检索结果-内蒙古大学图书馆

4th International Conference on Emerging Trends in Networks and computer Communications, ETNCC 2024

作者： Baber, Ahmed Ahmed, Faizan Rehman, Attique Ur Javaid, Sabeen Alshammeri, Menwa Mir, Azka Kumar, Deepak University of Sialkot Department of Software Engineering Sialkot Pakistan College of Computer and Information Sciences Al Jouf University Department of Computer Science Saudi Arabia Lovely Professional University Division of Research and Development Phagwara144411 India KKR and KSR institute of technology and sciences Andhra Pradesh Guntur India

ISBN: (纸本)9798350353266

Heart failure occurs when the heart's lower cham-bers (ventricles) weaken and can't pump blood effectively. The heart contains 2 ventricles that are left and right. When left ventricular failure occurs, it causes shortness of breath and fatigue, and when right ventricular failure occurs, it causes peripheral and abdominal fluid accumulation. Heart failure is a disorder in breathing and oxygen supply to the whole body. As we know, Heart is responsible for circulating blood all over the body parts. When it stops pumping, blood can no longer circulate effectively causing fluid to build up in the lungs causing difficulty in breathing and in the legs, causing swelling. The fluid buildup can cause shortness of breath and swelling of the legs and feet. As a result, fluctuation in breathing takes place and, in the end, the patient dies. This study investigates the use of machine learning tools, like k-Nearest Neighbors, Decision Trees, Naïve Bayes, and Random Forests, to identify heart failure. We are proposing a model for Heart Failure Prediction using a machine learning algorithm and a dataset to determine the performance in terms of accuracy. As a result, the Random Forest classifier along with the SMOTE operator provides the highest accuracy of 91.12%, precision of 87.88%, recall of 95.39%, and F1 measure of 91.48% among the models considered. This research is a very important contribution to healthcare for effective predictions of this disease, as the number of patients is increasing day by day. The results hold significance for future modifications too in medical diagnostics and helping material for more accurate detection methodologies. © 2024 IEEE.

关键词： Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

Efficient Models for Detecting Monkeypox using Skin Lesion Images 3

Efficient Models for Detecting Monkeypox using Skin Lesion I...

引用

3rd International Conference on Innovative Mechanisms for Industry Applications, ICIMIA 2023

作者： Sunda, Neelam Sharma, Divya Battu, Sujith Banoth, Rewanth Nayak Rahul Monika Kanoria PG Mahila Mahavidyalaya Department of Computer Science Jaipur India Kanoria PG Mahila Mahavidhyalaya Department of Computer Science jaipur India Delhi Technological University Dept. of Software Engineering New Delhi India Delhi Technological University Department of Applied Physics New Delhi India University of Delhi Shaheed Rajguru College of Applied Sciences for Women Department of Computer Science India

ISBN: (纸本)9798350343632

Monkeypox is predicted to be the next pandemic and is spreading over African countries like water under a mat. The study basically investigates three deep learning imaging models for the identification of monkeypox from skin lesion photos from the MSID dataset. The motto is to define a computer-based technique to identify monkeypox from just its image, making it cheaper and faster with accurate results. The study achieved the highest accuracy of 99.37% as compared to previous works related to Resnet 50. The limits and complexity of the procedures in real-world situations are also clearly addressed. © 2023 IEEE.

关键词： Convolutional Neural Network Image preprocessing Monkeypox Performance Evaluation Metrics Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Context aware facial expression recognition with deep learning architectures

Context aware facial expression recognition with deep learni...

