检索结果-内蒙古大学图书馆

2023 IEEE Applied Imagery Pattern Recognition Workshop, AIPR 2023

作者： Murugadoss, Bhuvanashree Amudha, J. Sugumaran, Vijayan Amrita Vishwa Vidyapeetham School of Computing Department of Computer Science and Engineering Karnataka Bengaluru India Oakland University Center for Data Science and Big Data Analytics RochesterMI United States Oakland University Department of Decision and Information Sciences RochesterMI United States

ISBN: (纸本)9798350359527

Automated radiotherapy treatment planning aims to improve treatment accuracy and efficiency. However, the prevalent Knowledge-Based Planning (KBP) method faces issues like lengthy manual problem formulation and challenges in accurately modeling human anatomy and processing high-dimensional data. This work focuses on treatment plan optimization and considers deep learning as a potential solution. Deep learning algorithms, by virtue of their ability to learn from large quantities of data and model complex relationships, can automate the formulation of the optimization problem in KBP, saving significant time and effort. However, despite these compelling advantages, it should be noted that the current convolution-based encoder-decoder models used for radiotherapy treatment plan optimization have a limited capability in capturing long-range dependencies between distant voxels. This work aims to introduce 'DE-ConvGraph 3D UNet', a novel deep learning model, to address these limitations and optimize radiotherapy treatment plans for oropharyngeal cancer. The proposed 'DE-ConvGraph 3D UNet' model includes a Graph Convolutional Network (GCN) component to capture long-range dependencies between distant voxels. Furthermore, the dual-encoder structure of the model combines the strengths of GCN and 3D Convolutional U-Net, enabling global relationships and local pattern capturing in a 3D patient volume. Experiments were conducted using the benchmark dataset-OpenKBP-Opt. The proposed model shows improvements in performance in comparison to state-of-The-Art U-Net variants in terms of mean squared voxel-wise error, dose volume histogram points and clinical criteria satisfaction. © 2023 IEEE.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Intent Identification Using Few-Shot and Active Learning with User Feedback 25th

Intent Identification Using Few-Shot and Active Learning wi...

引用

25th International Conference on Web Information Systems engineering, WISE 2024

作者： Yuvaraj, Senthil Ganesan Benatallah, Boualem Motahari-Nezhad, Hamid Reza Rabhi, Fethi School of Computer Science and Engineering University of New South Wales Sydney Australia Insight SFI Research Centre on Data Analytics Dublin City University Dublin Ireland UpBrains AI Inc. RestonVA United States Macquarie University Sydney Australia

ISBN: (纸本)9789819605729

Collaboration tools contain many intents in workplace conversation, and identifying these intents is important to increase workplace productivity. However, labelling these intents for a large collection of conversations is expensive and data availability for new intents is quite limited. The pre-trained models show outstanding results in text classification tasks and large language models have recently produced accurate models with few samples. We explored few-shot learning methods and active learning strategies for this problem. Our proposed method, "SetFit with AL" is a combination of Sentence Transformer Fine-tuning (SetFit) and active learning for intent identification. This method fine-tunes a sentence-transformer model to develop accurate models. The intent classification evaluation dataset was used to evaluate this method. The results show that our proposed method outperforms state-of-the-art large language model GPT-3.5 and is comparable to GPT-4. This method also can utilize user feedback to adapt to new data and develop personalized models. Thus, the contribution of this paper is that fine-grained intents are identified using minimal data and the model is adaptable based on user feedback. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Active learning

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient Multi-Objective Hybrid Flowshop Scheduling Problem with Blocking Constraints 9

Energy-Efficient Multi-Objective Hybrid Flowshop Scheduling ...

引用

9th International Conference on Control, Decision and Information Technologies, CoDIT 2023

作者： Missaoui, Ahmed Ozturk, Cemalettin O'Sullivan, Barry University College Cork Insight Centre for Data Analytics Cork Ireland Munster Technological University Process Energy Transport Engineering Cork Ireland School of Computer Science & It University College Cork Cork Ireland

ISBN: (纸本)9798350311402

The social context in relation to energy policies, energy supply, and sustainability concerns, as well as advances in more energy-efficient technologies is driving a need for a change in the manufacturing industry. In this paper, a hybrid ftowshop production system with blocking constraints is investigated from both sustainability and productivity dimensions. For an efficient solution to this proven NP-hard problem, we implemented a multi-objective iterated greedy algorithm first time to minimize the makespan and total energy consumption simultaneously. We provide small, medium, and large instances to benchmark our approach against non-dominated sorting genetic algorithm-II (NSGA-II) which shows efficiency of the proposed methodology. © 2023 IEEE.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Hybrid Convolutional Neural Networks for Enhanced Detection of Mango Leaf Diseases 6

Hybrid Convolutional Neural Networks for Enhanced Detection ...

