检索结果-内蒙古大学图书馆

2024 International Conference on Distributed Systems, computer Networks and Cybersecurity, ICDSCNC 2024

作者： Padmakala, S. Al-Jawahry, Hassan M. Palanivel, R. John, Y.M. Mahaboob Madhavi, Arelli Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Department of Computer Science and Engineering Chennai India College of Technical Engineering The Islamic University Department of Computers Techniques Engineering Najaf Iraq Nitte Meenakshi Institute of Technology Department of Ai & Ds Bengaluru India Mahendra College of Engineering Department of Ece Salem India Gokaraju Rangaraju Institute of Engineering and Technology Department of Ai&ml Hyderabad India

ISBN: (纸本)9798350375442

The Distributed Denial-of-Service (DDoS) attack is a crucial cybersecurity threat for Software-Defined Network (SDN). However, DDoS in SDN severely affect network availability which reduces the classifier performance. Hence, Circle Search Algorithm with Convolutional Neural Network (CSA-CNN) is proposed for detecting DDoS anomaly attacks in SDN. The DDoS anomaly dataset such as CIC-DDoS2019 is preprocessed through label encoding which changes categorical data to arithmetical data types through allocating single numerical labels to every class. Then, CSA is applied for feature selection which helps to efficiently detect malicious traffic patterns by exploring local and global search spaces and improves the detection accuracy. The CNN has ability to detect known and unseen attacks due to handling multidimensional data which increase the security of SDN. The CSA-CNN achieved better performance in terms of 99.97%, 99.95%, 99.94% and 99.98% of precision, sensitivity, f1-score and accuracy for CIC-DDoS2019 dataset when compared to Gated Recurrent Unit (GRU). © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

An Optimization Model for Logistics Services in E-Commerce Market 2

An Optimization Model for Logistics Services in E-Commerce M...

引用

2nd International Conference on Data science and Information System, ICDSIS 2024

作者： Sivaparthipan, C.B. Alabdeli, Haider Harshitha, P. Nagendar, Y. Kulkarni, Girija G. Tagore Institute Of Engineering And Technology Department Of Cse Salem India The Islamic University College Of Technical Engineering Department Of Computers Techniques Engineering Najaf Iraq Nitte Menashaki Institute Of Technology Department Of Ai Ml Bengaluru India Sr University School Of Computer Science And Engineering Telangana Warangal India SacramentoCA United States

ISBN: (纸本)9798350381665

The E-commerce market is the most hype and growth sector in the economic, and many countries showing interest on e-commerce to develop the economy. In e-commerce the logistic is the key factor to consider for the profitable growth so focus on the reverse logistic for efficient distribution and increase profit. The reverse logistic is highlighted in this study for decrease the distribution cost and increases the distribution efficiency for growth of the e-commerce market. The study proposes the Hierarchical Density-Based Spatial Clustering of Application with noise (HDBSCAN) clustering algorithm for analyzing the customer behavior to solve route optimization problem. Then mathematical programming model was built for reducing the damages cost it includes fixed cost, green cost, cargo cost. Thereafter, the genetic algorithm was used to solve problem of the model and achieved 93.50% accuracy. The proposed method results show the promising results in solving the route optimization problem with consideration of the customer priority. Moreover, the propose method is greatly used for enterprises in reverse logistics to minimize the cost and time. © 2024 IEEE.

关键词： Electronic commerce

来源：评论

学校读者我要写书评

暂无评论

Improved AO based Classification Framework for Eye Diseases 2

Improved AO based Classification Framework for Eye Diseases

引用

2nd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2024

作者： Saju, Binju Asha, V. Mathew, Jincy C Sangma, Sengcheng Ghosh, Shouvik Sivaguru, K. Adi Shankara Institute of Engineering & Technology Department of Computer Science - AI Engineering Kerala Kalady India New Horizon College of Engineering Master of Computer Applications Bengaluru India

ISBN: (纸本)9798350327533

A sensory organ that reacts to visible light, the human eye is a component of the sensory nervous system. A new approach is needed since, although physical detection of the eye condition is still a possibility, it is challenging and time-consuming. The study recommends a hybrid paradigm to classify various eye illnesses. Prior to further processing, pictures are first reduced in size, made grayscale, and noise-free using a combination of the Weiner and Median filters. Histogram equalization based on a Gaussian Mixture is also used to enhance pictures. Picture features are recovered with the aid of a thick convolutional neural network. An improved Aquila optimized ResNet101 model is used for classification. The effectiveness of the models is contrasted with that of related studies in the literature. A F1 score of 98.18%, accuracy of 99.2%, sensitivity of 98.9%, specificity of 98.91%, and precision of 98% were attained by the suggested model. © 2024 IEEE.

