The proceedings contain 105 papers. The topics discussed include: personal credit risk identification based on combined machinelearning model;compliant robotic assembly based on deep reinforcement learning;recognitio...
ISBN:
(纸本)9781665417365
The proceedings contain 105 papers. The topics discussed include: personal credit risk identification based on combined machinelearning model;compliant robotic assembly based on deep reinforcement learning;recognition and classification of surface defects of aluminum castings based on machine vision;a 3D space violation detection method of substations based on the deep neural network;research on audio playing system design factors modeling based on interpretive structure model;research on audio playing system design factors modeling based on interpretive structure mode;forecasting short-term power grid load based on recurrent neural network;an improved recommendation model based on matrix factorization;and modular attention network based on language model for referring expression.
The proceedings contain 94 papers. The topics discussed include: classification method of surface defects of aluminum profile based on transfer learning;an improved anchor-free object detection method;lightweight real...
ISBN:
(纸本)9781665492461
The proceedings contain 94 papers. The topics discussed include: classification method of surface defects of aluminum profile based on transfer learning;an improved anchor-free object detection method;lightweight real-time object detection system based on embedded ai development kit;video content understanding based on feature selection and semantic alignment network;transferability of pretrained convolutional neural networks for breast cancer detection;analyzing the determinations of financial inclusion in Africa based on random forest model and logistic regression model;the impact of the distance sensors orientation on the obstacle avoidance ability of the robot;research on the performance of different convolutional neural network models on small datasets;construction method of network feasible path for power data platform;resource management scheduling-based on proximal policy optimization;and a study of fair prediction on credit assessment based on counterfactual fairness.
The proceedings contain 95 papers. The topics discussed include: a trusted mechanism for participant screening and verification in federated learning;real-time rice disease spot segmentation using an improved YOLOv8 f...
ISBN:
(纸本)9798350375077
The proceedings contain 95 papers. The topics discussed include: a trusted mechanism for participant screening and verification in federated learning;real-time rice disease spot segmentation using an improved YOLOv8 framework;real-time rice disease spot segmentation using an improved YOLOv8 framework;real-time AR inspection method for main equipment of converter station based on two-channel threshold segmentation and visual feature value;Improved 3D object detection method based on PointPillars;design of track logistics control system based on digital twin;inverse kinematics solution algorithm of electric climbing robot based on improved beetle antennae search algorithm;and installation design based on the relationship between artificial intelligence and art development.
With the increasing demand for unmanned surface vehicles (USVs) in fields such as marine environmental monitoring, resource exploration, and emergency rescue, the development of intelligent decision and planning techn...
详细信息
With the increasing demand for unmanned surface vehicles (USVs) in fields such as marine environmental monitoring, resource exploration, and emergency rescue, the development of intelligent decision and planning technologies has become critical. However, the complexity and dynamic nature of marine environments pose significant challenges to traditional methods in practical applications. In recent years, the rapid advancement of machinelearning (ML) has offered novel solutions for the intelligent decision and planning of USVs. This paper systematically reviews the research progress in USV decision and planning based on ML. First, it reviews the classification of USV autonomy levels and the historical development of ML in unmanned marine systems. Then, the paper proposes and elaborates on the "ML-MDP" framework (a ML-based Mission planning, Dynamic decision, and Path planning framework) for USVs, analyzing the latest research outcomes in these areas and explores the suitability of various ML algorithms in addressing these challenges. Finally, the paper analyzes the challenges faced by ML in USV applications and its future development directions. This review aims to provide a valuable reference for researchers in related fields, highlighting the potential of ML in marine unmanned systems and promoting advancements in USV intelligence.
Universitat Polit`ecnica de Val`encia (UPV) faces challenges in managing its Alfresco document repository, which contains 600,000 PDF files, of which only 100,000 are correctly categorised. Manual classification is la...
