检索结果-内蒙古大学图书馆

7th International Conference on Computer science and Computational Intelligence, CSCI 2022

作者： Daniel Cenggoro, Tjeng Wawan Pardamean, Bens Computer Science Department BINUS Graduate Program - Master of Computer Science Program Bina Nusantara University Jakarta11480 Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia

Detecting COVID-19 as early as possible and quickly is one way to stop the spread of COVID-19. Machine learning development can help to diagnose COVID-19 more quickly and accurately. This report aims to find out how far research has progressed and what lessons can be learned for future research in this sector. By filtering titles, abstracts, and content in the Google Scholar database, this literature review was able to find 19 related papers to answer two research questions, i.e. what medical images are commonly used for COVID-19 classification and what are the methods for COVID-19 classification. According to the findings, chest X-ray were the most commonly used data to categorize COVID-19 and transfer learning techniques were the method used in this study. Researchers also concluded that lung segmentation and use of multimodal data could improve performance. © 2022 Elsevier B.V.. All rights reserved.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

An Enhanced BERTopic Framework and Algorithm for Improving Topic Coherence and Diversity 24

An Enhanced BERTopic Framework and Algorithm for Improving T...

引用

24th IEEE International Conference on High Performance Computing and Communications, 8th IEEE International Conference on data science and Systems, 20th IEEE International Conference on Smart City and 8th IEEE International Conference on Dependability in Sensor, Cloud and Big data Systems and Application, HPCC/DSS/SmartCity/DependSys 2022

作者： Sawant, Sahil Yu, Jinhong Pandya, Kirtikumar Ngan, Chun-Kit Bardeli, Rolf Data Science Program Worcester Polytechnic Institute WorcesterMA United States Big Data and Consumer Analytics Vodafone GmbH NRW Duesseldorf Germany

ISBN: (纸本)9798350319934

In this paper, we enhance and customize the existing BERTopic framework to develop and implement an automated pipeline that delivers a more coherent and diverse set of topics with an even moderate dataset. More specifically, the contributions of this work are threefold: (1) integrate a dynamic and advanced optimizer into the existing BERTopic framework to learn the optimal number of dimensions of different document embeddings, (2) develop a k-means-based algorithm in the optimizer to support the dimension-embedding learning, and (3) conduct an extensive experimental study on three distinct types of datasets, including DBPedia, AG News, and Reuters, to evaluate the performance of our approach in terms of the topic quality (TQ) score computed by the topic coherence and the topic diversity. From the results, we can conclude that our enhanced, automated BERTopic framework with its dimension-embedding learning algorithm on documents outperforms the TQ score of the existing framework by 4.49% (before removing the stop words) and 16.52% (after removing the stop words) among all the four representable document-embedding approaches, including the BERTopic's Default Sentence Transformer, Google's Universal Sentence Encoder, OpenAI GPT-2, and our investigators' developed Context-aware Embedding Model, on all the three datasets. © 2022 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Comparative Study of Testing Indigenous Air Filters for Fine PM Removal 1st

Comparative Study of Testing Indigenous Air Filters for Fine...

引用

1st International Conference on Pollution Control for Clean Environment, ICPCCE 2023

作者： Nawale, Prashant Sahu, Manoranjan Aerosol and Nanoparticle Technology Laboratory Environmental Science and Engineering Department Indian Institute of Technology Bombay Mumbai400076 India Interdisciplinary Program in Climate Studies Indian Institute of Technology Bombay Mumbai400076 India Centre for Machine Intelligence and Data Science Indian Institute of Technology Bombay Mumbai400076 India

ISBN: (纸本)9789819778454

Air pollution has become a serious global issue, which has significant impacts on both human health and the environment. Over the past decade, air quality has deteriorated due to various anthropogenic activities including construction, urbanization and industrialization. These activities release hazardous particles and harmful gases into the atmosphere, contributing to poor air quality. Developing countries such as India have been particularly affected, with some of their cities among the most polluted worldwide. To address this serious concern, it is imperative to develop and implement air pollution control technologies for both indoor and outdoor environments. This study focuses on the structured investigation of the performance of locally available air filter media in terms of their removal efficiency for submicron and micron-size particles. Various indigenous air filter media are subjected to rigorous testing to evaluate their overall and size-specific filtration efficiency and corresponding differential pressure drop. The results of these performance evaluations are then compared to their effectiveness in removing coarse and fine particles from the air. This research aims to provide valuable insights into the development of effective air filtration systems to combat air pollution. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Air filters Air pollution control technology Air purification Coarse PM Fine PM

来源：评论

学校读者我要写书评

暂无评论

Energy Efficiency in Sustainable Software Development: Clean Code Approaches

Energy Efficiency in Sustainable Software Development: Clean...

