The challenge of executing iterative big data analysis algorithms within the Google Cloud MapReduce environment has been addressed by developing a parallel K-means algorithm capable of leveraging the distributed computing power of the platform. Traditional K-means, which requires iterative steps, is adapted into a parallel version using MapReduce to enhance computational efficiency. This parallel algorithm is structured into multiple super-steps, each of which executes in parallel but is processed sequentially across super-steps. Each super-step corresponds to one iteration of the serial K-means algorithm, with parallel computation carried out at each node to determine the mean of each cluster center. Experimental evaluations have demonstrated that the parallel K-means algorithm performs effectively and accurately. Notably, for a dataset of 450 water samples, a parallel speedup factor of 20.8 was achieved, significantly reducing the time required for data analysis. This substantial reduction in processing time is critical in time-sensitive applications, such as coal mine rescue operations, where quick decision-making is essential. The results indicate that the proposed parallel K-means algorithm is both a feasible and efficient solution for handling large-scale datasets within cloud environments, providing substantial benefits in both computational speed and practical application.
Digital ink Chinese character recognition (DICCR) systems have predominantly been developed using datasets composed of native language writers. However, the handwriting of foreign students, who possess distinct writing habits and often make errors or deviations from standard forms, poses a unique challenge to recognition systems. To address this issue, a robust and adaptable approach is proposed, utilizing a residual network augmented with multi-scale dilated convolutions. The proposed architecture incorporates convolutional kernels of varying scales, which facilitate the extraction of contextual information from different receptive fields. Additionally, the use of dilated convolutions with varying dilation rates allows the model to capture long-range dependencies and short-range features concurrently. This strategy mitigates the gridding effect commonly associated with dilated convolutions, thereby enhancing feature extraction. Experiments conducted on a dataset of digital ink Chinese characters (DICCs) written by foreign students demonstrate the efficacy of the proposed method in improving recognition accuracy. The results indicate that the network is capable of more effectively handling the non-standard writing styles often encountered in such datasets. This approach offers significant potential for the error extraction and automatic evaluation of Chinese character writing, especially in the context of non-native learners.
The accurate estimation of the age of orange trees is a critical task in orchard management, providing valuable insights into tree growth, yield prediction, and the implementation of optimal agricultural practices. Traditional methods, such as counting growth rings, while precise, are often labor-intensive and invasive, requiring tree cutting or core sampling. These techniques are impractical for large-scale application, as they are time-consuming and may cause damage to the trees. A novel non-invasive system based on fuzzy logic, combined with linear regression analysis, has been developed to estimate the age of orange trees using easily measurable parameters, including trunk diameter and height. The fuzzy inference system (FIS) offers an adaptive, intuitive, and accurate model for age estimation by incorporating these key variables. Furthermore, a multiple linear regression analysis was performed, revealing a statistically significant correlation between the predictor variables (trunk diameter and height) and tree age. The regression coefficients for diameter (p = 0.0134) and height (p = 0.0444) demonstrated strong relationships with tree age, and an R-squared value of 0.9800 indicated a high degree of model fit. These results validate the effectiveness of the proposed system, highlighting the potential of combining fuzzy logic and regression techniques to achieve precise and scalable age estimation. The model provides a valuable tool for orchard managers, agronomists, and environmental scientists, offering an efficient method for monitoring tree health, optimizing fruit production, and promoting sustainable agricultural practices.