详细信息
ISBN:
(纸本)9783031777301;9783031777318
Universitat Polit`ecnica de Val`encia (UPV) faces challenges in managing its Alfresco document repository, which contains 600,000 PDF files, of which only 100,000 are correctly categorised. Manual classification is laborious and error-prone, hindering information retrieval and advanced search capabilities. This project presents an automated pipeline that integrates optical character recognition (OCR) and machinelearning to efficiently classify documents. Our approach distinguishes between scanned and digital documents, accurately extracts text and categorises it into 51 predefined categories using models such as BERT and RF. By improving document organisation and accessibility, this work optimises UPV's document management and paves the way for advanced search technologies and real-time classification systems.
The intelligent Internet of Things(IIoT) involves real-world things that communicate or interact with each other through networking technologies by collecting data from these “things” and using intelligent approache...
详细信息
The intelligent Internet of Things(IIoT) involves real-world things that communicate or interact with each other through networking technologies by collecting data from these “things” and using intelligent approaches, such as Artificial Intelligence(AI) and machinelearning, to make accurate decisions. Data science is the science of dealing with data and its relationships through intelligent approaches. Most state-of-the-art research focuses independently on either data science or IIoT, rather than exploring their integration. Therefore, to address the gap, this article provides a comprehensive survey on the advances and integration of data science with the intelligent IoT(IIoT) system by classifying the existing IoT-based data science techniques and presenting a summary of various characteristics. The paper analyzes the data science or big data security and privacy features, including network architecture, data protection, and continuous monitoring of data, which face challenges in various IoT-based systems. Extensive insights into IoT data security, privacy, and challenges are visualized in the context of data science for IoT. In addition, this study reveals the current opportunities to enhance data science and IoT market development. The current gap and challenges faced in the integration of data science and IoT are comprehensively presented, followed by the future outlook and possible solutions.
machinelearning models often excel in controlled environments but may struggle with noisy, incomplete, or shifted real-world data. Ensuring that these models maintain high performance despite these imperfections is c...
详细信息
ISBN:
(纸本)9783031777370;9783031777387
machinelearning models often excel in controlled environments but may struggle with noisy, incomplete, or shifted real-world data. Ensuring that these models maintain high performance despite these imperfections is crucial for practical applications, such as medical diagnosis or autonomous driving. This paper introduces a novel framework to systematically analyse the robustness of machinelearning models against noisy data. We propose two empirical methods: (1) Noise Tolerance Estimation, which calculates the noise level a model can withstand without significant degradation in performance, and (2) Robustness Ranking, which ranks machinelearning models by their robustness at specific noise levels. Utilizing Cohen's kappa statistic, we measure the consistency between a model's predictions on original and perturbed datasets. Our methods are demonstrated using various datasets and machinelearning techniques, identifying models that maintain reliability under noisy conditions.
With the rapid development of the aviation industry, air traffic flow is showing a rapid growth trend, and the mutual influence and interference between aircraft in the airspace are also increasing. In order to ensure...
详细信息
Counterfactual explanations are a well-known technique in Explainable machinelearning (XML) to provide simple explanations on complex machinelearning (ML) models. Through understandable "what if" scenarios...
详细信息
ISBN:
(纸本)9783031777301;9783031777318
Counterfactual explanations are a well-known technique in Explainable machinelearning (XML) to provide simple explanations on complex machinelearning (ML) models. Through understandable "what if" scenarios, counterfactuals explore how changes in the input data affect the results of a model. This article leverages counterfactual explanations for sustainable tourism, an emerging approach within the tourism industry to mitigate the negative impacts of mass tourism on ecological systems and local communities. The proposed method analyzes the relationships between several Sustainable Tourism Indicators (STIs) defined for a specific tourist destination and its general sustainability assessment. It identifies the key changes needed in the STIs to achieve an improved global sustainability score. As a result, a decision-making system is offered for sustainable tourism management, which domain experts can use to make more informed decisions. The effectiveness of the proposed method is illustrated through its application to Mallorca, a popular Spanish tourist destination.
暂无评论