引用

International Conference on Electrical Engineering and Computer science (ICECOS)

作者： Inayatullah Wijang Widhiarso Deris Stiawan Department Program in Engineering Science Faculty of Computer Science Universitas Multi Data Palembang Palembang Indonesia Department Program in Engineering Science Faculty af Computer Science Universitas Sriwijaya Palembang Indonesia Faculty of Computer Science Universitas Multi Data Palembang Palembang Indonesia Faculty af Computer Science Universitas Sriwijaya Palembang Indonesia

ISBN: (数字)9798350368253

ISBN: (纸本)9798350368260

The use of technology and information devices contributes to global warming. This issue has also become a concern for UN institutions, as stated in international environmental agreements, which aim to stabilize greenhouse gas emissions in the atmosphere at a level that prevents anthropogenic and dangerous disturbances to the environmental system. This research uses a line of code derived from the tanjak dataset, a student project from 2003 to 2020, numbering 500. This research aims to apply energy consumption efficiency to reduce CO2 emissions produced using computer devices, especially in developing software. The approach used in this research is clean code, which can provide benefits in the form of a line of code that is easy to read, understand, test, and maintain so that it can create savings in energy use. In the test, the line of code used was 1,072,089, producing an energy of 82,152.18 Joules, minus the line of code comments, which was 76,750, producing an energy of 2,971.25 Joules. Initial research results show that the clean code approach can be used to save energy usage, with the result of the line of code used being 995,339 and producing 79,180 Joules of energy, so it can affect reducing CO2 emissions when implementing software development.

关键词： Electrical engineering Computer science Energy consumption Codes Software Global warming Energy efficiency Greenhouse gases Carbon emissions Software development management

来源：评论

学校读者我要写书评

暂无评论

A Novel Machine Learning Classifier Based on Genetic Algorithms and data Importance Reformatting

arXiv

引用

arXiv 2024年

作者： Alkhayyat, A.K. Hewahi, N.M. Big Data Science and Analytics Program College of Science University of Bahrain Bahrain Department of Computer Science College of Information Technology University of Bahrain Bahrain

In this paper, a novel classification algorithm that is based on data Importance (DI) reformatting and Genetic Algorithms (GA) named GADIC is proposed to overcome the issues related to the nature of data which may hinder the performance of the Machine Learning (ML) classifiers. GADIC comprises three phases which are data reformatting phase which depends on DI concept, training phase where GA is applied on the reformatted training dataset, and testing phase where the instances of the reformatted testing dataset are being averaged based on similar instances in the training dataset. GADIC is an approach that utilizes the exiting ML classifiers with involvement of data reformatting, using GA to tune the inputs, and averaging the similar instances to the unknown instance. The averaging of the instances becomes the unknown instance to be classified in the stage of testing. GADIC has been tested on five existing ML classifiers which are Support Vector Machine (SVM), K-Nearest Neighbour (KNN), Logistic Regression (LR), Decision Tree (DT), and Naïve Bayes (NB). All were evaluated using seven open-source UCI ML repository and Kaggle datasets which are Cleveland heart disease, Indian liver patient, Pima Indian diabetes, employee future prediction, telecom churn prediction, bank customer churn, and tech students. In terms of accuracy, the results showed that, with the exception of approximately 1% decrease in the accuracy of NB classifier in Cleveland heart disease dataset, GADIC significantly enhanced the performance of most ML classifiers using various datasets. In addition, KNN with GADIC showed the greatest performance gain when compared with other ML classifiers with GADIC followed by SVM while LR had the lowest improvement. The lowest average improvement that GADIC could achieve is 5.96%, whereas the maximum average improvement reached 16.79%. © 2024, CC BY.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Phishing Email Detection Model Using Deep Learning

