obesity has been significantly influenced by shifts in dietary habits that have been exacerbated by external factors such as the COVID-19 pandemic. This study aims to analyze the trends in Romanian dietary habits from 2015 to 2023, focusing on the impact of the COVID-19 pandemic and the role of socio-economic factors, seasonality, and cultural practices. Methods: For dietary habits, we used nationally representative data from the Romanian Household Budget Survey provided by the Romanian National Institute of Statistics. The survey includes 30,000 households annually. From the same provider, we downloaded data about potential drivers of food consumption, such as income, the consumer price index, and the unemployment rate. The analysis mixes descriptive statistics and panel data analysis. Among the main drivers, the econometric models include seasonality and regional factors, ensuring a comprehensive understanding of the changes in dietary behavior. Results: During the COVID-19 pandemic, daily calorie consumption increased to over 3000 calories per person, representing a 20% increase compared to the pre-pandemic period. Post-pandemic, food consumption remains elevated, averaging 2500–2600 calories per person daily. The pandemic also led to a shift in dietary composition, with significant changes. Thus, we mark an increase in fat (p < 0.001) and carbohydrate intake (p < 0.01) and a decrease in protein intake (p < 0.001). Beyond the presence of health disruptors, we confirm the significant impact of income (p < 0.001) and seasonality (p < 0.001). Other factors like unemployment, the consumer price index, and hidden regional factors have a minor role. Conclusions: The COVID-19 pandemic has had a lasting impact on Romanian dietary habits, reinforcing unhealthy eating patterns that were already prevalent. The sustained increase in calorie consumption, particularly of nutrient-poor, energy-dense foods, poses a significant public health challenge. The study also highlights significant seasonal variations, with a marked increase in food intake during the last quarter of the year, driven by cultural and religious traditions. These findings underscore the need for targeted public health interventions and policies that address economic factors and cultural and regional influences to promote healthier dietary behaviors in Romania. Full article

The real-time data collected by wearable devices enables personalized health management and supports public health monitoring. However, sharing these data with third-party organizations introduces significant privacy risks. As a result, protecting and securely sharing wearable device data has become a critical concern. This paper proposes a local differential privacy-preserving algorithm designed for continuous data streams generated by wearable devices. Initially, the data stream is sampled at key points to avoid prematurely exhausting the privacy budget. Then, an adaptive allocation of the privacy budget at these points enhances privacy protection for sensitive data. Additionally, the optimized square wave (SW) mechanism introduces perturbations to the sampled points. Afterward, the Kalman filter algorithm is applied to maintain data flow patterns and reduce prediction errors. Experimental validation using two real datasets demonstrates that, under comparable conditions, this approach provides higher data availability than existing privacy protection methods for continuous data streams. Full article

Questionnaire consumer survey research is primarily used for marketing research. To obtain credible results, collecting responses from numerous participants is necessary. However, two crucial challenges prevent marketers from conducting large-sample size surveys. The first is cost, as organizations with limited marketing budgets struggle to gather sufficient data. The second involves rare population groups, where it is difficult to obtain representative samples. Furthermore, the increasing awareness of privacy and security concerns has made it challenging to ask sensitive and personal questions, further complicating respondent recruitment. To address these challenges, we augmented small-sized datawith synthesized data generated using deep generative neural networks (DGNNs). The synthesized data from three types of DGNNs (CTGAN, TVAE, and CopulaGAN) were based on seed data. For validation, 11 datasets were prepared: real data (original and seed), synthesized data (CTGAN, TVAE, and CopulaGAN), and augmented data (original + CTGAN, original + TVAE, original + CopulaGAN, seed + CTGAN, seed + TVAE, and seed + CopulaGAN). The large-sample-sized data, termed “original data”, served as the benchmark, whereas the small-sample-sized data acted as the foundation for synthesizing additional data. These datasets were evaluated using machine learning algorithms, particularly focusing on classification tasks. Conclusively, augmenting and synthesizing consumer survey data have shown potential in enhancing predictive performance, irrespective of the dataset’s size. Nonetheless, the challenge remains to minimize discrepancies between the original data and other datasets concerning the values and orders of feature importance. Although the efficacy of all three approaches should be improved in future work, CopulaGAN more accurately grasps the dependencies between the variables in table data compared with the other two DGNNs. The results provide cues for augmenting data with dependencies between variables in various fields. Full article

Every country in the world, except for African nations, faces significant challenges due to the increasing older population, with China being particularly affected. This issue is more pronounced in rural areas compared to urban centers. To better understand consumer attitudes and willingness to pay (WTP) for age-friendly retrofitting and to identify industry development shortcomings, this study designed a retrofitting scenario and organized a questionnaire survey to collect WTP and its influencing factors from respondents in the Wuhu area of Anhui Province, China. This study determined the retrofit cost to be CNY 12,224.4 and found that over 80% of respondents intended to pursue age-friendly retrofitting. The analysis results indicated that respondents’ education level, perceived psychological benefits, and perceived social benefits were positively correlated with their WTP. Additionally, education level, monthly personal income, and choice of retirement area positively influenced retrofitting budgets, whereas age bracket, employment status, and perceived situational risk negatively influenced them. The study’s findings will assist consumers in making informed retrofitting decisions and support the government in formulating appropriate policies to enhance the quality of rural residential environments and improve the living standards of the elderly. Full article