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
Anil Rahate et al.
Summary: Industry 5.0 emphasizes collaboration between humans and machines, requiring robustness, efficiency, and accuracy of intelligent and innovative components. Multimodal sensor fusion provides higher accuracies than single-source/mode systems. However, in real-world applications, data is often unavailable or noisy, making robust sensor fusion necessary.
Article
Engineering, Electrical & Electronic
Jie Luo et al.
Summary: This study presents an electronic nose-based method for detecting food spoilage by identifying and estimating gas concentrations. The response data of sensors were transformed into pictures using the Fourier series and a convolutional neural network (CNN) model was used to identify the gases (C2H5OH, NH3, and H2S). To improve classification models, the synthetic minority oversampling technique (SMOTE) and dropout technique were employed. The model achieved a gas identification accuracy rate of 96.67% and a regression model was proposed to estimate gas concentrations. The method showed satisfactory predictive performance for evaluating the freshness of kiwifruit, pork, and beef.
IEEE SENSORS JOURNAL
(2023)
Article
Green & Sustainable Science & Technology
Omneya Attallah et al.
Summary: This paper proposes an efficient and robust ensemble deep learning-based diagnosis method for inter-turn short-circuit faults detection in induction rotating machines. The proposed technique achieves 100% classification accuracy and reduces the input features' size to the classifier.
Article
Chemistry, Analytical
Magdalena Pilat-Rozek et al.
Summary: The work successfully combines gas sensors, instrumentation, and machine learning methods to create an electronic nose for accurate classification of different stages in wastewater treatment. Dimensionality reduction using t-SNE method and discretization evaluation using k-median method were performed on the multidimensional data from the gas sensors array. A random forest supervised machine learning method was employed to classify observations based on sensor measurements, which resulted in a high-quality classification model.
Article
Chemistry, Multidisciplinary
Omneya Attallah
Summary: Routine checks can help prevent cervical cancer. Artificial intelligence can enhance the traditional testing procedure and improve diagnostic accuracy.
APPLIED SCIENCES-BASEL
(2023)
Article
Medicine, General & Internal
Omneya Attallah
Summary: Retinopathy of prematurity (ROP) is a serious ocular problem in premature infants. This paper proposes an automated CAD tool called GabROP, which uses Gabor wavelets and multiple deep learning models for ROP diagnosis. GabROP analyzes fundus images using Gabor wavelets and trains three CNN models independently. The features from these models are fused using discrete cosine transform (DCT) to obtain the final diagnosis result. Experimental results demonstrate the accuracy and efficiency of GabROP.
Article
Social Sciences, Interdisciplinary
Kamali N. N. Sripathi et al.
Summary: Assessing student knowledge based on their writing using traditional qualitative methods is time-consuming. To improve speed and consistency of text analysis, we developed a machine learning predictive model to analyze student writing. Our approach involved two stages: an exploratory sequential design and an iterative complex design. We trained our predictive model using qualitative coding of categories in student writing and revised it based on instructor feedback. Our study contributes to mixed methods research by utilizing machine learning as a rapid and consistent additional coder and predictor for student writing codes.
JOURNAL OF MIXED METHODS RESEARCH
(2023)
Article
Automation & Control Systems
Rabeb Faleh et al.
Summary: In the field of electronic noses, research has focused on deep learning for gas classification. Compared to traditional machine learning algorithms, convolutional neural network (CNN) architectures achieve higher classification accuracy. This study proposed a hybrid CNN-LDA model for the classification of pollutant gases and applied it to an open-source gas dataset. The results showed that the hybrid CNN-LDA model achieved the highest test accuracy of 93%, outperforming the individual CNN and LDA models with accuracies of 90% and 83% respectively.
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS
(2023)
Article
Multidisciplinary Sciences
Lydia T. Liu et al.
Summary: Machine learning techniques are widely used in education, but there is a need to investigate how these techniques align with education principles and goals. This study examines education machine learning papers published in top conferences over the past decade, using qualitative insights from interviews with education experts. The research finds a cross-disciplinary gap in the formulation of machine learning problems from education goals and the translation of predictions to interventions. An extended machine learning life cycle is proposed based on these insights.
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
(2023)
Article
Chemistry, Analytical
Zhongzhou Li et al.
Summary: To improve the poor selectivity of semiconductor gas-sensor systems, a high-integrated and highly selective electronic nose (E-nose) with two independent gas-sensing elements on a low-power microhotplate (MHP) was proposed. Pd-SnO2 nanoflowers and Pd-WO3 microparticles were used to form an array of sensors on the MHP through electrohydrodynamic inkjet printing and in-situ infrared laser curing. The gas-sensor array achieved high response and low cross-sensitivity for various gases. Wavelet transform was applied to reduce noise and dimensionality of the signals. Qualitative identification accuracy of 99.86% was achieved using the k-nearest neighbor (kNN) model, while the p neighbors back propagation neural network (pN-BPNN) model improved quantitative identification accuracy for gas concentration estimation, especially for hydrogen.
