检索结果-内蒙古大学图书馆

14th International Conference on Advances in computing, Control, and Telecommunication Technologies, ACT 2023

作者： Sujithra, M. Rathika, J. Velvadivu, P. Abinanda, P. Gayathri, G. Rekha, V.S. Department of Computing – Data Science Coimbatore Institute of Technology Coimbatore India

Dental Biometric is a new field of study in the sector of biometrics identification. This technique can be sometimes used instead of the usual fingerprint biometric identification. In most of the cases, Dental Biometric credentials come handy to analyze the details of a dead person where, the Dental Biometrics of the person before death and the person after their death could potentially explain various reasons for their death and could justify their identity after death. Neural Networks have the potential to learn about anything using their complex construction structure. Here, x-ray copies of the dental teeth structure of a potential individual are given or fed to the network and the neural network with the help of an object detection platform such as OpenCV2 detects the teeth structure and can visualize the teeth structure with x-ray of that individual alone. As the neural is now able to see the teeth, it can learn a lot of crucial details about it from the picture it can understand. The interpretation about the teeth contours and the number of teeth is made along the way. The proposed methodology has better accuracy than the fuzzy clustering relevant methods. Also Suggested to use the appropriate values of parameters that should be opted for the algorithm. © Grenze Scientific Society, 2023.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Hybrid Recommender System for E-Learning Platforms 14

Hybrid Recommender System for E-Learning Platforms

引用

14th International Conference on Advances in computing, Control, and Telecommunication Technologies, ACT 2023

作者： Sujithra, M. Rajarajeshwari, K. Dhamodaran, B. Department of computing – Data Science Coimbatore Institute of Technology Coimbatore India

Internet use has steadily increased over the past 25 years. Numerous online services are improving and simplifying life for people. E-learning is one of these services, which makes the learning process simpler. In this work, a recommendation system will be presented that will assist online course providers in automating course suggestion. By finding patterns in courses based on some attributes like field of interest, skill set, educational qualification, course content, etc. of an individual and courses, this recommendation system is built using hybrid machine learning recommendation techniques, i.e., combination of Collaborative (item based) and content-based recommendation and KNN classifiers. Lastly, the recommendations are pooled from the two blocks of recommended courses (which were discovered using a collaborative technique), similar courses (which is found using content-based finding). © Grenze Scientific Society, 2023.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Emotion Recognition using CNN, LSTM for Multimodal Text, Speech, and Facial Analysis 5

Deep Learning-Based Emotion Recognition using CNN, LSTM for ...

引用

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

作者： Firdou, Talat Binti Ashra, Mohammed Kalpan, A.V. School of Computing Srm Institute of Science and Technology Department of Data Science and Business Systems Tamil Nadu Kattankulathur India

ISBN: (纸本)9798350389609

Emotion detection is a critical field in AI as well as computer vision, seeking to recognize or detect human emotions from facial expressions. Although this area has been greatly advanced through Convolutional Neural Networks (CNNs), current methods using only single-modal data often exhibit reduced accuracy. In this work, we confront these challenges with a hybrid deep learning method for disparate modalities of information such as speech, video, and text. We pre-process and then use CNN feature extractors for the FER2013 data set. The hybrid deep learning model, hence proposed, achieved a weighted accuracy of 79.3% on FER2013, overcoming the conventional unimodal methods. We are using transformers library with the pre-trained RoBERTa model for text. For speech emotion features, we are using TESS dataset then using a CNN and LSTM (Long Short-Term Memory) model. The CNN extracts feature from the speech, while the LSTM is used for temporal analysis to detect emotions. Once these multimodal features have been obtained, our work would be to fuse in order to get the final emotion recognition using Deep Neural Networks (DNNs). The process increases the precision and reliability of the recognition systems, helping to accumulate even more detailed intuition for different emotional states for a combined approach. © 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

ZeroMark: Towards dataset Ownership Verification without Disclosing Watermarks 38

ZeroMark: Towards Dataset Ownership Verification without Dis...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Guo, Junfeng Li, Yiming Chen, Ruibo Wu, Yihan Liu, Chenxi Huang, Heng Department of Computer Science Institute of Health Computing University of Maryland College Park United States College of Computing and Data Science Nanyang Technology University Singapore

High-quality public datasets significantly prompt the prosperity of deep neural networks (DNNs). Currently, dataset ownership verification (DOV), which consists of dataset watermarking and ownership verification, is the only feasible solution to protect their copyright by preventing unauthorized use. In this paper, we revisit existing DOV methods and find that they all mainly focused on the first stage by designing different types of dataset watermarks and directly exploiting watermarked samples as the verification samples for ownership verification. As such, their success relies on an underlying assumption that verification is a onetime and privacy-preserving process, which does not necessarily hold in practice. To alleviate this problem, we propose ZeroMark to conduct ownership verification without disclosing dataset-specified watermarks. Our method is inspired by our empirical and theoretical findings of the intrinsic property of DNNs trained on the watermarked dataset. Specifically, ZeroMark first generates the closest boundary version of given benign samples and calculates their boundary gradients under the label-only black-box setting. After that, it examines whether the given suspicious method has been trained on the protected dataset by performing a hypothesis test, based on the cosine similarity measured on the boundary gradients and the watermark pattern. Extensive experiments on benchmark datasets verify the effectiveness of our ZeroMark and its resistance to potential adaptive attacks. The codes for reproducing our main experiments are publicly available at GitHub. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