Phishing Email Detection Model Using Deep Learning

引用

Cybernetics and Innovations (ICCI), International Conference on

作者： Natthaphong Pimpason Pranodnard Viboonsang Somkiat Kosolsombat Data Science and Innovation Program College of Interdisciplinary Studies Thammasat University Pathum Thani Thailand

ISBN: (数字)9798331533267

ISBN: (纸本)9798331533274

Phishing via email continues to be a concern in the cybersecurity realm as it exposes both individuals and companies to levels of risk due to clever social engineering methods employed by cybercriminals. This study introduces an extensive deep learning strategy for identifying phishing emails using a blend of various models such as Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), Bidirectional Encoder Representations from Transformers (BERT), Convolutional Neural Network (CNN), and Recurrent Neural Network (RNN). The suggested approach utilizes natural language processing and learning techniques to evaluate and categorize email material by identifying subtle attributes that differentiate valid from harmful communication effectively. Through testing and careful evaluation of the model performance, achieved results; the LSTM model attained a notable accuracy of 99.92% in detecting phishing emails. This progress highlights the promise of learning methods in addressing complex phishing threats and improving email security measures. The research offers insights into the effectiveness of neural network approaches in detecting phishing emails by comparing the performance of multiple deep learning architectures. The high level of accuracy attained indicates a path for creating smarter email security solutions that can evolve to counter cyber threats effectively.

关键词： Deep learning Accuracy Phishing Feature extraction Natural language processing Encoding Electronic mail Security Convolutional neural networks Long short term memory

来源：评论

学校读者我要写书评

暂无评论

Graph Coordinates and Conventional Neural Networks - An Alternative for Graph Neural Networks

Graph Coordinates and Conventional Neural Networks - An Alte...

引用

2023 IEEE International Conference on Big data, Bigdata 2023

作者： Qin, Zheyi Paffenroth, Randy Jayasumana, Anura P. Colorado State University Electrical and Computer Engineering Fort Collins United States Worcester Polytechnic Institute Department of Data Science Program WorcesterMA United States

ISBN: (纸本)9798350324457

Graph-based data present unique challenges and opportunities for machine learning. Graph Neural Networks (GNNs), and especially those algorithms that capture graph topology through message passing for neighborhood aggregation, have been a leading solution. However, these networks often require substantial computational resources and may not optimally leverage the information contained in the graph's topology, particularly for large-scale or complex *** propose Topology Coordinate Neural Network (TCNN) and Directional Virtual Coordinate Neural Network (DVCNN) as novel and efficient alternatives to message passing GNNs, that directly leverage the graph's topology, sidestepping the computational challenges presented by competing algorithms. Our proposed methods can be viewed as a reprise of classic techniques for graph embedding for neural network feature engineering, but they are novel in that our embedding techniques leverage ideas in Graph Coordinates (GC) that are lacking in current *** results, benchmarked against the Open Graph Benchmark Leaderboard, demonstrate that TCNN and DVCNN achieve competitive or superior performance to message passing GNNs. For similar levels of accuracy and ROC-AUC, TCNN and DVCNN need far fewer trainable parameters than contenders of the OGBN Leaderboard. The proposed TCNN architecture requires fewer parameters than any neural network method currently listed in the OGBN Leaderboard for both OGBN-Proteins and OGBN-Products datasets. Conversely, our methods achieve higher performance for a similar number of trainable parameters. These results hold across diverse datasets and edge features, underscoring the robustness and generalizability of our methods. By providing an efficient and effective alternative to message passing GNNs, our work expands the toolbox of techniques for graph-based machine learning. A significantly lower number of tunable parameters for a given evaluation metric makes TCNN and DVCNN especiall

关键词： graph analytics graph coordinate graph embedding green AI network embedding

来源：评论

学校读者我要写书评

暂无评论

Optimizing Malware Detection with Random Forest, XGBoost, LightGBM, and LLM-Reporting

Optimizing Malware Detection with Random Forest, XGBoost, Li...