关键词： DCNN Diabetic retinopathy Gaussian Mixture IAO ResNet

来源：评论

学校读者我要写书评

暂无评论

EVA2.0:Investigating Open-domain Chinese Dialogue Systems with Large-scale Pre-training

引用

Machine Intelligence Research 2023年第2期20卷 207-219页

作者： Yuxian Gu Jiaxin Wen Hao Sun Yi Song Pei Ke Chujie Zheng Zheng Zhang Jianzhu Yao Lei Liu Xiaoyan Zhu Minlie Huang The Conversational AI Group Tsinghua UniversityBeijing 100084China Department of Computer Science and Technology Tsinghua UniversityBeijing 100084China Department of Electrical Engineering and Computer Science York UniversityToronto M3J1P3Canada

Large-scale pre-training has shown remarkable performance in building open-domain dialogue ***,previous works mainly focus on showing and evaluating the conversational performance of the released dialogue model,ignoring the discussion of some key factors towards a powerful human-like chatbot,especially in Chinese *** this paper,we conduct extensive experiments to investigate these under-explored factors,including data quality control,model architecture designs,training approaches,and decoding *** propose EVA2.0,a large-scale pre-trained open-domain Chinese dialogue model with 2.8 billion parameters,and will make our models and codes publicly *** and human evaluations show that EVA2.0 significantly outperforms other open-source *** also discuss the limitations of this work by presenting some failure cases and pose some future research directions on large-scale Chinese open-domain dialogue systems.

关键词： Natural language processing deep learning(DL) large-scale pre-training dialogue systems Chinese open-domain conversational model

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Deep Learning Models for Guava Leaf Disease Detection 3

A Comparative Study of Deep Learning Models for Guava Leaf D...

引用

3rd International Conference on Advances in Electrical, Computing, Communication and Sustainable Technologies, ICAECT 2023

作者： Thangaraj, Rajasekaran Mohan, M. Moulik, M. Logeshwari, A. Loganathan, T. Koushika, P. Centre for IoT and AI Department of Computer Science and Engineering KPR Institute of Engineering and Technology Coimbatore India KPR Institute of Engineering and Technology Department of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9781665494007

Plant diseases are regarded as one of the major variables affecting food production and reducing production losses. Early identification and disease diagnosis of fruit crops are essential for the food industry to increase production. The development of the healthy fruit sector is highly dependent on plant diseases. Guava fruit is a good source of fiber, calcium, pectins, and vitamin C. Guava disease has become a major issue for guava production, which has a negative impact on farmers' socioeconomic growth. Infections that harm guava plants and fruits pose the greatest obstacles, although they can be avoided by early identification. Deep learning has recently been widely used to automatically identify a variety of diseases that cannot be seen with the human eye. In this study, convolution neural models are suggested to use leaf images to detect guava disease. The presented models can be used to categorize the main guava leaf diseases, including Canker, Dot, Healthy, Mummification and Rust. The kaggle dataset is used to gather images of guava with the disease Canker, Dot, Healthy, Mummification and Rust. In our work, CNN models like DenseNet121, DenseNet169, InceptionV3, and Xception are used to categorize the diseases that affect guava leaves. The experimental findings indicate that, with an accuracy of 96.12%, the DenseNet169 model outperformed other models. When the model's effectiveness is assessed using performance metrics like precision, recall, and F1 score, the results demonstrate that DenseNet169 gives excellent results. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Competition on robust deep learning

引用

National science Review 2023年第6期10卷 13-15页

作者： Yinpeng Dong Chang Liu Wenzhao Xiang Hang Su Jun Zhu Department of Computer Science and Technology Institute for AI Tsinghua-Bosch Joint ML Center THBI Lab BNRist Center Tsinghua University Institute of Image Communication and Networks Engineering in the Department of Electronic Engineering (EE) Shanghai Jiao Tong University Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Peng Cheng Laboratory Pazhou Laboratory (Huangpu)

PROBLEM In recent years,the rapid development of artificial intelligence (ai) technology,especially machine learning and deep learning, is profoundly changing human production and *** various fields,such as robotics,face recognition,autonomous driving and healthcare,ai is playing an important ***,although ai is promoting the technological revolution and industrial progress,its security risks are often *** studies have found that the wellperforming deep learning models are extremely vulnerable to adversarial examples [1-3].The adversarial examples are crafted by applying small,humanimperceptible perturbations to natural examples,but can mislead deep learning models to make wrong *** vulnerability of deep learning models to adversarial examples can raise security and safety threats to various realworld applications.

关键词： robustness adversarial example adversarial training deep learning

来源：评论

学校读者我要写书评

暂无评论

Prediction of River Water Quality Index and Uncertainty Analysis using Machine Learning Techniques 1

Prediction of River Water Quality Index and Uncertainty Anal...

