检索结果-内蒙古大学图书馆

4th International Conference on Computational Intelligence, Communications and Business Analytics, CICBA 2022

作者： Sarkar, Sandip Das, Dipankar Pakray, Partha Pinto, David Computer Science and Application Hijli College Kharagpur India Computer Science and Engineering Jadavpur University Kolkata India Computer Science and Engineering NIT Silchar Silchar India Facultad de Ciencias de la Computacion Benemerita Universidad Autonoma de Puebla Puebla Mexico

ISBN: (纸本)9783031107658

Building an automatic system to solve Math word problem is very interesting in AI domain. From last four decades Math word problem takes more attention of the researchers. Automatic system of math word problem can increase the effectiveness of e-learning system which is often used in current days. Many research claimed promising result but most of them has worked on small dataset or similar types of problems. It is really difficult to build a system which can work on huge dataset as well as different types of math word problem In this paper, we are trying to build a hybrid deep learning system which can work on large dataset as well as different forms of math word problem. We have done our experiments on Math23K dataset. Our proposed model gives better result than statistical learning and rule based approach. For our experiments we have used Bahdanau attention mechanism which gives better result than traditional methods for math word problem. The accuracy of our proposed mechanism is 0.58 in BLEU score. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

Recall, Retrieve and Reason: Towards Better In-Context Relation Extraction

arXiv

引用

arXiv 2024年

作者： Li, Guozheng Wang, Peng Ke, Wenjun Guo, Yikai Ji, Ke Shang, Ziyu Liu, Jiajun Xu, Zijie School of Computer Science and Engineering Southeast University China Ministry of Education China Beijing Institute of Computer Technology and Application China

Relation extraction (RE) aims to identify relations between entities mentioned in texts. Although large language models (LLMs) have demonstrated impressive in-context learning (ICL) abilities in various tasks, they still suffer from poor performances compared to most supervised fine-tuned RE methods. Utilizing ICL for RE with LLMs encounters two challenges: (1) retrieving good demonstrations from training examples, and (2) enabling LLMs exhibit strong ICL abilities in RE. On the one hand, retrieving good demonstrations is a non-trivial process in RE, which easily results in low relevance regarding entities and relations. On the other hand, ICL with an LLM achieves poor performance in RE while RE is different from language modeling in nature or the LLM is not large enough. In this work, we propose a novel recall-retrieve-reason RE framework that synergizes LLMs with retrieval corpora (training examples) to enable relevant retrieving and reliable in-context reasoning. Specifically, we distill the consistently ontological knowledge from training datasets to let LLMs generate relevant entity pairs grounded by retrieval corpora as valid queries. These entity pairs are then used to retrieve relevant training examples from the retrieval corpora as demonstrations for LLMs to conduct better ICL via instruction tuning. Extensive experiments on different LLMs and RE datasets demonstrate that our method generates relevant and valid entity pairs and boosts ICL abilities of LLMs, achieving competitive or new state-of-the-art performance on sentence-level RE compared to previous supervised fine-tuning methods and ICL-based methods. © 2024, CC BY.

关键词： Demonstrations

来源：评论

学校读者我要写书评

暂无评论

Formula Retrieval Using Structural Similarity

Formula Retrieval Using Structural Similarity

引用

2022 Conference and Labs of the Evaluation Forum, CLEF 2022

作者： Sarkar, Sandip Das, Dipankar Pakray, Partha Pinto, David Computer Science and Application Hijli College Kharagpur India Computer Science and Engineering Jadavpur University Kolkata India Computer Science and Engineering NIT Silchar Silchar India Benemerita Universidad Autonoma de Puebla Facultad de Ciencias de la Computacion Puebla Mexico

Nowadays, the amount of scientific documents which contain mathematical equations is gradually increasing. Retrieving specific documents related to mathematical equations is very challenging. Traditional IR systems cannot deal with scientific documents. For this reason, researchers give more focus to the Mathematical Information Retrieval system, which is one of the domain-specific applications of Information Retrieval (IR). The goal of MathIR is to retrieve documents that contain normal texts as well as mathematical equations. This paper describes the JU_NITS system which has been used for math type data of Math Stack Exchange of ARQMath-3 task. We have participated in Task 2: formula retrieval. For our task, we have created three inverted indexes using three representations of mathematical equations (i.e. Latex, Opt, and slt). For similarity calculation between query and inverted index, we have used cosine similarity. The efficiency of the system is represented in terms of nDCG’, MAP’ and Precision at 10 measures. For each year we have submitted three runs. Among them, formulaL run gives better results which are 0.238, 0.178, and 0.161 (in nDCG’ measure) for ARQMath-1, ARQMath-2, and ARQMath-3 respectively. © 2022 Copyright for this paper by its authors.