SENSORS AND ACTUATORS B-CHEMICAL
(2023)
Article
Automation & Control Systems
Omneya Attallah
Summary: An automated tool called RADIC was developed to train deep learning models using radiomics-generated images, improving the accuracy of COVID-19 diagnosis with a final accuracy of 99.4% and 99% on two benchmark datasets.
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS
(2023)
Article
Agronomy
Yunwei Xiong et al.
Summary: The study proposes a method using conversion to images for an electronic nose to detect the freshness of chicken breasts. Deep learning can automatically extract features and uncover potential patterns in data, minimizing the influence of subjective factors. The retrained ResNet model achieves an accuracy of 99.70%, higher than the 94.33% correct rate of the SVM model. Therefore, the electronic nose combined with conversion to images shows great potential for chicken freshness classification using deep transfer learning methods.
Article
Computer Science, Artificial Intelligence
Omneya Attallah
Summary: This study proposes an efficient computer-aided diagnostic (CAD) system called CerCan.Net for the automatic diagnosis of cervical cancer. It utilizes lightweight convolutional neural networks (CNNs) to accurately and rapidly diagnose cervical cancer, overcoming the limitations of traditional diagnosis.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Ali Amkor et al.
Bulletin of Electrical Engineering and Informatics
(2023)
Article
Horticulture
Omneya Attallah
Summary: Tomatoes are valuable vegetables and an economic pillar for many countries. Automatic identification of tomato leaf diseases using deep learning models has been widely studied, but existing methods suffer from high computational complexity and large dimensionality. This study proposes a pipeline that utilizes compact convolutional neural networks and transfer learning for condensed and high-level representation. The pipeline also applies a hybrid feature selection approach to reduce dimensions and achieves high accuracy in tomato leaf disease identification.
Article
Education & Educational Research
Tatiana Cardona et al.
Summary: This study presents a systematic review of using machine learning algorithms to predict student retention in higher education. Increasing student retention is critical to improve graduation rates and predicting retention provides opportunities for intentional student advising. The review provides a research perspective and key findings on factors and methodologies used in predicting student retention, which are important for enhancing prediction capability and developing strategies for improving student retention.
JOURNAL OF COLLEGE STUDENT RETENTION-RESEARCH THEORY & PRACTICE
(2023)
Article
Chemistry, Analytical
Lihang Feng et al.
Summary: Sensor drift is a challenging problem in electronic nose systems. This paper proposes an augmented convolutional neural network (ACNN) approach that can solve gas discrimination problems with high accuracy rates over an extended period. The ACNN model automatically transforms time-varying gas signals into multi-dimensional feature matrices and compensates for model deviation caused by sensor drift.
SENSORS AND ACTUATORS B-CHEMICAL
(2022)
Article
Chemistry, Multidisciplinary
Mingu Kang et al.
Summary: Semiconductor metal oxide (SMO) gas sensors are considered as next-generation environmental monitoring sensors, but they have limitations in actual applications due to low selectivity. This study solves these problems by fabricating uniform gas sensor arrays and applying a deep learning algorithm, achieving real-time selective gas detection for various gases.
Article
Engineering, Industrial
Femi Olan et al.
Summary: Over the past decade, food and beverage supply chain management has become a critical component of global operations strategy. The expansion of global food and beverage industries has led to challenges in coordinating operations across countries, particularly in terms of financial support for multi-layered supply chain networks. Despite limited literature on artificial intelligence in FDIs, the study explores AI theory in supply chain networks and alternative supply chain financing, proposing a new conceptual framework based on theoretical contributions identified through literature. The research indicates that AI-driven supply chain networks may provide a sustainable financing stream for the food and beverage supply chain.
INTERNATIONAL JOURNAL OF PRODUCTION RESEARCH
(2022)
Article
Biology
Omneya Attallah
Summary: This paper proposes a new method, ECG-BiCoNet, for diagnosing COVID-19 using electrocardiogram (ECG) data. The results show that ECG data can be used to accurately diagnose COVID-19, which helps clinicians with automatic diagnosis and overcomes limitations of manual diagnosis.
COMPUTERS IN BIOLOGY AND MEDICINE
(2022)
Article
Engineering, Environmental
Alibek Kopbayev et al.
Summary: Detection and diagnosis of natural gas leakage is crucial for ensuring safety. This study combines a convolutional network and a bi-directional long short-term memory layer network to perform leak detection and diagnosis. The model successfully predicts gas leakage and classifies its size, showing promising results for early and accurate leak detection in natural gas facilities.
