检索结果-内蒙古大学图书馆

3rd Conference on Lifelong Learning Agents, CoLLAs 2024

作者： Kumar, Saurabh Marklund, Henrik Van Roy, Benjamin Department of Computer Science Stanford University United States Department of Electrical Engineering Department of Management Science and Engineering Stanford University United States

In continual learning, plasticity refers to the ability of an agent to quickly adapt to new information. Neural networks are known to lose plasticity when processing non-stationary data streams. In this paper, we propose L2 Init, a simple approach for maintaining plasticity by incorporating in the loss function L2 regularization toward initial parameters. This is very similar to standard L2 regularization (L2), the only difference being that L2 regularizes toward the origin. L2 Init is simple to implement and requires selecting only a single hyper-parameter. The motivation for this method is the same as that of methods that reset neurons or parameter values. Intuitively, when recent losses are insensitive to particular parameters, these parameters should drift toward their initial values. This prepares parameters to adapt quickly to new tasks. On problems representative of different types of nonstationarity in continual supervised learning, we demonstrate that L2 Init most consistently mitigates plasticity loss compared to previously proposed approaches. © 2024 CoLLAs. All Rights Reserved.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

IVIDNet: Intelligent iris vitality detection via weighted prediction score level fusion

引用

Multimedia Tools and Applications 2023年第29期82卷 45959-45981页

作者： Verma, Palak Selwal, Arvind Sharma, Deepika Department of Computer Science and Engineering Indian Institute of Technology Jammu PO-Nagrota Jammu181221 India Department of Computer Science and Information Technology Central University of Jammu Samba181143 India

Iris recognition is one of the most widely used human authentication mechanism that has gained huge popularity due to its security and efficiency. However, recently attackers have breached the security of these systems via synthetically generated fake iris traits using a variety of artefacts such as paper printouts, video attacks, and cosmetic lenses. To countermeasure these attacks, an anti-deception sub-system is instilled between sensor and feature extractor modules of the system. These sub-systems intelligently measure the vitality of the presented iris traits and are popularly known as iris vitality detection (IVID) or iris anti-spoofing techniques. Recently, the deep learning-based models are widely deployed for iris anti-spoofing approaches, but these methods result in additional training overhead as well as require larger training dataset. In this paper, we expound a novel iris vitality detection network (IVIDNet) that employs the robust features of two pre-trained deep convolutional neural networks (DCNN). The extracted features are then integrated via a new weighted score-level fusion technique. To demonstrates the efficacy of the proposed technique, experimental analysis is carried out on benchmark iris liveness detection Notre Dame 2017 and Notre Dame cosmetic lenses dataset (NDCLD) 2015. The proposed IVIDNet exhibits excellent performance in the known attack scenario with an average classification error rate (ACER) of 0.60%. Moreover, IVIDNet shows superior performance in the unseen attacks scenario (i.e. cross-database) with an ACER of 9.72%. In overall, the proposed model outperforms other similar iris anti-spoofing approaches and efficient in terms of computational overhead. © 2023, The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature.

关键词： Biometrics

来源：评论

学校读者我要写书评

暂无评论

Obtaining Crisp Priorities for Triangular and Trapezoidal Fuzzy Judgments

引用

computer Systems science & engineering 2022年第4期41卷 157-170页

作者： Raman Kumar Goyal Jaskirat Singh Nidhi Kalra Anshu Parashar Gagan Singla Sakshi Kaushal Computer Science and Engineering Department Thapar Institute of Engineering and TechnologyPatialaPunjabIndia Computer Science and Engineering University Institute of Engineering and TechnologyPanjab UniversityChandigarhIndia

This paper proposes anoptimal fuzzy-based model for obtaining crisp priorities for Fuzzy-AHP comparison *** judgments cannot be given for real-life situations,as most of these include some level of fuzziness and *** these situations,judgments are represented by the set of fuzzy *** of the fuzzy optimization models derive crisp priorities for judgments repre-sented with Triangular Fuzzy Numbers(TFNs)*** do not work for other types of Triangular Shaped Fuzzy Numbers(TSFNs)and Trapezoidal Fuzzy Numbers(TrFNs).To overcome this problem,a sum of squared error(SSE)based optimization model is *** some other methods,the proposed model derives crisp weights from all of the above-mentioned fuzzy judgments.A fuzzy number is simulated using the Monte Carlo method.A threshold-based constraint is also applied to minimize the deviation from the initial *** Algorithm(GA)is used to solve the optimization *** have also conducted casestudiesto show the proposed approach’s advantages over the *** show that the proposed model outperforms other models to minimize SSE and deviation from initial ***,the proposed model can be applied in various real time scenarios as it can reduce the SSE value upto 29%compared to the existing studies.

关键词： Analytic hierarchy process comparison matrices priority vectors fuzzy judgments triangular fuzzy numbers triangular-shaped fuzzy numbers trapezoidal fuzzy numbers

来源：评论

学校读者我要写书评

暂无评论

IDTCKS: An Intelligent Integrative Approach for Disaster Tweet Classification and Disaster-Related Document Classification Using Knowledge-Driven Hybrid Semantics 2nd

IDTCKS: An Intelligent Integrative Approach for Disaster Twe...