关键词： Information retrieval

来源：评论

学校读者我要写书评

暂无评论

Melanoma Malignancy Prognosis Using Deep Transfer Learning

Melanoma Malignancy Prognosis Using Deep Transfer Learning

引用

2023 International Conference on Artificial Intelligence and applications, ICAIA 2023 and Alliance Technology Conference, ATCON-1 2023

作者： Shobarani, R. Sharmila, R. Kathiravan, Mathur Nadarajan Anbarasa Pandian, A. Narasimha Chary, Ch Vigneshwaran, K. Computer Science and Engineering Dr.M.G.R Edu. & Research Institute Tamilnadu Maduravoyal India Computer Application Dhanalakshmi Srinivasan Engg. College Tamilnadu Perambalur India Dr. N. G. P Arts and Science College Department of Biotechnology Tamilnadu Coimbatore India Computer Science & Engineering Panimalar Engineering College Tamilnadu Poonamallae India Computer Science and Engineering Sriindu College of Engg. & Technology Telangana Hyderabad India Electronics & Commu. Engineering K.Ramakrishnan College of Engineering Tamilnadu Trichy India

ISBN: (纸本)9781665456272

Melanoma is a type of Skin cancer that spreads rapidly and has a significant death risk if it is not detected early and treated. A prompt and accurate diagnosis can improve the patient's chances of survival. The creation of a skin cancer diagnostic support system based on computer technologies is highly essential. This study suggests a unique deep transfer learning model for categorizing melanoma malignancy. The proposed system comprises of three main phases including image preprocessing, feature extraction and melanoma classification. The preprocessing phase employs image filters such as mean, median, gaussian and non-local means filter along with histogram equalization techniques to obtain the preprocessed images. Feature extraction and classification are performed using pre-trained Convolutional Neural Network architectures such as DenseNet121, Inception-Resnet-V2 and Xception. Using the ISIC 2020 dataset, the suggested deep learning model's effectiveness is assessed. The experimental findings show that, in terms of precision and computational expense, the suggested deep transfer learning model performs better than cutting-edge deep learning algorithms. © 2023 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

A Single-Stage Deep Learning Approach for Multiple Treatment and Diagnosis in Panoramic X-ray 23th

A Single-Stage Deep Learning Approach for Multiple Treatment...

引用

23rd International Conference on Intelligent Systems Design and applications, ISDA 2023

作者： Singh, Nripendra Kumar Faisal, Mohammad Hasan, Shamimul Goswami, Gaurav Raza, Khalid Department of Computer Science Jamia Millia Islamia New Delhi India Department of Computer Application Galgotias College of Engineering and Technology Greater Noida India Faculty of Dentistry Jamia Millia Islamia New Delhi India Deep Learning Research Team Synergy Labs Gurugram India

ISBN: (纸本)9783031648120

This work investigates the recognition of multiple dental treatment and diagnosis conditions in a full scan dental panoramic image. In this study, we proposed a single-stage oriented deep learning model for five dental therapies, namely restoration, root canal treatment (RCT), RCT with crown, dental implant (DI), and DI with crown, two dental diagnoses (impacted tooth and tooth bud), and natural teeth without any treatment as tooth class. However, considering all eight classes to achieve a wide range of dental radiology data interpretation results in a highly imbalanced dataset. We considered a custom dataset of 661 dental panoramic images where a frequent category is tooth counted 11,282 times, while the least presence category is DI with the crown having 75 instances. The performance of the proposed work was evaluated with average precision of each treatment and diagnosis class. The result of RCT from the dental treatment category achieved an average precision score of 82.63% and recognition of impacted teeth with an average precision score of 18.78% from the dental diagnosis categories. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing Hyperspectral Image Classification Performance Using Adaptive Spectral Band Selection and Clustering-based Mutual Information (ASBS-CMI)

Enhancing Hyperspectral Image Classification Performance Usi...

