Search in Publications
Found 5152 publications
A hybrid physics-informed neural and explainable AI approach for scalable and interpretable AQI predictions
Publication Name: Methodsx
Publication Date: 2025-12-01
Volume: 15
Issue: Unknown
Page Range: Unknown
Description:
Air Pollution is a critical environmental issue affecting public health, climate, and ecosystems. However, accurately predicting and classifying Air Quality Index (AQI) levels across different regions remains a challenging task due to the complex nature of air pollution patterns. Conventional and ensemble ML and DL models often fail to capture the physical laws goverming the air pollution, which leads to inaccurate predictions. This study addresses these issues by introducing an approach that employs Physics-Informed Neural Networks (PINN) with Explainable AI (XAI) techniques for AQI classification (AirSense-X). The proposed approach utilizes PINN for regression, along with mapping for classification and XAI for interpretation. PINN ensures that the model learns from physical laws governing air quality rather than relying solely on data. The dataset utilized in this study is a publicly available dataset containing the AQI data at daily levels from various stations across multiple cities in India. The proposed AirSense-X approach achieves an accuracy of 98 %, with 97 % precision, 95 % recall, and an F1 score of 0.96, ensuring reliability. Similarly, the confusion matrix for the proposed approach indicated that the model correctly classified 21,306 and misclassified 268 instances. The key focuses of this study include: • Introducing a novel approach, AirSense-X, which employs PINN for accurate AQI prediction and XAI for enhanced interpretability. Additionally, the study also involves comparative analysis with conventional and ensemble ML and DL models. • Employing structure mapping technique for classification based on the predicted AQI values. • Integrating physical laws governing air pollution using a PINN model enhances prediction accuracy and ensures that the model learns beyond relying on data-driven insights.
Open Access: Yes
Effect of heat stress and feed restriction on performance, carcass traits, and meat quality of growing rabbits
Publication Name: Livestock Science
Publication Date: 2025-12-01
Volume: 302
Issue: Unknown
Page Range: Unknown
Description:
The effects of heat stress and feed restriction were evaluated on a total of 180 weaned rabbits divided into three experimental groups (60 animals/group): 2 groups were fed ad libitum and reared under different temperatures (20 °C – 20AD and 30 °C – 30AD), while a third group was housed under controlled temperature (20 °C) but pair-fed to 30AD rabbits, thus feed restricted (20FR). During the trial, both 30AD and 20FR groups exhibited reduced growth performance, including body weight and daily weight gain (both, P < 0.001), although feed conversion ratio improved (P = 0.016). The reference carcasses of 20FR and 30AD rabbits were lighter and leaner (both, P < 0.001) than that of 20AD rabbits, while the slaughter yield decreased only in 20FR rabbits (P = 0.001). Regarding meat physical traits, 20FR rabbits exhibited the highest pHu (P < 0.001) and the lowest total losses (P < 0.001), whereas the meat-to-bone ratio decreased in both 20FR and 30AD groups (P = 0.007). As for meat proximate composition, protein and lipid contents were lower (P = 0.008 and P = 0.0002, respectively) in 20FR and 30AD rabbits, while water content was greater (P < 0.001) compared to 20AD rabbits. At the lipid level, higher TBARS (P = 0.001) were found in both 20FR and 30AD groups. The 20FR and 30AD groups showed some differences in their carcass and meat quality traits, however the majority of changes induced by chronic heat stress were mostly attributed to the reduced feed intake.
Open Access: Yes
Decision-analytics-based electric vehicle charging station location selection: A cutting-edge fuzzy rough framework
Publication Name: Energy Reports
Publication Date: 2025-12-01
Volume: 14
Issue: Unknown
Page Range: 711-735
Description:
Electric vehicles are of great significance in supporting sustainable transportation and sustainability. In parallel with the increasing demand for such vehicles worldwide, the electric vehicle charging stations (EVCSs) market has grown dramatically. The study presents a practical model for selecting EVCS sites integrating multi-criteria decision-making (MCDM), fuzzy, and rough sets. The research aims to bridge the gap in evaluating EVCS locations by leveraging the superiorities of fuzzy and rough set theories to address vagueness effectively. Firstly, assessment criteria cover the environment, economic, technology, and social drivers. Secondly, a fuzzy Defining Interrelationships Between Ranked criteria (F-DIBR) model is applied to determine the weight values of siting factors. Last, for the first time, the Mixed Aggregation by COmprehensive Normalization Technique (MACONT) with hybrid fuzzy rough numbers (FRN-MACONT) model is proposed to obtain the ranking results. Further, a new approach for defining hybrid fuzzy rough numbers is suggested, based on an improved methodology for determining rough numbers' lower and upper limits, allowing consideration of mutual relations between a set of objects and flexible representation of rough boundary intervals depending on the dynamic environmental conditions. The study's novelties reside in deciding the importance of the driving forces used in determining the EVCS site location with a novel method, F-DIBR, and selecting the optimal site with a new FRN-MACONT approach. The results show that “economy” is the most significant criterion, whereas “system reliability” is the most critical sub-criterion. The findings also indicate that the Konak territory performs the best, whereas the Cigli territory is the second best. Comprehensive sensitivity analysis verifies the proposed framework's validity, robustness, and effectiveness. As per the research findings and analyses, some managerial implications are further discussed. The approach introduced has the potential to contribute to the green transport literature.
