Cardiovascular diseases (CVDs) stand as a significant global health concern, characterized by a rising number of cases and fatalities. Within this context, arrhythmias emerge as critical manifestations that require ad...
详细信息
ISBN:
(纸本)9783031718472;9783031718489
Cardiovascular diseases (CVDs) stand as a significant global health concern, characterized by a rising number of cases and fatalities. Within this context, arrhythmias emerge as critical manifestations that require advanced diagnostic tools. In this study, we focus on ECG signals analysis plotted and saved as images employing deep learning methods to address the challenges associated with limited data in medical datasets. Through transfer learning with a relatively small ECG dataset, our research explores the effectiveness of three pre-trained models, inception-V3, DenseNet121, and Xception, in developing robust ECG image classification models. Furthermore, we utilize ensemble learning techniques, specifically averaging, to enhance classification accuracy. Our evaluation results present individual model accuracies and an enhanced weighted average ensemble accuracy of 97.82%, providing a comprehensive and effective approach for arrhythmia detection.
One of the main objectives of the pharmaceutical industry is to provide products that are safe, of high quality and effective. Additionally to that, most often companies would like to reduce costs. To achieve this, th...
详细信息
ISBN:
(纸本)9783031764585;9783031764592
One of the main objectives of the pharmaceutical industry is to provide products that are safe, of high quality and effective. Additionally to that, most often companies would like to reduce costs. To achieve this, they must implement Good Manufacturing Practices (GMP). Pharmaceutical production planning and scheduling is a very complex task, as not only resources, materials and equipment have to be taken into account, but also regulatory deadlines and legal requirements. In addition, there are many constraints such as limited availability of sub-products, skilled personnel or equipment. This paper presents a review of production planning and scheduling methods in the pharmaceutical industry with its preliminary analysis, which will form the basis for future work in this area.
Diabetic retinopathy, an insidious complication arising from diabetes, emerges as a predominant catalyst for vision impairment. Early identification of this condition remains a pressing need to prevent the risk of bli...
详细信息
ISBN:
(纸本)9783031718472;9783031718489
Diabetic retinopathy, an insidious complication arising from diabetes, emerges as a predominant catalyst for vision impairment. Early identification of this condition remains a pressing need to prevent the risk of blindness. Many existing approaches for diabetic retinopathy identification focus on the processing of retinal images via standard preprocessing techniques before feeding them to classification models, without exploring alternative representations. Additionally, recent segmentation techniques, which may particularly contribute to diabetic retinopathy detection or progression, face challenges related to high computational and time consumption. To address diabetic retinopathy diagnosis from performance improvement and computational time reduction perspectives, we have focused on two primary contributions. The first involves diabetic retinopathy identification utilizing a novel fundus retinal image transformation approach. This novel representation aims to extract meaningful retinal information while discarding insignificant borders, effectively reducing image size. The second contribution entails retinal part segmentation using a hybrid approach that leverages the strengths of both convolutional neural networks and Vision Transformers in terms of rapidity and accuracy, respectively. The results obtained by the diabetic retinopathy identification using the novel representation approach on both datasets, namely EyePACS [5] and APTOS [6], as well as those obtained through the proposed segmentation approach on the IDRiD Dataset [9], are promising.
The integration of Artificial Intelligence (AI) tools into the User Experience/User Interface (UX/UI) design process poses challenges and opportunities. While AI can enhance efficiency and innovation, it raises questi...
详细信息
ISBN:
(纸本)9789819750344;9789819750351
The integration of Artificial Intelligence (AI) tools into the User Experience/User Interface (UX/UI) design process poses challenges and opportunities. While AI can enhance efficiency and innovation, it raises questions about the changing role of designers and the potential risks associated with reduced human control. The rapid growth of AI technology in UX/UI design requires a comprehensive understanding of how AI can effectively complement human creativity and intuition, ensuring high-quality design outcomes while addressing concerns about job displacement and autonomy. This study develops a research framework that explores the interplay between AI applications and human skills in the context of modern UX/UI design. The framework aims to examine the impact of AI on design quality and how various factors moderate this influence. The hypotheses suggest that AI applications and user skills have a positive effect on design quality, but their impact is moderated by factors such as design complexity, user expectations, and collaboration. The research methodology combines literature review, data collection through surveys, data analysis, and expert evaluation to test these hypotheses rigorously. This research provides a foundation for further exploration of AI's role in UI/UX design, offering opportunities for examining its impact in diverse organizational contexts, user groups, and long-term UX effects. Ultimately, the study aims to enhance UI/UX design practices through informed AI integration.
Most of the current solar energy systems use fixed solar panels that are oriented toward one direction. In this paper, we present the initial stages of an ongoing project that considers absorbing maximum solar energy ...
详细信息
ISBN:
(纸本)9789819750344;9789819750351
Most of the current solar energy systems use fixed solar panels that are oriented toward one direction. In this paper, we present the initial stages of an ongoing project that considers absorbing maximum solar energy by tracking the sun's direction. This will maximize the produced electricity and enhance system efficiency. The proposed architecture consists of hardware and software aimed at sensing maximum illumination based on a photovoltaic panel controlled by a servomotor. This solar tracking system is remotely managed by a wireless communication system based on Wi-Fi technology. This is accomplished by two user interfaces that offer different parameter readings and various statistical analyses. The obtained results are encouraging and promising and furnish a platform for future applications in the field of solar energy generation.
