检索结果-内蒙古大学图书馆

12th International Conference on Soft Computing for Problem Solving, SocProS 2023

作者： Din, Nusrat Mohi Ud Assad, Assif Sabha, Saqib Ul Bhat, Muzafar Rasool Department of Computer Science and Engineering Islamic University of Science and Technology Kashmir India Department of Computer Science Islamic University of Science and Technology Kashmir India

ISBN: (纸本)9789819731794

Class-imbalanced datasets pose a significant challenge for classification tasks in supervised learning, as standard classification algorithms are designed under the assumption that the datasets have balanced class distributions. This can lead to biased models that perform poorly on minority classes. To address this challenge, several approaches have been proposed at both the data level and algorithmic level. In this research study, comparative analysis of Deep Reinforcement Learning (DRL) methods and Oversampling techniques (SMOTE, SVM-SMOTE, ADASYN) along with Deep Learning (DL) algorithms have been performed on two benchmark imbalanced datasets—"Breakhis" and stroke prediction datasets. The experimentation has been carried out by taking different imbalanced ratios of 0.05, 0.1, 0.2, and 0.3 on the Breast Cancer training dataset and 0.05 imbalanced ratio on the Brain Stroke dataset. The comparison of DRL and Oversampling methods has been performed, and the results demonstrate that the DRL model outperformed oversampling techniques on all imbalanced ratios of the "Breakhis" dataset. For the Stroke prediction dataset, Oversampling techniques completely failed in classifying the minority class samples. These findings suggest that the Deep Reinforcement Learning algorithm presents itself as a promising alternative for imbalanced dataset classification in the medical domain and could potentially contribute to improving patient outcomes. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

DFNet: Dense fusion convolution neural network for plant leaf disease classification

引用

Agronomy Journal 2024年第3期116卷 826-838页

作者： Faisal, Muhamad Leu, Jenq-Shiou Avian, Cries Prakosa, Setya Widyawan Köppen, Mario Department of Electronic and Computer Engineering (ECE) National Taiwan University of Science and Technology Taipei City Taiwan Department of Computer Science and Systems Engineering (CSSE) Graduate School of Computer Science and Systems Engineering Kyushu Institute of Technology Fukuoka Iizuka-shi Japan

The early identification of plant diseases is crucial for preventing the loss of crop production. Recently, the advancement of deep learning has significantly improved the identification of plant leaf diseases. However, most approaches depend on a single convolutional neural network (CNN) to extract the leaf features, ignoring the opportunity to take full advantage of the feature richness available in the images. This paper explores a novel CNN model with multiple automated feature extractors, namely, dense fusion CNN (DFNet), for classifying plant leaf diseases. DFNet aims to increase the diversity of extracted features in order to improve discrimination. Instead of using a single-CNN model, DFNet relies on a double-pretrained CNN model, MobileNetV2 and NASNetMobile, as the feature extractor. The features extracted from each CNN are fused in the fusion layer using a fully connected network. The proposed method was evaluated using corn (Zea mays L.) and coffee (Coffea canephora) leaf disease datasets and compared to the existing models. The experiment showed that DFNet is superior and consistent to other CNN methods by achieving an accuracy of 97.53% for corn leaf diseases and 94.65% for coffee leaf diseases. © 2023 The Authors. Agronomy Journal © 2023 American Society of Agronomy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Punny_Punctuators@DravidianLangTech-EACL2024: Transformer-based Approach for Detection and Classification of Fake News in Malayalam Social Media Text 4

Punny_Punctuators@DravidianLangTech-EACL2024: Transformer-ba...

