Accurate and interpretable plant disease classification remains a key challenge in precision agriculture, where subtle visual symptoms and complex backgrounds complicate reliable detection. While deep learning has advanced performance in this domain, most existing models lack adaptability and offer limited transparency in their decision-making processes. This study proposes Dynamic Self-Attention (DSA) mechanism - a lightweight, input-adaptive module that dynamically emphasizes disease-relevant features such as lesions, edge deformations, and discolorations, while suppressing irrelevant background information. Designed for modular integration, DSA plugs seamlessly into standard convolutional backbones without requiring changes to the underlying architecture. Evaluated on a large-scale, multi-class grape leaf disease dataset comprising 9027 images, the DSA model achieved a state-of-the-art test accuracy of 99.34%, outperforming leading architectures including VGG16, DenseNet121, ResNet50, MobileNetV2, ConvNeXt, and Vision Transformers. Beyond quantitative gains, interpretability analysis using Grad-CAM and DSA attention maps revealed sharply localized focus on pathological regions, validating the model's diagnostic reliability. These results position DSA as a robust and explainable plug-and-play attention mechanism, well-suited for deployment in real-world agricultural settings, especially in environments with limited computational resources.

PurposeThe main purpose of this study is to investigate the critical factors influencing Generation Zers ' acceptance of service robots for mental health and well-being application. This leads to the development of a conceptual framework within the theoretical background of the theory of personality traits and health belief model.Design/Methodology/ApproachThis study adopted a qualitative approach via semistructured interviews to address the research question. It was conducted in West Java, Indonesia, involving 25 participants. There were 11 women and 14 men among the participants, and the participants were 21 years old on average. Social media sites like Facebook and LinkedIn were used to recruit these participants.FindingsThe results show that robot design, personality traits, and user perception have some influence on Generation Zers ' use of service robots for mental and health well-being. Generation Zers are willing to use service robots if the service robots are user-friendly and cheap to operate for efficiently providing the necessary information. They highlighted the importance of service robots ' features and capabilities in understanding, interpreting, and responding to their needs. This study also reveals that individuals who have these personality traits such as agreeable and open to new experiences are likely to use service robots for mental and health well-being. In terms of health-related behavior, Generation Zers ' use of service robots is dependent on the severity of their health condition. From the theoretical side, this study provides a validated research model for exploring the Generation Zers ' acceptance of service robots for mental health and well-being. Practically, this study provides useful insights for enhancing user engagement, reducing barriers to care, and fostering trust in automated mental health solutions. Moreover, the findings may contribute to shaping best practices, policy frameworks, and ethical standards for the integration of service robots into mental health delivery systems.

Smart agriculture increasingly requires solutions that deliver real-time analytics alongside verifiable data integrity. Artificial Intelligence (AI) enables rapid insights for tasks such as crop disease detection and yield prediction, while blockchain technology provides transparency, auditability, and decentralized trust. Yet, most existing systems treat these technologies separately, failing to leverage the complementary capabilities of these technologies. This paper introduces MetaCropZ, a microservices-based architecture that systematically integrates AI-driven insights and blockchain-based traceability through layered components: presentation, microservices, intelligence, blockchain, and storage, linked by a unified API gateway. Analytical results such as disease outbreak classifications are processed through secure microservices, allowing authorized users to initiate on-chain transactions; corresponding event metadata is reliably stored off-chain via the InterPlanetary File System (IPFS). A working prototype demonstrates the feasibility of structured AI-blockchain convergence through secure microservices orchestration, role-based smart contract execution, and seamless dual-token lifecycle management. These architectural innovations confirm that modular integration enables scalable, real-time, and trustworthy analytics for nextgeneration agri-food systems.

This paper proposes MetaCropX, a smart agriculture framework that introduces a dual-token design to represent and track field-level events as they occur. Upon detecting a real-time crop event, a fungible AgriTrack Token (ATT) is minted and incrementally updated using stack-based metadata appends, maintaining an immutable record of disease status, treatments, and environmental conditions. Role-Based Access Control (RBAC) enforced via smart contracts ensures that only authorized stakeholders contribute metadata. At the end of the crop cycle, selected ATTs are converted into a single non-fungible AgriProof Asset (APA) token consisting of the verified crop lifecycle. On the other hand, off-chain InterPlanetary File System (IPFS) storage reduces on-chain data load and supports efficient metadata management. Simulated crop scenarios validate transitions, role enforcement, and metadata integrity. The proposed framework enhances transparency and traceability by allowing the stakeholders to verify the crop data in a secure manner.

