检索结果-内蒙古大学图书馆

22nd international conference on Hybrid Intelligent Systems, HIS 2022 and the 18th international conference on Information Assurance and Security, IAS 2022

作者： Lakshminarayana Reddy, D. Shoba Bindu, C. Research Scholar Department of Computer Science and Engineering JNTUA Andhra Pradesh Anantapuramu India Department of Computer Science and Engineering JNTUACEA Andhra Pradesh Anantapuramu India

ISBN: (纸本)9783031274084

Valuable information from a corpus for a specific purpose can be obtained by finding, extracting, and processing the text through text mining. A corpus is a group of documents and the documents could be anything from newspaper articles, tweets, or any kind of data that needs to study. For processing and understanding the structure of a corpus, a technique in text mining is Natural Language Processing (NLP). The study of a corpus in different fields like bioinformatics, software engineering, sentiment analysis, Education, and Linguistics (scientific research) is a challenging task as it contains a vast amount of data. Thus for latent data identification, establishing connections between data and text documents needs topic modeling. Evolutions of topic models are analyzed in this paper from 1990 to present. To better understand the topic modeling concept, a detailed evaluation of techniques is discussed in detail. In this study, we looked into highly scientific articles from 2010 to 2022 based on methods used in different areas to discover current trends, research development, and the intellectual structure of topic modeling. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Extraction of key information from Chinese text of gas station safety accident cases 22

Extraction of key information from Chinese text of gas stati...

引用

Proceedings of the 2022 5th international conference on machine learning and Natural Language Processing

作者： Heng Li School of Software and Artificial Intelligence Chongqing Institute of Engineering China

ISBN: (纸本)9781450399067

Keyword matching-based text structuring of gas station safety accident cases can automatically perform keyword extraction and store them in the database, and then the structured data can be subjected to multi-dimensional statistics, visual analysis, knowledge graph management and law mining. 516 cases of gas station safety accidents since 1981, which belong to unstructured electronic text data, were collected in four ways. Through the establishment of a keyword dictionary, 516 case texts were extracted and stored in a structured way using a progressive model of exact matching, phrase matching and intelligent matching+manual verification. The actual evaluation results show that the success rate of exact matching is 30% - 87%, the cumulative success rate of phrase matching is 70% - 100%, the cumulative matching rate of intelligent matching+manual verification is 91% - 100%, the overall matching effect is good, and the method is practical and useful.

关键词： Chinese text of safety accident cases Phrase matching Intelligent matching Exact matching Keyword extraction

来源：评论

学校读者我要写书评

暂无评论

Optimizing Multilingual Sentiment Analysis in Low-Resource Languages with Adaptive Pretraining and Strategic Language Selection

Optimizing Multilingual Sentiment Analysis in Low-Resource L...

引用

Computing and machine Intelligence (ICMI), international conference on

作者： Nilanjana Raychawdhary Amit Das Sutanu Bhattacharya Gerry Dozier Cheryl D. Seals Computer Science & Software Engineering Auburn University Auburn AL USA Computer Science & Computer Information Systems Auburn University at Montgomery Montgomery AL USA

ISBN: (数字)9798350372977

ISBN: (纸本)9798350372984

In the realm of natural language processing (NLP), sentiment analysis has traditionally focused on resource-rich languages like English, often overlooking the linguistic diversity and potential of low-resource languages. This research aims to ad-dress this imbalance by concentrating on multilingual sentiment classification in twelve African languages: Hausa, Yoruba, Igbo, Nigerian Pidgin, Amharic, Algerian Arabic, Moroccan Arabic Darija, Swahili, Kinyarwanda, Twi, Mozambican Portuguese, and Xitsonga. Recognizing the critical lack of comprehensive datasets for these languages, our research not only highlights the need for such resources but also endeavors to fill this gap by assessing current NLP techniques and devising novel methodologies specifically tailored to these linguistically diverse yet under- resourced languages. Central to our study is the development and deployment of a transformer-based language model that is intricately adapted for African languages with limited resources. By refining the XLM-R model on the AfriSenti-SemEval 2023 Shared Task 12 multilingual sentiment classification datasets, we explore the model's efficacy in handling sentiment analysis tasks across these languages. The empirical results demonstrate the model's capability to perform sentiment analysis with considerable accuracy, even in languages that have traditionally been marginalized in the digital sphere due to minimal linguistic resources. This research not only contributes to the field of NLP by extending its reach to less-researched African languages but also underscores the importance of linguistic inclusivity in the development of AI technologies. By successfully navigating the challenges posed by multilingual sentiment classification in low-resource languages, our study takes a significant stride in closing the digital language divide. It emphasizes the potential of NLP to be a tool for cultural and linguistic preservation and highlights the necessity of developing technolog

