检索结果-内蒙古大学图书馆

2024 International Research Conference on Smart Computing and systems Engineering, SCSE 2024

作者： Sritharan, Niruthikka Gnanavel, Nishaanthini Inparaj, Prathushan Meedeniya, Dulani Yogarajah, Pratheepan University of Moratuwa Department of Computer Science and Engineering Moratuwa Sri Lanka Ulster University School of Computing Engineering and Intelligent Systems Londonderry United Kingdom

ISBN: (纸本)9798350375688

Cervical cancer, which is ranked fourth among cancers affecting women, is highly treatable when detected early through the pap smear test. Deep Learning (DL) models, particularly Convolutional Neural Networks (CNNs), analyze pap smear images, yet their Black-Box nature raises transparency concerns in medical diagnostics. This paper introduces a solution named EnsembleCAM to enhance interpretability by unifying visual explanations through the combination of diverse Class Activation Maps (CAMs). Using the Herlev Dataset, we employ data pre-processing, data augmentation techniques, develop an XceptionNet based binary classification model with an accuracy of 89% and apply GradCAM, GradCAM++, Score-CAM, Eigen-CAM and LayerCAM on this classifier. Then, the novel EnsembleCAM is constructed taking the median of activation maps from the five individual CAM methods. The analysis of activation maps of each CAM method and EnsembleCAM confirmed that in activation maps of EnsembleCAM, higher activation values were more concentrated around the nucleus which is the most important region in indicating cervical malignancy. The evaluation using pixel flipping performance metric also proved that the EnsembleCAM effectively recognises regions vital to the model's decision-making through its steepest drop in the mean prediction score when the pixels in the region contributing most to the model's decision were flipped. © 2024 IEEE.

关键词： Visualization

来源：评论

学校读者我要写书评

暂无评论

Recurrent neural networks: vanishing and exploding gradients are not the end of the story 38

Recurrent neural networks: vanishing and exploding gradients...

引用

38th Conference on Neural Information Processing systems, NeurIPS 2024

作者： Zucchet, Nicolas Orvieto, Antonio Department of Computer Science ETH Zürich Switzerland ELLIS Institute Tübingen MPI for Intelligent Systems Tübingen AI Center Germany

Recurrent neural networks (RNNs) notoriously struggle to learn long-term memories, primarily due to vanishing and exploding gradients. The recent success of deep state-space models (SSMs), a subclass of RNNs, to overcome such difficulties challenges our theoretical understanding. In this paper, we delve into the optimization challenges of RNNs and discover that, as the memory of a network increases, changes in its parameters result in increasingly large output variations, making gradient-based learning highly sensitive, even without exploding gradients. Our analysis further reveals the importance of the element-wise recurrence design pattern combined with careful parametrizations in mitigating this effect. This feature is present in deep SSMs, as well as in other architectures, such as LSTMs. Overall, our insights provide a new explanation for some of the difficulties in gradient-based learning of RNNs and why some architectures perform better than others. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Interpretable Cervical Cell Classification: A Comparative Analysis 4

Interpretable Cervical Cell Classification: A Comparative An...

引用

4th International Conference on Advanced Research in Computing, ICARC 2024

作者： Gnanavel, Nishaanthini Inparaj, Prathushan Sritharan, Niruthikka Meedeniya, Dulani Yogarajah, Pratheepan University of Moratuwa Department of Computer Science and Engineering Moratuwa Sri Lanka School of Computing Engineering and Intelligent Systems Ulster University Londonderry United Kingdom

ISBN: (纸本)9798350384864

Cervical cancer is a significant global health issue, and traditional screening methods like Pap smears are labor-intensive and may miss some cases. Automation is needed, but it faces challenges in terms of interpretability and data availability. To address this, the paper proposes using Explainable Artificial Intelligence (XAI) techniques like GradCAM, GradCAM++, and LRP to improve the transparency and interpretability of a cervical cell classification model, making it a novel contribution to enhancing the trustworthiness of automated cervical cancer detection. Using the Herlev Dataset, we employ data pre-processing, data augmentation techniques and develop a binary classification model, achieving a 91.94% accuracy with VGG16. The qualitative analysis of XAI methods confirmed that the model relied on nucleus and cytoplasm features, key indicators of malignancy. The least mean image entropy of 2.4849 and steep prediction confidence drop with perturbations quantitatively proved Layer-wise Relevance Propagation (LRP) to be the most effective XAI technique for cervical cell classification. © 2024 IEEE.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Continuous-Time Prediction of Industrial Paste Thickener System With Differential ODE-Net