PROCESS SAFETY AND ENVIRONMENTAL PROTECTION
(2022)
Article
Chemistry, Multidisciplinary
Han Fan et al.
Summary: In this paper, an ensemble learning based approach (ELBA) is proposed for the detection of chemical compounds using electronic noses. The approach initializes the system with clean air and learns online by detecting the presence of chemicals and updating the models. Real-world experiments demonstrate the effectiveness of the approach in an uncontrolled environment and suggest the potential for hybridization with other supervised learning models.
FRONTIERS IN CHEMISTRY
(2022)
Article
Chemistry, Analytical
Omneya Attallah
Summary: Accurate and rapid diagnosis of COVID-19 is crucial for controlling its spread, reducing lockdown restrictions, and alleviating the burden on healthcare systems. This study introduces a novel automated diagnostic tool based on ECG data, utilizing deep learning models to achieve high accuracy in diagnosing COVID-19 at binary and multiclass levels.
Article
Automation & Control Systems
Christos Spandonidis et al.
Summary: The ESTHISIS project aims to develop a low-cost and low-energy wireless sensor system for the immediate detection of leaks in metallic piping systems for the transport of liquid and gaseous petroleum products. Two leakage detection methodologies were presented in this study: a 2D-Convolutional Neural Network (CNN) model for supervised classification and a Long Short-Term Memory Autoencoder (LSTM AE) for unsupervised leakage detection. Field tests and evaluation in a real environment showed the effectiveness of the methods.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2022)
Article
Engineering, Multidisciplinary
Omneya Attallah et al.
Summary: This paper introduces an intelligent E-Nose called GasCon-Enose to identify both the type and concentration level of combustible gases. GasCon-Enose extracts features from different domains and introduces a hybrid feature selection approach. The experimental results show that GasCon-Enose has high recognition accuracy and can be employed as a reliable platform for combustible gas sensing and concentration level identification in smart city environments.
Article
Computer Science, Artificial Intelligence
Omneya Attallah et al.
Summary: The quick and accurate diagnosis of COVID-19 is crucial for preventing its spread and improving treatment outcomes. This study proposes a deep learning-based pipeline called CoviWavNet, which utilizes 3D multiview CT slices and spectral-temporal information to enhance the diagnostic accuracy of COVID-19.
APPLIED SOFT COMPUTING
(2022)
Article
Computer Science, Information Systems
Parag Narkhede et al.
Summary: This paper introduces a novel multimodal dataset for gas leakage detection, consisting of samples collected using seven different gas-detecting sensors and a thermal imaging camera. The dataset is helpful for researchers and system developers to develop and train advanced artificial intelligence models and systems.
Article
Chemistry, Analytical
Dedy Rahman Wijaya et al.
Summary: Electronic nose systems are valuable in meat production and processing, with ensemble learning methods being key for e-nose signal processing and sensor optimization in beef quality assessment.
SENSING AND BIO-SENSING RESEARCH
(2022)
Review
Chemistry, Physical
Hongyu Liu et al.
Summary: Metal oxide semiconductor (MOS) gas sensors have been widely used in various industries due to their small size, low power consumption, high sensitivity, and good silicon chip compatibility. However, the poor selectivity of MOS sensors has limited their potential application in the Internet of Things (IoT) era. This paper reviews the progress in addressing the selectivity issues of MOS sensors and introduces three strategies for selective MOS sensors and performance improvements.
ACTA PHYSICO-CHIMICA SINICA
(2022)
Review
Computer Science, Artificial Intelligence
D. R. Sarvamangala et al.
Summary: This article discusses the importance of imaging techniques in capturing anomalies of the human body and the use of convolutional neural networks in medical image understanding. It also explores various tasks and applications in medical image diagnosis, focusing on the challenges and potentials of CNN in this field.
EVOLUTIONARY INTELLIGENCE
(2022)
Article
Automation & Control Systems
Junchi Bin et al.
Summary: The article proposes a tensor-based leakage detection (TBLD) framework for detecting LNG leakage from surveillance thermal cameras in rural areas, aiming to improve sensitivity and accuracy. By utilizing 50 layers of residual networks (ResNet50), TBLD can accurately detect LNG leakage and consistently outperforms contemporary frameworks in detecting LNG leakage at different distances.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2021)
Article
Automation & Control Systems
E. J. Perez-Perez et al.
Summary: In this paper, a methodology using artificial neural networks (ANN) techniques and online measurements of pressure and flow rate is presented for detecting and locating water leaks in pipelines. The method estimates the friction factor of the pipe and uses this information to compute the leak position, showing good performance and applicability in experimental tests.
