相关参考文献
注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article
Computer Science, Artificial Intelligence
Xin Ning et al.
Summary: In this study, a flexible and plastic hyper-sausage coverage function (HSCF) neuron model is proposed based on the mechanism of human cognition. A novel cross-entropy and volume-coverage (CE_VC) loss function is defined to enhance class separability and intra-class compactness. The introduced divisive iteration method adaptively determines the optimal number of HSCF neurons and a end-to-end learning framework is constructed. Experimental results demonstrate the effectiveness of the proposed method and its potential for boosting deep neural networks with neuron plasticity.
PATTERN RECOGNITION
(2023)
Article
Medicine, General & Internal
Zhen Yang et al.
Summary: This study aimed to explore a conceptual model of home-based cardiac rehabilitation exercise adherence in patients with chronic heart failure and reveal its internal behavioral logic. Semi-structured interviews were conducted to collect qualitative data and construct the conceptual model. The results formed a conceptual model of home-based cardiac rehabilitation exercise adherence, including core behaviors such as seeking supports, rehabilitation exercise, exercise monitoring, and information feedback.
PATIENT PREFERENCE AND ADHERENCE
(2023)
Article
Computer Science, Information Systems
Hui Zhang et al.
Summary: This study aims to enhance the core competitiveness and financing feasibility of small and medium-sized enterprises (SMEs) under economic globalization by utilizing deep learning. It proposes a supply chain symbiosis system based on DL, economics, and Stackelberg game theory, and designs a structural framework for supply chain financing (SCF). The results demonstrate that the proposed IoT-based SCF SMEs-oriented BPNN credit evaluation model achieves a prediction accuracy of 91.4%, effectively eliminating information asymmetry between banks and various capitals.
JOURNAL OF ORGANIZATIONAL AND END USER COMPUTING
(2023)
Review
Computer Science, Theory & Methods
Arash Heidari et al.
Summary: Deep Learning (DL) and Machine Learning (ML) are widely used in various sectors such as healthcare, industry, and academia. The Internet of Drones (IoD) is a recent development that offers adaptability to unpredictable situations. Unmanned Aerial Vehicles (UAVs) have diverse applications, including rescue missions, farming, and surveillance systems, due to their technical advantages. However, deploying drone systems presents challenges related to wireless unpredictability, mobility, and battery life. This research aims to provide a comprehensive understanding of IoD/UAV fundamentals, recent developments, existing methods, and areas for further investigation.
ACM COMPUTING SURVEYS
(2023)
Article
Computer Science, Information Systems
Hui Zhang et al.
Summary: This study aims to enhance the core competitiveness and financing attainability of small and medium-sized enterprises (SMEs) using deep learning technology. By constructing a supply chain symbiosis system and designing a credit evaluation model based on the internet of things (IoT), the study effectively reduces information asymmetry between banks and various capitals, achieving a prediction accuracy of 91.4%.
JOURNAL OF ORGANIZATIONAL AND END USER COMPUTING
(2023)
Article
Computer Science, Cybernetics
Xiaoli Dong et al.
Summary: An artistic line portrait robot is capable of generating, processing, and drawing line portraits. A method based on a triangle coordinate system (TCS) is proposed to synthesize line portraits with recognizable expressions. Experimental results demonstrate that the generated expression line portraits have high recognizability.
IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS
(2023)
Article
Chemistry, Analytical
Feng He et al.
Summary: A new method for bearing fault diagnosis based on wavelet packet transform and convolutional neural network optimized by a simulated annealing algorithm is proposed, showing better and more reliable diagnosis effect compared to existing machine learning and deep learning methods.
Review
Engineering, Industrial
Marcel Panzer et al.
Summary: Deep Reinforcement Learning is increasingly used in optimizing production systems, providing real-time responses and reducing reliance on traditional methods. However, future research should focus on applying findings to real-world systems and analyzing safety and reliability under prevailing conditions.
INTERNATIONAL JOURNAL OF PRODUCTION RESEARCH
(2022)
Article
Computer Science, Artificial Intelligence
Chen Wang et al.
Summary: This paper proposes a novel approach to estimate uncertainties in stereo matching end-to-end, using the NIG distribution to calculate uncertainties and additional loss functions to enhance sensitivity and smoothness. Experimental results show that this method improves stereo matching results, particularly performing well on out-of-distribution data.
PATTERN RECOGNITION
(2022)
Article
Green & Sustainable Science & Technology
Tanveer Ahmad et al.
Summary: The current trend indicates that energy demand and supply will eventually be controlled by autonomous software that optimizes decision-making and energy distribution operations. New state-of-the-art machine learning (ML) technologies are integral in optimizing decision-making in energy distribution networks and systems. This study focuses on the urgent need to research data-driven probabilistic ML techniques that can be applied in smart energy systems and networks. The study examines the use of ML in core energy technologies and energy distribution utilities, highlighting their potential in areas such as energy material manufacturing, renewable energy integration, and big data analytics.
RENEWABLE & SUSTAINABLE ENERGY REVIEWS
(2022)
Article
Mathematical & Computational Biology
Xuesheng Wang et al.