With the recent surge in the electric vehicle market, there is a pressing demand for solutions and platforms to enhance vehicle lifecycle management. This is particularly pertinent for motorcycles, which are widely us...
详细信息
ISBN:
(纸本)9783031764585;9783031764592
With the recent surge in the electric vehicle market, there is a pressing demand for solutions and platforms to enhance vehicle lifecycle management. This is particularly pertinent for motorcycles, which are widely used in urban environments (e.g., for food delivery services) and require frequent maintenance. The present study proposes the research and development of a platform, along with mobile and web applications, focusing on optimizing the lifecycle of electric motorcycles. Central to this project is the implementation of Product Lifecycle Management (PLM) to simplify the planning of technical maintenance and the recording and access to technical events and information in the most transparent and non-intrusive way for all involved parties. This project aims to establish innovative and effective communication between owners, manufacturers, and service partners, ensuring the longevity and reliability of motorcycles.
The DE-MCZ algorithm is an improvement of the DE-MC method, which joins the differential evolution with the theory of the Markov chains. It aims to ensure the numerical effectiveness and the convergence speed of the s...
详细信息
ISBN:
(纸本)9783031739965;9783031739972
The DE-MCZ algorithm is an improvement of the DE-MC method, which joins the differential evolution with the theory of the Markov chains. It aims to ensure the numerical effectiveness and the convergence speed of the special variant of the Metropolis-Hastings algorithm with the help of an additional, self-adapting initial matrix. In this paper, we add the modes detection procedures to the DE-MCZ algorithm to increase its abilities in sampling from multimodal target densities. As our numerical experiments suggest, the obtained DE-MCmodes algorithm provides results that give a better fit to the desired target density than the classical approaches.
Educational establishments have progressively accepted the use of computers in the classroom due to the quick development of technology. To guarantee that computer technology has a good influence on students' lear...
详细信息
ISBN:
(纸本)9789819754403;9789819754410
Educational establishments have progressively accepted the use of computers in the classroom due to the quick development of technology. To guarantee that computer technology has a good influence on students' learning, however, extensive consideration and study are necessary before implementing it in elementary school. This study's main goal is to determine and evaluate the best practices for incorporating computer technology into elementary school environments. To provide a strong theoretical framework for the investigation, a thorough analysis of the body of prior research on the topic will be carried out. The study will further examine the possible advantages and difficulties linked to integrating computer technology into the elementary curriculum. To collect information from a variety of sources, including educators, students, and school officials, a combination of techniques will be used. While information of a qualitative nature will be gathered using interviews and observation to acquire understanding of the method of implementation and its influence on the educational setting, quantitative information will be gathered using surveys and standardized assessments to assess pupil educational results. The research intends to provide light on a number of topics related to computer technology integration in elementary schools, including infrastructures teacher preparation, curriculum design, and accessible. This research aims to provide educators and policymakers with useful advice by identifying effective implementation methods and comprehending their implications on student learning. The discoveries of this study will add to the corpus of information about computer technology convergence.
The fifth generation (5G) mobile network is designed to revolutionize mobile broadband technology by addressing the shortfalls of its predecessor the fourth generation (4G) mobile network, also known as the long-term ...
详细信息
ISBN:
(纸本)9789819754403;9789819754410
The fifth generation (5G) mobile network is designed to revolutionize mobile broadband technology by addressing the shortfalls of its predecessor the fourth generation (4G) mobile network, also known as the long-term evolution (LTE), with key considerations of higher data rate, improved power efficiency, low latency and better quality of service. This work analyzes the impact of small cells on the performance of LTE (4G) and 5G networks. In this paper, 4G LTE and 5G networks were simulated using Excel for simplicity and performance evaluations were carried out. The performance metrics used for the evaluations are basic system throughput and offloading. The results of the evaluations on both networks were analyzed. The results showed that 5G network performs better than 4G LTE network whether the small cell base station (SBS) is closer to the macro base station (MBS) or at the edge of the macro base station.
This study delves into attribute recognition challenges within computer vision and deep learning methodologies, aiming to address real-world complexities encountered in the identification of nuanced traits like gender...
详细信息
ISBN:
(纸本)9783031718472;9783031718489
This study delves into attribute recognition challenges within computer vision and deep learning methodologies, aiming to address real-world complexities encountered in the identification of nuanced traits like gender, age, clothing styles, and accessories. Despite remarkable advancements in this field, obstacles persist due to occlusion, lighting variations, and image noise. Conventional approaches exhibit limitations in handling these disruptions, leading to the introduction of an innovative approach augmenting traditional deep learning techniques. Through experiments utilizing perturbed datasets and a filtering mechanism, this study demonstrates enhanced model resilience against disruptions, surpassing traditional models in accuracy amidst visual noise and reduced resolutions. These findings underscore the practical potential and robustness of the augmented approach in overcoming real-world complexities in attribute recognition, suggesting avenues for broader applicability across diverse domains.
暂无评论