引用

International Conference on Energy, Power, Environment, Control and Computing (ICEPECC 2025)

作者： Nudrat Bano Muhammad Asif Muhammad Azam Zia Hafiz Muhammad Bilal Department of Computer Science University of Agriculture Faisalabad Faisalabad Pakistan Department of Computer and Software Engineering Information Technology University (ITU) Punjab Pakistan

ISBN: (数字)9781837243150

Facial expression recognition (FER) plays a pivotal role in applications such as mental health diagnosis, security, marketing, human-robot interaction, healthcare, education, and gaming. However, challenges like varied facial poses, uneven lighting, and the presence of facial accessories often hinder accurate detection. Traditional methods frequently struggle with effectiv e feature extraction and classification. To address these limitations, this study proposes a robust facial expression recognition architecture based on Convolutional Neural Networks (CNNs) coupled with advanced preprocessing techniques. The model effectively mitigates issues such as lighting variations and class imbalances while achieving enhanced recognition accuracy. A comprehensive evaluation using k-fold cross-validation was conducted on the CK+ dataset, renowned for its high-quality labeled images of primary emotions. The proposed model achieved an accuracy of 96%, significantly outperforming established benchmarks, including VGG-19 (90%), ResNet50 (92%), and MobileNet (94%). These results underscore the efficacy of the CNN-based approach in advancing FER accuracy. Future work will focus on extending this research to real-time facial expression detection, leveraging transfer learning to adapt the model to diverse datasets, and integrating emotio n recognition with multimodal data such as speech and EEG signals to broaden its applicability across industries.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MobileNetV3 Layer Sensitivity and Sparsity

MobileNetV3 Layer Sensitivity and Sparsity

引用

IEEE/ACM International Workshop on software engineering Research & Practices for the Internet of Things (SERP4IoT)

作者： Belal Nwiran Adam Krzyzak Department of Computer Science and Software Engineering Concordia University Montréal Québec Canada

ISBN: (数字)9798400705786

ISBN: (纸本)9798350352542

State-of-the-art Convolution Neural Networks (CNNs) have hun-dreds of millions of parameters and require billions of operations. Deploying such CNNs in resource-constrained environments, such as IoT devices, can be challenging. To tackle this issue, a range of methods have been explored; including compression approaches like pruning, automation like network architecture search, and efficient architectures like separable depthwise convolution. In this work, we study the sensitivity of the MobileNetV3 layers, defined as a layer's impact on a model accuracy, and calculate the maxi-mum sparsity that its layers can have with minimal accuracy loss compared to the unpruned model.

关键词： Accuracy Sensitivity Automation Convolution Neural networks Network architecture Internet of Things

来源：评论

学校读者我要写书评

暂无评论

HVAdam: A Full-Dimension Adaptive Optimizer 39

HVAdam: A Full-Dimension Adaptive Optimizer

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Zhang, Yiheng Wu, Shaowu Xu, Yuanzhuo Wu, Jiajun Xu, Shang Drew, Steve Niu, Xiaoguang School of Computer Science Wuhan University China Department of Electrical and Software Engineering University of Calgary Canada Department of Computer Science University College London United Kingdom

ISBN: (纸本)157735897X

Adaptive optimizers such as Adam and RMSProp have gained attraction in complex neural networks, including generative adversarial networks (GANs) and Transformers, thanks to their stable performance and fast convergence compared to non-adaptive optimizers. A frequently overlooked limitation of adaptive optimizers is that adjusting the learning rate of each dimension individually would ignore the knowledge of the whole loss landscape, resulting in slow updates of parameters, invalidating the learning rate adjustment strategy and eventually leading to widespread insufficient convergence of parameters. In this paper, we propose HVAdam, a novel optimizer that associates all dimensions of the parameters to find a new parameter update direction, leading to a refined parameter update strategy for an increased convergence rate. We validated HVAdam in extensive experiments, showing its faster convergence, higher accuracy, and more stable performance on image classification, image generation, and natural language processing tasks. Particularly, HVAdam achieves a significant improvement on GANs compared with other state-of-the-art methods, especially in Wasserstein-GAN (WGAN) and its improved version with gradient penalty (WGAN-GP). Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

American Sign Language Recognition Based on Machine Learning and Neural Network 2

American Sign Language Recognition Based on Machine Learning...