Open Access: Yes
Halal tourism research in Indonesian context: a bibliometric analysis
Publication Name: Discover Sustainability
Publication Date: 2025-12-01
Volume: 6
Issue: 1
Page Range: Unknown
Description:
Halal tourism is a growing sector of tourism that has attracted considerable attention in recent years due to its potential for economic growth and the need to meet the demands of Muslim travelers. This study aims to provide a comprehensive overview of halal tourism research in Indonesia through the utilization of bibliometric approach. The study utilizes Scopus database to analyze the publication trends, co-authorship, and thematic analysis, as well as the future research directions on this field in the context of Indonesia spanning the years 2017 to 2024. The findings indicate that there is a disparity in the involvement of authors and affiliations from Indonesia in terms of publications. The results show consistent growth in Indonesian publications, but emphasize the need for better quality and global dissemination. Moreover, the findings suggest that Indonesia plays a key role in the development of tourism in Indonesia due to its Muslim population and integration of Islamic principles in education and tourism. These findings highlight the importance of understanding Muslims tourists’ behavior, political economy influences, and service quality in different regions of Indonesia, thereby informing policy-making, industry practices, and future research agendas in this field.
Open Access: Yes
Understanding patient perception of digital value co-creation in electronic health record through clustering approach
Publication Name: Scientific Reports
Publication Date: 2025-12-01
Volume: 15
Issue: 1
Page Range: Unknown
Description:
Patients are central to healthcare services, and comprehending their perceptions is crucial for fostering effective value co-creation. This study aimed to investigate the user characteristics and perceptions of value co-creation within the context of Mobile Electronic Health Records (EHR). Using a questionnaire collected from 422 patients, the study employed the K-modes clustering algorithm in R-Studio to group users based on shared characteristics and perceptions of value co-creation. The analysis revealed three distinct user clusters, which are high familiarity-positive perception, low familiarity-positive perception and high familiarity-neutral to negative perception. These clusters characterized by unique attributes such as socio-economic, history of medical visit, intention to use, technological familiarity, and different perception of value co-creation in Mobile EHR systems. Descriptive statistics were used to further interpret the clusters, revealing differences in user characteristics and perception across cluster. The findings emphasize the importance of alignment between user expectations and system interactions. Effective alignment fosters value co-creation through resource access, sharing, integration, and recombination, while misalignment may result in value destruction. This study highlights the need to design and implement Mobile EHR systems that align with the diverse characteristics and of their users to enhance engagement and promote value co-creation.
Open Access: Yes
Analysis of Wireless Communications for Smart Grid: MABAC Model Based on Complex Propositional Picture Fuzzy Sugeno Weber Power Aggregation Information
Publication Name: Systems and Soft Computing
Publication Date: 2025-12-01
Volume: 7
Issue: Unknown
Page Range: Unknown
Description:
In this study, the shortcoming of the conventional procedure is demonstrated by proposing the novel technique of complex propositional picture fuzzy sets with some fundamental concepts based on algebraic and Sugeno Weber norms. In addition, the authors classified the different types of power operators based on Sugeno Weber norms for complex propositional picture fuzzy values, called the complex propositional picture fuzzy Sugeno Weber power averaging, complex propositional picture fuzzy Sugeno Weber weighted power averaging, complex propositional picture fuzzy Sugeno Weber power geometric, complex propositional picture fuzzy Sugeno Weber weighted power geometric operators and also designed their three different properties for each operator. As well, the authors designed the multi-attributive border approximation area comparison for the proposed operator. Further, wireless communication networks are playing a critical and vital role in the circumstance of development and operation of smart grids, which incorporate advanced technologies to enhance the capability, efficiency, and sustainability of electricity distribution. Finally, the designed techniques and models are applied to the wireless communications for smart grids in Taiwan. Sensitivity and comparative analysis are derived to obey the strength and competence of the developed model. This study gives an inventive decision analysis structure, which varieties a substantial contribution to wireless communication in smart grid assessment difficulties under the indeterminate situation.