引用

2024 International Conference on E-Mobility, Power Control and Smart Systems, ICEMPS 2024

作者： Nisha, A. Anitha, A. Noorul Islam Centre For Higher Education Department of Computer Application Kanyakumari District Tamil Nadu Kerala Thuckalay629 180 India Noorul Islam Centre For Higher Education Department of Computer Science and Engineering Kanyakumari District Tamil Nadu Kerala Thuckalay629 180 India

ISBN: (数字)9798350394399

ISBN: (纸本)9798350394399

Hyperspectral imaging is an emerging tool in remote sensing applications for acquiring detailed spectral data. This paper introduces the Adaptive Spectral Band Selection and Clustering-based Mutual Information (ASBS-CMI) approach, employing adaptive spectral band selection through clustering and mutual information to enhance hyperspectral imaging classification. The ASBS-CMI method includes preprocessing for data quality improvement, clustering to group similar pixels, mutual information calculation for identifying informative spectral bands, and subsequent feature extraction from selected bands for classification. Principal Component Analysis is meant for feature extraction to capture spatial-spectral information. Class labels are assigned to hyperspectral data using a Random Forest classifier. Experimental results on Pavia University Scenes and Indian Pines datasets, along with comparisons to Support Vector Machine and Feed Forward Neural Network, demonstrate improved accuracy within a limited time. The proposed methodology's efficiency is evidenced by evaluating performance through various metrics, showcasing its potential to advance hyperspectral image analysis in remote sensing applications. © 2024 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Urban Growth Estimation of Moradabad City Using Sentinel-2 Images

Urban Growth Estimation of Moradabad City Using Sentinel-2 I...

引用

Artificial Intelligence and Emerging Technology (Global AI Summit), International Conference on

作者： Saurabh Srivastava Tasneem Ahmed Rajeev Kumar Department of Computer Science & Engineering Moradabad Institute of Technology Moradabad India Department of Computer Application Integral University Lucknow India

ISBN: (数字)9798350379716

ISBN: (纸本)9798350379723

Accurate monitoring and assessment are necessary due to the enormous challenges posed by rapid urbanization to sustainable development and resource management. This study utilizes Sentinel-2 satellite images of Moradabad City, located in Uttar Pradesh, India, to analyze urban growth through a machine learning approach. Sentinel-2 imagery is widely used for land cover monitoring, and images from 2017 and 2023 were selected to assess the rapid expansion of urbanization. Various techniques, including SVM, ANN and minimum distance (MD), were employed for land surface classification. Among these, SVM produced the most reliable results for estimating urban areas, based on both the Kappa coefficient (Kc) and overall accuracy (O.A.). The SVM estimates that in 2017 about 8.308% of the region was classified as an urban area, and from 2023 that number had increased to about 11.64%, which could be a serious concern for Moradabad city's residents. The motivation behind this study to explore the potential applications of machine learning methods for small-scale urban dynamics monitoring and analysis through satellite image analysis. The research advances knowledge of urbanization processes and offers insightful advice for sustainable urban growth in quickly expanding places.

关键词： Support vector machines Accuracy Urban areas Land surface Estimation Machine learning Satellite images Resource management Sustainable development Monitoring

来源：评论

学校读者我要写书评

暂无评论

Meta In-Context Learning Makes Large Language Models Better Zero and Few-Shot Relation Extractors

arXiv

引用

arXiv 2024年

作者： Li, Guozheng Wang, Peng Liu, Jiajun Guo, Yikai Ji, Ke Shang, Ziyu Xu, Zijie School of Computer Science and Engineering Southeast University Bangladesh Ministry of Education China Beijing Institute of Computer Technology and Application China