引用

IEEE/CAA Journal of Automatica Sinica 2022年第4期9卷 686-698页

作者： Zhaolin Yuan Xiaorui Li Di Wu Xiaojuan Ban Nai-Qi Wu Hong-Ning Dai Hao Wang the Beijing Advanced Innovation Center for Materials Genome Engineering Institute of Artificial IntelligenceBeijing Key Laboratory of Knowledge Engineering for Materials ScienceSchool of Computer and Communication EngineeringUniversity of Science and Technology Beijing the Department of ICT and Natural Science Norwegian University of Science and Technology IEEE the Institute of Systems Engineering and Collaborative Laboratory for Intelligent Science and SystemsMacao University of Science and Technology the Department of Computing and Decision Sciences Lingnan University the Department of Computer Science Norwegian University of Science and Technology

It is crucial to predict the outputs of a thickening system,including the underflow concentration(UC)and mud pressure,for optimal control of the *** proliferation of industrial sensors and the availability of thickening-system data make this ***,the unique properties of thickening systems,such as the non-linearities,long-time delays,partially observed data,and continuous time evolution pose challenges on building data-driven predictive *** address the above challenges,we establish an integrated,deep-learning,continuous time network structure that consists of a sequential encoder,a state decoder,and a derivative module to learn the deterministic state space model from thickening *** a case study,we examine our methods with a tailing thickener manufactured by the FLSmidth installed with massive sensors and obtain extensive experimental *** results demonstrate that the proposed continuous-time model with the sequential encoder achieves better prediction performances than the existing discrete-time models and reduces the negative effects from long time delays by extracting features from historical system *** proposed method also demonstrates outstanding performances for both short and long term prediction tasks with the two proposed derivative types.

关键词： Industrial 24 paste thickener ordinary differential equation(ODE)-net recurrent neural network time series prediction

来源：评论

学校读者我要写书评

暂无评论

Counterfactual discriminative micro-expression recognition

引用

Visual Intelligence 2024年第1期2卷 1-10页

作者： Li, Yong Liu, Menglin Lao, Lingjie Wang, Yuanzhi Cui, Zhen Department of Computer Science City University of Hong Kong 999077 Hong Kong School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing 210094 China Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing 210094 China

Micro-expressions are spontaneous, rapid and subtle facial movements that can hardly be suppressed or fabricated. Micro-expression recognition (MER) is one of the most challenging topics in affective computing. It aims to recognize subtle facial movements which are quite difficult for humans to perceive in a fleeting period. Recently, many deep learning-based MER methods have been developed. However, how to effectively capture subtle temporal variations for robust MER still perplexes us. We propose a counterfactual discriminative micro-expression recognition (CoDER) method to effectively learn the slight temporal variations for video-based MER. To explicitly capture the causality from temporal dynamics hidden in the micro-expression (ME) sequence, we propose ME counterfactual reasoning by comparing the effects of the facts w.r.t. original ME sequences and the counterfactuals w.r.t. counterfactually-revised ME sequences, and then perform causality-aware prediction to encourage the model to learn those latent ME temporal cues. Extensive experiments on four widely-used ME databases demonstrate the effectiveness of CoDER, which results in comparable and superior MER performance compared with that of the state-of-the-art methods. The visualization results show that CoDER successfully perceives the meaningful temporal variations in sequential faces. © The Author(s) 2024.

关键词： Affective computing Causal graph Counterfactual reasoning Micro-expression recognition Temporal variation

来源：评论

学校读者我要写书评

暂无评论

A Game-Theoretic Approach to Safe Crowd Evacuation in Emergencies

引用

computers, Materials & Continua 2024年第4期79卷 1631-1657页

作者： Maria Gul Imran Ali Khan Gohar Zaman Atta Rahman Jamaluddin Mir Sardar Asad Ali Biabani May IssaAldossary Mustafa Youldash Ashraf Saadeldeen Maqsood Mahmud Asiya Abdus Salam Dania Alkhulaifi Abdullah AlTurkey31Department of Computer Science COMSATS University IslamabadAbbottabad CampusAbbottabad22010Pakistan Department of Computer Science Abbottabad University of Science and TechnologyAbbottabad22010Pakistan Department of Computer Science College of Computer Science and Information TechnologyImam Abdulrahman Bin Faisal UniversityP.O.Box 1982Dammam31441Saudi Arabia Science and Technology Unit Umm Al-Qura UniversityMakkah21955Saudi Arabia Deanship of Scientific Research Umm Al-Qura UniversityMakkah21955Saudi Arabia Department of Computer Information Systems College of Computer Science and Information TechnologyImam Abdulrahman Bin Faisal UniversityP.O.Box 1982Dammam31441Saudi Arabia Department of Computer Engineering College of Computer Science and Information TechnologyImam Abdulrahman Bin Faisal UniversityP.O.Box 1982Dammam31441Saudi Arabia Department of Computer Science Faculty of Computer Science and Information TechnologyOmdurman Islamic UniversityOmdurman14415Sudan Business Analytic Program Department of Management and MarketingCollege of Business AdministrationUniversity of BahrainSakhir32038Bahrain

