检索结果-内蒙古大学图书馆

Staged transfer learning for multi-label half-face emotion recognition

Journal of engineering and Applied Science 2025年第1期72卷 1-25页

作者： ElMaksoud, Mohamed M. Abd ElGohary, Sherif H. Kandil, Ahmed H. Systems and Biomedical Engineering Department Faculty of Engineering Cairo University Giza Egypt

As fundamental drivers of human behavior, emotions can be expressed through various modalities, including facial expressions. Facial emotion recognition (FER) has emerged as a pivotal area of affective computing, enabling accurate detection of human emotions from visual cues. To enhance the efficiency and maintain accuracy, we propose a novel approach that leverages deep learning and transfer learning techniques to classify emotions based on only half of the human face. We introduce EMOFACE, a comprehensive half-facial imagery dataset annotated with 25 distinct emotion labels, providing a diverse and inclusive resource for multi-label half-facial emotion classification. By combining this dataset with the established FER2013 dataset, we employ a staged transfer learning framework that effectively addresses the challenges of multi-label half facial emotion classification. Our proposed approach, which utilizes a custom convolutional neural network (ConvNet) and five pre-trained deep learning models (VGG16, VGG19, DenseNet, MobileNet, and ResNet), achieves impressive results. We report an average binary accuracy of 0.9244 for training, 0.9152 for validation, and 0.9138 for testing, demonstrating the efficacy of our method. The potential applications of this research extend to various domains, including affective computing, healthcare, robotics, human–computer interaction, and self-driving cars. By advancing the field of half-facial multi-label emotion recognition, our work contributes to the development of more intuitive and empathetic human–machine interactions. © The Author(s) 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Novel Multi-Stage Bispectral Deep Learning Method for Protein Family Classification

引用

Computers, Materials & Continua 2023年第7期76卷 1173-1193页

作者： Amjed Al Fahoum Ala’a Zyout Hiam Alquran Isam Abu-Qasmieh Biomedical Systems and Informatics Engineering Department Hijjawi Faculty for Engineering TechnologyYarmouk UniversityIrbid21163Jordan

Complex proteins are needed for many biological *** amino acid chains reveals their properties and *** support healthy tissue structure,physiology,and *** medicine and treatments require quantitative protein identification and *** technical advances and protein sequence data exploration,bioinformatics’“basic structure”problem—the automatic deduction of a protein’s properties from its amino acid sequence—remains *** function inference from amino acid sequences is the main biological data *** study analyzes whether raw sequencing can characterize biological facts.A massive corpus of protein sequences and the Globin-like superfamily’s related protein families generate a solid vector representation.A coding technique for each sequence in each family was devised using two representations to identify each amino acid precisely.A bispectral analysis converts encoded protein numerical sequences into images for better protein sequence and family *** and validation employed 70%of the dataset,while 30%was used for *** paper examined the performance of multistage deep learning models for differentiating between sixteen protein families after encoding and representing each encoded sequence by a higher spectral representation image(Bispectrum).Cascading minimized false positive and negative cases in all *** initial stage focused on two classes(six groups and ten groups).The subsequent stages focused on the few classes almost accurately separated in the first stage and decreased the overlapping cases between families that appeared in single-stage deep learning *** single-stage technique had 64.2%+/-22.8%accuracy,63.3%+/-17.1%precision,and a 63.2%+/19.4%*** two-stage technique yielded 92.2%+/-4.9%accuracy,92.7%+/-7.0%precision,and a 92.3%+/-5.0%*** work provides balanced,reliable,and precise forecasts for all families in all measures.