引用

2nd International Conference on Advances in data-driven Computing and Intelligent Systems, ADCIS 2023

作者： Nama, Vihaan Deepak, Gerard Department of Computer Science Engineering RV College of Engineering Bengaluru India Department of Computer Science Engineering Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India

ISBN: (纸本)9789819995172

There is an immediate requirement for a strategic semantically inclined, semantic web accommodating framework for disaster tweet classification and disaster document and newsfeed documents recommendation to perform disaster risk mitigation and management. This framework proposes an IDTCKS framework for disaster management as a domain of choice, wherein an agent-driven model for integrating auxiliary knowledge from several news and Twitter APIs is encompassed. Subsequently, the TF-IDF discovers informative terms from the documents. The frameworks encompass two distinct classifiers, namely the AdaBoost Classifier to classify the disaster tweets using the upper ontology for the disaster domain as the features and upper ontology is considered by using the LDA to the enriched disaster terms. Subsequently, the upper ontology and the LDA-enriched disaster terms are also used as a feature-driven logistic regression classifier that helps in classifying the dataset. Semantic relevance is achieved using Twitter Semantic Similarity and Horn’s Index with a threshold and step deviance measure and overall precision of 97.39, an accuracy of 98.24, and a very low False Negative Rate of 0.01 has been achieved by the IDTCKS model for disaster classification while an overall precision of 96.57, accuracy of 97.65, and a very low False Negative Rate of 0.02 has been achieved by the IDTCKS model for document classification, which performs much better than other baseline models. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Disasters

来源：评论

学校读者我要写书评

暂无评论

Artify - An Artistic NFT Marketplace

Artify - An Artistic NFT Marketplace

引用

2024 IEEE Students Conference on engineering and Systems, SCES 2024

作者： Gayathri, G. Gokul Krishna, S. Houshic, B. Shanmugapriya, S. Sri Ramakrishna Engineering College Department of Computer Science and Engineering Coimbatore India

ISBN: (数字)9798350374711

ISBN: (纸本)9798350374711

In today's digital age, there is a grow in demand for unique and personalized artistic contents which paves a path for NFT marketplace. NFT marketplace is a platform for the sale and auction of the contents produced by independent artists. These contents can be varied from music tracks to paintings, etc. This system provides the decentralized platform so that the artist can claim the ownership and sell it online without any forgery by using the blockchain technology such as smart contracts which ensures that the artist can continue to receive compensation for their work even after it has been sold in the marketplace. It also includes features which allows the new gen artist to create a painting by reviving the stylings of the legendary artists and their painting styles which creates a unique touch to their paintings. Style transfer is a technique that is used to transfer the artistic style of single or multiple images (style image) onto another image (content image). These paintings can be claimed by the independent artist and can be sold in the marketplace. It also allows the users to bid for the artist's work which they admire and own that artist's work without losing the artist's ownership. In summary, this system seeks to combine blockchain and artistic style transfer techniques, which results in creating multiple opportunities for the new gen artists and then they can claim their ownership. © 2024 IEEE.

关键词： Marketplaces

来源：评论

学校读者我要写书评

暂无评论

Unraveling Dyscalculia: Identifying Mathematical Learning Difficulties in Early Education

Unraveling Dyscalculia: Identifying Mathematical Learning Di...

引用

2024 International Conference on Innovations and Challenges in Emerging Technologies, ICICET 2024

作者： Mukherjee, Kingshuk Kumar, Reitika Vasishat, Sam Bhargava, Naman Upadhyay, Siddhi Muhuri, Samya Thapar Institute of Engineering and Technology Department of Computer Science & Engineering Patiala India

ISBN: (纸本)9798350319019

This study presents a comprehensive intervention approach designed to address dyscalculia in early education. The strategy employs a comprehensive approach that incorporates colour identification, numerical enumeration, mathematical computation, and verbal communication. The initiative seeks to employ a technology for creating interactive learning modules that successfully engage students in various numerical activities. Student progress is evaluated by the application of fuzzy logic, which allows for a thorough understanding of each student's unique learning trajectory. The adaptive approach tailors the difficulty level of exercises based on the student's performance, ensuring a tailored learning experience. This intervention specifically focuses on primary school students, aiming to provide early support and intervention to those who are either at risk of or have already been diagnosed with dyscalculia. The objective of the study is to provide a robust foundation for forthcoming mathematical abilities. © 2024 IEEE.

