The latest publications from ICI Innolabshttps://innolabs.ro/https://innolabs.ro/paper/stkdmrbxqx6udnm9r553ikq2/https://innolabs.ro/paper/stkdmrbxqx6udnm9r553ikq2/Evaluating alternatives in multi-criteria decision-making (MCDM) is particularly challenging in domains like cybersecurity. This paper proposes a hybrid multi-criteria approach (TWV-ETOP), that combines the new two weight vectors (TWV) weighting method with the extended TOPSIS (ETOPSIS) method that uses the Minkowski metric. The main novelty of TWV lies in its reduced computational complexity: the optimization problem involves only two variables, compared to n + 1 variables in the classical Best-Worst Method (BWM), as well as in the introduction of a transparent and user-adjustable consistency calculation based on explicit vector norms. The TWVETOP approach is applied to calculate a cybersecurity composite index (CSEC) for ten Eastern European countries, based on six cybersecurity indexes and a digital performance index. In the numerical example, the TWV produced criteria weights very close to those obtained with BWM (maximum absolute difference: 0.0131) while being simpler to compute. The composite CSEC index generated by the hybrid approach provided a robust and comprehensive ranking of countries, with four countries consistently identified across all tested metrics. By combining the computational efficiency of TWV with the flexibility of ETOPSIS, the proposed TWV-ETOP approach offers a transparent and powerful tool for multi-criteria decision analysis in cybersecurity and other domains requiring composite index construction.Fri, 26 Sep 2025 09:34:18 GMThttps://innolabs.ro/paper/o3t3cjl4hgqiscskl923r3xn/https://innolabs.ro/paper/o3t3cjl4hgqiscskl923r3xn/On a worldwide scale, neurodegenerative diseases, including multiple sclerosis, Parkinson’s, and Alzheimer’s, face considerable healthcare challenges demanding the development of novel approaches to early detection and efficient treatment. With its ability to provide real-time patient monitoring, customized medical care, and advanced predictive analytics, artificial intelligence (AI) is fundamentally transforming the way healthcare is provided. Through the integration of wearable physiological sensors, motion sensors, and neurological assessment tools, the NeuroPredict platform harnesses AI and smart sensor technologies to enhance the management of specific neurodegenerative diseases. Machine learning algorithms process these data flows to find patterns that point out disease evolution. This paper covers the design and architecture of the NeuroPredict platform, stressing the ethical and regulatory requirements that guide its development. Initial development of AI algorithms for disease monitoring, technical achievements, and constant enhancements driven by early user feedback are addressed in the discussion section. To ascertain the platform’s trustworthiness and data security, it also points towards risk analysis and mitigation approaches. The NeuroPredict platform’s capability for achieving AI-driven smart healthcare solutions is highlighted, even though it is currently in the development stage. Subsequent research is expected to focus on boosting data integration, expanding AI models, and providing regulatory compliance for clinical application. The current results are based on incremental laboratory tests using simulated user roles, with no clinical patient data involved so far. This study reports an experimental technology evaluation of modular components of the NeuroPredict platform, integrating multimodal sensors and machine learning pipelines in a laboratory-based setting, with future co-design and clinical validation foreseen for a later project phase.Fri, 05 Sep 2025 15:38:20 GMThttps://innolabs.ro/paper/p42mshxb0gavgkcg18xw5nd5/https://innolabs.ro/paper/p42mshxb0gavgkcg18xw5nd5/Abstract Introduction/Objective: Post-bariatric surgery patients require long-term, coordinated care to address complex nutritional, physiological, and behavioral challenges. Personalized smart nutrition, combining individualized dietary strategies with targeted monitoring, has emerged as a valuable direction for optimizing recovery and long-term outcomes. This article examines how traditional medical protocols can be enhanced by digital solutions in a multidisciplinary framework. Methods: The study analyzes current clinical practices, including personalized meal planning, physical rehabilitation, biochemical marker monitoring, and psychological counseling, as applied in post-bariatric care. These established approaches are then analyzed in relation to the NutriMonitCare system, a digital health system developed and tested in a laboratory environment. Used here as an illustrative example, the NutriMonitCare system demonstrates the potential of digital tools to support clinicians through real-time monitoring of dietary intake, activity levels, and physiological parameters. Results: Findings emphasize that medical protocols remain the cornerstone of post-surgical management, while digital tools may provide added value by enhancing data availability, supporting