PulseSync BP: A Neural Network Framework for Non-Contact Blood Pressure Estimation

PulseSync BP: A Neural Network Framework for Non-Contact Blo...

引用

2024 International Conference on Advances in data Engineering and Intelligent computing Systems, ADICS 2024

作者： Ghosh, Tanumay Singal, Omisha Lodh, Namit Suchitra, S. School Of Computing Srm Institute Of Science And Technology Department Of Data Science And Business Systems Tamil Nadu Kattankulathur India

ISBN: (纸本)9798350364828

Using a cutting-edge neural network framework, 'PulseSync BP' estimates blood pressure without contact. Using photoplethysmogram (PPG) signals and other physiological data, this novel model uses advanced signal processing. The suggested framework changes blood pressure monitoring by eliminating cuff-based measures. PulseSync BP's RNN architecture is carefully designed for optimal prediction accuracy. The algorithm effectively estimates blood pressure through extensive experimentation, demonstrating its potential for continuous healthcare applications. This framework's capacity to use various physiological cues shows its adaptability and versatility. PulseSync BP allows real-time, non-intrusive blood pressure monitoring, advancing individualized health tracking solutions. Cuffless blood pressure estimate is advanced here, demonstrating how artificial intelligence could improve healthcare accessibility and patient-centric monitoring. PulseSync BP and other revolutionary technologies can transform blood pressure monitoring in healthcare. © 2024 IEEE.

关键词： Blood pressure

来源：评论

学校读者我要写书评

暂无评论

E-Evaluation Based Authentication for Virtual Discussion on an Online Platform 2

E-Evaluation Based Authentication for Virtual Discussion on ...

引用

2nd International Conference on Disruptive Technologies, ICDT 2024

作者： Rajkumar, K. Arikumar, K.S. Ragupathi, T. School of Computing Srm Institute of Science and Technology Department of Data Science and Business Systems Tamil Nadu Kattankulathur India

ISBN: (纸本)9798350371055

The main aim of this work is to develop an Online Discussion platform for users. The platforms will become more mature while having more users. In the paper, a sophisticated strategy is suggested to tackle a critical challenge by presenting an effective and secure method for authentication using e-evaluation. The proposal doesn't require extra elements and considers continuous authentication through the random generation of a variable number of questions derived from the gathered information. This application works in various types of browsers as well as in various networks. Many users can use this Discussion platform at the same time. The IP address plays the main role in this application. Discussion platforms and conversational interfaces as they are also known provide a new way for users to interact with other users. A Discussion platform user to share their thoughts and feelings in the same manner that they might address a person. Online discussion forums are considered associate degree extension of ancient learning that promotes dialogue, reflection, information construction, and self-assessment. Given their Potential advantages, online discussion forums are widely adopted as a tool for online learning However, Discussion platforms are currently being adopted at a high rate on computer chat platforms. © 2024 IEEE.

关键词： chats idea knowledge post thoughts Virtual Discussion platform

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Relational Approach Toward Stock Price Prediction and Profitability

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第11期5卷 5844-5854页

作者： Patel, Manali Jariwala, Krupa Chattopadhyay, Chiranjoy Sardar Vallabhbhai National Institute of Technology Department of Computer Science and Engineering Surat395007 India FLAME University School of Computing and Data Sciences Pune412115 India

An accurate estimation of future stock prices can help investors maximize their profits. The current advancements in the area of artificial intelligence (AI) have proven prevalent in the financial sector. Besides, stock market prediction is difficult owing to the considerable volatility and unpredictability induced by numerous factors. Recent approaches have considered fundamental, technical, or macroeconomic variables to find hidden complex patterns in financial data. At the macro level, there exists a spillover effect between stock pairs that can explain the variance present in the data and boost the prediction performance. To address this interconnectedness defined by intrasector stocks, we propose a hybrid relational approach to predict the future price of stocks in the American, Indian, and Korean economies. We collected market data of large-, mid-, and small-capitalization peer companies in the same industry as the target firm, considering them as relational features. To ensure efficient feature selection, we have utilized a data-driven approach, i.e., random forest feature permutation (RF2P), to remove noise and instability. A hybrid prediction module consisting of temporal convolution and linear model (TCLM) is proposed that considers irregularities and linear trend components of the financial data. We found that RF2P-TCLM gave the superior performance. To demonstrate the real-world applicability of our approach in terms of profitability, we created a trading method based on the predicted results. This technique generates a higher profit than the existing approaches. © 2024 IEEE.