The COVID-19 pandemic has highlighted the importance of e-learning systems worldwide. While much research has explored how learners' personality traits affect their acceptance of e-learning, there's a gap in understanding their readiness to continue using online platforms post-pandemic. This study aims to address this gap by developing a more comprehensive framework for examining the role of the Big -five personality traits in student engagement, satisfaction, and stickiness with e-learning platforms. Data was collected from 403 students across three Australian higher education providers and analyzed using structural equation modeling. The findings indicate that agreeableness and conscientiousness positively influence student engagement, while extroversion and agreeableness impact satisfaction. Furthermore, students' extrovert and conscientious personality traits influence their stickiness towards e-learning. Additionally, student engagement positively correlates with satisfaction, leading to greater stickiness towards elearning. These insights can inform the development of more user-centric e-learning designs and contribute to future research on educational technologies and sustainable user behavior.

Studies have been conducted on university students' acceptance of e-learning systems during COVID-19. However, less attention has been paid to students' use of e-learning post-pandemic. This research provides a more comprehensive framework to investigate the effects of e-learning students' various quality perceptions on attitude, learning engagement, and stickiness toward e-learning platforms. A survey-based quantitative method is adopted by this study in which sample data are collected from students in Australian universities. A total of 403 valid samples were analysed using covariance-based structural equation modelling. This study found that students' perceived educational quality, service quality, information quality, and technical system quality play different roles in their attitudes and behaviours towards e-learning. It expands the information system success model by comparing the effects of students' various perceived qualities on their ongoing commitment to e-learning. It provides insights to e-learning providers in pursuing better designs and more sustainable development of educational information systems.

The identification and classification of plant diseases is challenging due to the complexity and variability of symptoms across different species, and the need for timely and accurate diagnosis to effective disease management. However, the existing methods of diagnosing plant diseases often require extensive expert knowledge and can be labor-intensive and time-consuming. This paper presents a novel method leveraging a dynamic self-attention mechanism within convolutional neural networks to enhance the classification accuracy of plant diseases. By allowing the mechanism to focus adaptively on the most informative parts of the input images, this method successfully detects the complex patterns and relationships within the disease symptoms. This method is evaluated by incorporating it in a model that specifically leverages the strengths of EfficientNet architecture combined with the Scaled Exponential Linear Unit (SeLU) activation function on grape leaves dataset containing various types of diseases. This model demonstrates superior performance in detecting a variety of plant diseases, surpassing existing baseline convolutional network methods in both speed and accuracy. This research not only advances the field of plant disease management with cutting-edge AI techniques but also offers a scalable and efficient tool for agriculture practitioners to combat plant diseases more effectively.

Smart and sustainable agricultural practices are more complex than other industries as the production depends on many pre- and post-harvesting factors which are difficult to predict and control. Previous studies have shown that technologies such as blockchain along with sustainable practices can achieve smart and sustainable agriculture. These studies state that there is a need for a reliable and trustworthy environment among the intermediaries throughout the agrifood supply chain to achieve sustainability. However, there are limited studies on blockchain technology adoption for smart and sustainable agriculture. Therefore, this systematic review uses the PRISMA technique to explore the barriers and enablers of blockchain adoption for smart and sustainable agriculture. Data was collected using exhaustive selection criteria and filters to evaluate the barriers and enablers of blockchain technology for smart and sustainable agriculture. The results provide on the one hand adoption enablers such as stakeholder collaboration, enhance customer trust, and democratization, and, on the other hand, barriers such as lack of global standards, industry level best practices and policies for blockchain adoption in the agrifood sector. The outcome of this review highlights the adoption barriers over enablers of blockchain technology for smart and sustainable agriculture. Furthermore, several recommendations and implications are presented for addressing knowledge gaps for successful implementation.

Information security management (ISM) ensures the protection of organisations' data assets. Studying actual security events becomes more critical for ISM preparation. The Capital Market constitutes a wealth of data sources which react to various security incidents. ISM is an essential part of this industry due to high technology dependency. The previous literature emphasises the need for a holistic approach for ISM; therefore, there is necessary to investigate the current state of the ISM to develop a cybersecurity and ISM culture. Research should further explore the impact of national and organisational culture and its effects on ISM and explore ISM practices and initiatives that organisations implement to develop a security culture. This paper explores the factors in order to improve how employees' culture and IS awareness affect ISM implementation. A qualitative approach using the case study method was applied to understand the problem. Twenty-two semi-structured interviews were conducted in the Middle Eastern Capital Market. The thematic data analysis revealed that Middle Eastern culture is a dominant factor influencing ISM and the security culture and awareness significantly impact ISM. This suggests that organisations should focus on security culture and, even more, on IS awareness to improve ISM. This research identifies several challenges in current security practices in the Middle Eastern Capital Market industry, including the lack of attention to cultural effects, generic SETA programs that do not consider specific industry needs, and a lack of connection between culture and awareness programs.