individualized decision making, and reinforcing patient adherence. Systems like the NutriMonitCare system could be integrated into interdisciplinary care models to refine nutrition-focused interventions and improve communication across care teams. However, their clinical utility remains theoretical at this stage and requires further validation. Conclusions: In conclusion, the integration of digital health tools with conventional post-operative care has the potential to advance personalized smart nutrition. Future research should focus on clinical evaluation, real-world testing, and ethical implementation of such technologies into established medical workflows to ensure both efficacy and patient safety.Fri, 05 Sep 2025 12:38:58 GMThttps://innolabs.ro/paper/ia583hq35xphdb46hbsl4gao/https://innolabs.ro/paper/ia583hq35xphdb46hbsl4gao/The Monit4Healthy system is an IoT-enabled health monitoring solution designed to address critical challenges in real-time biomedical signal processing, energy efficiency, and data transmission. The system’s modular design merges wireless communication components alongside a number of physiological sensors, including galvanic skin response, electromyography, photoplethysmography, and EKG, to allow for the remote gathering and evaluation of health information. In order to decrease network load and enable the quick identification of abnormalities, edge computing is used for real-time signal filtering and feature extraction. Flexible data transmission based on context and available bandwidth is provided through a hybrid communication approach that includes Bluetooth Low Energy and Wi-Fi. Under typical monitoring scenarios, laboratory testing shows reliable wireless connectivity and ongoing battery-powered operation. The Monit4Healthy system is appropriate for scalable deployment in connected health ecosystems and portable health monitoring due to its responsive power management approaches and structured data transmission, which improve the resiliency of the system. The system ensures the reliability of signals whilst lowering latency and data volume in comparison to conventional cloud-only systems. Limitations include the requirement for energy profiling, distinctive hardware miniaturizing, and sustained real-world validation. By integrating context-aware processing, flexible design, and effective communication, the Monit4Healthy system complements existing IoT health solutions and promotes better integration in clinical and smart city healthcare environments.Fri, 05 Sep 2025 12:22:19 GMThttps://innolabs.ro/paper/pfualef20gad02s2f5yb8nnk/https://innolabs.ro/paper/pfualef20gad02s2f5yb8nnk/The integration of artificial intelligence (AI) in healthcare has revolutionized cancer care, enabling earlier detection, more accurate prognoses, and tailored treatment strategies. This chapter explores the transition from Healthcare 4.0 to Healthcare 5.0, highlighting the shift from a technology-centric approach to one that is deeply personalized and patient-centered. In Healthcare 5.0, we envision the focus will be on leveraging AI to empower patients and create a truly patient-centric experience. This includes using predictive modeling to anticipate treatment outcomes, employing explainable AI (XAI) to ensure transparency and trust, and utilizing cutting-edge technologies such as generative AI and digital twins to simulate patient-specific disease progressions and treatment responses. The chapter delves into the foundational machine-learning techniques used in cancer diagnosis, such as supervised learning, unsupervised learning, deep learning, and reinforcement learning. It then explores more advanced AI technologies, including generative AI, XAI, and digital twins, and discusses their applications in cancer care. Additionally, the chapter emphasizes the importance of data curation and augmentation in ensuring the availability of high-quality, diverse datasets for AI systems. It also examines computational pathology, which combines traditional pathology with AI to analyze pathology data in unprecedented ways. This chapter provides a comprehensive overview of the current and future applications of AI in cancer care, highlighting its potential to transform the way cancer is diagnosed and treated.Mon, 18 Aug 2025 21:02:25 GMThttps://innolabs.ro/paper/hqjgtnwsah0q82y5qvlee57k/https://innolabs.ro/paper/hqjgtnwsah0q82y5qvlee57k/In the digital era, developing and testing emerging and disruptive technologies are an absolute necessity to maintain competitiveness in an interconnected world. This paper presents ICI INNOLABS, a platform implemented with the objective to facilitate the development and testing of emerging and disruptive technologies. Having a software-focused infrastructure that integrates hardware resources, making it useful in hosting the development of IoT management platforms and tools for data analysis.Mon, 18 Aug 2025 20:58:41 GMThttps://innolabs.ro/paper/unkuag49uygzd5oecpyhe17a/https://innolabs.ro/paper/unkuag49uygzd5oecpyhe17a/Blended learning is the combination of online and classroom instruction. It has changed the face of traditional