关键词： Profitability

来源：评论

学校读者我要写书评

暂无评论

Building Your Query Step by Step: A Query Wizard for the MY DGS - ANNIS Portal of the DGS Corpus 11

Building Your Query Step by Step: A Query Wizard for the MY ...

引用

11th Workshop on the Representation and Processing of Sign Languages: Evaluation of Sign Language Resources, sign-lang@LREC-COLING 2024

作者： Isard, Amy Institute of German Sign Language and Communication of the Deaf and House of Computing and Data Science University of Hamburg Germany

ISBN: (纸本)9782493814302

MY DGS - ANNIS makes the Public DGS Corpus available through the corpus query and visualization tool ANNIS. Due to the complex nature of the corpus, composing queries for advanced research questions can quickly become increasingly complicated. We present a Query Wizard which assists users in building valid queries for MY DGS - ANNIS. Complex queries are built up from smaller blocks, which can be linked to each other through context-sensitive connections. Blocks provide options specific to a given annotation tier and dynamically lead users through their construction while preventing the creation of invalid queries. Once completed, queries can be opened directly in MY DGS - ANNIS. © 2024 ELRA Language Resources Association: CC BY-NC 4.0.

关键词： ANNIS corpus query tool German Sign Language (DGS) query wizard

来源：评论

学校读者我要写书评

暂无评论

Expanding the Vocabulary of BERT for Knowledge Base Construction 1

Expanding the Vocabulary of BERT for Knowledge Base Construc...

引用

1st Workshop on Knowledge Base Construction from Pre-Trained Language Models and the 2nd Challenge on Language Models for Knowledge Base Construction, KBC-LM + LM-KBC 2023

作者： Yang, Dong Wang, Xu Celebi, Remzi Institute of Data Science Department of Advanced Computing Sciences Maastricht University Netherlands

Knowledge base construction entails acquiring structured information to create a knowledge base of factual and relational data, facilitating question answering, information retrieval, and semantic understanding. The challenge called"Knowledge Base Construction from Pretrained Language Models" at International Semantic Web Conference 2023 defines tasks focused on constructing knowledge base using language model. Our focus was on Track 1 of the challenge, where the parameters are constrained to a maximum of 1 billion, and the inclusion of entity descriptions within the prompt is prohibited. Although the masked language model offers sufficient flexibility to extend its vocabulary, it is not inherently designed for multi-token prediction. To address this, we present Vocabulary Expandable BERT for knowledge base construction, which expand the language model’s vocabulary while preserving semantic embeddings for newly added words. We adopt task-specific re-pre-training on masked language model to further enhance the language model. Through experimentation, the results show the effectiveness of our approaches. Our framework achieves F1 score of 0.323 on the hidden test set and 0.362 on the validation set, both data set is provided by the challenge. Notably, our framework adopts a lightweight language model (BERT-base, 0.13 billion parameters) and surpasses the model using prompts directly on large language model (Chatgpt-3, 175 billion parameters). Besides, Token-Recode achieves comparable performances as Re-pretrain. This research advances language understanding models by enabling the direct embedding of multi-token entities, signifying a substantial step forward in link prediction task in knowledge graph and metadata completion in data management. 1 © 2023 CEUR-WS. All rights reserved.

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

Feature Selection in Learning to Rank for Listwise Approach using Multiobjective Evolutionary Algorithm

Feature Selection in Learning to Rank for Listwise Approach ...

引用

2024 International Conference on Innovative computing, Intelligent Communication and Smart Electrical Systems, ICSES 2024

作者： Amala, K.J. Rajeswari, D. School of Computing College of Engineering and Technology Srm Institute of Science and Technology Department of Data Science and Business Systems Kattankulathur India

ISBN: (数字)9798331543624

ISBN: (纸本)9798331543617

Information retrieval systems commonly depend on ranking models to prioritize search results, which requires efficient feature selection to improve accuracy. Feature selection improves the model's query relevance ranking by selecting the most relevant features. This unique method avoids diluting the ranking model with unnecessary variables, resulting in more accurate ranks. The proposed approach consists of three separate stages: multi-objective instance selection, feature selection, and ensemble method. By utilizing a listwise methodology, the algorithm directly enhances the optimization of ranking criteria resulting in enhanced performance. The effectiveness of FS-listwise was evaluated using standardized datasets. After conducting experiments, results shown that the proposed method have peak performance than MOFSRank and classical ranking algorithms, such as ListNet and LambdaMART, in terms of Normalized Discounted Cumulative Gain and consistently selecting a minimal yet highly effective feature set. © 2024 IEEE.

关键词： Contrastive Learning

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：