引用

1st International Conference on Software, Systems and Information Technology, SSITCON 2024

作者： Alabdeli, Haider Pareek, Piyush Kumar Shivaraj, Shruti Rupavath, Rana Veer Samara Sihman Brahmatej Das, Abhijeet The Islamic University of Al Diwaniyah Department of Computers Techniques Engineering Al Diwaniyah Iraq Nitte Meenakshi Institute of Technology Department of Ai and Ml Bengaluru India Department of Civil Engineering Raichur India Indiana Wesleyan University Department of Computer Science MarionIN United States Department of Civil Engineering Odisha Bhubaneswar India

ISBN: (纸本)9798350352931

The increasing demand for clean water in river systems drives the development of new models for water quality prediction. The problem statement is the need for accurate and reliable prediction of water quality indices in various river basins using machine learning techniques. Through the integration of diverse methodologies in the proposed approach aims to overcome limitations associated with conventional methods and emerging in water quality concerns. The dataset used in Water Quality Prediction (WQP) in the river dataset was used to predict the water quality index. The proposed method in this paper consists of preprocessing, data standardization, and data splitting with the parameter and calculating the WQI. The combined machine learning algorithms include Random Forest (RF), Extreme Gradient Boosting (XGB), and K-Nearest Neighbor (KNN). The numerical validation of this paper is an MSE of 0.03, an RMSE of 0.09, an MAE of 0.02, and R 2~ 0.12. The existing methods like Water Quality Management Limitations (WQM-WQI), Sequential Minimal Optimization-Support Vector Machine (SMO-SVM), Principal Quality Analysis (PQA-WQI), and Artificial Neural Network (ANN-WQI) are overcome by the proposed method. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Analysis of Bigmart Outlets sales using Big Data Analytics Method 2

Analysis of Bigmart Outlets sales using Big Data Analytics M...

引用

2nd International Conference on Applied Artificial Intelligence and Computing, ICAaiC 2023

作者： Ramasami, Meaga Varsha Thangaraj, Rajasekaran Kumar, S Manoj Kpr Institute of Engineering and Technology Department of Computer Science and Engineering Coimbatore India Centre for IoT and Ai Kpr Institute of Engineering and Technology Department of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9781665456302

Sales prediction is an important problem for businesses. A sales forecast can guide a company's production, pricing, and promotion strategies, and can help mitigate risks associated with under or overproduction. Traditional methods of sales prediction utilized statistical techniques like regression analysis or time series analysis, but these methods have certain limitations, including the need for large and clean data sets. This research work focuses on exploring the patterns and trends present in a large-scale retail dataset through exploratory data analysis (EDA). The primary objective of this research is to uncover insights that can enhance the understanding of customer behaviour, identify opportunities to improve business processes and inform data-driven decisions. The data consists of daily sales records for 1560 products of ten BigMart Outlets. This study explores several preprocessing steps, such as handling missing values and outliers, scaling and normalization, and feature engineering. The findings also revealed that the top-selling items were bought by a diverse range of customer demographics, indicating that marketing campaigns should target a broader audience. Furthermore, the study identified several unusual transactions that required further investigation. © 2023 IEEE.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

Entropy Guided Extrapolative Decoding to Improve Factuality in Large Language Models 31

Entropy Guided Extrapolative Decoding to Improve Factuality ...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Das, Souvik Jin, Lifeng Song, Linfeng Mi, Haitao Peng, Baolin Yu, Dong Department of Computer Science and Engineering University at Buffalo NY United States Tencent AI Lab BellevueWA United States

ISBN: (纸本)9798891761964

Large language models (LLMs) exhibit impressive natural language capabilities but suffer from hallucination - generating content ungrounded in the realities of training data. Recent work has focused on decoding techniques to improve factuality during inference by leveraging LLMs' hierarchical representation of factual knowledge, manipulating the predicted distributions at inference time. Current state-of-the-art approaches refine decoding by contrasting early-exit distributions from a lower layer with the final layer to exploit information related to factuality within the model forward procedure. However, such methods often assume that the final layer is the most reliable and the lower-layer selection process depends on it. In this work, we first propose the extrapolation of critical token probabilities beyond the last layer for more accurate contrasting. We additionally employ layer-wise entropy-guided lower-layer selection, decoupling the selection process from the final layer. Experiments demonstrate strong performance, surpassing state-of-the-art on multiple different datasets by large margins. The analyzes show that different kinds of prompt respond to different selection strategies. Our source code will be available on GitHub. © 2025 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

The Effect of Programming Language in Software Bug Prediction 3

The Effect of Programming Language in Software Bug Predictio...

引用

3rd International Conference on Communication, Computing and Industry 4.0, C2I4 2022

作者： Jayadev, Gopika Gayathri, Kaparthi Babu, Tina Gandiboina, Harika Sudha, Kavya Venkteswalru, Bondu School of Engineering Dayananda Sagar University Department of AI and ML Bengaluru India School of Engineering Dayananda Sagar University Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9781665474979

Software maintenance is a very important phase in the life cycle of software development. As part of maintenance, we need to identify bugs within the code and fix them for every release. Software bug prediction (SBP) allows us to identify modules in the software that may have the tendency to be buggy. This enables us to perform targeted testing and properly plan maintenance cycles. In most research performed, we observed that dataset of software programs written in C language were used. Each programming language are inherently different and has it's own constructs, practices and nuances. In this research we focus on identifying if there exists a specific classifier that works well for each programming language which in turn is used to analyze the effect of programming language on Software Bug Prediction. Datasets of software written in C, C++ and Java has been collected and the most accurate classifier for each dataset of a programming language has been identified. The ml models used in this paper include Naive Bayes, Decision Tree and Random Forest. © 2022 IEEE.

关键词： Decision Tree Machine Learning Naïve Bayes Random Forest Software Bug Prediction

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：