关键词： Globin-like superfamily numerical encoding bispectral analysis classification model deep convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

An Innovative Bispectral Deep Learning Method for Protein Family Classification

引用

Computers, Materials & Continua 2023年第5期75卷 3971-3991页

作者： Isam Abu-Qasmieh Amjed Al Fahoum Hiam Alquran Ala’a Zyout Biomedical Systems and Informatics Engineering Department Hijjawi Faculty for Engineering TechnologyYarmouk UniversityIrbid21163Jordan

Proteins are essential for many biological *** example,folding amino acid chains reveals their functionalities by maintaining tissue structure,physiology,and *** that quantifiable protein characteristics are vital for improving therapies and precision *** automatic inference of a protein’s properties from its amino acid sequence is called“basic structure”.Nevertheless,it remains a critical unsolved challenge in bioinformatics,although with recent technological advances and the investigation of protein sequence *** protein function from amino acid sequences is crucial in *** study considers using raw sequencing to explain biological facts using a large corpus of protein sequences and the Globin-like superfamily to generate a vector *** power of two representations was used to identify each amino acid,and a coding technique was established for each sequence ***,the encoded protein numerical sequences are transformed into an image using bispectral analysis to identify essential characteristics for discriminating between protein sequences and their families.A deep Convolutional Neural Network(CNN)classifies the resulting images and developed non-normalized and normalized encoding ***,the dataset was split 70/30 for training and ***,the dataset was utilized for 70%training,15%validation,and 15%*** suggested methods are evaluated using accuracy,precision,and *** non-normalized method had 70%accuracy,72%precision,and 71%recall.68%accuracy,67%precision,and 67%recall after ***,the normalized approach without validation had 92.4%accuracy,94.3%precision,and 91.1%*** showed 90%accuracy,91.2%precision,and 89.7%*** that both algorithms outperform the *** paper presents that bispectrum-based nonlinear analysis using deep learning models outperforms standard machine learning methods and other deep learning

关键词： Globin-like superfamily numerical encoding bispectral analysis classification model deep convolutional neural network(CNN)

来源：评论

学校读者我要写书评

暂无评论

Improved QT ınterval estimation using conditional generative adversarial networks

引用

Neural Computing and Applications 2024年第18期36卷 10777-10789页

作者： Al−Zaben, Awad Al−Abed, Mohammad Biomedical Systems and Medical Informatics Department Hijjawi Faculty of Engineering Technology Yarmouk University Irbid Jordan Biomedical Engineering Department Faculty of Engineering the Hashemite University Zarqa Jordan College of Engineering and Technology American University of the Middle East Egaila54200 Kuwait

QT interval carries essential information about ventricular depolarization and repolarization. Therefore, in many investigations, it is vital to determine the QT interval accurately and monitor the corresponding QT interval variations. This paper presents a novel implementation of the Generative Adversarial Networks (GAN) to predict the QT waveform interval from the electrocardiogram. The network then estimates the Q and T locations to determine the QT interval. The accuracy of the proposed method in measuring the QT interval was 94.10%. The procedure is evaluated against ground truth performed by expert physicians, and the limits of agreement are used as the measure of performance. The bias in the estimate of the Q locations was 2.92 ms, with 11.48 ms as an upper limit of agreement and − 5.65 ms as the lower limit. The bias in estimating the T location was 1.14 ms with an upper limit of 15.04 ms and a lower limit of − 12.79 ms. Moreover, the bias in the estimate of the QT interval was − 7.10 ms with an upper limit of 50.17 ms and a lower limit of − 64.38 ms. These limits of agreements are clinically acceptable and show that the estimate of the QT interval agrees with the expert’s annotations. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

Staged Transfer Learning for Multi-Label Facial Emotion Recognition from Full Faces 6

Staged Transfer Learning for Multi-Label Facial Emotion Reco...

引用

6th IEEE Novel Intelligent and Leading Emerging Sciences Conference, NILES 2024

作者： Elmaksoud, Mohamed M. Abd Kandil, Ahmed H. Elgohary, Sherif H. Cairo University Faculty of Engineering Biomedical Engineering and Systems Dept Giza Egypt