关键词： Adaptation models Sentiment analysis Analytical models Navigation Transfer learning Refining Linguistics

来源：评论

学校读者我要写书评

暂无评论

Research on Abnormal Network Traffic Detection Method Based on Stacked Capsule Autoencoder 23

Research on Abnormal Network Traffic Detection Method Based ...

引用

Proceedings of the 2023 4th international conference on machine learning and Computer Application

作者： Qinglin Chen Hailati Kezierbieke Yue Wang Yuyuan Chang College of Information Science and Engineering Xinjiang University China School of Software Xinjiang University China

ISBN: (纸本)9798400709449

With the increasing complexity and prevalence of network attacks, abnormal network traffic detection has become a critical task for ensuring network security. Traditional rule-based and feature-based approaches face challenges in handling large-scale and high-dimensional network traffic data. This paper proposes an abnormal network traffic detection model based on stacked capsule autoencoders (SCAE), aiming to improve feature reuse capability and alleviate gradient issues by incorporating dense convolutional blocks. Additionally, a novel random quantization channel attention mechanism is introduced to allow the model to reduce the interference of redundant information and extract more representative features, thereby enhancing its learning effectiveness. This paper also proposes a visualization approach based on feature spatial correlation to transform network traffic into image-like representations. propose. This study conducted an analysis of feature correlations in the CIC-IDS-2018 dataset and transformed them into visualized images. The proposed model, Random Quantization Channel Attention Stacked Capsule Autoencoder (RQCA-SCAE), was trained and tested on these network traffic images. After training, RQCA-SCAE performed multi-class classification on the network traffic images to distinguish between normal and abnormal traffic. Finally, the experimental results were evaluated using accuracy, precision, recall, and F1 score. RQCA-SCAE demonstrates the best performance which achieved an accuracy of 99.34% on the 15-classification task of network traffic in CIC-IDS-2018 dataset. Through experiments, this article has demonstrated the effectiveness and excellent performance of the proposed solution.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Message from the ICBC 2023 General and Technical Program Chairs

2023 IEEE International Conference on Blockchain and Cryptoc...

引用

2023 IEEE international conference on Blockchain and Cryptocurrency, ICBC 2023 2023年

作者： Mnaouer, Adel Ben Stiller, Burkhard Karray, Fakhreddine Bin Zayed, Mohamed Canadian University Dubai United Arab Emirates University of Zurich Switzerland University of Ai Abu Dhabi United Arab Emirates

来源：评论

学校读者我要写书评

暂无评论

Enhancing Content-Based Image Retrieval for Lung Cancer Diagnosis: Leveraging Texture Analysis and Ensemble Models

Enhancing Content-Based Image Retrieval for Lung Cancer Diag...

引用

international conference on Image Information Processing

作者： K A Jayabalaji Bagam Laxmaiah Jayendra Gopal Thatipudi Chandraprabha K Pravin Badhe Allam Balaram Department of Software Systems Sri Krishna Arts and Science College Coimbatore Tamilnadu India Department of CSE CMR Technical Campus Kandlakoya Telangana India Department of Computer Science University of North Texas Denton Texas USA Department of Information Technology Bannari Amman Institute of Technology Sathyamangalam Tamilnadu India Department of Pharmacology Sinhgad College of Pharmacy and Swalife Biotech Pune India Department of Computer Science and Engineering MLR Institute of Technology Hyderabad Telangana India

