Search

In the rapidly evolving field of business process management, there is a growing need for analytical tools that can transform complex data into actionable insights. This research introduces a novel approach by integrating Large Language Models (LLMs), such as ChatGPT, into process mining tools, making process analytics more accessible to a wider audience. The study aims to investigate how ChatGPT enhances analytical capabilities, improves user experience, increases accessibility, and optimizes the architectural frameworks of process mining tools. The key innovation of this research lies in developing a tailored prompt engineering strategy for each process mining submodule, ensuring that the AI-generated outputs are accurate and relevant to the context. The integration architecture follows an Extract, Transform, Load (ETL) process, which includes various process mining engine modules and utilizes zero-shot and optimized prompt engineering techniques. ChatGPT is connected via APIs and receives structured outputs from the process mining modules, enabling conversational interactions. To validate the effectiveness of this approach, the researchers used data from 17 companies that employ BehfaLab's Process Mining Tool. The results showed significant improvements in user experience, with an expert panel rating 72% of the results as "Good". This research contributes to the advancement of business process analysis methodologies by combining process mining with artificial intelligence. Future research directions include further optimization of prompt engineering, exploration of integration with other AI technologies, and assessment of scalability across various business environments. This study paves the way for continuous innovation at the intersection of process mining and artificial intelligence, promising to revolutionize the way businesses analyze and optimize their processes.

In this paper, we explore the concept of the ``matrix product of graphs," initially introduced by Prasad, Sudhakara, Sujatha, and M. Vinay. This operation involves the multiplication of adjacency matrices of two graphs with assigned labels, resulting in a weighted digraph. Our primary focus is on identifying graphs that can be expressed as the graphical matrix product of two other graphs. Notably, we establish that the only complete graph fitting this framework is $K_{4n+1}$, and moreover the factorization is not unique. In addition, the only complete bipartite graph that can be expressed as the graphical matrix product of two other graphs is $K_{2n,2m}$ Furthermore, we introduce several families of graphs that exhibit such factorization and, conversely, some families that do not admit any factorization such as wheel graphs, friendship graphs, hypercubes and paths.

We show that the transition function of the cascaded connection of two FSRs can be viewed as a wreath product element. This allows us to study periods of cascaded connections with algebraic methods, obtaining both a general, nontrivial upper bound on the maximum period of a cascaded connection and a complete, explicit understanding of the periods in the important case of the cascaded connection of an $n$-dimensional De Bruijn sequence into an $m$-dimensional linear FSR., Comment: 28 pages, 2 figures

Technology has become an indispensable competitive tool as science and technology have progressed throughout history. Organizations can compete on an equal footing by implementing technology appropriately. Technology trends or technology lifecycles begin during the initiation phase. Finally, it reaches saturation after entering the maturity phase. As technology reaches saturation, it will be removed or replaced by another. This makes investing in technologies during this phase unjustifiable. Technology forecasting is a critical tool for research and development to determine the future direction of technology. Based on registered patents, this study examined the trends of IOT technologies. A total of 3697 patents related to the Internet of Things from the last six years of patenting have been gathered using lens.org for this purpose. The main people and companies were identified through the creation of the IOT patent registration cooperation network, and the main groups active in patent registration were identified by the community detection technique. The patents were then divided into six technology categories: Safety and Security, Information Services, Public Safety and Environment Monitoring, Collaborative Aware Systems, Smart Homes/Buildings, and Smart Grid. And their technical maturity was identified and examined using the Sigma Plot program. Based on the findings, information services technologies are in the saturation stage, while both smart homes/buildings, and smart grid technologies are in the saturation stage. Three technologies, Safety and Security, Public Safety and Environment Monitoring, and Collaborative Aware Systems are in the maturity stage.