education by allowing a custom-fit lesson plan. By integrating Massive Open Online Courses (MOOCs), students can watch lectures from subject matter experts wherever and whenever. The main focus of every type of education, whether it is online or traditional learning, examines the academic performances of the students. This paper provides an in-depth study on the evaluation of academic performance among undergraduate and postgraduate levels using MOOCs in a blended learning context. The results indicate differential effects on student performance by course type. It also reviews how methods of evaluation like quizzes, assignments, and exams measure the active involvement in student learning. This paper will help educators and institutions regarding the proper implementation of MOOCs in a blended learning context.Wed, 30 Jul 2025 03:52:56 GMThttps://innolabs.ro/paper/pw6f9dm3ocx68ay1nwrjn2ha/https://innolabs.ro/paper/pw6f9dm3ocx68ay1nwrjn2ha/Bear encounters have become a problem in many parts of the world. Bear numbers have grown alarmingly, making the work of authorities complicated. Using a design science perspective (Gregor and Hevner (2013)), we develop a system and implement an efficient and reliable bear detection system utilizing global positioning system (GPS) tracking technology. This system aims to accurately monitor the movements of bears in real-time, providing valuable data for understanding their behavior and habitat usage. By leveraging GPS technology, the system can track bears across various terrains, offering precise location updates that help predict potential human-bear interaction zones. The ultimate goal is to make this technology accessible to individuals, communities, and institutions involved in wildlife management and conservation. Whether used by park rangers, researchers, or local authorities, the system will serve as a critical tool for mitigating conflict, enhancing public safety, and supporting informed decision-making in the management of wild animal activity. This work is intended to prevent potential encounters between bears and humans, and enhance travel security in environments where these encounters may occur. Our research has the potential to reshape public perception and inform relevant organizations regarding the necessity for dependable bear detection systems. Heightened consciousness of the challenges confronting both human communities and wildlife can yield favorable consequences for both parties. In the end, we hope this initiative will facilitate the allocation of resources and provide backing for the development and deployment of efficient measures to mitigate human-wildlife conflicts. We extend the existing and growing research in development of digital tools that help human-wildlife coexistence. Development and research in this area can also yield positive economic implications, especially for industries such as tourism. Travelers will be more confident visiting and exploring wilderness areas where wildlife encounters may currently be a deterrent. This can contribute to economic development in these regions and increase income for local communities.Wed, 30 Jul 2025 03:42:42 GMThttps://innolabs.ro/paper/z3rhl488jyhi2107koe13243/https://innolabs.ro/paper/z3rhl488jyhi2107koe13243/Generative Artificial Intelligence (GenAI) tools are transforming academic research by significantly enhancing efficiency, accuracy, and productivity. However, selecting the most appropriate GenAI tool requires careful evaluation of multiple, interdependent criteria. This paper makes two main contributions. First, it introduces IDEMATEL, an improved decision-making method that advances beyond the traditional DEMATEL approach. Unlike DEMATEL, which can encounter technical limitations when analyzing complex relationships, IDEMATEL ensures robust and reliable results by guaranteeing the necessary mathematical conditions for analysis in all cases. This enhancement makes IDEMATEL more broadly applicable and dependable for evaluating interrelated criteria. Second, the paper demonstrates the practical value of IDEMATEL by applying it to the selection of GenAI tools for academic research. Using this method, a comprehensive set of criteria—including functionality, ease of use, cost, data security, and community support—is systematically analyzed. The results provide researchers and decision-makers with clearer insights into how these factors interact and influence the selection process. By leveraging IDEMATEL, stakeholders can make more informed and confident choices, ensuring that the selected GenAI tools best meet the diverse needs of academic research.Wed, 30 Jul 2025 02:53:07 GMThttps://innolabs.ro/paper/iw847d3zswontxwb7lt4gfgy/https://innolabs.ro/paper/iw847d3zswontxwb7lt4gfgy/Multiple Sclerosis (MS), an autoimmune disorder impacting the central nervous system, is increasingly prevalent. In this context, automated tools for MS lesions segmentation could aid healthcare professionals accelerate treatment decisions and monitor disease progression. In particular, detecting small lesions may prove pivotal for early disease detection. However, current