引用

4th Workshop on Speech, Vision, and Language Technologies for Dravidian Languages, DravidianLangTech 2024

作者： Tabassum, Nafisa Aodhora, Sumaiya Rahman Akter, Rowshon Hossain, Jawad Ahsan, Shawly Hoque, Mohammed Moshiul Department of Computer Science and Engineering Chittagong University of Engineering and Technology Bangladesh

ISBN: (纸本)9798891760783

The alarming rise of fake news on social media poses a significant threat to public discourse and decision-making. While automatic detection of fake news offers a promising solution, research in low-resource languages like Malayalam often falls behind due to limited data and tools. This paper presents the participation of team Punny_Punctuators in the Fake News Detection in Dravidian Languages shared task at DravidianLangTech@EACL 2024, addressing this gap. The shared task focuses on two subtasks: 1. classifying social media texts as original or fake, and 2. categorizing fake news into 5 categories. We experimented with various machine learning (ML), deep learning (DL) and transformer-based models as well as processing techniques such as transliteration. Malayalam-BERT achieved the best performance on both sub-tasks, which obtained us 2nd place with a macro f1-score of 0.87 for the subtask-1 and 11th place with a macro f1-score of 0.17 for the subtask-2. Our results highlight the potential of transformer models for low-resource languages in fake news detection and pave the way for further research in this crucial area. © 2024 Association for Computational Linguistics.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Effective & Smart Urban Mobility System at Low Cost 2

Effective & Smart Urban Mobility System at Low Cost

引用

2nd International Conference Computational and Characterization Techniques in engineering and sciences, IC3TES 2024

作者： Jyothula, Hari Rao, Y Laxmana Prasad, K. Vara Usha, Chiriki Manikyamba, I Lakshmi Aditya University Department of Computer Science and Engineering Surampalem India Vignan's Institute of Engineering for Women Department of It Visakhapatnam India Avanthi Institute of Engineering & Technology I Department of Computer Science and Engineering India Dadi Institute Of Engineering And Technology Department of Computer Science and Engineering India University College of Engineering Science & Technology Hyderabad Jawaharlal Nehru Technological University Department of Computer Science and Engineering Hyderabad India

ISBN: (纸本)9798350364699

There is no established metric for measuring urban smartness at this time. Various writers use various metrics to assess smart city transportation systems. The assessment indicators for the transport system that were offered in the scholarly works were reviewed, and the most relevant and impactful indicators were chosen. A hierarchical assessment model for smart city transport systems is developed in this paper. There are five categories, or "factors,"that the indications fall into. Several indicators are assigned to each of the categories. This study used the hybrid MCDM (multi-criteria decision-making) method to evaluate urban transport systems and identify which of the given characteristics were most important. Top Priority Sorting based on Ideal Solution Similarity (TOPSIS), COPRAS, and Simple Additive Weighting (SAW) were the multi-criteria assessment methods in use. The importance of the components and indicators was determined using an analytical hierarchy process (AHP), rankings (prioritization), and direct evaluation (experts evaluate each criterion as a percentage;total assessments of all criteria equal 100%). There were two phases to the evaluation and comparison of mobility systems: first, smart mobility systems were evaluated comprehensively according to the integrated importance of the indicators;and second, multi-criteria evaluations were conducted according to the indicators of every factor separately. Based on the amount of intelligence, a top city is determined and rated. Building a hierarchical model for evaluating smart transportation systems is the focus of this paper. © 2024 IEEE.

关键词： Evaluation smart transportation MCDM Smart City Smart Mobility System Urban smartness

来源：评论

学校读者我要写书评

暂无评论

Path Authentication for Multiple Switches within First Communication Packets 6

Path Authentication for Multiple Switches within First Commu...

引用

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

作者： Anna, Koziol Agata Shen, Shan-Hsiang Shen, Chung-An Huang, Chin-Ya National Taiwan University of Science and Technology Department of Computer Science and Information Engineering Taiwan National Taiwan University of Science and Technology Department of Electronic and Computer Engineering Taiwan

ISBN: (纸本)9798350378511

This paper introduces a new approach to switch authentication within a network environment, addressing the challenges associated with multiple switch configurations. The proposed continuous authentication process is seamlessly integrated into the TCP handshake, leveraging public-private key encryption and challenge-based authentication methodologies. This novel solution aims to improve performance of traditional one-to-one authentication methods, both in terms of efficiency and security. The research demonstrates the efficiency gains achieved by the proposed authentication process through a comparative analysis with one-to-one solution based on the same authentication mechanism. The results reveal a significant reduction in authentication time, thanks to link latency reduction. The incorporation of public-private key encryption enhances the security, ensuring protection against unauthorized access and switch spoofing attempts. © 2024 IEEE.

