检索结果-内蒙古大学图书馆

15th International Conference on computing Communication and Networking Technologies, ICCCNT 2024

作者： Rama, P. Pandiaraj, A. Angayarkanni, V. Prakash, Y. Jagadeesh, S. SRM Institute of Science and Technology Computing Technologies College of Engineering and Technology Faculty of Engineering and Technology SRM Nagar TN Kattankulathur603203 India SRM Institute of Science and Technology Computing Technologies College of Engineering and Technology SRM Nagar TN Kattankulathur603203 India

ISBN: (纸本)9798350370249

This paper introduces IR-GAN (Image Restoration Generative Adversarial Network), a groundbreaking tool accessible on GitHub, designed to elevate image quality and rejuvenate damaged or low-resolution photographs. Leveraging the power of generative facial priors, IR-GAN adeptly transforms aged images, effectively reducing blurriness and revitalizing historical snapshots with remarkable precision. At the heart of IR-GAN lies its pre-trained Generative Adversarial Network (GAN) model, meticulously crafted to intelligently fill in missing or damaged areas within images by discerning intricate patterns present in the dataset. This innovative approach enables IR-GAN to seamlessly replace distorted or blurred segments with visually coherent elements, preserving the authenticity and essence of the original photographs. Through the integration of advanced image processing techniques and state-of-the-art deep learning methodologies, IR-GAN emerges as a promising solution for digital restoration and preservation endeavours. Its ability to breathe new life into old photographs while maintaining their historical significance holds immense value for archivists, historians, and enthusiasts alike. Experimental results presented in this paper underscore IR-GAN's efficacy in the transformative process of old photographs into visually appealing images. The showcased capabilities of IR-GAN align with the burgeoning demand for sophisticated image enhancement tools within the realm of image processing, paving the way for future advancements in digital restoration and preservation technologies. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral anomaly detection via memory‐augmented autoencoders

引用

CAAI Transactions on Intelligence Technology 2023年第4期8卷 1274-1287页

作者： Zhe Zhao Bangyong Sun Faculty of Printing Packaging Engineering and Digital Media TechnologyXi'an University of TechnologyXi'anChina Norwegian Colour and Visual Computing Laboratory Norwegian University of Science and TechnologyGjovikNorway

Recently,the autoencoder(AE)based method plays a critical role in the hyperspectral anomaly detection ***,due to the strong generalised capacity of AE,the abnormal samples are usually reconstructed well along with the normal background ***,in order to separate anomalies from the background by calculating reconstruction errors,it can be greatly beneficial to reduce the AE capability for abnormal sample reconstruction while maintaining the background reconstruction performance.A memory‐augmented autoencoder for hyperspectral anomaly detection(MAENet)is proposed to address this challenging ***,the proposed MAENet mainly consists of an encoder,a memory module,and a ***,the encoder transforms the original hyperspectral data into the low‐dimensional latent ***,the latent representation is utilised to retrieve the most relevant matrix items in the memory matrix,and the retrieved matrix items will be used to replace the latent representation from the ***,the decoder is used to reconstruct the input hyperspectral data using the retrieved memory *** this strategy,the background can still be reconstructed well while the abnormal samples *** conducted on five real hyperspectral anomaly data sets demonstrate the superiority of the proposed method.

关键词： anomaly detection hyperspectral images memory autoencoder

来源：评论

学校读者我要写书评

暂无评论

Utilizing Big Data Analytics for Social Media Insights 5

Utilizing Big Data Analytics for Social Media Insights

引用

5th International Conference on IoT Based Control Networks and Intelligent Systems, ICICNIS 2024

作者： Vedhika Srinidhi, V.S. Sanjana, S. Rozario, Neo Joseph Dewan, Sia Gouthaman, P. School of Computing College of Engineering & Technology SRM Institute of Science and Technology Department of Networking and Communications Kattankulathur603203 India School of Computing Faculty of Engineering & Technology SRM Institute of Science and Technology Department of Networking and Communications Kattankulathur603203 India