Relation extraction (RE) is an important task that aims to identify the relationships between entities in texts. While large language models (LLMs) have revealed remarkable in-context learning (ICL) capability for general zero and few-shot learning, recent studies indicate that current LLMs still struggle with zero and few-shot RE. Previous studies are mainly dedicated to design prompt formats and select good examples for improving ICL-based RE. Although both factors are vital for ICL, if one can fundamentally boost the ICL capability of LLMs in RE, the zero and few-shot RE performance via ICL would be significantly improved. To this end, we introduce MICRE (Meta In-Context learning of LLMs for Relation Extraction), a new meta-training framework for zero and few-shot RE where an LLM is tuned to do ICL on a diverse collection of RE datasets (i.e., learning to learn in context for RE). Through meta-training, the model becomes more effectively to learn a new RE task in context by conditioning on a few training examples with no parameter updates or task-specific templates at inference time, enabling better zero and few-shot task generalization. We experiment MICRE on various LLMs with different model scales and 12 public RE datasets, and then evaluate it on unseen RE benchmarks under zero and few-shot settings. MICRE delivers comparable or superior performance compared to a range of baselines including supervised fine-tuning and typical in-context learning methods. We find that the gains are particular significant for larger model scales, and using a diverse set of the meta-training RE datasets is key to improvements. Empirically, we show that MICRE can transfer the relation semantic knowledge via relation label name during inference on target RE datasets. © 2024, CC BY.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Innovative Deep Learning Model-based Stock Price Prediction using a Hybrid Approach of CNN and Gradient Recurrent Unit 8

Innovative Deep Learning Model-based Stock Price Prediction ...

引用

8th International Conference on Communication and Electronics Systems, ICCES 2023

作者： Rao, B. Srinivasa Bhattacharya, Rajib Tiwari, Manoj Kumar Kumari, K. Aruna Devmane, Mahavir A. Singh, Kamlesh Gokaraju Rangaraju Institute of Engineering and Technology Department of Computer Science and Engineering Telangana Hyderabad India Globsyn Business School Department of Pgdm Bishnupur JL No. 101 South 24 Paganas West Bengal Chandipur India Jecrc University Department of Computer Application Rajasthan Jaipur India University Mathematics Gss Visakhapatnam India Vppcoe & Va Department of Computer Engineering Maharashtra Mumbai India Graphic Era Hill University Department of Computer Science and Engineering Dehradun India

ISBN: (纸本)9798350396638

The fluctuation in stock prices from industry to industry are a major source of concern in the market. As the market attracts more participants and stock prices play a larger role in more transactions, the ability to accurately predict stock price movements becomes more valuable. When making an investment, many people first look at the share price and then try to anticipate whether or not that price will go up or down in the future. The traditional problem of forecasting the stock market using Machine Learning tools and methodologies has been thoroughly studied. Time dependence, volatility, and similar complicated dependencies are interesting aspects that make this modeling non-trivial. To overcome this the proposed method in this work is a deep learning-based hybrid strategy for predicting stock prices. Preprocessing is performed after input is delivered to increase precision. Selecting MPSOA features is the next step. In the end, it's put to use in MC-GRU model training. The proposed method achieves better results than both the CNN and GRU models. © 2023 IEEE.

关键词： Investments

来源：评论

学校读者我要写书评

暂无评论

Examining Driver Sleepiness Detection Based on Visual Actions Using Haar Cascading and CNN

Examining Driver Sleepiness Detection Based on Visual Action...

引用

Disruptive Technologies (ICDT), International Conference on

作者： Vandana Rawat Pratibha Manral Lakshya Gupta Nidhi Joshi Department of Computer Science & Engineering Graphic Era Deemed to be University Dehradun India Department of Computer Application Graphic Era Deemed to be University Dehradun India Department of Computer Application Graphic Era Hill University Dehradun India

ISBN: (数字)9798331519582

ISBN: (纸本)9798331519599

Every hour, there are numerous road accidents all over the world. Some of these accidents are caused by drunk driving, lack of sleep, inattention behind the wheel, and a variety of other factors that can be dangerous for both passengers and other road users. The most frequent circumstance is sleeping deprivation, which can cause the driver to be reckless while operating a motor vehicle. Driver drowsiness detection systems are particularly effective in identifying drowsiness by measuring the size of the driver's eyes and the rate at which they blink using a camera and software that is connected to it. The driver fatigue detection system works utterly offline, leveraging the Haar Cascade and Perclos machine learning methodologies, and can warn the driver via alarm if he or she is feeling drowsy.

关键词： Training Visualization Accuracy Sleep Lighting Wheels Software Software measurement Vehicles Testing

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：