关键词： Fuzzy logic

来源：评论

学校读者我要写书评

暂无评论

Efficiency & Innovation in Recruitment usingAI & Android

Efficiency & Innovation in Recruitment usingAI & Android

引用

2024 International Conference on Knowledge engineering and Communication Systems, ICKECS 2024

作者： Chalana, Kanika Gautam, Ashwin Ravi Raj, Anand Daivik, J.S. Amrutha, H.R. Dayananda Sagar College of Engineering Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350359688

The goal of screening resumes is to determine the top applicants for a position and to inform users of their resume score and areas for improvement. The literature on existing approaches has been analyzed, and it has been discovered that the traditional systems like manual screening may result in false assumptions and the wasting of human potential, but they lackrobustness Regarding processing, accuracy and efficiency. To acquire accurate results, software must utilized to process natural language and machine learning techniques to match and rate the candidates in real-time by ranking their resumes. The input would be the resumes and output would be a ranked candidate's resumes on the admin side and recommendations for the user side. Instantaneous real-time output results are acquired by employing Object character recognition. In The system that is being suggested the authors used OCR model and android principles along with python scripts. This system has the many benefits including security, interpretability, high accuracy, lightweight model, and quick processing. © 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

AgriAI: Revolutionizing Agriculture with data science 2

AgriAI: Revolutionizing Agriculture with Data Science

引用

2nd IEEE International Conference on Networking and Communications, ICNWC 2024

作者： Raut, Nitin B. Ashwin, U. Aswin, S. Bala Selva Vishnu, N. KPR Institute of Engineering and Technology Department of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350365269

In this ambitious agricultural project, cutting-edge technologies such as Machine Learning (ML) and Deep Learning (DL) are harnessed to revolutionize farming practices in India. The primary focus lies in automating vital tasks like crop disease detection, crop recommendation, and fertilizer suggestion, which are traditionally laborious and time-consuming for farmers. Leveraging recent advancements in ML algorithms, a comprehensive solution is envisaged. This innovative approach involves the integration of sophisticated models into a user-friendly website, creating a seamless user experience. Through this platform, farmers gain access to automated tools that significantly enhance their crop management strategies. The platform provides a comprehensive solution by combining deep learning-based crop disease detection mechanisms, intelligent crop recommendation systems, and effective fertilizer recommendations derived from machine learning algorithms. This combination of technologies helps farmers maximize their overall crop yields and minimize losses caused by diseases in addition to streamlining farming procedures. The synergy of ML, and DL on a unified web interface stands as a testament to the transformative power of technology in agriculture, marking a pivotal step toward sustainable and efficient farming practices in India. © 2024 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Spectral-Spatial Subspace Detection for Improved Change Detection in Hyperspectral Images 3

Spectral-Spatial Subspace Detection for Improved Change Dete...

引用

3rd International Conference on Advancement in Electrical and Electronic engineering, ICAEEE 2024

作者： Afjal, Masud Ibn Mondal, Md. Nazrul Islam Mamun, Md. Al Rajshahi University of Engineering and Technology Department of Computer Science and Engineering Rajshahi Bangladesh

ISBN: (纸本)9798350388282

HyperSpectral Images Change Detection (HSI-CD) plays a pivotal role in precise earth observation through remote sensing, leveraging abundant spectral and spatial information. However, prevailing methods, relying on image difference and band selection, encounter challenges in preserving spectral characteristics, neglecting nonlinear relationships among bands, and addressing high data dimensionality, thus limiting their overall efficacy. In this paper, we introduce S2HNet, a hybrid spectral-spatial network crafted to tackle end-to-end HSI-CD challenges. Our proposed S2HNet excels in efficiently extracting significant spectral-spatial information within a reduced feature space, achieved by integrating a principal component analysis (PCA) based feature subspace reduction module into a hybrid 3D-2D convolutional neural network (CNN). Consequently, the generated subspace demonstrates superior change detection performance compared to related baseline and advanced approaches. Thorough experiments were run on two publicly accessible baseline HSICD datasets: China farmland (CH) and USA irrigated farmland (USA), along with one synthesized dataset, Indian Pines (IP). These experiments rigorously validate the effectiveness and efficiency of the proposed methodology. The results demonstrate the superiority of the proposed approach, achieving the highest change detection performances, specifically 97.51% and 96.57% for CH and USA datasets, respectively, and 99.04% for our synthesized IP dataset. © 2024 IEEE.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Plastic Litter Detection using YOLOv8 Algorithm 2

Plastic Litter Detection using YOLOv8 Algorithm

引用

2nd International Conference on Self Sustainable Artificial Intelligence Systems, ICSSAS 2024

作者： Dhanishtaa, R. Elakkiya, E. Gunashri, R. Madhumathi, R. Sri Ramakrishna Engineering College Department of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350368413

One of the most concerning environmental issues is water pollution, which is mostly brought on by plastic waste that is dumped into the aquatic region from land. These plastics pose a threat to the marine ecosystem's equilibrium, the coastal communities, economic health, and their animals. This would unavoidably have an impact on aquatic and human life. Even if they work well, most widely used techniques have several drawbacks when it comes to identifying and measuring plastics. As a result, it is important to implement alternative techniques that will make it simple to recognize plastics and facilitate their removal using latest technologies. This research study utilizes the You Only Look Once (YOLO) v8 Deep Learning (DL) algorithm for object detection and identifying plastics in the surface of water bodies and gives the count of the plastics that are detected as a result. © 2024 IEEE.

关键词： Plastics

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：