ISBN: (纸本)9798331518097

Big Data analytics is a rapidly evolving field that offers profound insights into various sectors by enabling the analysis of massive and diverse datasets. This research paper focuses on the application of Big Data techniques to social media and airline networks, leveraging tools such as sentiment analysis, clustering, and data visualization to extract actionable information. The study analyses Twitter data to uncover public sentiment trends and classifies topics using advanced machine learning techniques. Furthermore, the research explores the use of clustering algorithms within the Hadoop ecosystem to process large-scale datasets efficiently. Insights from airline customer feedback and network planning data demonstrate how Big Data analytics can optimize operational efficiency and enhance customer satisfaction. Key findings include the identification of distinct sentiment patterns in social media data, the efficiency of novel clustering techniques in handling high-volume datasets, and the utility of advanced visualization methods to convey complex data. These results have significant implications for industries ranging from social media platforms to the airline sector, providing valuable tools for enhancing decision-making processes and improving user experiences across diverse domains. The study highlights the potential of Big Data analytics to drive innovation and operational excellence in dynamic environments. © 2024 IEEE.

关键词： Airline networks Big Data analytics Clustering algorithms Data visualization Sentiment analysis Social media

来源：评论

学校读者我要写书评

暂无评论

Real-Time Weapon Detection System for Enhanced Security Monitoring 4

Real-Time Weapon Detection System for Enhanced Security Moni...

引用

4th International Conference on Ubiquitous computing and Intelligent Information Systems, ICUIS 2024

作者： Kuppili, Rohan Agarwal, Khusboo Bhosale, Tanmay Gouthaman, P. School of Computing College of Engineering and Technology Srm Institute of Science and Technology Department of Networking and Communications Kattankulathur603203 India School of Computing Srm Institute of Science and Technology Faculty of Engineering and Technology Department of Networking and Communications Kattankulathur603203 India

ISBN: (纸本)9798331529635

Innovative technology for weapon detection during security monitoring is necessary today due to the rising threats of violence and terror. The paper discusses a detailed design of a weapon detection system intended for application in enhancing security surveillance specifically using a deep learning approach. The system employs YOLOv3 (You Only Look Once, Version 3) mood and adaption aimed at live footage weapon detection. To do this on broader scale, this system incorporates big data tools Hadoop, Docker, Spark and Kafka for reasons of real time processing and effectiveness in high volume data situations. This model is applied on the live footage surveillance of public and private places to determine if the model can detect weapons, to warn relevant authorities in the aim of decreasing response time and averting security breach occurrences. The experiments conducted confirm that the model is capable of performing weapon detection tasks in an indoor environment with changes in illumination conditions with few false alarms. © 2024 IEEE.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Real-time polling to help corral university-learners' wandering minds

引用

Journal of Research in Innovative Teaching and Learning 2022年第1期15卷 98-109页

作者： Price, Trevor John Built Environment Faculty of Computing Engineering and Science University of South Wales

Purpose: This research investigates the use of real-time online polling to enhance university teaching and learning. Design/methodology/approach: Using a case study and employing action research, this work shows how polling can improve professional practice, learner engagement and teaching performance. Findings: Incorporating the right type of online real-time polling into lessons is a professional challenge and can be hard work for teachers but has overriding benefits. Research limitations/implications: This research reports one lecturer's experiences within two UK universities, limited to location, variety of students and lecturer technical capability. The research implications are that online polling, especially in different learning environments, is needed. Previous research is outdated or limited to real-time polling for teaching and learning during physical classes. There are research opportunities therefore in the use of polling before, during and after class. Practical implications: This research finds that the field of online polling needs to be seen as a modern teaching tool that now uses students' personal technology for easier use by students and teachers: it is more than the use of archaic “clickers” which were extra classroom items to be bought and maintained. Also, online polling, before, during and after classes, can be employed usefully and have validity within teachers' toolboxes. This paper shows how such polls can be successfully deployed. Originality/value: Whilst there are previous reports of polling undertaken within teaching and learning events, this paper builds upon those experiences and boosts collective understanding about the use of polling as a way to improve professional practice and increase learning. © 2021, Trevor John Price.