引用

6th International Conference on Cybernetics, Cognition and Machine Learning Applications, ICCCMLA 2024

作者： Porna, Shweta Bhattacharjee Kabir, Md. Firoz Rana, Md. Imran Chowdhury Sajol, Md. Saiful Islam Roy, Tonmoy Khan, Mohammad Aman Ullah Adnan, Md. Al Bhavani, Girigula Durga Ahsanullah University of Science and Technology Department of Computer Science and Engineering Dhaka Bangladesh Master's in Information Technology University of the Cumberlands United States Bachelor of Business Administration International American university Los Angeles CA United States Louisiana State University Department of Computer Science and Engineering LA United States Data Analytics & Information Systems Utah State University Logan United States Brac University School of Data and Sciences Department of Computer Science and Engineering Dhaka1212 Bangladesh Noakhali Science And Technology University Bsc in software engineering Bangladesh Andhra Pradesh Amaravati522237 India

ISBN: (纸本)9798331505790

The classification of mango leaf diseases is critical for effective disease management and ensuring high-quality yields in mango cultivation. This paper presents a comprehensive study on using deep learning techniques to classify various mango leaf diseases, leveraging convolutional neural networks (CNNs) and hybrid models. A total of 7,524 images were used in our study. These included 4,000 training samples and 3,524 testing samples. The images were split into eight groups, which were powdery mildew, cutting weevil, anthracnose, bacterial canker, sooty mold, gall midge, healthy, and die back. The suggested method starts with feature extraction using VGG19 and MobileNetB1, then classification using both standalone models (ResNet50V2 + EfficientNetB1 and VGG16 + MobileNetB1). We employed data augmentation techniques like random brightness adjustment, rotation, and flipping to enhance the robustness of the model. We conducted hyperparameter tuning using hyperband and Bayesian optimization to optimize the model's performance. Experimental results demonstrate that the hybrid models achieved superior performance, with ResNet50V2 and EfficientNetB1 attaining a perfect accuracy of 100 % on the test set. These findings highlight the potential of deep learning techniques to improve the accuracy and reliability of mango leaf disease diagnosis, contributing significantly to the advancement of precision agriculture. © 2024 IEEE.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

Graph-Based Visualization & Analysis of Azerbaijani Web

Graph-Based Visualization & Analysis of Azerbaijani Web

引用

International Conference on Application of Information and Communication Technologies (AICT)

作者： Anar Shikhaliyev Abzatdin Adamov Master of Computer Science and Data Analytics ADA University Baku Azerbaijan School of IT & Engineering ADA University Baku Azerbaijan

ISBN: (数字)9798350387537

ISBN: (纸本)9798350387544

Understanding the dynamics of the Azerbaijani internet landscape is crucial for analyzing information dissemination patterns and assessing national cybersecurity resilience. This study employs web crawling techniques and graphical analysis to construct a comprehensive network diagram of local websites. The objective is twofold: first, to catalog and analyze local web entities using a Python-based crawler integrated with databases; second, to visualize the web structure using graph theory and evaluate node importance through ranking algorithms. data extraction from Ministry of Communication & Information Technologies' databases feeds into both Postgres and Neo4j databases, facilitating graph representation where nodes and edges denote websites and their relationships. The results emphasize visualization insights with ongoing analytical implementations for comprehensive web mapping.

关键词： Ecosystems data visualization Strategic planning Information retrieval Graph theory Information and communication technology Visual databases Servers Feeds Resilience

来源：评论

学校读者我要写书评

暂无评论

Received Signal Strength Prediction Using Generative Adversarial Networks for Indoor Localization

Received Signal Strength Prediction Using Generative Adversa...