This study introduces novel algebraic techniques within the framework of complex Fermatean fuzzy sets (CFFSs) by incorporating confidence levels, presenting a suite of operators tailored for advanced decision-making. Specifically, the confidence complex Fermatean fuzzy weighted geometric (CCFFWG) operator, the confidence complex Fermatean fuzzy ordered weighted geometric (CCFFOWG) operator, and the confidence complex Fermatean fuzzy hybrid geometric (CCFFHG) operator are developed to address multi-attribute group decision-making (MCGDM) challenges. These methodologies are designed to enhance decision-making in scenarios where decision-makers provide asymmetric or imprecise information, often encountered in environmental and industrial contexts. To validate the applicability of the proposed approach, a practical case study involving the selection of an optimal fire extinguisher from several alternatives is conducted. The performance of the newly developed operators is benchmarked against established methods from prior studies, with results demonstrating superior decision outcomes in terms of precision and reliability. By embedding confidence levels into complex Fermatean fuzzy operations, the proposed techniques offer greater robustness in managing uncertainty and variability across multiple attributes. These findings suggest that the advanced algebraic framework contributes significantly to improving decision quality in complex group decision-making environments.
Self-regulated learning (SRL) is conceptualized as a series of interrelated cognitive and affective processes rather than as isolated events. To elucidate the relationship between students' cognitive engagement and their comprehension of self-regulation strategies, a conceptual model was developed to examine learner engagement during a hypothetical learning scenario. The model posits that the learning environment can be represented as a social network in which the mechanisms of knowledge diffusion significantly influence a learner's adoption of self-regulatory processes. The results obtained from this model corroborate the modes of cognitive engagement as predicted by the Interactive, Constructive, Active, and Passive (ICAP) framework, manifesting as absorbing-state phase transitions. These transitions are interpreted as self-tuned phase changes associated with self-schema and personal adaptive and reflexive learning thresholds. This framework suggests that learners engage in retrospective monitoring processes that activate SRL mechanisms. It is inferred that learning occurs through continuous change; wherein self-regulated practices can be viewed as processes leading to specific events that subsequently trigger further learning. This conceptualization underscores the dynamic nature of SRL and highlights the potential for computer simulations to model and understand these processes.
Multi-Criteria Decision-Making (MCDM) represents a critical area of research, particularly in artificial intelligence, through the modeling of real-world decision-making scenarios. Numerous methods have been developed to address the challenges of integrating non-quantitative, incomplete, and imprecise information under conditions of uncertainty. This paper presents the enhancement of the Defining Interrelationships Between Ranked Criteria II (DIBR II) method by incorporating interval grey numbers, in accordance with the principles of Grey theory, its arithmetic operations, and the DIBR II methodology. The enhancement includes the introduction of a conviction degree to reflect decision-makers' or experts' confidence in their assertions. The application of this enhanced method is demonstrated through an illustrative example, following the procedural steps. Additionally, its efficacy is validated in a real-world scenario involving the selection of Lean organization system management techniques, utilizing the Rough Multi-Attributive Border Approximation Area Comparison (Rough MABAC) method. The results indicate that the enhanced DIBR II method is effective in determining criteria weight coefficients, offering a more nuanced distribution compared to traditional crisp methods. Furthermore, when implemented in a multi-criteria model, it yields a more refined ranking of alternatives, contingent on the degree of confidence in the given claims.
Blockchain has attracted widespread attention due to its unique features such as decentralization, traceability, and tamper resistance. With the rapid development of blockchain technology, an increasing number of industries are gradually applying blockchain technology to various fields such as the Internet of Things, healthcare, finance, agriculture, and government affairs. However, there are certain differences in the underlying architecture, data structures, consensus algorithms, and other aspects of blockchain technology across different sectors, which restrict transactions to occur within a single blockchain. Achieving interoperability between different blockchains is challenging, hindering data exchange and collaborative business to some extent, inevitably leading to the problem of “data silo”. Against this backdrop, this study aims to explore a cross-chain solution based on relay technology to address the current challenges of interoperability between blockchain systems. By employing relay-based cross-chain technology, a blockchain cross-chain collaboration platform is established to simulate the construction of a real cross-chain network. By deploying business contracts, data and resources between heterogeneous blockchains can seamlessly communicate, resolving the challenge of cross-chain interoperability. The research findings demonstrate that the blockchain cross-chain solution based on relay technology can effectively enhance interoperability between different blockchain systems, enabling cross-chain asset circulation and information transmission, highlighting the practical applicability and scalability of this study.