Summary: This paper introduces the research on intelligent interaction in early childhood physical education using dynamic image capture and recognition technology. By judging children's physical abilities and identifying the accuracy and safety of movements, a new recognition model is proposed and experimentally shown to have the advantages of high accuracy and fast speed.
COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE
(2022)
Article
Chemistry, Multidisciplinary
Selim Reza et al.
Summary: This article proposes a traffic state prediction model based on 1D CNN and LSTM, which shows promising performance on Zenodo and PeMS datasets, significantly outperforming traditional models.
APPLIED SCIENCES-BASEL
(2022)
Article
Computer Science, Artificial Intelligence
Lulu Zhang et al.
Summary: This paper proposes a new posture positioning strategy based on attention mechanism and context learning, including a large receptive field residual module and an efficient human pose estimation model framework. By designing a large receptive field network and incorporating context information, the accuracy and robustness of the model are improved while maintaining efficiency.
NEURAL COMPUTING & APPLICATIONS
(2022)
Article
Environmental Sciences
Zhuomei Huang et al.
Summary: A light gradient boosting model (LGBM) based on particle swarm optimization (PSO) algorithm is proposed for accurate prediction of aboveground biomass of mangroves. The model outperforms other machine learning algorithms in performance and provides more accurate prediction results for large-scale mangroves.
GEOCARTO INTERNATIONAL
(2022)
Review
Computer Science, Artificial Intelligence
Xinyi Yang et al.
Summary: This review focuses on the modern machine learning (ML) approaches for combinatorial optimization problems (COPs) in the energy areas. Recent research on solving COPs using ML is sorted out based on different methods, and practical applications of ML in the energy areas are summarized. Challenges in this field are also analyzed.
Review
Automation & Control Systems
Aya Nabil Sayed et al.
Summary: The building internet of things (BIoT) is a promising concept for reducing energy consumption, cutting costs, and promoting building transformation. Integrating artificial intelligence (AI) into the BIoT is crucial for data analysis and intelligent decision-making. This article provides an in-depth survey of strategies used to analyze sensor data and determine building occupancy, with a focus on deep learning and transfer learning approaches. Privacy and precision concerns in the current occupancy detection system are thoroughly discussed. Various directions are proposed to address privacy issues and improve detection accuracy.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2022)
Article
Chemistry, Analytical
Junhong Wang et al.
Summary: This study proposes a novel method for automatic classification of muscle fatigue based on sEMG signals using an LSTM network, achieving better classification performance than other models. Improved wavelet packet threshold denoising algorithm and feature extraction were used to enhance performance in denoising sEMG signals.
Article
Computer Science, Artificial Intelligence
Sonain Jamil et al.
Summary: Coral reefs are declining due to various factors, despite their crucial roles in both ecosystems and medical treatments. This paper introduces a bag of features-based approach for detecting and locating bleached corals, showcasing its effectiveness through comparison with current methods.
BIG DATA AND COGNITIVE COMPUTING
(2021)
Article
Computer Science, Information Systems
Shuai Liu et al.
Summary: In this paper, a multi-layer template update mechanism is proposed to achieve effective monitoring in a multimedia environment. By utilizing weighted and unweighted templates alternatively, it ensures that the target will not be lost during the monitoring process. Experimental results show that this strategy maintains real-time speed and improves robustness in a multimedia background.
IEEE TRANSACTIONS ON MULTIMEDIA
(2021)
Article
Green & Sustainable Science & Technology
Zhuoqun Sun et al.
Summary: This study aims to establish a method to estimate emissions of transit buses with four different fuel types using long short-term memory network, which outperformed the compared method in terms of emission rates and average emission factors. The proposed models effectively consider the time dependence of emissions response to vehicle operation situation, showing better accuracy and stability.
INTERNATIONAL JOURNAL OF SUSTAINABLE TRANSPORTATION
(2021)
Article
Computer Science, Artificial Intelligence
Long Wen et al.
NEURAL COMPUTING & APPLICATIONS
(2020)
Article
Energy & Fuels
Zhuochao Li et al.
Article
Computer Science, Information Systems
Grega Vrbancic et al.
Article
Green & Sustainable Science & Technology
Rodrigo Pinheiro Toffano Pereira et al.
CLEANER AND RESPONSIBLE CONSUMPTION
(2020)
Article
Computer Science, Artificial Intelligence
Goncalo Marques et al.
APPLIED SOFT COMPUTING
(2020)
Review
Green & Sustainable Science & Technology
Soheil Fathi et al.
RENEWABLE & SUSTAINABLE ENERGY REVIEWS
(2020)
Article
Computer Science, Artificial Intelligence
Yingzhi Zhang et al.
JOURNAL OF INTELLIGENT MANUFACTURING
(2019)
Article
Chemistry, Multidisciplinary
Huawei Chen et al.
Proceedings Paper
Engineering, Mechanical
Shen Gui-xiang et al.
INTERNATIONAL CONFERENCE ON MECHANICAL ENGINEERING AND APPLIED COMPOSITE MATERIALS
(2018)
Review
Neurosciences
Mark P. Mattson
FRONTIERS IN NEUROSCIENCE
(2014)