ISBN: (数字)9798350371406

ISBN: (纸本)9798350371413

In image retrieval systems, many search engines rely on text-based methods, extracting information from descriptions and tags to retrieve relevant images. However, this conventional approach often overlooks the optical or semantic information present in photographs, leading to errors in the retrieved results. To address this issue, it is essential to consider content-based information such as intensities, edges, and pixel values when designing image retrieval systems, especially in domains like medicine. This study focuses on developing a Content-Based Image Retrieval (CBIR) system for the domain of medicine, with a particular emphasis on lung cancer detection. Early identification and treatment of lung cancer are critical for patient outcomes, making suitable Computer-Aided Diagnosis (CAD) systems essential for assisting clinicians. The proposed ensemble model incorporates various feature extraction methods, including image processing techniques and wavelet transform, to harness the valuable information from images. These features are then fed into a deep learning model to assess their effectiveness in image retrieval tasks. By combining machine learning and image processing techniques, this work presents a comprehensive CBIR system capable of efficiently retrieving relevant medical images. Such advancements in image retrieval technology hold significant promise for aiding medical professionals in diagnosing and treating diseases like lung cancer promptly.

关键词： Wavelet transforms Solid modeling Design automation Computational modeling Image retrieval Lung cancer Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Cornucopia : A Framework for Feedback Guided Generation of Binaries 22

Cornucopia : A Framework for Feedback Guided Generation of B...

引用

Proceedings of the 37th IEEE/ACM international conference on Automated software engineering

作者： Vidush Singhal Akul Abhilash Pillai Charitha Saumya Milind Kulkarni Aravind Machiry Electrical and Computer Engineering Purdue University United States of America Electrical and Computer Engineering Purdue University USA

ISBN: (纸本)9781450394758

Binary analysis is an important capability required for many security and software engineering applications. Consequently, there are many binary analysis techniques and tools with varied capabilities. However, testing these tools requires a large, varied binary dataset with corresponding source-level information. In this paper, we present Cornucopia, an architecture agnostic automated framework that can generate a plethora of binaries from corresponding program source by exploiting compiler optimizations and feedback-guided learning. Our evaluation shows that Cornucopia was able to generate 309K binaries across four architectures (x86, x64, ARM, MIPS) with an average of 403 binaries for each program and outperforms BinTuner [53], a similar technique. Our experiments revealed issues with the LLVM optimization scheduler resulting in compiler crashes (∼ 300). Our evaluation of four popular binary analysis tools angr, Ghidra, ida, and radare, using Cornucopia generated binaries, revealed various issues with these tools. Specifically, we found 263 crashes in angr and one memory corruption issue in ida. Our differential testing on the analysis results revealed various semantic bugs in these tools. We also tested machine learning tools, Asm2Vec, SAFE, and Debin, that claim to capture binary semantics and show that they perform poorly (e.g., Debin F1 score dropped to 12.9% from reported 63.1%) on Cornucopia generated binaries. In summary, our exhaustive evaluation shows that Cornucopia is an effective mechanism to generate binaries for testing binary analysis techniques effectively.

关键词： Compiler Optimizations Fuzzing Automated Binary Generation Binary Code Difference

来源：评论

学校读者我要写书评

暂无评论

Stability and generalization of the decentralized stochastic gradient descent ascent algorithm 23

Stability and generalization of the decentralized stochastic...

引用

Proceedings of the 37th international conference on Neural Information Processing Systems

作者： Miaoxi Zhu Li Shen Bo Du Dacheng Tao School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence and Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University China JD Explore Academy China The University of Sydney Australia

The growing size of available data has attracted increasing interest in solving minimax problems in a decentralized manner for various machine learning tasks. Previous theoretical research has primarily focused on the convergence rate and communication complexity of decentralized minimax algorithms, with little attention given to their generalization. In this paper, we investigate the primal-dual generalization bound of the decentralized stochastic gradient descent ascent (D-SGDA) algorithm using the approach of algorithmic stability under both convex-concave and nonconvex-nonconcave settings. Our theory refines the algorithmic stability in a decentralized manner and demonstrates that the decentralized structure does not destroy the stability and generalization of D-SGDA, implying that it can generalize as well as the vanilla SGDA in certain situations. Our results analyze the impact of different topologies on the generalization bound of the D-SGDA algorithm beyond trivial factors such as sample sizes, learning rates, and iterations. We also evaluate the optimization error and balance it with the generalization gap to obtain the optimal population risk of D-SGDA in the convex-concave setting. Additionally, we perform several numerical experiments which validate our theoretical findings.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research and Innovation of Artificial Intelligence Curriculum System—Under the Background of "Double First-Class" Construction 5th

Research and Innovation of Artificial Intelligence Curriculu...