This study introduces logarithmic operations tailored to intuitionistic fuzzy sets (IFSs) aimed at mitigating uncertainty in decision-making processes. Through logarithmic transformations, the membership and non-membership degrees are effectively scaled, thereby enhancing interpretability and facilitating the assessment of uncertainty. Advanced logarithmic aggregation operators have been developed, specifically the Induced Confidence Logarithmic Intuitionistic Fuzzy Einstein Ordered Weighted Geometric Aggregation (ICLIFEOWGA) operator and the Induced Confidence Logarithmic Intuitionistic Fuzzy Einstein Hybrid Geometric Aggregation (ICLIFEHGA) operator. These operators serve as versatile tools, providing robust frameworks for integrating diverse information sources in decision-making and assessment processes. The versatility of the operators is demonstrated through their application across various industries and domains, where they support the integration of multiple criteria in complex decision-making scenarios. An algorithm for the decision-making process is presented, and the effectiveness and efficiency of the proposed techniques are illustrated through a case study on laptop selection.
To facilitate early intervention and control efforts, this study proposes a soybean leaf disease detection method based on an improved Yolov5 model. Initially, image preprocessing is applied to two datasets of diseased soybean leaf images. Subsequently, the original Yolov5s network model is modified by replacing the Spatial Pyramid Pooling (SPP) module with a simplified SimSPPF for more efficient and precise feature extraction. The backbone Convolutional Neural Network (CNN) is enhanced with the Bottleneck transformer (BotNet) self-attention mechanism to accelerate detection speed. The Complete Intersection over Union (CIoU) loss function is replaced by EIoU-Loss to increase the model's inference speed, and Enhanced Intersection over Union (EIoU)-Non-Maximum Suppression (NMS) is used instead of traditional NMS to optimize the handling of prediction boxes. Experimental results demonstrate that the modified Yolov5s model increases the mean Average Precision (mAP) value by 4.5% compared to the original Yolov5 network model for the detection and identification of soybean leaf diseases. Therefore, the proposed method effectively detects and identifies soybean leaf diseases and can be validated for practicality in actual production environments.
The T-spherical fuzzy set (T-SFS), an advancement over the spherical fuzzy set (SFS), offers a refined approach for addressing contradictions and ambiguities in data. In this context, similarity measures (SMs) serve as critical tools for quantifying the resemblance between fuzzy values, traditionally relying on the calculation of distances between these values. Nevertheless, existing methodologies often encounter irrational outcomes due to certain characteristics and complex operations involved. To surmount these challenges, a novel parametric similarity measure is proposed, grounded in three adjustable parameters. This enables decision-makers to tailor the SM to suit diverse decision-making styles, thereby circumventing the aforementioned irrationalities. An analytical comparison with existing SM reveals the superiority of the proposed measure through mathematical validation. Furthermore, the utility of this measure is demonstrated in the resolution of multi-attribute decision-making (MADM) problems, highlighting its efficacy over several existing approaches within the domain of T-SFS. The implementation of the proposed SM not only enhances the precision of similarity assessment in fuzzy sets but also significantly contributes to the optimization of decision-making processes.
The regulatory system for hazardous materials is complex, with poor inter-departmental communication and low levels of data sharing, making effective regulation challenging. Blockchain technology, known for its decentralization, traceability, and secure and trustworthy information, is widely applied in data sharing. Concurrently, attribute-based encryption (ABE), a novel encryption technique, offers high security and fine-grained access control, providing technical support for secure data access and privacy protection. However, existing attribute encryption algorithms do not consider the hierarchical relationship of access structures among data files during data sharing. Moreover, the immutable nature of blockchain means that access policies stored on it cannot be altered, leading to a lack of flexibility in data sharing. To address these issues, this paper proposes a blockchain and attribute-based dynamic layered access scheme for hazardous materials circulation data sharing. By constructing a Linear Secret-Sharing Scheme (LSSS) matrix, layered access control is achieved, allowing data decryption related to the matching parts of a user's attributes with the access structure. Additionally, through the design of a policy update algorithm, the blockchain structure is organized into transaction blocks and policy blocks, storing the encrypted symmetric keys separately to enable dynamic updates of access policies. Security analysis and experimental comparisons demonstrate the scheme's effectiveness and security in hazardous materials circulation data sharing.
