检索结果-内蒙古大学图书馆

5th International Conference on Control, Communication and Computing, ICCC 2023

作者： Bharath, T.U. Suresh, Subalesh Suresh, Kavya Shaji, Sikha Mathew, Tessy Department of Computer Science and Engineering Trivandrum India

ISBN: (纸本)9798350334128

Nowadays internet anonymity has turned into a head-scratcher issue for most law enforcement agencies. As the technological developments in the digital field are still rising exponentially so are cyber crimes. In cyber forensics, digital profiling of anonymous tweets is done by analysing and comparing the suspect's tweets texting idiolects the anonymous author's writing style. Hence our project proposal is to develop a model using transformers and natural language processing (NLP) techniques for identifying the author of the anonymous chat. © 2023 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

A Specular Reflection Removal Technique in Cervigrams 1

A Specular Reflection Removal Technique in Cervigrams

引用

1st IEEE International Conference on Contemporary Computing and Communications, InC4 2023

作者： Mukku, Lalasa Thomas, Jyothi Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350335774

Cancer detection through medical image segmentation and classification is possible owing to the advancement in image processing techniques. Segmentation and classification tasks carried out to predict and classify diseases need to be dependable and precise. Specular reflections are the high-intensity and low-saturation areas that reflect the light from the probing devices that capture the picture of the organ surface. These areas sometimes mimic the features that are key identifying factors for cancers like acetowhite lesions. This review article examines the various methods proposed for removing specular reflections from medical images, especially those captured by colposcopes. The fundamentals of specular reflection removal and its associated challenges are discussed. The paper reviews several prominent approaches for removal of specular reflections proposes a novel method to remove the specular reflections. The comprehensive review can be a strong foundation for researchers looking to decide on appropriate techniques to employ in their respective research approaches. © 2023 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Ensemble Learning for Enhanced Mango Leaf Disease Classification: A Deep Learning Approach 3

Ensemble Learning for Enhanced Mango Leaf Disease Classifica...

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Neog, Protyush P. Kaur, Navjot Department of Computer Science and Engineering Lovely Professional University Punjab Phagwara India

ISBN: (纸本)9798331527549

Mangoes are highly consumed fruits especially in the tropical as well as subtropical zones of the earth. It is said that nearly half of the earth’s population consumes mangoes in some form or the other either as fresh mangoes or in processed form such as juice, dried mangos, or other cooked dishes. That said, this significant food crop has a number of limitations in its cultivation and the least of these is attack by pests. The agro-ecosystem of mango plantation includes several factors such as soil, insects, diseases, weather and many more which determine the well-being of the mango trees in that plantation. Of all these concerns, leaf diseases turn out to be the most offensive by causing losses in both the quantity and quality of mangoes produced. To mitigate these problems, research has been done and continues to be done towards identifying and classifying the mango leaf diseases with better yields and less losses thanks to processing techniques such as deep learning and image processing. Recently published papers focus on these modern methods and analyze the advantages of their applications for the diagnosis and treatment of mango plants. This paper proposes a novel framework that identifies the diseases in mango leaves. The approach demonstrates an impressive 99.94% testing accuracy employing ensemble learning and transfer learning techniques. It is superior to other popular deep learning-based models that include DenseNet121, ResNet50 and VGG19. The results of the study demonstrate the efficiency of the proposed approach as well as its superiority in important performance metrics such as precision and recall. This evolution provides a viable answer to the very pertinent challenge of disease detection in mango cultivation allowing for better management of crops and hence increased production. © 2025 IEEE.

关键词： Plant diseases

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach for Sentiment Analysis on social media using BERT & ROBERTA Transformer-Based Models 8

A Novel Approach for Sentiment Analysis on social media usin...

引用

8th IEEE International Conference for Convergence in Technology, I2CT 2023

作者： Prasanthi, Kundeti Naga Eswari Madhavi, Rallabandi Sai Sabarinadh, Degala Naga Sravani, Battula Department of Computer Science and Engineering Mylavaram India

ISBN: (纸本)9798350334012

Sentiment analysis on social media platforms has gained immense popularity in recent years due to its ability to analyze and classify users' emotions and opinions on different topics. This paper proposes a sentiment analysis model for Twitter that utilizes two powerful transformer models BERT and ROBERTA, to classify tweets based on their sentiment. The use of BERT and ROBERTA transformers offers several advantages over traditional sentiment analysis models. These transformers can capture contextual information and understand the relationships between words in a sentence, making them well-suited for the nuanced language used in social media platforms like Twitter. To train the model, transfer learning is employed, allowing the transformers to learn from a vast dataset of tweets before fine-tuning on the sentiment analysis task. This approach enables the model to understand the nuances of informal language and slang used in tweets, improving its ability to accurately classify sentiment. Another advantage of the proposed model is its ability to handle the informal language used in tweets. However, BERT and ROBERTA transformers have been trained on a vast corpus of informal language, enabling them to accurately analyze and classify sentiment in tweets. Lastly, the proposed model's scalability and efficiency are also advantages. This model can handle large volumes of data with high efficiency and can be fine-tuned to adapt to new domains with minimal training data, making it highly versatile and applicable in various applications. © 2023 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Brinjal Leaf Diseases Detection Based on Deep Convolutional Neural Network 4