evaluation metrics such as the Dice score estimate an algorithm’s overall performance without considering its potential variability in handling lesions of diverse sizes. To address this issue, we propose an original metric, which we call ‘Dice spectrum’ that offers a more accurate estimation of the model’s performance on lesions of varying sizes. This is particularly important for early disease detection, which involves small lesions, for which the model may behave poorly despite high values of the normal Dice score. On the other hand, the Dice spectrum will clearly show the specific model’s performance on such small lesions.Mon, 21 Jul 2025 05:13:54 GMThttps://innolabs.ro/paper/typdulrv6jg88a830c45mjqw/https://innolabs.ro/paper/typdulrv6jg88a830c45mjqw/This paper explores the development and implementation of an Intelligent Virtual Assistant (IVA) leveraging Large Language Models (LLMs) to enhance interactions with Internet of Things (IoT) systems. Our work demonstrates the initial success in enabling the IVA to perform telemetry readings and basic interpretations, showcasing the potential of LLMs in transforming Natural Language Processing (NLP) applications within smart environments. We discuss the future enhancements planned for the IVA, including the ability to sequentially call multiple tools, perform readings from various sources, and execute robust data analysis. Specifically, we aim to fine-tune the LLM to translate human intentions into Prometheus queries and integrate additional analytical tools like MindDB to extend the system’s capabilities. These advancements are expected to improve the IVA’s ability to provide comprehensive responses and deeper insights, ultimately contributing to more intelligent and intuitive virtua l assistants. Our ongoing research highlights the potential of integrating advanced NLP, IoT, and data analytics technologies, paving the way for significant improvements in smart home and vehicle environments.Tue, 06 May 2025 05:53:50 GMThttps://innolabs.ro/paper/bropacze02kug1b2na1tusjb/https://innolabs.ro/paper/bropacze02kug1b2na1tusjb/Sensors for health are a dynamic technology and sensor-based medical devices (SMD) are becoming an important part of health monitoring systems in healthcare centers and ambulatory care. The rapid growth in the number, diversity and costs of medical devices and Internet of Things (IoT) healthcare platforms imposes a challenge for healthcare managers: making a rational choice of SMD vendor from a set of potential SMD vendors. The aim of this paper is to develop a hybrid approach that combines a performance evaluation model and a multi-objective model for the SMD vendor selection problem. For determining the criteria weights in the performance evaluation model, an original version of the best worst method (BWM) is applied, which we call the flexible best worst method (FBWM). The multi-objective model has two objective functions; one is to maximize the SMD performance and the other is to minimize the SMD cost. A case study for the application of the hybrid approach for SMD procurement in a healthcare center is analyzed. The hybrid approach can support healthcare decision makers in their SMD procurement decisions.Fri, 21 Mar 2025 07:06:42 GMThttps://innolabs.ro/paper/wyatso9kku2oxkpyn9z08zbt/https://innolabs.ro/paper/wyatso9kku2oxkpyn9z08zbt/The growth of Internet of Things (IoT) systems is driven by their potential to improve efficiency, enhance decision-making, and create new business opportunities across various domains. In this paper, the main selection problems in IoT-type systems, criteria used in multi-criteria evaluation, and multi-criteria methods used for solving IoT selection problems are identified. Then, a Hybrid Group Multi-Criteria Approach for solving selection problems in IoT-type systems is proposed. The approach contains the Best Worst Method (BWM) weighting method, multi-criteria Simple Additive Weighting (SAW), Technique for Order Preference by Similarity to an Ideal Solution (TOPSIS), VIseKriterijumska Optimizacija I Kompromisno Resenje (VIKOR), and Complex Proportional Assessment Method (COPRAS), and a method that combines the solutions obtained using the four considered multi-criteria methods to obtain a single solution. The SAW, TOPSIS, VIKOR, and COPRAS methods were analyzed in relation to their advantages, disadvantages, inputs, outputs, measurement scale, type of normalization, aggregation method, parameters, complexity of implementation, and interactivity. An application of the Hybrid Group Multi-Criteria Approach for IoT platform selection and a comparison between the SAW, TOPSIS, VIKOR, and COPRAS solutions and the solution of the proposed approach is realized. A Spearman correlation analysis is presented.Fri, 21 Mar 2025 07:05:14 GMThttps://innolabs.ro/paper/dbsbpmekr5ncumqerobfss42/https://innolabs.ro/paper/dbsbpmekr5ncumqerobfss42/In the last decades multi-criteria methods have known an important development and their area of application was significantly enlarged. Multi-criteria methods are used for making decisions that involve multiple and conflicting criteria. These