关键词： Authentication Protocol

来源：评论

学校读者我要写书评

暂无评论

Exploring the Impact of Different Similarity Measures on Query-by-Example Spoken Term Detection

引用

SN computer science 2025年第5期6卷 1-10页

作者： Gaonkar, Manisha Naik Thenkanidiyoor, Veena Dileep, A.D. Computer Science and Engineering Department National Institute of Technology Goa Kottamol Plateau Goa Cuncolim 403703 India Computer Science and Engineering Department Indian Institute of Technology Dharwad Karnataka Dharwad India Computer Engineering Department Goa College of Engineering Farmagudi Goa Ponda 403401 India

The growth in Internet audio data has highlighted the need for accurate and efficient search methodologies. In this context, query-by-example spoken term detection (QbE-STD) plays a pivotal role, mainly when dealing with multilingual datasets lacking proper transcription information. Recent advancements in the field include integrating convolutional neural networks (CNN) as classifiers, emphasizing the computation of matching matrices for accurate term detection. This research conducts a comparative analysis of similarity measures for QbE-STD, aiming to highlight the performance differences across different metrics. The results reveal distinctive patterns in accuracy, with kernel-based measures leading the pack. Distance-based measures demonstrate comparable accuracies, albeit slightly lower than other metrics, while DTW yields the lowest accuracy. The implications of these findings extend to optimizing QbE-STD systems, guiding practitioners in selecting suitable similarity measures based on their specific requirements. The study contributes valuable insights to spoken term detection, paving the way for enhanced methodologies in audio search applications. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： CNN Kernel-based matching QbE-STD Similarity measures Spoken term detection

来源：评论

学校读者我要写书评

暂无评论

Emotion identification in human faces through ensemble of deep learning models

引用

Journal of Intelligent and Fuzzy Systems 2023年第6期45卷 9729-9752页

作者： Naveen Kmuar, M. Godfrey Winster, S. Department of Computer Science and Engineering Saveetha Engineering College Thandalam India Department of Computing Technologies Faculty of Engineering and Technology Srm Institute of Science and Technology Tamil Nadu Kattankulathur India

Investigation of human face images forms an important facet in affective analysis. The work, a DL-based ensemble is proposed for this purpose. Seven pre-trained models namely Facenet, Facenet2018, VGG16, Resnet-50, Senet-50, Arcface and Openface that have been developed for face verification have been exploited and customized for emotion identification. To each of these models, each all over interaction with softmax method to classification groups are augmented and entire network is then trained completely for emotion recognition. After training all the models individually, the probabilities for each of the class by each of the model are summed to derive at the final value. The class that holds the highest of this value is finalized as the predicted emotion. Thus, the proposed methodology involves image collection, image pre-processing comprising of contrast enhancement, face detection and extraction, face alignment, image augmentation facilitating rotation, shifting, flipping and zooming transformations and appropriate resizing and rescaling, feature extraction and classification through ensemble of customized afore-mentioned pre-trained convolutional neural networks, evaluation and evolving of best weights for emotion recognition from face images with enhanced accuracy. The proposed methodology is evaluated on the well-established FER-2013 dataset. The methodology achieves a validation accuracy of 74.67% and test accuracy of 76.23%. Further, similar images of another dataset (Face Expression Recogniton dataset) are included for training the models and the impact of extra training is assessed to see if there is improvement in performance. The experiments reveal marked improvement in face emotion identification performance reaching values of 94.98% for both validation and test set of FER-2013 dataset and 94.99% on validation set of Face Expression Recognition dataset. © 2023 - IOS Press. All rights reserved.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Sandalphon@DravidianLangTech-EACL2024: Hate and Offensive Language Detection in Telugu Code-mixed Text using Transliteration-Augmentation 4

Sandalphon@DravidianLangTech-EACL2024: Hate and Offensive La...

