Voltage source converter (VSC), owing to the advantages of their modular multilevel converters (MMC), such as simple structure, low switching losses, and the absence of harmonic filters, have found extensive applicati...
详细信息
A partitioning control strategy tailored specifically for distribution networks is introduced in this paper,which is reliant on precise electrical distance calculations and an in-depth grey relational analysis of powe...
详细信息
the continuous rising trend shown by greenhouse emissions has led to a global situation in which the promotion of clean alternative technologies is crucial. In this context, small green power self-consumption installa...
详细信息
ISBN:
(纸本)9783031741852;9783031741869
the continuous rising trend shown by greenhouse emissions has led to a global situation in which the promotion of clean alternative technologies is crucial. In this context, small green power self-consumption installations represent an effective and clean solution to reduce climate change. However, they must be subjected to exhaustive supervision of the process, from mechanical, electrical, or electronic components, to ensure good performance and economic feasibility. this work proposes different data imputation techniques to deal with missing data derived from sensor missreadings in a minieolic installation. the performance of regression techniques over each reconstructed set is evaluated with successful results.
Machine Learning and data Mining imply notable privacy vulnerabilities since they have the potential to expose confidential details about people or collectives that have contributed to the data. this paper proposes a ...
详细信息
Detecting icons in Graphical User Interfaces (GUIs) is essential for effective application automation. this study examines the impact of different annotation methods on the performance of object detection models for i...
详细信息
ISBN:
(纸本)9783031741821;9783031741838
Detecting icons in Graphical User Interfaces (GUIs) is essential for effective application automation. this study examines the impact of different annotation methods on the performance of object detection models for icon detection in GUIs. We compared manual, automated, and hybrid annotations using three models: Faster R-CNN, YOLOv8, and YOLOv9. the results show that manual annotations achieve the highest accuracy, with YOLOv9 reaching an Average Precision (AP) of 68.23% and Faster R-CNN achieving 61.82%. Hybrid methods that combine automated annotations with manual corrections also show significant improvements, though they do not perform as well as manual annotations alone. these findings underscore the importance of high-quality, consistent annotations for training effective detection models. While we used HTML code for automated annotations to simplify the process, we encountered inconsistencies that affected model performance. this highlights the need to develop better hybrid methods tailored to specific tasks, ensuring efficiency and accuracy in data annotation.
the current growth in population density has increased the demand for potable water and aggravated water scarcity in reservoirs, especially in urban and metropolitan areas. this problem, coupled with other aspects suc...
详细信息
ISBN:
(纸本)9783031741852;9783031741869
the current growth in population density has increased the demand for potable water and aggravated water scarcity in reservoirs, especially in urban and metropolitan areas. this problem, coupled with other aspects such as climate change and rain irregularity, has proven that current water management techniques, which rely on human operator knowledge, are insufficient and inefficient. Observing the development of data Science and Machine Learning techniques, these intelligent algorithms seem to be an interesting approach that could support water management operations by predicting water usage depending on several factors. A first step involves characterizing user consumption behaviors by applying feature extraction and data visualization techniques to discover similarities and common patterns among users.
this article analyzes the energy efficiency evaluation indicators of data centers and highlights the importance of accurate measurement of electrical energy data. Based on the characteristics of online operation of po...
详细信息
this article introduces a novel data Quality Assessment Methodology (DQAM) tailored to the challenges of Big data and Machine Learning (ML), particularly in the context of Federated Learning. DQAM offers a standardise...
详细信息
data play a pivotal role in supporting both national economic development and scientific research, and ensuring their authenticity and integrity has become a key concern for scholars. To this end, various authenticati...
详细信息
ISBN:
(纸本)9783031649479;9783031649486
data play a pivotal role in supporting both national economic development and scientific research, and ensuring their authenticity and integrity has become a key concern for scholars. To this end, various authentication algorithms, such as digital signatures, message authentication codes, and hash functions have been proposed. Many of these algorithms treat data as a unity, which can lead to different authentication results if the elements order of the data changes. However, spatial data object is a point set that lack a predetermined order, varying data acquisition and management systems used by operators may result in the same data appearing in different orders, and these approaches are no longer effective. therefore, this study proposes an authentication algorithm for spatial data objects based on set nature. We consider spatial data objects as a data set, and each element in set will be transferred into a string data. then, we use hash function SHA to compute each string data, and perform XOR operation to obtain message M. Finally, the final hash code is obtained by computing M using the SHA. through tampering experiments, it has been shown this algorithm has the property of ignoring the data order, good sensitivity, diffusion, confusion, and security. this algorithm can overcome the limitations that rely on data order, contribute to improving the authentication process for spatial data objects, and enhance data integrity and reliability in various applications.
the rapid expansion of mobile apps on Android platforms, particularly AI-based medical chatbots, presents both remarkable opportunities and significant privacy challenges within the healthcare sector. this paper explo...
详细信息
ISBN:
(纸本)9783031741852;9783031741869
the rapid expansion of mobile apps on Android platforms, particularly AI-based medical chatbots, presents both remarkable opportunities and significant privacy challenges within the healthcare sector. this paper explores the complex privacy issues arising from the use of such chatbots, focusing on the sensitive nature of health information exchange. We critically assess the effectiveness of current dynamic analysis techniques and the limitations they face in addressing the unique privacy concerns associated with medical chatbots, including third-party integration, encryption of user interactions, and data sharing practices. Our research introduces a novel methodology that employs network packet capture and analysis, using the HTTP Toolkit to scrutinize data traffic between mobile apps and servers in real-time. through the detailed examination of HAR files and the incorporation of ChatGPT 4.0, our study provides insights into the web interactions and data handling processes of AI-based medical chatbots.
暂无评论