引用

2nd International Conference on Machine Learning and Intelligent Systems engineering, MLISE 2022

作者： Li, Lanxi Liu, Da Shen, Chenlin Sun, Jing The Ohio State University Computer Science And Engineering Columbus43201 United States Sichuan University Department Of Computer Science Chengdu610207 China Jilin University Faculty Of Software Engineering Changchun130012 China Institute Of Information And Software Engineering University Of Electronic Science And Technology Of China Chengdu610066 China

ISBN: (数字)9781665492461

ISBN: (纸本)9781665492461

Numerous disabilities such as deaf and mute are suffered from not being capable of communicating with normal people, it is necessary to find a way to solve this problem. A feasible method is Sign Language Recognition (SLR) which is a sort of pattern recognition technique. In this paper, machine learning and deep learning methods are applied to recognize and classify American Sign Language (ASL), and only 24 English letters are classified because letter J and Z require fingers to move. First, Principal Component Analysis (PCA) and manifold algorithms are used to do dimension reduction to accelerate the training of machine learning and visualize it. Second, various machine learning methods such as Random Forest Classification (RFC), K-Nearest Neighbor (KNN), Gaussian Naïve Bayes (GNB), Support Vector Machine (SVM), and Stochastic Gradient Descent (SGD) are applied to classify the pattern. Since the SVM algorithm has several hyperparameters, this study uses the Grid Search method to find the best combination of hyperparameter which lead to predicting more accurately. It is found that different dimensionality reduction algorithms have unequal effects on the accuracy of each prediction model, and it can be concluded that the manifold algorithm is the best dimension reduction algorithm only for KNN but not for other prediction models, and PCA is much more feasible than KNN applied in such machine learning algorithms except KNN. Two deep learning algorithms such as Convolutional Neural Networks (CNN) and Deep Neural Networks (DNN) are also used in classification and their accuracy is highest among such algorithms mentioned above. © 2022 IEEE.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

A Multi-Task and Multi-Label Classification Model for Implicit Discourse Relation Recognition

arXiv

引用

arXiv 2024年

作者： Costa, Nelson Filipe Kosseim, Leila Laboratory Department of Computer Science and Software Engineering Concordia University MontréalQC Canada

We address the inherent ambiguity in Implicit Discourse Relation Recognition (IDRR) by introducing a novel multi-task classification model capable of learning both multi-label and single-label representations of discourse relations. Our model is trained exclusively on the DiscoGeM corpus and evaluated both on the DiscoGeM and the PDTB 3.0 corpus. We establish the first benchmark on multi-label IDRR classification and achieve SOTA results on single-label IDRR classification using the DiscoGeM corpus. Finally, we present the first evaluation on the potential of transfer learning between the DiscoGeM and the PDTB 3.0 corpus on single-label IDRR classification. © 2024, CC BY.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Explainability-based Trust Algorithm for electricity price forecasting models

引用

Energy and AI 2023年第4期14卷 141-158页

作者： Leena Heistrene Ram Machlev Michael Perl Juri Belikov Dmitry Baimel Kfir Levy Shie Mannor Yoash Levron Electrical Engineering Department School of TechnologyPandit Deendayal Energy UniversityGandhinagarGujarat382007India The Andrew and Erna Viterbi Faculty of Electrical&Computer Engineering Technion-Israel Institute of TechnologyHaifa3200003Israel Department of Software Science Tallinn University of TechnologyAkadeemia tee 15ATallinn12618Estonia Electrical&Electronics Engineering Department Sami Shamoon College of EngineeringBeer-Sheva84100Israel

Advanced machine learning(ML)algorithms have outperformed traditional approaches in various forecasting applications,especially electricity price forecasting(EPF).However,the prediction accuracy of ML reduces substantially if the input data is not similar to the ones seen by the model during *** is often observed in EPF problems when market dynamics change owing to a rise in fuel prices,an increase in renewable penetration,a change in operational policies,*** the dip in model accuracy for unseen data is a cause for concern,what is more,challenging is not knowing when the ML model would respond in such a *** uncertainty makes the power market participants,like bidding agents and retailers,vulnerable to substantial financial loss caused by the prediction errors of EPF ***,it becomes essential to identify whether or not the model prediction at a given instance is *** this light,this paper proposes a trust algorithm for EPF users based on explainable artificial intelligence *** suggested algorithm generates trust scores that reflect the model’s prediction quality for each new *** scores are formulated in two stages:in the first stage,the coarse version of the score is formed using correlations of local and global explanations,and in the second stage,the score is fine-tuned further by the Shapley additive explanations values of different *** score-based explanations are more straightforward than feature-based visual explanations for EPF users like asset managers and traders.A dataset from Italy’s and ERCOT’s electricity market validates the efficacy of the proposed *** show that the algorithm has more than 85%accuracy in identifying good predictions when the data distribution is similar to the training *** the case of distribution shift,the algorithm shows the same accuracy level in identifying bad predictions.