The number of malicious bots is increasing rapidly with the growing popularity of social media. We evaluate the importance of 19 commonly used features for Twitter bot detection. Our goal is to propose a set of minimal user-specific features for developing scalable Twitter bot detection systems. To identify the most important features, we apply three model inspection methods - Permutation Importance (PI), SHapely Additive exPlanation (SHAP), and Local Interpretable Model-agnostic Explanations (LIME). We find that the number of followers, friends, and favourites, and the rate of Tweets, making friends and liking Tweets are the most important user-specific features for Twitter bot detection. We apply the Wilcoxon signed rank test to compare the performance of the models trained using all features, using the important features and the features not found as important in our evaluation, respectively. We observe that there are no significant differences between the performance of the models trained using all features and the models trained using the important features. On the other hand, the models using the unimportant features by our evaluation show statistically significant poor performance. We demonstrate that the above six features are sufficient to identify Twitter bots.

Smart waste management systems (SWMS), including various technologies, including routing, scheduling, infrastructure, and the Internet of Things (IoT), are used to enhance the efficiency and automation of waste management processes. The availability of big data generated by IoT sensors has the potential to significantly improve waste management systems by providing valuable insights and enabling automation. This study presents a data analytics framework that supports decision-makers in implementing, monitoring, and optimising SWMS. The framework utilises IoT sensor data and employs data analytic techniques to analyse and predict municipal bins’ waste generation trends and patterns. Finally, the framework demonstrates the capability to forecast waste generation, leading to the development of a sustainable environment and efficient managerial administration in waste management.

The immense growth of the population generates a polluted environment that must be managed to ensure environmental sustainability, versatility and efficiency in our everyday lives. Particularly, the municipality is unable to cope with the increase in garbage, and many urban areas are becoming increasingly difficult to manage. The advancement of technology allows researchers to transmit data from municipal bins using smart IoT (Internet of Things) devices. These bin data can contribute to a compelling analysis of waste management instead of depending on the historical dataset. Thus, this study proposes forecasting models comprising of 1D CNN (Convolutional Neural Networks) long short-term memory (LSTM), gated recurrent units (GRU) and bidirectional long short-term memory (Bi-LSTM) for time series prediction of public bins. The execution of the models is evaluated by Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Coefficient determination (R2) and Root Mean Squared Error (RMSE). For different numbers of epochs, hidden layers, dense layers, and different units in hidden layers, the RSME values measured for 1D CNN, LSTM, GRU and Bi-LSTM models are 1.12, 1.57, 1.69 and 1.54, respectively. The best MAPE value is 1.855, which is found for the LSTM model. Therefore, our findings indicate that LSTM can be used for bin emptiness or fullness prediction for improved planning and management due to its proven resilience and increased forecast accuracy.

Previous studies have been conducted on the importance of students' personality traits in their acceptance of e-learning services. However, there is a lack of research on the effects of students' personality traits on their academic performance and long-term stickiness in e-learning usage, and how these effects are moderated by their students' engagement. This study presents a conceptual framework for investigating how students' personality traits affect their learning engagement, academic performance and stickiness in elearning. From a theoretical perspective, this study will provide a validated research model for exploring the effects of students' personality traits on their academic performance and long-term stickiness in e-learning usage for achieving better student learning outcomes and commitment to life-long learning. From a practical perspective, this study will provide insightful research findings to aid in the creation of tailored strategies for the development of e-learning platforms for promoting the delivery of highquality education.

Student-centred learning is an emerging terminology questioning the relevance of traditional terminologies such as teacher-centred and institution-centred learning. Teacher-centred and institution-centred learning align more towards teachers and institutions making the students passive recipients of knowledge. These traditional paradigms of teaching have been questioned in recent years and they have been replaced by student-centred learning which focuses on placing the students at the forefront and taking responsibility for their learning. Internet technology has offered tremendous support in the process of students playing a key role in student-centred learning. This chapter presents a summary of emerging technologies that have played a key role in enhancing the quality of student-centred learning in higher education. Five key technology trends such as Learning Management Systems, Virtual Reality, Internet of Things, MOOCs and Social Media are critically analysed to explore their role in the development of a student-centric learning and teaching program. The chapter identifies the strengths and weaknesses of these technologies and how they can be successfully applied to enhance the quality of student-centric learning and teaching program.

Information Security Risk Management (ISRM) in Information Technology Outsourcing (ITO) is among the most critical and under-studied areas of ITO research. This study investigates the body of knowledge focusing on ISRM in ITO by conducting a systematic literature review (SLR) and analyzes 63 papers published between 1994 and 2020. The findings suggest that developing conceptual models or providing commentary is the most popular methodology. Most studies collect data from secondary sources instead of industry. A majority of the studies neither investigate any specific industry nor ITO orientation, i.e., client or service providers. Information security risks (ISRs) from the literature are categorized into 27 types. Most ISRs belong to operations practice, while lack of staff loyalty is the least investigated type of ISRs. Theories, frameworks and models discussed in the literature are explored. A critical analysis of the findings is conducted to identify the gaps and future directions. Since most of the literature is based on conceptual work, it is hard for practitioners to apply this knowledge in the industry unless validated by further research. Specialized literature from the perspectives of ITO orientation, industry type and demographics is required to investigate focused issues and develop accurate knowledge of ISRM in ITO.