引用

Cybernetics and Innovations (ICCI), International Conference on

作者： Aticha Charoenthanakitkul Pranodnard Viboonsang Somkiat Kosolsombat Data Science and Innovation Program College of Interdisciplinary Studies Thammasat University Pathum Thani Thailand

ISBN: (数字)9798331533267

ISBN: (纸本)9798331533274

This study presents a comprehensive framework for malware detection that integrates traditional machine learning algorithms with advanced large language models (LLMs) to enhance both classification accuracy and automated report generation. The proposed approach leverages three widely used machine learning models-Random Forest, XGBoost, and LightGBM-to classify different types of malwares based on extracted features from the EMBER dataset, a well-known benchmark dataset for malware analysis. Each of these models was trained and evaluated to determine their effectiveness in identifying malicious software with high accuracy. Among the tested algorithms, LightGBM exhibited the best performance, achieving an impressive classification accuracy of 83%. XGBoost followed closely with 81%, while Random Forest achieved an accuracy of 79%. To further enhance the usability of the system for cybersecurity analysts, the study incorporates a large language model, specifically LLaMA, which is accessed via an API. This model is employed to generate detailed, human-readable reports that provide insights into detected malware threats. By automating the reporting process, the framework aims to reduce the manual effort required for malware analysis, allowing security professionals to focus on high-priority threats. Future research will focus on improving classification performance through advanced feature engineering techniques and exploring deep learning-based neural network architectures to further enhance the accuracy and efficiency of malware detection and analysis.

关键词： Training Analytical models Accuracy Machine learning algorithms Computational modeling Large language models Feature extraction Malware Computer security Random forests

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Educational Fund Management and Operational Cost Efficiency: Analyzing U.S. Public Schools data

Evaluation of Educational Fund Management and Operational Co...

引用

Artificial Intelligence and Mechatronics Systems (AIMS), International Conference on

作者： Kevina Nugraha Eleeas Richie Muljana Lintang Diah Ayuningtyas Alexander Agung Santoso Gunawan Karli Eka Setiawan Data Science Program School of Computer Science Bina Nusantara University Jakarta Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia

This study investigates the challenges and opportunities of managing educational funds and controlling operational costs in two educational systems. It examines how factors such as school infrastructure, technology integration, teacher professional development, and parental involvement influence educational funding and quality. This study also explores the importance of equitable and efficient fund allocation, especially for remote schools that face resource constraints and development gaps. To analyze the financial trends of educational fund management, this study applies three machine learning models: decision trees, random forests, and support vector machines. The results show that the random forest model has the highest overall accuracy (90%) and the decision tree model has perfect accuracy in classifying institutions based on local income. This study identifies the most relevant features and demonstrates the effectiveness of the models in categorizing institutions and evaluating the fund management performance in the education sector.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Phishing URL Detection Using Machine Learning and Deep Learning in NLP

Phishing URL Detection Using Machine Learning and Deep Learn...

引用

Cybernetics and Innovations (ICCI), International Conference on

作者： Nutcha Srilachai Pranodnard Viboonsang Somkiat Kosolsombat Data Science and Innovation Program College of Interdisciplinary Studies Thammasat University Pathum Thani Thailand

ISBN: (数字)9798331533267

ISBN: (纸本)9798331533274

Phishing attacks are an emerging cyber threat that makes use of fake URLs to pilfer sensitive information of users, such as their login credentials and other financial details. In line with this, the present study involves the adoption of NLP methods with machine-learning algorithms in effectively detecting phishing URLs. To this end, five different algorithms are considered for effectiveness in the study: LSTM, GRU, Random Forest, Support Vector Machine, and Logistic Regression. Each of them was trained and then tested with a complete dataset, containing phishing and legitimate URLs for correctness in distinguishing malicious URLs from the benign ones. Amongst them, the LSTM model recorded an accuracy as high as 98% due to its capability for handling sequential dependencies in addition to contextual patterns within the URLs. This research underlines the promise of LSTM-based models in fighting phishing threats and further proposes a scalable solution to enable real-time phishing URL detection and enhance cybersecurity defense.

关键词： Uniform resource locators Deep learning Support vector machines Logistic regression Accuracy Phishing Computational modeling Real-time systems Long short term memory Random forests

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：