CONTROL ENGINEERING PRACTICE
(2021)
Article
Computer Science, Artificial Intelligence
Said Yacine Boulahia et al.
Summary: Multimodal action recognition techniques combine multiple image modalities, including early fusion, intermediate fusion, and late fusion methods for more robust recognition. By deeply investigating different fusion levels, new schemes are proposed to better combine features from different modalities and achieve better recognition results than traditional methods.
MACHINE VISION AND APPLICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Cristiano Rafael Steffens et al.
Summary: This study introduces an evaluation framework that simulates common image distortions in robot vision, rigorously evaluating the robustness of image recognition models and their performance under different distortion conditions. Most CNN models are slightly affected by mild distortions, but show significant decrease in accuracy and precision under extreme distortion.
JOURNAL OF INTELLIGENT & ROBOTIC SYSTEMS
(2021)
Review
Chemistry, Analytical
Zhenyi Ye et al.
Summary: Machine learning methods enable precise odor identification and analysis with the electronic nose (E-Nose) for both qualitative and quantitative purposes. Advanced machine learning techniques are crucial for improving the performance of the E-Nose and enhancing its capabilities in various applications, leading to increased prediction accuracy and stability.
Article
Medicine, General & Internal
Omneya Attallah
Summary: Medulloblastoma (MB) is a dangerous malignant pediatric brain tumor. Precise diagnosis is essential. The computer-aided diagnosis system MB-AI-His combines deep learning and texture analysis for automatic diagnosis of pediatric MB and its subtypes from histopathological images efficiently and reliably.
Article
Computer Science, Artificial Intelligence
Omneya Attallah et al.
Summary: The article proposes a CADx system named Gastro-CADx for classifying multiple GI diseases using DL techniques. The system consists of three stages: extracting spatial features using CNN, extracting temporal-frequency and spatial-frequency features using DWT and DCT, and fusing multiple feature combinations for optimal output selection.
PEERJ COMPUTER SCIENCE
(2021)
Article
Medicine, General & Internal
Omneya Attallah
Summary: Retinopathy of Prematurity (ROP) affects preterm neonates and could lead to blindness. Deep Learning (DL) can assist ophthalmologists in diagnosing ROP, and the automated diagnostic tool DIAROP achieved an accuracy of 93.2%.
Article
Computer Science, Information Systems
Parag Narkhede et al.
Summary: With the rapid industrialization and technological advancements, innovative engineering technologies are essential, and sensor fusion is necessary for robust and reliable detection in several real-world applications. Our proposed novel approach utilizing multimodal AI fusion techniques outperformed single sensor detection, with a testing accuracy of 96% compared to 82% and 93% for individual models based on Gas Sensor data and thermal images data, respectively.
APPLIED SYSTEM INNOVATION
(2021)
Article
Computer Science, Artificial Intelligence
Huixiang Liu et al.
Article
Chemistry, Analytical
Patricia Arroyo et al.
Review
Computer Science, Artificial Intelligence
Jing Gao et al.
NEURAL COMPUTATION
(2020)
Article
Chemistry, Analytical
Saifur Rahman et al.
Review
Chemistry, Multidisciplinary
Ghenadii Korotcenkov
Article
Electrochemistry
Junyu Zhang et al.
JOURNAL OF THE ELECTROCHEMICAL SOCIETY
(2020)
Article
Computer Science, Information Systems
Fanyu Zeng et al.
Article
Construction & Building Technology
Tao Yang et al.
INDOOR AND BUILT ENVIRONMENT
(2019)
Article
Computer Science, Information Systems
Xiaofang Pan et al.
Article
Computer Science, Information Systems
Wenzhong Guo et al.
Article
Optics
Aref Miri et al.
Article
Chemistry, Analytical
Pai Peng et al.
Article
Computer Science, Artificial Intelligence
Qihe Liu et al.
INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS
(2015)
Article
Computer Science, Artificial Intelligence
Jie Lu et al.
KNOWLEDGE-BASED SYSTEMS
(2015)
Article
Engineering, Electrical & Electronic
Dana Lahat et al.
PROCEEDINGS OF THE IEEE
(2015)
Article
Engineering, Environmental
Sarah Bonvicini et al.
PROCESS SAFETY AND ENVIRONMENTAL PROTECTION
(2015)
Proceedings Paper
Engineering, Biomedical
Masahiro Imahashi et al.
OLFACTION AND ELECTRONIC NOSE: PROCEEDINGS OF THE 14TH INTERNATIONAL SYMPOSIUM ON OLFACTION AND ELECTRONIC NOSE
(2011)
Article
Chemistry, Analytical
EL Kalman et al.
ANALYTICA CHIMICA ACTA
(2000)