This study proposes a novel video recommendation approach that leverages implicit user feedback in the form of viewing percentages and social network analysis techniques. By constructing a video similarity network based on user viewing patterns and computing centrality measures, the methodology identifies important and well-connected videos. Modularity analysis is then used to cluster closely related videos, forming the basis for personalized recommendations. For each user, candidate videos are selected from the cluster containing their preferred items and ranked using an ego-centric index that measures proximity to the user's likes and dislikes. The proposed approach was evaluated on real user data from an Asian video-on-demand platform. Offline experiments demonstrated improved accuracy compared to conventional methods such as Naive Bayes, SVM, decision trees, and nearest neighbor algorithms. An online user study further validated the effectiveness of the recommendations, with significant increases observed in click-through rate, view completion rate, and user satisfaction scores relative to the platform's existing system. These results underscore the value of incorporating implicit feedback and social network analysis for video recommendations. The key contributions of this research include a novel video recommendation framework that integrates implicit user data and social network analysis, the use of centrality measures and modularity-based clustering, an ego-centric ranking approach, and rigorous offline and online evaluation demonstrating superior performance compared to existing techniques. This study opens new avenues for enhancing video recommendations and user engagement in VOD platforms., Comment: Adding the results of operational implementation of the algorithm in the studied VoD platform + structural changes of the article

The rise of information technology has transformed the business landscape, with organizations increasingly relying on information systems to collect and store vast amounts of data. To stay competitive, businesses must harness this data to make informed decisions that optimize their actions in response to the market. Business intelligence (BI) is an approach that enables organizations to leverage data-driven insights for better decision-making, but implementing BI comes with its own set of challenges. Accordingly, understanding the key factors that contribute to successful implementation is crucial. This study examines the factors affecting the implementation of BI projects by analyzing the interactions between these factors using system dynamics modeling. The research draws on interviews with five BI experts and a review of the background literature to identify effective implementation strategies. Specifically, the study compares traditional and self-service implementation approaches and simulates their respective impacts on organizational acceptance of BI. The results show that the two approaches were equally effective in generating organizational acceptance until the twenty-fifth month of implementation, after which the self-service strategy generated significantly higher levels of acceptance than the traditional strategy. In fact, after 60 months, the self-service approach was associated with a 30% increase in organizational acceptance over the traditional approach. The paper also provides recommendations for increasing the acceptance of BI in both implementation strategies. Overall, this study underscores the importance of identifying and addressing key factors that impact BI implementation success, offering practical guidance to organizations seeking to leverage the power of BI in today's competitive business environment.

Global film production is witnessing a surge in international cooperation and cross-border investment. However, the dynamics and structure underlying these collaborative ventures remain underexplored. This study employs social network analysis (SNA) to investigate joint investments within the cinema industry. A network of 150 countries is constructed based on 7800 links representing shared creative themes in film productions. Centrality measures identify pivotal nodes like the United States, China, and England as influential countries with strong leadership potential to steer industry growth through collaboration. Community detection further uncovers distinct thematic clusters centered around common creative endeavors such as action films or social issues. Each community reveals opportunities for targeted cooperation and investment. For instance, the Global Thrill Seekers community produces mainstream blockbusters, whereas the Cultural-Social Cinema Group tackles worldwide issues. Overall, this SNA enhances understanding of the global film network and highlights pathways to optimize data-driven decision-making regarding collaborative initiatives. The research underscores SNA's value in predicting outcomes and paving the way for strategic unity in the creative industries.

The integration of artificial intelligence (AI) into human resource management (HRM) strategies has become increasingly common due to technological advancements. This has spurred a new field of research focused on evaluating the impact of AI adoption on business and individual outcomes, as well as how to evaluate AI-enabled HRM practices. However, there is limited cross-disciplinary research in this area, causing a fragmented body of knowledge. To address this issue, social network analysis has been recognized as a tool for analyzing and researching large-scale social phenomena in HRM. The study of scientific co-authorship networks is one application of social network analysis that can help identify the main components and trends in this field. Using social network analysis indicators, the current study examined the AI&HRM co-authorship network, which consists of 43,789 members and 81,891 scientific collaborations. The study analyzed articles related to AI&HRM published between 2000 and 2023 extracted from the WOS citation database. Through centrality measures, the most important members of the "AI&HRM" co-authorship network were identified using the TOPSIS method, which identified twenty prominent researchers in this field. The study also examined the keywords "AI&HRM" and the scientific cooperation network of nations, universities, and communities. Overall, this study highlights the importance of cross-disciplinary research and social network analysis in understanding the implications of AI adoption in HRM.