Brinjal Leaf Diseases Detection Based on Deep Convolutional ...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Anu Priya, A. Rajaram, K. Kit - Kalaignarkarunanidhi Institute of Technology Department of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798331523923

Brinjal leaf diseases, such as leaf spot, mosaic virus, and wilt, would critically reduce crop yield quality if the disease is spread during an early stage. Such reasons have made early identification imperative to ensure effective prevention and management. This article, therefore, aims at coming up with an effective technique of identifying brinjal leaf diseases using VGG16 CNN model. Traditional identification methods are based on manually examining plant diseases, an effort known to be highly labour-consuming, subjective, and even unreliable. In addition, most of the available machine learning methods fail in scalability, computational cost, and specific domain problems. However, our technique makes use of the high ability of VGG16 architecture to extract automatically relevant features from leaf images and then classify them with high accuracy. Used Eggplant Leaf Disease Dataset which contains six classes. The central idea of our approach is to employ deep convolutional layers of VGG16 to extract discriminative features from the images followed by classification using fully connected layers and softmax activation. The approach obtains 98.2% accuracy for determining of Brinjalleaf diseases. This work will impact the agricultural sector by means of providing a fast automated solution that gives accurate insights about early detection of leaf disease occurrence, hence reducing losses to crops and enhancing production. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Multi-Valued Connected Consensus: A New Perspective on Crusader Agreement and Adopt-Commit 27

Multi-Valued Connected Consensus: A New Perspective on Crusa...

引用

27th International Conference on Principles of Distributed Systems, OPODIS 2023

作者： Attiya, Hagit Welch, Jennifer L. Department of Computer Science Technion Haifa Israel Department of Computer Science and Engineering Texas A&M University College StationTX United States

ISBN: (纸本)9783959773089

Algorithms to solve fault-tolerant consensus in asynchronous systems often rely on primitives such as crusader agreement, adopt-commit, and graded broadcast, which provide weaker agreement properties than consensus. Although these primitives have a similar flavor, they have been defined and implemented separately in ad hoc ways. We propose a new problem called connected consensus that has as special cases crusader agreement, adopt-commit, and graded broadcast, and generalizes them to handle multi-valued inputs. The generalization is accomplished by relating the problem to approximate agreement on graphs. We present three algorithms for multi-valued connected consensus in asynchronous message-passing systems, one tolerating crash failures and two tolerating malicious (unauthenticated Byzantine) failures. We extend the definition of binding, a desirable property recently identified as supporting binary consensus algorithms that are correct against adaptive adversaries, to the multivalued input case and show that all our algorithms satisfy the property. Our crash-resilient algorithm has failure-resilience and time complexity that we show are optimal. When restricted to the case of binary inputs, the algorithm has improved time complexity over prior algorithms. Our two algorithms for malicious failures trade off failure resilience and time complexity. The first algorithm has time complexity that we prove is optimal but worse failure-resilience, while the second has failure-resilience that we prove is optimal but worse time complexity. When restricted to the case of binary inputs, the time complexity (as well as resilience) of the second algorithm matches that of prior algorithms. The contributions of the paper are first, a deeper insight into the connections between primitives commonly used to solve the fundamental problem of fault-tolerant consensus, and second, implementations of these primitives that can contribute to improved consensus algorithms. © Hagit Attiya and

关键词： Computational complexity

来源：评论

学校读者我要写书评

暂无评论

Trusting Classifiers with Interpretable Machine Learning Based Feature Selection Backpropagation 14

Trusting Classifiers with Interpretable Machine Learning Bas...

引用

2024 IEEE 14th Annual Computing and Communication Workshop and Conference, CCWC 2024

作者： Das, Saikat Das, Raktim Ranjan Sheldon, Frederick T. Shiva, Sajjan Utah Valley University Department of Computer Scinece OremUT United States Stamford University Department of Computer Science and Engineering Bangladesh University of Idaho Department of Computer Science MoscowID United States The University of Memphis Department of Computer Science MemphisTN United States