Obstacle removal in crowd evacuation is critical to safety and the evacuation system efficiency. Recently, manyresearchers proposed game theoreticmodels to avoid and remove obstacles for crowd evacuation. Game theoreticalmodels aim to study and analyze the strategic behaviors of individuals within a crowd and their interactionsduring the evacuation. Game theoretical models have some limitations in the context of crowd evacuation. Thesemodels consider a group of individuals as homogeneous objects with the same goals, involve complex mathematicalformulation, and cannot model real-world scenarios such as panic, environmental information, crowds that movedynamically, etc. The proposed work presents a game theoretic model integrating an agent-based model to removethe obstacles from exits. The proposed model considered the parameters named: (1) obstacle size, length, andwidth, (2) removal time, (3) evacuation time, (4) crowd density, (5) obstacle identification, and (6) route *** proposed work conducts various experiments considering different conditions, such as obstacle types, obstacleremoval, and several obstacles. Evaluation results show the proposed model’s effectiveness compared with existingliterature in reducing the overall evacuation time, cell selection, and obstacle removal. The study is potentially usefulfor public safety situations such as emergency evacuations during disasters and calamities.

关键词： Safe crowd evacuation public safety emergency transition probability cooperation

来源：评论

学校读者我要写书评

暂无评论

A novel deep learning approach for automated grading of knee osteoarthritis severity

引用

Multimedia Tools and Applications 2024年 1-20页

作者： Kaur, PrabSimran Kohli, Guneet Singh Bedi, Jatin Wasly, Saud Department of Computer Science and Engineering Thapar Institute of Engineering and Technology Punjab Patiala India Electrical and Computer Engineering Department King Abdulaziz University Jeddah22254 Saudi Arabia Center of Excellence in Intelligent Engineering Systems King Abdulaziz University Jeddah22254 Saudi Arabia

Knee Osteoarthritis (OA) is a prevalent musculoskeletal disorder that affects the knee joint that causes pain, stiffness, and reduced mobility. It is also known as "Degenerative Joint Disease" and is caused by the degeneration of cartilage in the knee joint, leading to bone-on-bone contact and further damage. Knee OA is prevalent in the population, affecting around 22% to 39% of people in India, and there is currently no treatment available that can halt the progression of the disease. Therefore, early diagnosis and management of symptoms are essential to reduce its impact on an individual’s quality of life. To address this issue, have introduced a framework that leverages ConvNeXt architecture, a modernization of ResNets (ResNet-50) architecture towards Hierarchical Transformers (Swin Transformers), to provide accurate identification and classification of knee osteoarthritis. The classification of knee osteoarthritis was done using the Kellgren and Lawrence (KL) graded X-ray images. These images of the damaged knees are preprocessed and augmented, creating a scaled, enhanced, and varied version of the features, thus making the data fitter and more significant for classification. The performance estimation of the proposed strategy is conducted on the Osteoarthritis Initiative (OAI), a research project focused on knee osteoarthritis that works in partnership with NIH and other private industries to develop a public domain dataset that can facilitate research and evaluation. It involves training the prepared data using various hyper-tuned versions of ConvNeXt. The different fine-tuned results of the ConvNeXt models on each KL Grade are evaluated against the other state-of-the-art models and vision transformers. The comparative assessment of widely used performance measures shows that the proposed approach outperforms the conventional models by generating the highest score for all the KL grades. Lastly, an approach is employed to statistically confirm the validity of t

关键词： Joints (anatomy)

来源：评论

学校读者我要写书评

暂无评论

Facial Image-Based Autism Detection:A Comparative Study of Deep Neural Network Classifiers

引用

computers, Materials & Continua 2024年第1期78卷 105-126页

作者： Tayyaba Farhat Sheeraz Akram Hatoon SAlSagri Zulfiqar Ali Awais Ahmad Arfan Jaffar Faculty of Computer Science and Information Technology The Superior UniversityLahore54600Pakistan Intelligent Data Visual Computing Research(IDVCR) Faculty of Computer Science and Information TechnologyThe Superior UniversityLahore54600Pakistan Information Systems Department College of Computer and Information SciencesImam Mohammad Ibn Saud Islamic University(IMSIU)Riyadh12571Saudi Arabia School of Computer Science and Electronic Engineering(CSEE) University of EssexWivenhoe ParkColchesterCO43SQUK

