Procedia Computer Science最新文献

{"title":"Human Resources Sptimization with MultiLayer Perceptron: An Automated Selection Tool","authors":"Reginaldo G. de S. Neto ,&nbsp;Mariana N. Jatobá ,&nbsp;Matheus Santana ,&nbsp;Paula Sdete Fernandes ,&nbsp;João J. Ferreira ,&nbsp;Juliano Henrique Foleis ,&nbsp;João Paulo Teixeira","doi":"10.1016/j.procs.2025.02.117","DOIUrl":"10.1016/j.procs.2025.02.117","url":null,"abstract":"<div><div>This study aims to create an artificial neural network (ANN) model with a multi-layer perceptron (MLP) architecture, designed to analyze the CVs of candidates for the position of sales consultant. To do this, a database of 600 CVs cataloged with scores from 0 to 10 by specialists with experience in recruitment and selection (R&amp;S) is used. Fourteen characteristics are extracted from each CV, including ordinal and nominal attributes. A model with 3 hidden layers is used, which is trained with a split of 80% for training and 20% for testing. The activation function chosen for the hidden layers is the Rectified Linear Unit (ReLU), using the \"adam\" optimizer with a backpropagation algorithm during training using the Mean Squared Error (MSE) performance metric. The results show that the model is effective, giving a Mean Absolute Error (MAE) of 0.33, MSE of 0.37, Root Mean Squared Error (RMSE) of 0.61, and an r² Score of 0.96. These data not only confirm MLP’s ability to replicate human accuracy but also suggest that such technologies can provide a faster and less biased tool for evaluating CVs. This performance of ANN indicates avenues for future research into the integration of other Artificial Intelligence (AI) technologies to refine the interpretation of less quantifiable characteristics, as well as making the process of R&amp;S of new candidates in companies more agile.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"256 ","pages":"Pages 238-245"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143592576","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An Overview Towards the Assessment and Measurement of Enterprise Architecture Dynamics","authors":"Imane Ettahiri ,&nbsp;Latifa Rassam ,&nbsp;Karim Doumi ,&nbsp;Ahmed Zellou","doi":"10.1016/j.procs.2025.02.124","DOIUrl":"10.1016/j.procs.2025.02.124","url":null,"abstract":"<div><div>In a world of constant change and disruption, organizations must rapidly adapt and innovate to succeed. Responding to new opportunities, adopting technological advancements, and meeting evolving customer demands are essential. Enterprise architecture (EA) plays a crucial role by aligning IT infrastructure and business processes with strategic goals. However, a static EA is inadequate in this dynamic environment. Organizations need an agile EA that can seamlessly adapt to changing conditions. Evaluating and measuring EA dynamism is vital for maintaining competitiveness. This involves defining measurement indicators to quantify dynamism, identifying strengths and areas for improvement, tracking EA evolution, and enabling informed decision-making for continuous enhancement. In this paper we conduct a literature review of the measurement of dynamics in enterprise architecture with the goal to come out with a categorization of dynamic enterprise architecture metrics.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"256 ","pages":"Pages 300-307"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143592583","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Digital Tools in Education: The Impact on Entrepreneurial Intention and Attraction of Development Funding","authors":"Inese Mavlutova ,&nbsp;Kristaps Lesinskis ,&nbsp;Janis Hermanis","doi":"10.1016/j.procs.2025.02.147","DOIUrl":"10.1016/j.procs.2025.02.147","url":null,"abstract":"<div><div>The aim of the study is to investigate the structure of digital tools, as well as the impact of their use in entrepreneurship education on entrepreneurial intention and the readiness of entrepreneurs to attract development funding. Within the framework of this study, special attention was paid to gender issues, based on the results of previous studies, which indicate that women have less opportunities and willingness to attract funding for their business ideas. Attention is drawn to Latvia, where women are lagging behind in entrepreneurship.</div><div>Considering the relatively recent emergence of digital tools, there is very little research on the impact of their use in increasing entrepreneurial intention and attracting development funding. As a result of the study, proposals for stakeholders on how to design and use digital tools in entrepreneurship education in training young entrepreneurs are developed. Higher education institutions, development finance institutions, governmental and non-governmental organizations involved in entrepreneurship policy formation, promotion of entrepreneurship and representation of entrepreneurs’ interests, as well as local governments are examples of stakeholders within the framework of this research.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"256 ","pages":"Pages 513-520"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143592845","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"eDiagnosing mental health in neurodevelopmental disorders: Experiences with person centered development of a self-report tool.","authors":"Oddbjørn Hove ,&nbsp;Heidi Breistrand Bringsvor","doi":"10.1016/j.procs.2025.02.178","DOIUrl":"10.1016/j.procs.2025.02.178","url":null,"abstract":"<div><div>The MindMe project, related to the development of a tool system Inventory for Supported Psychological Evaluation (iSpe®), aims to design and develop a digital tool for the assessment of mental illness in people with cognitive challenges. In this paper, we describe and discuss experiences from the project over the last three years, with a primary focus on end-user involvement.