The rapid growth of technology and computer science, which has led to a surge in demand for skilled professionals in this field. The skill set required for computer science jobs has evolved rapidly, creating challenges for those already in the workforce who need to adapt their skills quickly to meet industry demands. To stay ahead of the curve, it is essential to understand the hottest skills needed in the field. The article introduces a new method for analyzing job advertisements using social network analysis to identify the most critical skills required by employers in the market. In this research, to form the communication network of skills, first 5763 skills were collected from the LinkedIn social network, then the relationship between skills was collected and searched in 7777 computer science job advertisements, and finally, the balanced communication network of skills was formed. The study analyzes the formed communication network of skills in the computer science job market and identifies four distinct communities of skills: Generalists, Infrastructure and Security, Software Development, and Embedded Systems. The findings reveal that employers value both hard and soft skills, such as programming languages and teamwork. Communication skills were found to be the most important skill in the labor market. Additionally, certain skills were highlighted based on their centrality indices, including communication, English, SQL, Git, and business skills, among others. The study provides valuable insights into the current state of the computer science job market and can help guide individuals and organizations in making informed decisions about skills acquisition and hiring practices.

The contemporary tourism landscape is undergoing rapid digitization, necessitating a nuanced comprehension of online user behavior to guide data-driven decision-making. This research bridges an existing gap by investigating the tourism website ecosystem through social network analysis. It focuses specifically on inter-website communication patterns based on user navigation. Data mining facilitates the identification of 162 core Iranian tourism websites, which are visualized as an interconnected network with websites as nodes and user transitions as weighted directed edges. By implementing community detection, eight key clusters are discerned, encompassing domains like ticket/tour bookings, accommodations, location services, and cuisine. Further analysis of inter-community relationships reveals website groupings frequently accessed together by users, highlighting complementary services sought during travel planning. The research derives invaluable insights into user preferences and information propagation within the tourism ecosystem. The methodology and findings contribute original perspectives to academia while offering pragmatic strategic recommendations to industry stakeholders like service providers, investors, and policymakers. This pioneering exploration of latent user behavior patterns advances comprehension of the evolving digital tourism landscape in Iran. It contributes pathways toward a sustainable future vision of the ecosystem, guiding stakeholders in targeted decision-making based on empirical evidence derived from social network analysis of websites and consumption patterns. The innovative methodology expands the toolkit for data-driven tourism research within academia.

The Early diagnosis and treatment of depression is essential for effective treatment. Depression, while being one of the most common mental illnesses, is still poorly understood in both research and clinical practice. Among different treatments, drug prescription is widely used, however the drug treatment is not effective for many patients. In this work, we propose a method for major depressive disorder (MDD) diagnosis as well as a method for predicting the drug response in patient with MDD using EEG signals. Method: We employ transformers, which are modified recursive neural networks with novel architecture to evaluate the time dependency of time series effectively. We also compare the model to the well-known deep learning schemes such as CNN, LSTM and CNN-LSTM. Results: The transformer achieves an average recall of 99.41% and accuracy of 97.14% for classifying normal and MDD subjects. Furthermore, the transformer also performed well in classifying responders and non-responders to the drug, resulting in 97.01% accuracy and 97.76% Recall. Conclusion: Outperforming other methods on a similar number of parameters, the suggested technique, as a screening tool, seems to have the potential to assist health care professionals in assessing MDD patients for early diagnosis and treatment. Significance: Analyzing EEG signal analysis using transformers, which have replaced the recursive models as a new structure to examine the time dependence of time series, is the main novelty of this research.