Autism Spectrum Disorder(ASD)is a neurodevelopmental condition characterized by significant challenges in social interaction,communication,and repetitive *** and precise ASD detection is crucial,particularly in regions with limited diagnostic resources like *** study aims to conduct an extensive comparative analysis of various machine learning classifiers for ASD detection using facial images to identify an accurate and cost-effective solution tailored to the local *** research involves experimentation with VGG16 and MobileNet models,exploring different batch sizes,optimizers,and learning rate *** addition,the“Orange”machine learning tool is employed to evaluate classifier performance and automated image processing capabilities are utilized within the *** findings unequivocally establish VGG16 as the most effective classifier with a 5-fold cross-validation ***,VGG16,with a batch size of 2 and the Adam optimizer,trained for 100 epochs,achieves a remarkable validation accuracy of 99% and a testing accuracy of 87%.Furthermore,the model achieves an F1 score of 88%,precision of 85%,and recall of 90% on test *** validate the practical applicability of the VGG16 model with 5-fold cross-validation,the study conducts further testing on a dataset sourced fromautism centers in Pakistan,resulting in an accuracy rate of 85%.This reaffirms the model’s suitability for real-world ASD *** research offers valuable insights into classifier performance,emphasizing the potential of machine learning to deliver precise and accessible ASD diagnoses via facial image analysis.

关键词： Autism Autism Spectrum Disorder(ASD) disease segmentation features optimization deep learning models facial images classification

来源：评论

学校读者我要写书评

暂无评论

Examining the impact of attitude, availability, price, and quality of service on broadband Internet customer satisfaction 9

Examining the impact of attitude, availability, price, and q...

引用

9th IEEE International Conference on Computing, Engineering and Design, ICCED 2023

作者： Arin, Ikrar Adinata Murad, Dina Fitria Warnars, Harco Leslie Hendric Spits Meyliana Bina Nusantara University Information System Department School of Information Systems Computer Science Department BINUS Graduate Program Computer Science Jakarta Indonesia Bina Nusantara University Information Systems Department BINUS Online Learning Jakarta Indonesia Bina Nusantara University Computer Science Department BINUS Graduate Program Computer Science Jakarta Indonesia Bina Nusantara University Information System Department School of Information Systems Jakarta Indonesia

ISBN: (纸本)9798350370126

After the COVID-19 pandemic, broadband internet utilization is predicted to continue to grow and experience a significant increase. The pandemic has changed how people work, study, communicate, shop, and carry out many aspects of daily life. Research reported that since 2018, research on broadband internet has continued to increase until now. This quantitative study examines the impact of the four critical variables on the link between attitude, availability, pricing, and quality of service (QoS) on broadband internet customer satisfaction using the Structural Equation Model approach and the Partial Lease Square technique. Three hundred and sixty-one citizen respondents in DKI Jakarta Province were collected using the snowball sampling method facilitated by Google Forms. At the same time, the COVID-19 post-pandemic was still ongoing in Indonesia. Through rigorous statistical analysis, the results show that customer satisfaction with broadband internet services is influenced by all factors, from attitude towards broadband Internet, broadband Internet availability, broadband Internet price, and service quality. The implications of this research are significant for service providers. They provide actionable insights for developing effective strategies to improve customer satisfaction and increase broadband internet subscriptions. © 2023 IEEE.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

Survey semantic Arabic language in deep learning based recommendation system 17

Survey semantic Arabic language in deep learning based recom...

引用

17th International Conference on INnovations in intelligent systems and Applications, INISTA 2023

作者： Kadhem, Rasha Mallat, Souheyl Zrigu, Mounir University of ALQadisiyah Department of Computer Science Iraq Research Laboratory in Algebra Numbers Theory and Intelligent Systems Monastir Tunisia University of Monastir Faculty of Sciences of Monastir Department of Computer Science Tunisia

ISBN: (纸本)9798350338904

Due to problems, Arabic-speaking internet users have surged, although nothing is done on it. It is challenging to develop a repliable recognition system (RS) for cursive languages such as Arabic. Variations in text size, fonts, word semantics, user Arabic region, etc. complicate these issues. Deep learning models can model big datasets and handle them. Good features can be selected and learned consecutively by both CNNs and RNNs. In numerous studies, both of these neural networks have proven to be superior than their counterparts. This is true for text recognition, voice recognition, and several NLP tasks (NLP), but they are not qualified to deal with the semantics of the text, so we decided to find the best DL technique for semantic Arabic language from a lot of research to be a survey to other searchers. Our paper compared different algorithms and their accuracy. © 2023 IEEE.

关键词： Semantics

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：