Open Access: Yes
Assessing food insecurity strategies across twelve countries from different income levels: a sustainability and food systems perspective
Publication Name: Discover Sustainability
Publication Date: 2025-12-01
Volume: 6
Issue: 1
Page Range: Unknown
Description:
Achieving Sustainable Development Goal 2 (Zero Hunger) by 2030 remains a persistent global challenge, especially under current overlapping crises such as climate change, economic instability, and geopolitical conflicts. This study critically analyzes the food security strategies of twelve countries across four income groups, as classified by the World Bank: Low-Income (Malawi, Afghanistan, Ethiopia), Lower-Middle-Income (Nigeria, India, Lebanon), Upper-Middle-Income (Maldives, Brazil, China) and High-Income (Canada, Germany, United Arab Emirates). Using a structured narrative review of national policies and programs (2016–2024) sourced from academic databases, government publications, and international reports, we assess the alignment of strategies with the sustainability pillars (economic, social, environmental) and six key agri-food system interventions. Findings show that lower-income countries emphasize social protection and foundational agriculture (e.g., Ethiopia’s safety net improved food security by 30%), while higher-income nations focus on technological and environmental innovations (e.g., Germany aims to reduce nutrient losses by 50% by 2030). However, 10 of the 12 countries are off track, progressing at less than 50% of the rate needed. China (80% SDG2 score), Canada (70%), and Afghanistan (35%) demonstrate the widespread nature of this trend across varying income groups. The study underscores the urgency for integrated, context-specific strategies, enhanced international cooperation, and financing to accelerate progress toward Zero Hunger.
Open Access: Yes
Social media applications through the lens of DeLone and McLean’s information system success model: does perceived privacy matter?
Publication Name: Humanities and Social Sciences Communications
Publication Date: 2025-12-01
Volume: 12
Issue: 1
Page Range: Unknown
Description:
Social media applications (SMAs) significantly impact higher education by affecting students, professors, and institutions through various features that may improve learning, communication, and collaboration. However, many studies have focused on the initial use of SMAs, rarely considering their post-adoption and continued usage. Additionally, there are growing concerns about the privacy behaviour of SMA users, which remains inadequately examined. Therefore, this study explores the impact of perceived privacy on the relationship between tripartite quality constructs, user satisfaction, and continual usage using DeLone and McLean’s information system success (ISS) model. This study surveyed 384 SMA users among university lecturers through a convenience sampling approach, and SmartPLS 4, nonparametric software, was used to analyse the data. These findings elucidate the elements affecting SMA usage, suggesting that service and information quality influence continual usage. The tripartite quality constructs correlate with users’ satisfaction, which robustly correlates with continual usage. In addition, perceived privacy influences the links between service quality, system quality, and continual usage. This study finds that perceived privacy is crucial to DeLone and McLean’s ISS model. Hence, information privacy must be ensured to create more secure, functional, and engaging applications. Suppliers and developers should focus on improving app quality, security, and protection, which are precursors to user satisfaction and continual usage. This study examines the moderating role of perceived privacy in DeLone and McLean’s model. Its strong predictive model demonstrates the theoretical robustness of the ISS model for studying the continual usage of SMAs.
Open Access: Yes
Assessing the texture profile and optimizing the temperature and soaking time for the rehydration of hot air-dried Auricularia auricula-judae mushrooms
Publication Name: Discover Food
Publication Date: 2025-12-01
Volume: 5
Issue: 1
Page Range: Unknown
Description:
Rehydrating dried jelly ear mushrooms allows them to take on the original shape, and texture, but no thorough study has been done to date to determine the ideal rehydration parameters. The study aimed to optimize the rehydration conditions of the hot-air-dried jelly ear mushroom, to achieve the most similar stock to the fresh mushroom. To achieve this, the mushrooms dried to a constant weight at 40 °C were soaked in water that had been heated to 20–100 °C for 10–70 min. The mushrooms were weighed and examined the texture profile to determine the rehydration %, hardness, gumminess, chewiness, springiness, and cohesiveness at each tested temperature and soaking time. The fresh mushroom used as a control had a moisture content of 95.39 m/m%, hardness of 847.40, springiness of 0.70, gumminess of 562.04, chewiness of 423.98 N/m2, and cohesiveness of 0.66 J/m3. These results were compared to the rehydrated mushroom samples texture profile test results, and it was found that the dried mushrooms recovered nearly the same texture as the fresh mushrooms with a 20-minute soak at 40 °C. As consumers prefer rehydrated products to be similar to fresh products in terms of texture and enjoyment value, it is crucial to determine the ideal rehydration parameters. However, each drying method and temperature has a different effect on the texture and water absorption capacity of the mushrooms, so the mentioned results are only achieved with the described parameters.
Open Access: Yes
