Figure - available from: Peer-to-Peer Networking and Applications
This content is subject to copyright. Terms and conditions apply.
Source publication
The Wireless Sensor Network (WSN) facilities were advanced in several digital wireless applications. However, managing the energy feature constraints is the main concern for maintaining optimal WSN performance. The clustering methods with other energy optimal protocols were implemented in the past, but the problems still do not end because of the m...
Citations
... Iris recognition has emerged as a robust biometric modality due to its uniqueness and stability [27]. Daugman's work (2004) [29]. The advent of deep learning has further revolutionized the field, as highlighted in works such as Jain and Li's "Handbook of Face Recognition" (1999). ...
... The system employs advanced machine learning algorithms, including deep learning models www.JNxtGenTech.com 29 such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs). These algorithms adaptively learn from diverse iris datasets, ensuring robust performance across varying environmental conditions and demographic factors. ...
As the demand for robust and secure biometric authentication systems continues to rise, this research presents "SmartIris ML," a cutting-edge approach that harnesses the power of machine learning to enhance multi-biometric iris recognition. Leveraging the unique and distinct features of the iris, our system integrates multiple modalities through a sophisticated machine learning framework, offering heightened accuracy and reliability. In this study, we delve into the intricacies of machine learning techniques, exploring their potential in handling diverse iris biometric data sources. We propose a comprehensive fusion strategy that optimally combines the strengths of individual iris modalities, resulting in a more robust and secure authentication system. The machine learning algorithms employed in SmartIris ML adaptively learn from the diverse datasets, ensuring adaptability to varying environmental conditions and demographic factors. Furthermore, we conduct a comparative analysis against existing iris recognition systems, demonstrating the superior performance of SmartIris ML in terms of accuracy, efficiency, and resilience against spoofing attacks. The integration of machine learning not only enhances the system's recognition capabilities but also provides insights into feature extraction and representation, contributing to a deeper understanding of multi-biometric iris recognition. The results conducted on large-scale datasets, showcase the effectiveness of SmartIris ML in real-world scenarios, highlighting its potential for applications in secure access control, identity verification, and other domains requiring robust authentication. This research marks a significant stride towards the advancement of biometric security, paving the way for smarter and more reliable multi-biometric iris recognition systems.
... The result shown that the COAER-UAVC system has achieved the lowest possible values of PLR. The COAER-UAVC technique yielded a lower PLR of 2.22% for the sample, which consisted of 10 UAVs; in comparison, the EENFNC-MRP method, the KHOA methodology, the GWO methodology, the ACOA methodology, and the PSOA methodology yielded a superior PLR of 10 A comparative analysis of the COAER-UAVC technique's average delay (AD) is carried out under a variety of UAVs, and the results can be seen in Table 6 and Figure 8. According to the findings, the COAER-UAVC strategy obtained the fewest values of AD during the course of the study. ...
... Joze M. Rozanec et al. [22] proposed an architecture for the XAI using semantic and AI technologies, and it is used to detect demand forecasting and deployed in the real world. The Knowledge graph is used to provide the explanation about the process of demand forecasting at a higher level of explanation than the specific features. ...
In the rapidly evolving landscape of healthcare, telemedicine has emerged as a pivotal tool, offering patients remote access to medical consultations and treatments. However, the trustworthiness of telemedicine platforms remains a concern, especially when artificial intelligence (AI) is employed to provide healthcare recommendations. This research paper delves into the application of Explainable AI (XAI) in telemedicine to enhance its trustworthiness and transparency. We investigate the current challenges faced by telemedicine platforms, particularly in the context of AI-driven recommendations, and explore how XAI can address these issues by offering clear, understandable explanations for AI-generated outputs. Our findings indicate that integrating XAI into telemedicine not only bolsters patient trust but also empowers healthcare professionals to make more informed decisions based on AI recommendations. We conclude by proposing a framework for the seamless integration of XAI in telemedicine platforms and discuss its potential implications for the future of remote healthcare.
... Saša Adamović, Milan Milosavljević, Nemanja Maček, Vladislav Miškovic, Marko Šarac, Muzafer Saračević, Milan Gnjatović et. al., [8] presents a novel and effective method for recognizing the iris that is based on machine learning techniques and stylometric features. In this analysis, an innovative machine learning-based iris identification system is presented. ...