关键词： Learning Online Polling Real-time Technology enhanced learning Vevox

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study on Spam Identification using Naive Bayes and SVM 5

A Comparative Study on Spam Identification using Naive Bayes...

引用

5th International Conference on Data Intelligence and Cognitive Informatics, ICDICI 2024

作者： Verma, Shashwat Agrawal, Shikhar Gulati, Shreshth Gouthaman, P. Srm Institute of Science and Technology Faculty of Engineering and Technology Department of Networking and Communications School of Computing Tamil Nadu Chennai India

ISBN: (纸本)9798350389609

Email is one of the most frequently employed digital means of communication among individuals use on an on-going basis. Sending unidentified messages to someone is termed as spam. The internet remains the most accessible source of information, and social media is becoming more and more prevalent. This research offers a unique framework that uses multinomial naive bayes (multinomial NB) and support vector machine (SVM) advanced machine learning approaches to improve email spam detection. It increases the classification efficiency and accuracy when compared to more conventional techniques like Random Forest and basic Naive Bayes. The method also includes a significant amount of data preprocessing, including text normalization, stemming, and count vectorization feature extraction. This approach can be enhanced by being utilized by email clients or servers to recognize spam emails. Experiments have demonstrated that the Support Vector Machine technique returns good accuracy, and this research advances email spam detection techniques. © 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 and Prediction of Lettuce Crop Yield in Aeroponic Vertical Farming using Logistic Regression Method 2

Analysis and Prediction of Lettuce Crop Yield in Aeroponic V...

引用

2nd International Conference on Sustainable computing and Data Communication Systems, ICSCDS 2023

作者： Gowtham, R. Jebakumar, R. Srm Institute of Science and Technology School of Computing Faculty of Engineering and Technology Department of Computing Technologies Chengalpattu Tamil Nadu Kattankulathur India

ISBN: (纸本)9781665491990

Human population growth strains food supplies, resulting in more than one billion of the world's 6.5 billion people facing hunger, which is the leading cause of death. In consequence, increasing crop production through traditional farming methods will not address the global food scarcity problem. As a precision agriculture approach, aeroponics, a soilless agriculture technique, can assist in cultivating in-demand food crops, which will help serve the people. Because aeroponics is an indoor farming technology, factors such as pH, EC, light, temperature, PPM, and turbidity will affect crop growth. Hence, monitoring an aeroponic crop growth system efficiently is crucial for achieving a high crop yield and reducing the need for food crops. Even though, many crop monitoring systems use IoT and machine learning algorithms, their prediction accuracy is not up to the level and if they are deployed in the real world, they may not meet customer expectations. In order to efficiently monitor crops, more advanced models are needed. However, understanding the large volume of data can be very tedious. Data visualization techniques can help make the distribution of the dataset easier to understand. Machine learning methods and packages can be used for environmental monitoring and visualization of the data where, the collection of crop growth dataset is carried out using various IoT sensors deployed in the growth environment. This study provides a comprehensive explanation of the data visualization techniques used to study the lettuce crop dataset and predict lettuce yield using the logistic regression machine learning method which is been implemented using Python coding language. © 2023 IEEE.

关键词： Lettuce

来源：评论

学校读者我要写书评

暂无评论

SecureML: Machine Learning-Powered Malware Detection 2

SecureML: Machine Learning-Powered Malware Detection

引用

2nd IEEE International Conference on Advances in Information Technology, ICAIT 2024

作者： Awasthi, Animay Ahsan, Mohd Vanusha, D. Delsi Robinsha, S. Department of Computing Technologies School of Computing SRM Institute of Science and Technology Chengalpattu District Tamilnadu Kattankulathur603 203 India Department of Computing Technologies School of Computing Faculty of Engineering and Technology SRM Institute of Science and Technology Chengalpattu District Tamilnadu Kattankulathur603 203 India