ISBN: (纸本)9798350378511

Human emotions play a crucial role in shaping human decisions and actions. These emotions can be conveyed through various channels, including facial expressions, vocal inflections, body language, written communication, and physiological changes. Affective computing and emotion recognition aim to develop software systems that can detect and classify human emotions. Researchers have traditionally employed two main approaches: computer vision and deep learning. Facial emotion recognition focuses on categorizing human emotions based on facial image data. While prior research has primarily focused on recognizing single emotions (multiclass), this study addresses the challenge of multilabel recognition, where an image can depict multiple emotions simultaneously. To address this complexity, we introduce a novel deep learning technique called staged transfer learning. This approach breaks down the learning process into manageable subtasks, where each stage leverages the knowledge acquired from the previous stage. We utilized the unique 'emoface' dataset containing multi-label facial imagery to evaluate the effectiveness of our proposed method. We implemented a two-step deep learning approach for facial emotion recognition. This approach leverages both custom convolutional neural networks (CNNs) and pre-trained models via transfer learning. In the first stage, transfer learning was applied to the fer2013 dataset, a large multiclass collection, to extract robust features for recognizing seven basic emotions (happiness, sadness, surprise, fear, anger, and disgust). Subsequently, the second stage transferred this learned knowledge to the emoface dataset, which is a smaller multilabel dataset encompassing 25 emotions. This staged approach achieved high performance, with an average binary accuracy of 0.9389 (training), 0.9220 (validation), and 0.9187 (testing), along with low binary cross-entropy loss. These results outperform the baseline models and existing research on multi-la

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Comparing Different Deep-Learning Models for Classifying Masses in Ultrasound Images

Comparing Different Deep-Learning Models for Classifying Mas...

引用

International Conference on Medical Imaging and Computer-Aided Diagnosis, MICAD 2023

作者： Ekhlas, Shereen Abd-Elsalam, Neveen M. AlSaidy, Zaid A. Kandil, Ahmed H. Al-bialy, Ahmed Youssef, Abou Bakr M. Department of Biomedical Engineering and Systems Faculty of Engineering Cairo University Giza Egypt

ISBN: (纸本)9789819713349

Breast cancer is still the predominant type of cancer that affects women worldwide. Artificial intelligence (AI) developers are making great efforts in developing automated computer-aided detection and diagnosis (CAD) systems for breast cancer prognosis and classification. There are currently no official guidelines recommending the use of AI with ultrasound in clinical practice, and further research is needed to investigate more advanced approaches and demonstrate their utility. In this paper, we use one of the state-of-the-arts segmentation model based on deep learning, as well as compare different recent pre-trained models for the purpose of segmenting and distinguishing between benign and malignant masses in breast ultrasound images. The results showed that among the compared models, the most accurate model was the EfficientNetB7 model which achieved 88% on the segmented input images, that were segmented using the ResUNet model with 0.8932 Dice score and 0.8572 Iou score. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Adaptive algorithm for controlling the power management system on offshore jack-up drilling rigs

引用

Energy Sources, Part A: Recovery, Utilization and Environmental Effects 2024年第1期46卷 16717-16737页

作者： Cemeljic, Hrvoje Havelka, Juraj Jeremic, Aleksandar Kuzle, Igor Department of Energy and Power Systems Faculty of Electrical Engineering and Computing University of Zagreb Zagreb Croatia Department of Electrical & Computer Engineering McMaster School of Biomedical Engineering McMaster University HamiltonON Canada Faculty of Electrical Engineering and Computing University of Zagreb Zagreb Croatia

The power systems of offshore jack-up drilling rigs consist of diesel generators running in parallel load-sharing mode, controlled by an automatic Power Management System (PMS). In this paper, the operational performance of the diesel generators (DG) and the PMS on a jack-up drilling rig is investigated, focusing on two critical offshore drilling operations: "pipe tripping" and "pulling/pumping out of the hole" (POOH). During these operations, large power swings occur in the system, subjecting the DGs to sudden load surges. These severe imbalances in the system cause the PMS to intermittently start and stop the engines throughout the operation, leading to various problematic conditions in the power plant. The paper provides a novel solution for intermittent starting and stopping of the DGs in the form of development and implementation of an adaptive PMS algorithm, a mathematical model of the system and a machine learning approach to event prediction of PMS operation in offshore drilling. Research demonstrates a noteworthy decrease in intermittent DG starting and stopping when the adaptive algorithm is implemented, with a 96% reduction during pipe tripping and an 87% reduction during POOH. This improvement comes at the expense of an 11% increase in engine running hours and a 1.5% rise in fuel consumption. Furthermore, by configuring the adaptive algorithm to economy mode, savings of up to 1700 liters of fuel per month are achievable. © 2024 Taylor & Francis Group, LLC.