关键词： Electricity price forecasting EPF Explainable AI model XAI SHAP Explainability

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Approach for Network Intrusion Classification

A Deep Learning Approach for Network Intrusion Classificatio...

引用

2024 IEEE Region 10 Symposium, TENSYMP 2024

作者： Bhuiyan, Mahbubul Haq Alam, Khorshed Shahin, Kamrul Islam Farid, Dewan Md. United International University Department of Computer Science and Engineering United City Madani Avenue Badda Dhaka1212 Bangladesh The Maersk Mc-Kinney Moller Institute University of Southern Denmark Software Engineering Campusvej 55 Odense MDK-5230 Denmark

ISBN: (纸本)9798350364866

A Network Intrusion Detection System (NIDS) serves as a sentinel for safeguarding data integrity. It watches over computer networks, looking out for and stopping threats that can sneak past normal defenses like malware and hackers. Deep Learning (DL) techniques offer a promising avenue for analyzing raw network data to uncover subtle patterns indicative of intrusion attempts. In this study, we address a critical research gap by developing a Deep Neural Network (DNN) model tailored for efficient detection of stealthy and polymorphic variants while mitigating false positives. Leveraging the NF-ToN-loT dataset, the proposed model achieves impressive performance metrics on test data, with an accuracy of 0.99, precision of 0.98, recall of 0.99, and F1-score of 0.99. To comprehensively assess the robustness of the proposed model, we use a multi-dataset validation strategy. The model is retrained and evaluated on established benchmark datasets, including NF-BoT-loT, NF-UNSW-NB15, and NF-UNSW-NB15-v2, demonstrating exceptional performance. Furthermore, to ensure the significance of our contribution, we compare our model against previously well-established architectures such as CNN+BiLSTM, DNN, GRU+RNN, and CNN+LSTM. Utilizing the NF-ToN-loT dataset as a common ground, the proposed model demonstrably outperforms these prior models, highlighting its efficacy and advancement in the field. Additionally, we conduct an ablation study to dissect the components of the DNN model, shedding light on their individual contributions towards detecting malware traffic and offering insights for optimizing future NIDS models in the cybersecurity domain. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Fine-Tuning GPT-4o-Mini for Programming Questions Generation

Fine-Tuning GPT-4o-Mini for Programming Questions Generation

引用

International Conference on computer and Applications (ICCA)

作者： Alaa Hesham Abeer Hamdy Department of Software Engineering Faculty of Informatics and Computer Science The British University in Egypt Cairo Egypt

ISBN: (数字)9798350367560

ISBN: (纸本)9798350367577

Creating programming questions that are both meaningful and educationally relevant is a critical task in computer science education. This paper introduces a fine-tuned GPT4o-mini model (C2Q). It is designed to generate meaningful questions by leveraging semantic feature extraction and well- crafted prompts. The approach addresses the limitations of traditional generative models, offering a deeper understanding of programming code and producing questions that are precise, diverse, and relevant to a given code snippets. The proposed framework incorporates essential code elements, such as control structures and method attributes, to generate questions that align with programming concepts. Evaluation metrics used were BLEU, ROUGE-1, and ROUGE-L to evaluate the model's performance. The findings reveal that the model achieves better structural coherence and conceptual relevance while focusing on contextual understanding over exact term matching. This work highlights the potential of the proposed approach to advance teaching and assessment methods in computer science.

关键词： Measurement Codes Computational modeling Semantics Natural language generation Focusing Feature extraction Question generation Prompt engineering Programming profession

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：