This study introduces novel aggregation operators aimed at enhancing data analysis and decision-making processes through the induction of confidence levels into complex polytopic fuzzy systems. Specifically, the induced confidence complex polytopic fuzzy ordered weighted averaging aggregation (ICCPoFOWAA) operator and the induced confidence complex polytopic fuzzy hybrid averaging aggregation (ICCPoFHAA) operator are proposed. By integrating confidence levels into the aggregation process, these operators facilitate a more nuanced interpretation of fuzzy data, allowing for the incorporation of expert judgment and uncertainty in decision-making frameworks. A practical demonstration is provided to validate the efficacy and proficiency of these innovative techniques. Through a comprehensive example, the ability of the ICCPoFOWAA and ICCPoFHAA operators to enhance decision-making accuracy and reliability is substantiated, showcasing their potential as powerful tools in the realms of data analysis and complex decision-making scenarios. The incorporation of confidence levels into fuzzy aggregation processes represents a significant advancement in the field, offering a sophisticated approach to handling uncertainty and expert opinions in multi-criteria decision-making problems. This work not only introduces groundbreaking aggregation operators but also sets a new standard for research in fuzzy decision-making, underscoring the importance of confidence levels in the analytical process.
In the era of branding, the design of plush toy brands often faces a contradiction with the needs of target user groups. Addressing the brand transformation challenges faced by small and micro enterprises in the plush toy industry, this paper proposes a method for generating creative design schemes for plush toy brands based on extension theory. This method involves introducing the theory of primitives, utilizing extension primitives to construct problem models, employing extension diamond thinking for ideation and divergence, and using extension analysis for a comprehensive description of brand design elements. Subsequently, the method involves transforming these elements through extension transformation to generate innovative brand design schemes.
In this study, a novel methodology is proposed for ranking the knowledge economies of European Union (EU) countries, leveraging their positioning within the global knowledge index (GKI). The GKI, encompassing seven pivotal indicators, serves as a benchmark for assessing a nation's knowledge economy. The EU, a prominent political and economic conglomerate, forms the focal point of this analysis. A multi-criteria analysis approach is adopted, wherein the Entropy method is utilized to determine the significance of individual GKI indicators. Additionally, the CRADIS (Compromise Ranking of Alternatives from Distance to Ideal Solution) method is employed for the ranking of these nations. The Entropy method, renowned for its efficacy in subjective weight determination, and the CRADIS method, a novel multi-criteria analysis tool yielding results based on deviations from the ideal and anti-ideal solutions, are integrated. This integration is pivotal, as it offers results comparable with other multi-criteria methodologies. The analysis reveals that Research Development and Innovation emerges as the most critical indicator. According to the CRADIS method, Sweden is identified as the leading country in terms of GKI indicators, followed by Finland and Denmark. This trend underscores a superior performance of the northern EU countries. Conversely, Eastern EU countries are observed to lag in their GKI standings. These findings are corroborated through comparative and sensitivity analyses, highlighting the influence of normalization on country rankings and pinpointing specific indicators necessitating enhancement for bolstering the knowledge economy. This research not only aids EU countries in identifying their strengths and weaknesses in the realm of knowledge economy but also serves as a strategic guide for policymakers. It provides actionable insights for fostering knowledge economy development, emphasizing the need for strengthening existing advantages and addressing shortcomings. Such strategic initiatives are crucial for enhancing global market competitiveness. The study's outcomes, therefore, offer valuable resources for decision-making in policy and economic development contexts.
Submit to IJKIS
Review for IJKIS
Propose a Special Issue 
Open Access
Journal Metrics
Journal Overview
Associated Journals