methods consider a set of alternatives and a set of criteria. Each alternative is evaluated according to each criterion. As a result, a best alternative or an alternatives ranking is obtained. The selection of the appropriate multi-criteria method, for a decision, is an important problem. Two classical multi-criteria methods are TOPSIS and VIKOR, which have been proven effective through a large number of applications. Sometimes the two methods give different solutions regarding the alternatives ranking when they are starting from the same input data. In this paper we propose a new method that is a combination of these two methods. The combined VIKOR-TOPSIS method, is applied to evaluate and ranking a set of CSP (Cloud Service Provider) for selecting a best CSP, taking into account the user requirements and Quality of Service (QoS) criteria.Fri, 21 Mar 2025 07:03:45 GMThttps://innolabs.ro/paper/wd8q4geipdyrodo09f6w5zft/https://innolabs.ro/paper/wd8q4geipdyrodo09f6w5zft/The Metaverse is a new concept that aims to revolutionize the way people perceive the time and space in which they live. Thus, through Metaverse, the convergence between the real and the virtual world is achieved on the basis of a combination of augmented reality, virtual reality, and other emerging technologies. The Metaverse has the potential to transform many aspects of society, from entertainment and gaming to education, health, culture, economy business, and social interaction. One of the key benefits of the Metaverse is its ability to connect people from all over the world in a virtual space. This could have a significant impact on the way we work, communicate, and socialize. It could also provide new opportunities for collaboration and innovation, as people from different parts of the world can easily connect and work together. The Metaverse could also have the potential to revolutionize the way we approach education and could open up new opportunities for learners of all ages and backgrounds. It could also provide new opportunities for content creators, such as virtual concerts, performances, and exhibitions. In this paper we intend to present the project “Advanced research in Metaverse and emerging technologies for the digital transformation of society“ and to analyze the most important implications of Metaverse in many aspects of society.Fri, 21 Mar 2025 05:46:10 GMThttps://innolabs.ro/paper/rb81t5v9ub3zbt8xmrrtaoa0/https://innolabs.ro/paper/rb81t5v9ub3zbt8xmrrtaoa0/The current research approaches the implementation of a real-time domains monitoring platform to determine their reputation, which involves data collection, machine learning analysis, and creating a realtime monitoring interface. Collaboration between various parties and continuous platform improvement are essential to meet evolving user needs and cybersecurity demands. This integrated approach strives to ensure a safer online environment by monitoring and enhancing the reputation of internet domains. The purpose of a domain name reputation system is to assess the trustworthiness of internet domain names. It relies on key components like whitelists, blacklists, registry data and domain rating tools for evaluation and security. Requirements for developing a domain name reputation system highlights the essential prerequisites for an effective domain name reputation system. A significant emphasis is placed on the identification and use of blacklists and whitelists to distinguish trusted from untrusted domains. Thu, 20 Mar 2025 11:23:14 GMThttps://innolabs.ro/paper/qfoniqyqfp32903q8644ggkg/https://innolabs.ro/paper/qfoniqyqfp32903q8644ggkg/The number of domain names is continuously increasing and the extent of security incidents is increasing accordingly. Thus, automated solutions are becoming necessary for monitoring the domain names and alerting their stakeholders. Determining the reputation level of a domain name increases domain security for individuals, public institutions and private companies because it enables users to gain a clear understanding of the trustworthiness associated with a certain domain name. This, in turn, creates a safer online environment. This paper aims to present the architecture of an automated monitoring platform, which is meant to dynamically establish the reputation for each .ro domain and other domains as well. The primary objective of this paper is to enhance people`s trust in the use of .ro domains by reducing the exposure to malicious activities on the Internet through automated monitoring and consequence mitigation.Thu, 20 Mar 2025 11:09:01 GMThttps://innolabs.ro/paper/w81esensm3dkd1v4anxja13f/https://innolabs.ro/paper/w81esensm3dkd1v4anxja13f/In just a few decades, the concept of the information society has transitioned from a vaguely established idea attempting to predict the future of humanity to a tangible reality that encompasses the entire globe. This rapid progress in the field of information technology and communication has resulted in the majority of our everyday devices, such as computers, televisions, home appliances, and even vehicles, being imbued with smart technology