引用

2023 Photonics and Electromagnetics Research Symposium, PIERS 2023

作者： Wu, Haochang Qin, Hao Ma, Siteng Lang, Hans-Dieter Zhang, Xingqi School of Electrical and Electronic Engineering University College Dublin Dublin Ireland School of Computer Science University College Dublin Insight Centre for Data Analytics Dublin Ireland Eastern Switzerland University of Applied Sciences OST SG Rapperswil Switzerland University of Alberta Department of Electrical and Computer Engineering Edmonton Canada

ISBN: (纸本)9798350312843

The popularity of WiFi networks has led to the adoption of fingerprint-based WiFi localization as one primary method for indoor location tracking. However, this technique requires a significant amount of time and effort to collect data at numerous reference points (RPs) to ensure accuracy. To reduce the cost and improve efficiency, generative models can be used to generate received signal strength (RSS) fingerprints. This paper proposes a Deep Convolutional Generative Adversarial Network (DCGAN) based model for building RSS fingerprint maps that can generate a comprehensive fingerprint database using only the location of a wireless access point. The proposed approach is expected to lower the cost and effort involved in the collection of RSS fingerprints while maintaining a high level of accuracy. © 2023 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing Intrusion Detection Systems Using Ensemble Machine Learning Techniques 5

Enhancing Intrusion Detection Systems Using Ensemble Machine...

引用

5th IEEE International Conference on Electro-Computing Technologies for Humanity, NIGERCON 2024

作者： Oyebade, Isaac Adedoyin Elesemoyo, Isaac Oluwafemi Ebute, Mercy Oka Adeniyi, Abidemi Emmanuel Awotunde, Joseph Bamidele Solomon, Akpan Caleb Imoize, Agbotiname Lucky Odulana, Kehinde Amudat Bowen University Department of Computer Science Iwo Nigeria Elizade University Department of Computer Engineering Ilara-Mokin Nigeria University of New Mexico Department of Accounting Anderson School of Management United States University of Ilorin Department of Computer Science Ilorin Nigeria University of Lagos Department of Electrical and Electronics Engineering Lagos Akoka Nigeria University of Hertfordshire School of Physics Engineering and Computer Science (Data Science and Analytics) United Kingdom

ISBN: (纸本)9798331542559

Intrusion detection systems are an essential part of the current cybersecurity environment, and IDS devices are intended to scan the activity of the network and systems to identify possible improper actions or violations. IDSs work in analyzing the traffic of networks and the traffic of networks and the behavior of systems, distinguishing suspicious information and signs of violation of legal access. This capability is critical for protecting information systems' characteristics, such as integrity, confidentiality, and availability. Useful data was collected from Kaggle data archives, and several base models such as K-Nearest Neighbor, Random Forest, Logistic Regression, and Decision Tree classifier will be used. Their predictions are combined using a Voting Classifier. The models are trained and evaluated based on accuracy, precision, recall, and F1-Score. Results show that the Voting classifier achieved an accuracy of 99.78%, with a precision of 99.67% and recall of 99.92% for intrusion detection. The Logistic Regression and K-Nearest Neighbor models achieved accuracies of 95.37% and 99.52%, respectively, while having a precision of 94.93% and 99.51%, respectively. The Decision Tree and Random Forest models achieved accuracies of 99.76% and 99.86%, respectively, while having a precision of 99.75% and 99.83%, respectively. These findings suggest ensemble techniques significantly enhance intrusion detection, making networks safer. © 2024 IEEE.

关键词： anomaly ensemble intrusion detection voting

来源：评论

学校读者我要写书评

暂无评论

Overview of the shared task on Fake News Detection from Social Media Text 3

Overview of the shared task on Fake News Detection from Soci...