</div><div>Results indicated that active user participation provided new insights at all stages of development. User feedback supplemented previous research findings and accessibility guidelines, ensuring that the solutions met the actual needs of the target audience. Usability testing and feasibility studies confirmed the tool’s effectiveness in enhancing comprehension and articulation of mental health symptoms among users. However, challenges such as response difficulties to symptom severity and reluctance to use audio support were also identified.</div><div>The project advances the understanding of user-centered design in psychological test development for individuals with NDD by documenting iterative feedback loops and user-centered approach that offers a practical framework for future projects. The collaborative approach ensured that the developed tool was clinically relevant, user-friendly and accessible, and can serve as a model for future projects.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"256 ","pages":"Pages 772-780"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143592864","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Hand Gesture Recognition using Machine Learning","authors":"Caminate Na Rang ,&nbsp;Paulo Jerónimo ,&nbsp;Carlos Mora ,&nbsp;Sandra Jardim","doi":"10.1016/j.procs.2025.02.112","DOIUrl":"10.1016/j.procs.2025.02.112","url":null,"abstract":"<div><div>Sign language recognition is a growing area of research, with applications ranging from gestural communication to controlling devices using gestures. One of the challenges inherent to sign language recognition is the ability to translate gestures into meaningful information, such as letters, words or even sentences. Machine Learning, which has emerged as a powerful tool for solving a wide variety of complex problems, namely in the field of computer vision, plays a key role, enabling computers to understand and interpret complex gestures. In this paper, we present a Machine Learning model focused on classifying hand gestures that represent the letters of the Latin alphabet. The objective of this work is to create a solution capable of accurately identifying which letter of the Latin alphabet is being represented by a hand gesture in an image. To classify manual gestures was used the Random Forest Machine Learning classification model, which is fed with the vector of features extracted from the region of interest in the image. To implement the proposed approach, a database of RGB images of hand gestures was created. To extract the characteristics of the gestures, was used the MediaPipe open source framework. The solution presents hand gesture classification precisions by class ranging between 98.8% and 74.4%, with an accuracy of 92.3%, that represents an improvement over previous approaches.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"256 ","pages":"Pages 198-205"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143593348","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"NFT-based Data Provenance for AI Transparency in Enterprise Information Systems","authors":"Yiannis Verginadis ,&nbsp;Orestis Almpanoudis ,&nbsp;Dimitris Apostolou ,&nbsp;Marcela T. de Oliveira ,&nbsp;Gregoris Mentzas","doi":"10.1016/j.procs.2025.02.153","DOIUrl":"10.1016/j.procs.2025.02.153","url":null,"abstract":"<div><div>Enterprise Information Systems have a long-established and crucial role for modern organizations, as they enable seamless integration and management of critical business processes, ensuring efficiency in operations, data accuracy, and enhanced decision-making capabilities. One of their most interesting emerging technologies refer to the use of Artificial Intelligence as they may seamlessly automate routine tasks, offer predictive analytics, and provide deep insights, ultimately leading to intelligent data-driven decisions and improved operational efficiency. Of course, this direction of work is accompanied by some important challenges that come from the opacity of certain AI models and their potential biases due to low-quality training data used. In this paper, we argue that such challenges can be mitigated by a novel framework able to integrate, in a transparent manner, quality-related metadata on datasets used for training the AI-enabled emerging technologies in the field of EIS systems. These metadata are minted as Non-Fungible Tokens (NFTs) over the blockchain.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"256 ","pages":"Pages 565-572"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143593382","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"User Satisfaction with Fall Detection Systems in Smart Elderly Care","authors":"Aurora Louise Weng,&nbsp;Mari Nysæther,&nbsp;Moutaz Haddara,&nbsp;Marius Langseth","doi":"10.1016/j.procs.2025.02.155","DOIUrl":"10.1016/j.procs.2025.02.155","url":null,"abstract":"<div><div>Falls among the elderly pose a growing global challenge, leading to costly injuries and diminished quality of life. Quick fall detection significantly reduces injury severity. Thus, timely innovations like fall detection (FD) systems are crucial. However, FD systems face challenges such as coverage, cost, and privacy concerns, with few studies exploring user experiences. Hence, this study investigates user satisfaction with FD systems, highlighting the benefits and challenges of enhancing elderly care. Three stakeholder groups using RoomMate in Ulstein municipality in Norway were interviewed: healthcare personnel, next-of-kin, and project managers. Our main findings suggest that user satisfaction is generally positive towards FD systems but highlight more challenges in home care services, particularly regarding system coverage. The findings also confirm that usability, personalization, and time savings are critical metrics influencing user satisfaction, aligning with the Updated DeLone &amp; McLean Information Systems Success Model, but providing new insights into the importance of service quality in public sector information systems.