that is intended to benefit society. While the evolution of the internet is linked to technological advancements, it is also heavily influenced by social factors that give rise to new consequences for our society. Given the fast-paced evolution of the Information Society, it is essential to keep up with the changes. In Romania, the .RO domains play a crucial role in shaping the country's information society. However, these domains are often targeted by attacks, and continuous measures must be implemented to ensure the Internet operates smoothly in the country. The management of .RO domains involves several specialized applications, and their development and security are an ongoing project. Despite the remarkable technological advancements made in recent decades, the physical location of a business or organization remains crucial. In this regard, national domain names are of significant importance. The Romanian Top Level Domain is a vital component of the information society, and its dependability and safety are fundamental for social, economic activities, and the smooth operation of online services. Although the Domain Name System is often viewed as merely a technical task, its administration involves many factors, such as infrastructure stability, system security, and resource allocation. DNS is not solely a function of Internet governance, as it encompasses technologies that contribute to the functioning of the Internet. The DNS embeds content, and conflicts over property rights may arise concerning domain names that contain text (letters and/or numbers). The system must have several checkpoints that sanitize and verify content access. Security plays a key role in Internet governance, and this issue is a significant concern at both the country and ccTLD level, as well as for Internet governing bodies such as ICANN and IANA. Organizations responsible for Internet governance continuously update their security policies and offer training and advisory sessions at various levels to counter security threats. At the ccTLD level, security is a continuous topic as the risks associated with it cannot be tolerated.Thu, 20 Mar 2025 10:28:29 GMThttps://innolabs.ro/paper/mvbp6di5q93f52536leoy66g/https://innolabs.ro/paper/mvbp6di5q93f52536leoy66g/While false information has always represented a challenge to societal trust, democratic engagement, and public discourse, new technological advancements have led to the emergence of deepfakes and created a new challenge related to disinformation. The Metaverse, as a platform for immersive virtual experiences, also raises concerns about misinformation, privacy, and security. In this article, we analyse the possibilities of addressing the risks of deepfakes but still harnessing the technology for positive outcomes within the Metaverse. We systematically reviewed the literature using the PRISMA methodology and discussed several use cases that show the potential ethical use of the technology.Thu, 20 Mar 2025 10:16:45 GMThttps://innolabs.ro/paper/zu0akjazce9ckch88err2jtx/https://innolabs.ro/paper/zu0akjazce9ckch88err2jtx/Digital transformation is a complex process that involves integrating new technologies into existing business practices to optimize operations and enhance performance. Standardization and interoperability are crucial elements of this process, as they facilitate seamless communication and collaboration between different systems, devices, and platforms. This paper examines the importance of standardization and interoperability in the context of digital transformation, highlighting their role in enabling organizations to leverage the full potential of emerging technologies such as the Internet of Things, artificial intelligence, and blockchain. The paper reviews current standards and protocols across various industries and identifies emerging trends that are likely to shape future interoperability requirements. The findings suggest that while standardization and interoperability may present challenges in terms of implementation and maintenance, they are essential for organizations seeking to stay competitive in a rapidly evolving digital landscape. Ultimately, this paper underscores the need for continued investment in standardization and interoperability as critical components of successful digital transformation strategies. Currently, a large part of the problems encountered by institutions in their digitization efforts is the lack of interoperability of existing IT systems and applications, deficiencies in the interconnection of used databases and the lack of common standards. These problems become increasingly difficult to solve as more and more online applications or services are conceived and implemented without a functional interoperability and standardization framework. To address these issues, measures are needed to facilitate the digital transformation of all interested organizations, not just those in the public sector. Under these conditions, the EU's standardization framework must adapt to the constant evolution of technology markets, as standards are vital for interoperability.Thu, 20 Mar 2025 10:09:47 GMT