引用

3rd Workshop on Speech and Language Technologies for Dravidian Languages, DravidianLangTech 2023

作者： Subramanian, Malliga Chakravarthi, Bharathi Raja Shanmugavadivel, Kogilavani Pandiyan, Santhiya Kumaresan, Prasanna Kumar Palani, Balasubramanian Singh, Muskaan Raja, Sandhiya Vanaja Mithunajha, S. Kongu Engineering College Tamil Nadu India Insight SFI Research Centre for Data Analytics School of Computer Science University of Galway Ireland Indian Institute of Information Technology Kottayam India Ulster University United Kingdom

ISBN: (纸本)9789544520854

The rapid proliferation of fake news has emerged as a significant challenge to the credibility of online information, largely due to the swift dissemination of content on social media platforms. This article provides a concise summary of the findings of the shared task on"Fake News Detection in Dravidian Languages1 - DravidianLangTech@RANLP 2023". The aim of this shared task is to categorize social media posts as either fake or original, specifically focusing on content in Malayalam. The shared task garnered participation from 8 teams who presented their systems. These systems encompassed a spectrum of methodologies including machine learning techniques and transformer-based models like MuRIL, XLMRoBERTa, and Indic BERT. Notably, the XLMRoBERTa-based model demonstrated exceptional performance, achieving a macro F1-score of 0.90. © DravidianLangTech 2023 - 3rd Workshop on Speech and Language Technologies for Dravidian Languages, associated with 14th International Conference on Recent Advances in Natural Language Processing, RANLP 2023 - Proceedings.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Leveraging Machine Learning to Assess Factors Influencing Undernourishment in Nigeria 1st

Leveraging Machine Learning to Assess Factors Influencing Un...

引用

1st International Conference on Intelligent Systems, Blockchain, and Communication Technologies, ISBCom 2024

作者： Mobark, Nada Elfiky, Noha Ahmedin, Ahmed Ibrahim, Ameera Abdel-Aziz, M. Hamad, Safwat Faculty of Computers and Information South Valley University Qena83523 Egypt Business Analytics and Data Science Department School of Economics and Business Administration Saint Mary’s College of California MoragaCA94575 United States Department of Artificial Intelligence Engineering Faculty of Computer Science and Engineering King Salman International University South Sinai46511 Egypt

ISBN: (纸本)9783031823763

Notwithstanding economic progress, Nigeria continues to countenance significant food security issues. This study investigates the root causes of this problem and attempts to develop predictive models to address hunger in Nigeria. The research covering data from 2000 to 2022, sourced primarily from the World Bank and other institutions. The trend analysis, along with the linear model, indicates that investment in farming is crucial for reducing undernourishment. Additionally, there is a strong relationship between agricultural expenditure, exports, access to electricity, and unemployment in relation to undernourishment. In this paper, a linear model, correlation analysis, ARIMA, and trend analysis are utilized to demonstrate how undernourishment, representing hunger and food insecurity, is influenced by other factors. As a result, it is recommended to maintain the unemployment rate between 3.5% and 3.7%, while ensuring that exceeds 5% of government spending is recommended. In other words, to combat hunger in Nigeria, it is important to focus on investing in agriculture, creating jobs, and improving infrastructure. This aligns with our findings and with another research around the world. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： ARIMA Nigeria predictive model Undernourishment

来源：评论

学校读者我要写书评

暂无评论

AttentionFaultFormer: An attention-enhanced 3D CNN & transformer model for seismic fault detection

引用

Journal of Applied Geophysics 2025年 238卷

作者： Wang, Jing Ma, Siteng Liu, Yue Dong, Ruihai School of Computer Science and Engineering North China Institute of Aerospace Engineering China The Insight Centre for Data Analytics School of Computer Science University College Dublin Dublin Ireland

In seismic exploration, accurately identifying faults is fundamental for interpreting seismic data. Due to the highly sparse distribution of faults in the seismic volume and the heavy reliance on local features to reconstruct fault segmentation masks, predicting faults using 3D Vision Transformers (ViT) remains challenging. We propose a novel attention-enhanced 3D U-shaped CNN and ViT hybrid model, called AttentionFaultFormer, specifically for fault detection tasks. AttentionFaultFormer includes a transformer-based encoder, a residual-based decoder, and attention-enhanced skip connection. The skip connection integrates local feature extraction from convolutional layers with channel and spatial attention mechanisms to enhance the representation of detailed fault features. Furthermore, based on the geometric structure of faults, we designed the Multi-Axis Striped Convolution Attention (MASCA) module and incorporated it into the shallow skip connections to help the model delineate continuous long faults. We applied our model to three field seismic datasets (F3, Kerry3D, and Thebe). Comparative analysis against two CNN models and two ViT models reveals that our model predicts more continuous and interpretable faults. © 2025

关键词： Attention mechanism CNN Fault detection Seismic interpretation Vision transformer

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：