ISBN: (纸本)9798350383867

As malware threats become increasingly complex, the development of advanced detection systems is necessary to protect digital assets. SecureML Using Machine Learning presents an innovative approach to combat the escalating threat of malicious software by leveraging machine learning algorithms. This research paper outlines the design, implementation, and evaluation of SecureML, emphasizing its effectiveness in detecting both known and novel malware strains. Through comprehensive feature selection techniques and algorithmic comparison, SecureML identifies crucial features and selects the Random Forest algorithm as the most effective for malware detection, achieving an impressive accuracy rate of 99.40% on the test set. The system's low false positive and false negative rates validate its robustness and reliability in accurately distinguishing between benign and malicious files. SecureML demonstrates significant potential in bolstering cybersecurity defenses and safeguarding digital assets against evolving malware threats. © 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

AFuNet: an attention-based fusion network to classify texts in a resource-constrained language

引用

Neural computing and Applications 2025年第9期37卷 6725-6748页

作者： Hossain, Md. Rajib Hoque, Mohammed Moshiul Dewan, M. Ali Akber Hoque, Enamul Siddique, Nazmul Department of Computer Science & Engineering Chittagong University of Engineering & Technology Chittagong4349 Bangladesh School of Computing and Information Systems Faculty of Science and Technology Athabasca University AthabascaABT9S 3A3 Canada School of Information Technology York University TorontoONM3J 1P3 Canada School of Computing Engineering and Intelligent Systems Ulster University Coleraine United Kingdom

In the era of widespread Internet use and extensive social media interaction, the digital realm is accumulating vast amounts of unstructured text data. This unstructured data often contain undesirable information, necessitating time-consuming manual classification efforts. An intelligent text classification system capable of automatically categorizing digitized texts based on semantic meaning is crucial. However, this task is particularly challenging for low-resource languages like Bengali due to a shortage of annotated corpora, issues with out-of-vocabulary words, lack of domain-specific hyperparameter tuning, limited ability to extract generalized text features, and class imbalances within the corpus. AFuNet: an attention-based fusion network to classify texts in a resource-constrained language. AFuNet undergoes a comprehensive four-phase experimental process, including baseline model evaluation and hyperparameter tuning, late fusion and model selection, attention-based early fusion and model identification, and an ablation study with impact analysis. Fine-tuned based on five Bengali text classification corpora, AFuNet achieves impressive accuracies: 96.60 ± 0.2 (BTCC11), 85.37 ± 0.2 (OSBC), 97.35 ± 0.2 (BARD), 93.74 ± 0.2 (IndicNLP), and 96.51 ± 0.2 (ProthomAlo). In comparison with previous state-of-the-art models on these corpora, AFuNet demonstrates significant accuracy improvements ranging from 0.54% to 4.49%, showcasing its effectiveness in advancing text classification capabilities for the Bengali language. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Financial Fraud Detection for Credit Card Transactions Using Apache Spark 5

Financial Fraud Detection for Credit Card Transactions Using...

引用

5th International Conference on Sustainable Communication Networks and Application, ICSCNA 2024

作者： Jha, Pratyush Srivastava, Srijan Gandhi, Tanishq Gouthaman, P. School of Computing College of Engineering and Technology SRM Institute of Science and Technology Department of Networking and Communications Kattankulathur603203 India School of Computing SRM Institute of Science and Technology Faculty of Engineering and Technology Department of Networking and Communications Kattankulathur603203 India

ISBN: (纸本)9798331530013

The financial sector's rapid adoption of digital transformation has made identifying fraud a progressively complex challenge, since modern fraudulent activities present significant risks to institutions globally. This paper presents a novel methodology for detecting financial fraud that integrates big data analytics and machine learning techniques within a distributed environment. With an extensive number of actual financial transactions, the system uses Apache Spark for real-time data processing and machine learning algorithms to accurately classify fraudulent transactions. This method effectively addresses two major issues: efficiently processing large data sets and managing the severe class imbalance between fraudulent and non-fraudulent transactions. Collectively, these solutions provide a scalable and resilient framework for improving fraud detection in the digital era. © 2024 IEEE.

关键词： Nearest neighbor search

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：