引用

5th international conference on Computer Science and Educational Informatization, CSEI 2023

作者： Wei, Dongmei Meng, Dan Wang, Ping School of Management Science and Engineering Southwest University of Finance and Economics Chengdu611130 China School of Computer and Software Engineering Xihua University Chengdu610039 China

ISBN: (纸本)9789819994915

Under the background that the construction of artificial intelligence technology and intelligent science has become a national strategy, how to establish the development direction of professional characteristics and build a scientific curriculum system has become an urgent problem to be solved. With the goal of constructing artificial intelligence talent training system and curriculum system and creating first-class majors, we will carry out high-quality intelligent science curriculum system construction and teaching research from the goal of first-class professional curriculum construction. By taking the specialty of intelligent science and technology of Xihua University as an example, this thesis expounds the establishment of the specialty characteristic direction, the goal of cultivating high-quality artificial intelligence technical talents to meet the social needs, the application and innovation of the hierarchical talent training mode. The thesis builds the specific implementation path of the intelligent science relating to curriculum system, and applies it to the actual teaching. This research perspective is unique and innovative, and has obvious practical application value, so as to achieve the training goal of senior intelligent science professionals required by the development of local artificial intelligence industry. These results also provide reference for the construction of Intelligent Technology Specialty in Colleges and universities. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： machine learning

来源：评论

学校读者我要写书评

暂无评论

EMD and VMD in Pre-Movement EEG Signal Analysis: A Hybrid Mode Selection to Classify Upper Limb Complex Movements Using Statistical Features

EMD and VMD in Pre-Movement EEG Signal Analysis: A Hybrid Mo...

引用

international Symposium on High Capacity Optical Networks and Enabling Technologies, HONET

作者： Beenish Khalid Ali Hassan Ehsan Ullah Munir Imran Khan Niazi Dept. of Computer and Software Engineering College of Electrical and Mechanical Engineering National University of Sciences and Technology (NUST) Islamabad Pakistan Dept. of Computer Science COMSATS University Islamabad Pakistan Centre of Chiropractic Research College of Chiropractic Auckland New Zealand

Electroencephalogram (EEG) signals, inherently non-stationary and non-linear, present significant challenges in their processing and interpretation. This paper presents a hybrid mode selection approach using two advanced decomposition methods: Empirical Mode Decomposition (EMD) and Variational Mode Decomposition (VMD), to analyze these signals, targeting their application in the classification of upper limb complex movements for enhanced prosthetic limb control and rehabilitation therapy assessment. Using optimized statistical features extracted from selected modes, Intrinsic mode functions (IMFs) via EMD and modes via VMD, we seek to better distinguish neural activities in pre-movement EEG signal. Our methodology involves the following two strategies: straightforward extraction of statistical features from modes yielded by EMD and VMD; a genetic algorithm (GA) feature selection technique to select the most optimal set from these statistical features. These derived features train machine learning (ML) classifiers to differentiate limb movements. The results, derived from proprietary dataset from Aalborg University, Denmark, comprising five distinct upper limb movements, demonstrate the effectiveness of our hybrid approach. The usage of EMD and VMD significantly enhanced the discriminatory power of the extracted features, leading to improved classification performance. Furthermore, our hybrid approach yielded classification accuracies of 93.1 % and 95.6% with EMD and VMD respectively when the K-NN classifier was deployed with a 10-fold cross-validation. K-NN classifier outperformed traditional ML classifiers in terms of computational time, highlighting its potential as lightweight yet robust algorithm for classification of complex movements. The primary goal is to present and validate a hybrid mode (IMFs/modes) selection approach through EMD and VMD to analyze EEG signals associated with upper limb complex movements.

关键词：

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：