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"256 ","pages":"Pages 583-593"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143593384","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The Role of AI in Military Cyber Security: Data Insights and Evaluation Methods","authors":"Clara Maathuis ,&nbsp;Kasper Cools","doi":"10.1016/j.procs.2025.02.078","DOIUrl":"10.1016/j.procs.2025.02.078","url":null,"abstract":"<div><div>The integration of Artificial Intelligence (AI) in the cyber security domain is revolutionising capabilities in preventing, detecting, and responding to cyber threats, particularly in the military domain where unique challenges exist. Despite advancements in AI applications across various domains, a significant knowledge gap remains with respect to possibilities related to data availability and ways of evaluating AI-based cyber security solutions in the military domain for supporting digital sovereignty of various actors by safeguarding national assets and responding to adversarial activities that threaten state sovereignty. This research aims to conduct a systematic literature review to synthesise existing knowledge on AI integration when building cyber security solutions in military contexts, addressing two research objectives: (1) to identify and analyse the datasets and data sources used in developing AI-based cyber security applications and (2) to examine the evaluation mechanisms employed to assess the effectiveness of these applications, providing valuable insights into the current landscape of AI in military cyber security, and thereby informing future research, development, and policy initiatives in this domain.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"254 ","pages":"Pages 191-200"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143550982","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Trust Policy Meta-Model for Trustworthy and Interoperability of Digital Identity Systems","authors":"Dara TITH ,&nbsp;Jean-Noël COLIN","doi":"10.1016/j.procs.2025.02.067","DOIUrl":"10.1016/j.procs.2025.02.067","url":null,"abstract":"<div><div>Trust is a fundamental aspect of information security, ensuring the accuracy and legitimacy of the information presented in credentials. An individual may possess multiple credentials issued by different identity providers, which has led researchers to propose numerous frameworks and policy models to enhance trust both within individual organizations and across different organizations. However, it lacks a formal meta-model for trust policy, making policy enforcement for credential ownership verification from different identity providers more challenging. We propose a new trust policy meta-model scheme and architecture to address this gap, which is generic and applicable to different situations. Validating the trust policy requires defining the scope's boundaries by specifying the context in which entities must meet both system and business requirements. Consequently, trust attributes are detailed in our meta-model diagram and policy language, which are essential for establishing trust policies, while the trust policy architecture is used for enforcing these policies. We provide an example of its application in dealing with Self-Sovereign Identity (SSI) applications. This meta-model allows us to describe and enforce a trust policy in formal terms.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"254 ","pages":"Pages 88-97"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143551019","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhancing Digital Autonomy in Peer-to-Peer Energy Trading: A Blockchain and Predictive Analytics Approach","authors":"Rohit Shorya ,&nbsp;Priti Jagwani","doi":"10.1016/j.procs.2025.02.082","DOIUrl":"10.1016/j.procs.2025.02.082","url":null,"abstract":"<div><div>Distributed power generation from renewable energy sources is rapidly expanding and is serving as a clean energy alternative to fossil fuel-based energy sources, which pose significant environmental and health hazards. However, individuals still lack access to electricity and experience unreliable power supplies and services as demand increases. Energy distribution is still centralized, resulting in various challenges for users and contributing to disparities in energy distribution among individuals. To address these challenges, the predictive analytics approach and blockchain are employed together, while maintaining digital control and privacy for all participants in the decentralised energy trading system. The users can utilize their own historical energy consumption data to predict their own future energy requirements for the next period. Also, the prosumers (who both produce and consume energy) can predict their renewable energy generation. After analysing their consumption and generations users can use smart contracts to schedule and transfer energies over the blockchain network. This system guarantees transparency and security in energy trading between utility providers, prosumers, and consumers. The blockchain and smart contracts enables energy to be distributed fairly and automatically. This decentralization ensures digital autonomy within the energy trading system by enabling users to set their trading preferences, control their energy resources and data independently. This system with blockhain in energy trading builds trust among the participants. This proposed energy trading system is evaluated using a real world energy consumption and generation time series dataset of residential households. The proposed models for prediction are developed using Recurrent Neural Networks (RNN), such as Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU). The results of both the models are compared using performance metrics such as mean absolute error (MAE) and root mean square error (RMSE). The results of experimental evaluation show that this approach can ensure reliable and equitable energy distribution, while ensuring digital autonomy and sovereignty in the proposed energy trading system.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"254 ","pages":"Pages 230-239"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143551078","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}