关键词： Adaptive algorithms

来源：评论

学校读者我要写书评

暂无评论

AI-Based Communication Tool for High-Functioning Autistic Children

AI-Based Communication Tool for High-Functioning Autistic Ch...

引用

2023 IEEE EMBS Special Topic Conference on Data Science and engineering in Healthcare, Medicine and Biology, IEEECONF 2023

作者： Ossama, Farah Issam, Fatmah Hesham, Menna Kamel, Menna Hamdy, Yumna Bibars, Merna Sadek, Ibrahim Cairo University Faculty of Engineering Systems and Biomedical Engineering Department Egypt Helwan University Faculty of Engineering Biomedical Engineering Department Egypt

ISBN: (纸本)9798350383386

High-functioning autistic children tend to have poor verbal and nonverbal communication skills, which makes it hard for them to understand people's cues and blend in with their community. This paper presents a solution to help Arabic-speaking autistic children communicate effectively and understand others' feelings. Our AI-based Communication Tool uses a mobile camera to capture the speaker's image and informs the autistic child of their emotions through a mobile app. We used images from the FER+ dataset to train on several TensorFlow models to achieve accurate facial recognition. We achieved 83.97% accuracy. Furthermore, we develop games on the mobile application using Unity to help autistic children practice different social scenarios. © 2023 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Transfer Learning for Multi-label Emotion Recognition: A Promising Approach for biomedical Applications 11

Transfer Learning for Multi-label Emotion Recognition: A Pro...

引用

11th International Japan-Africa Conference on Electronics, Communications, and Computations, JAC-ECC 2023

作者： Abd Elmaksoud, Mohamed M Elgohary, Sherif H. Cairo University Biomedical Engineering and Systems Faculty of Engineering Giza Egypt

ISBN: (纸本)9798350369328

Human emotions play a major role in our daily lives, influencing our thoughts, actions, and decisions. We propose a state-of-the-art, diverse, and inclusive dataset for emotional artificial intelligence (EAI) or affective computing. Our goal is to develop a system that can classify and recognize multiple emotions in images simultaneously, similar to how humans identify emotions. Using transfer learning with pre-trained deep neural networks like vgg16 added on top of it 4-layers deep neural network reaching 91.90% training accuracy with 0.28 training loss and 90.34% validation accuracy with 0.33validation loss trained on a dataset of 1000 images total being 800 images for training and 200 images for validation. The second architecture used was vgg19 with the same 4-layer deep neural network achieved 91.88% training accuracy with 0.28 training loss and 90.12% validation accuracy with 0.39 validation loss. The third and last architecture used was resnet added on top of it 4-layer deep neural network accomplished 90.15% training accuracy with 0.32 training loss and 90.90% validation accuracywith 0.33 validation loss. The results are really promising as the data has been collected reliably and accurately. Images were processed to only focus on the region of interest (ROI) in the images which is the face of the male or female that appears in the image. One of this study's primary aims is to develop a biomedicalprogram to treat children with autism, as they struggle to identify human emotions and distinguish between basic emotions such as anger, fear, surprise, happiness, sadness, and disgust. © 2023 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of PPG Signal Capturing Using Piezoelectric, Photosensor, and Earlobe Devices 2

Comparative Analysis of PPG Signal Capturing Using Piezoelec...

引用

2nd Jordanian International biomedical engineering Conference, JIBEC 2024

作者： Al-Fahoum, Amjed Al Omari, Ghadeer Yarmouk University Hijjawi Faculty for Engineering Technology Biomedical Systems and Informatics Engineering Dept Irbid Jordan

ISBN: (纸本)9798331539542

This paper provides an in-depth analysis of the use of three different photoplethysmography (PPG) sensors;piezoelectric, photosensor, and earlobe device to capture PPG signals from normal subjects. This study uses bispectrum analysis to provide insight into the time characteristics, frequency characteristics, time-frequency distributions, and frequency-frequency distributions at Yarmouk University Labs. The results provide information on how well each type of sensor performs and whether it is appropriate for use in clinical and research settings. While the photosensor and earlobe device offered useful advantages in terms of setup and usability, the piezoelectric sensor impressed with its improved signal quality and analytical clarity. © 2024 IEEE.

关键词： Piezoelectricity

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：