ISBN: (纸本)9798350360134

In a machine learning classification problem, feature selection is a required pre-processing phase which identifies important and relevant features from the dataset to potentially reduce the computational complexity and improves the overall classification performances. Feature reduction mechanisms, such as Information Gain, Gain Ratio, Chi-squared, ReliefF, Deep Learning, etc. along with domain knowledge are used to find the appropriate features from a dataset. In this paper, we propose a novel feature selection process based on interpretable machine learning technique (IMLFS) to find the optimal relevant features in detecting DDoS cyber-attacks. Based on the effectiveness of critical features, this technique is also used to explain a detected DDoS attack. These relevant features are used in the feature selection phase to retrain the model for better accuracy. The benchmark dataset, NSL-KDD is used to evaluate the proposed approach. Moreover, using the extracted features obtained from this dataset, we investigated our recently developed ensemble supervised framework. This investigation confirms the efficacy of the IMLFS approach by producing both higher detection accuracy and lower false positive alarms. A significant improved accuracy and model training times compared to earlier studies that compared various IML methods are reported here. © 2024 IEEE.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Tianshu: Towards Accurate Measuring, Modeling and Simulation of Deep Neural Networks 36

Tianshu: Towards Accurate Measuring, Modeling and Simulation...

引用

36th European Modeling and Simulation Symposium, EMSS 2024, Held at the 21st International Multidisciplinary Modeling and Simulation Multiconference, I3M 2024

作者： Huang, Hongming Xu, Hong Guan, Nan Department of Computer Science City Univ of Hong Kong Hong Kong Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong

ISBN: (纸本)9791281988026

To help train DNN models more efficiently, researchers have developed a series of new computation devices and parallel training strategies. Choosing which device and strategy to use among those vast candidates is challenging for developers. Simulation is an effective solution to this question since it does not need to deploy models with different settings practically. However, most existing works still require users to measure models on the target hardware first, which cannot help users choose the proper hardware in advance. This paper presents Tianshu, which adopts the ahead-of-time idea to solve this problem. Tianshu first designs an accurate measuring tool to measure the operation's time-use and store the result in a database, which can be shared among the community. For uncovered cases, Tianshu designs an automatic mechanism to train neural network models that can estimate their execution time. Therefore, Tianshu can support simulation without a target hardware. Finally, Tianshu leverages a discrete event simulator to simulate the DNN model's execution. Evaluation on Azure clusters with 8x V100 GPUs shows that Tianshu achieves 93% average accuracy for six well-known DNN models. Tianshu's operation estimator also achieves 96% average accuracy on 9 typical operations and outperforms existing works. © 2024 The Authors.

关键词： Digital elevation model

来源：评论

学校读者我要写书评

暂无评论

A mathematical multi-objective optimization model and metaheuristic algorithm for effective advertising in the social internet of things

引用

Neural Computing and Applications 2025年第6期37卷 4797-4821页

作者： Molaei, Reza Rahsepar Fard, Kheirollah Bouyer, Asgarali Department of Computer Engineering and Information Technology University of Qom Qom Iran Department of Software Engineering Azarbaijan Shahid Madani University Tabriz Iran Department of Software Engineering Faculty of Engineering and Natural Science Istinye University Istanbul Turkey

The integration of social networks with the Internet of Things (IoT) has been explored in recent research, giving rise to the Social Internet of Things (SIoT). One promising application of SIoT is viral marketing, which plays a critical role in modern advertising. However, current solutions proposed for viral marketing are often impractical in real-world scenarios, and there has been limited investigation into viral marketing within the context of SIoT. To address this issue, we present a multi-objective integer linear programming model named ILP-ASoT that facilitates advertising through SIoT. Our approach introduces two realistic parameters: the node sociality rate and the node appropriateness rate as an advertising destination. By balancing the cost of selecting a seed set with the number of users who receive the advertisement, our model offers an appropriate trade-off. Since this is proven as an NP-hard problem, A PSO-based metaheuristic algorithm is proposed to provide near-optimal solutions for advertising in SIoT, called PSO-ASoT. Through simulations, we show that our PSO-ASoT algorithm outperforms state-of-the-art algorithms in several metrics, such as influence spread, advertising cost, and duplicated advertising rate. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving Social Network Clustering Using Differential Privacy

Privacy-Preserving Social Network Clustering Using Different...

引用

2024 International Conference on Smart Systems for Electrical, Electronics, Communication and computer engineering, ICSSEEC 2024

作者： Sathiyapriya, K. Aravindhan, R. Kavin Kireshvanth, B. Ranganathan, Yadav Hardik, P. PSG College of Technology Department of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350378177

In the contemporary landscape of online social networks, preserving users' privacy while applying clustering techniques is a pivotal concern. This paper explores the integration of differential privacy into social network clustering to strike a balance between privacy and clustering effectiveness. The principal objective is to safeguard users' personal information, and the study meticulously examines the trade-offs inherent in differential privacy parameters and their influence on clustering performance. This paper provides a comprehensive insight into the nuanced interplay between user privacy, data utility, and clustering effectiveness within the distinctive dynamics of social networks, offering a promising solution for the field. © 2024 IEEE.

关键词： Differential privacy

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：