引用

4th Workshop on Speech, Vision, and Language Technologies for Dravidian Languages, DravidianLangTech 2024

作者： Tabassum, Nafisa Khan, Mosabbir Hossain Ahsan, Shawly Hossain, Jawad Hoque, Mohammed Moshiul Department of Computer Science and Engineering Chittagong University of Engineering and Technology Bangladesh

ISBN: (纸本)9798891760783

Hate and offensive language in online platforms pose significant challenges, necessitating automatic detection methods. Particularly in the case of codemixed text, which is very common in social media, the complexity of this problem increases due to the cultural nuances of different languages. DravidianLangTechEACL2024 organized a shared task on detecting hate and offensive language for Telugu. To complete this task, this study investigates the effectiveness of transliteration-augmented datasets for Telugu code-mixed text. In this work, we compare the performance of various machine learning (ML), deep learning (DL), and transformer-based models on both original and augmented datasets. Experimental findings demonstrate the superiority of transformer models, particularly Telugu-BERT, achieving the highest f1-score of 0.77 on the augmented dataset, ranking the 1st position in the leader-board. The study highlights the potential of transliteration-augmented datasets in improving model performance and suggests further exploration of diverse transliteration options to address real-world scenarios. © 2024 Association for Computational Linguistics.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Machine Learning and Clinical Insights Analysis of BMI Dataset Predictive Models 4

Machine Learning and Clinical Insights Analysis of BMI Datas...

引用

4th IEEE International Conference on Data engineering and Communication Systems, ICDECS 2024

作者： Kadyan, Laksh Neerugatti, Vikram Taranum, Ayesha Rani, Geetha Somasekar, J. Faculty of Engineering and Technology Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350393354

Machine learning (ML) has developed at a superlative rate, accompanying requests spanning various fields. This research investigates the experience of strength data, exceptionally the request of machine learning (ML) algorithms to a Body Mass Index (BMI) dataset. The basic aim of searching out unwinds the dossier's many linkages and patterns, eventually chief to more thorough information of the variables deciding BMI. The study starts accompanying an initiation to the subject within reach, understood by a thorough study of appropriate work, a complex mechanics division, and an itemized reason of the reached results. However, because of advances in Machine Learning, we immediately have the talent to handle this issue in a more excellent manner. We've built an advance dossier-study system that can think a patient has diabetes, a suggestion of correction, admitting for early mediation. This predicting plan uses dossier analysis methods to extractable intuitions from a big number of diabetes-accompanying facts. Its basic aim is to correctly determine a patient's risk of diabetes. We've working categorization plans to a degree Decision Tree, Artificial Neural Networks (ANN), Naive Bayes, and Support Vector Machine (SVM) algorithms to cultivate the model. These outcomes show the influence of the subsystems in thinking diabetes risk admit a large size of veracity. This predictive finish can create a meaningful dissimilarity in labeling at-risk things early and providing bureaucracy with essential care and counseling before the ailment progresses. In summary, our machine intelligence-located scheme offers a natural still strong solution to call the risk of diabetes in subjects. By controlling the wherewithal of dossier reasoning and categorization algorithms, we can enhance early discovery and deterrent measures for this weighty affliction, eventually reconstructing patient consequences and reducing the burden of BMI-related complications. © 2024 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Document Classification and Data Extraction 3

Document Classification and Data Extraction

引用

3rd IEEE World Conference on Applied Intelligence and Computing, AIC 2024

作者： Khurana, Madhav Chaturvedi, Ravi Prakash Mishra, Annu Gupta, Devika Negi, Ishika Mishra, Ambuj Sharma, Hirdesh Jemtec Department of Computer Science & Engineering Greater Noida India Sharda School of Engineering and Technology Department of Computer Science & Applications Greater Noida India Sharda School of Engineering and Technology Department of Computer Science & Engineering Greater Noida India

ISBN: (纸本)9798350384598

T- Data classification and extraction are fundamental tasks in the field of computer vision and data analysis. This abstract presents an overview of these concepts along with the utilization of Python and OpenCV, a popular computer vision library, in building data extraction tools. Data classification involves organizing data into categories or classes based on certain characteristics or features. It enables efficient data management and analysis by grouping similar data together. In the context of computer vision, data classification often involves categorizing images or videos based on their content, such as identifying objects, scenes, or patterns within them. Data extraction, on the other hand, involves retrieving specific information or features from a dataset. This process is crucial for tasks like data mining, information retrieval, and automated document processing. In computer vision applications, data extraction often entails locating and extracting relevant information from images or videos, such as text, objects, or numerical data. © 2024 IEEE.

关键词： Data assimilation

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：