检索结果-内蒙古大学图书馆

Ancient Character Recognition: A Comprehensive Review

IEEE Access 2023年 13卷 1-1页

作者： Krithiga, R Varsini, SR Gabriel Joshua, R Om Kumar, C U School of Computer Science and engineering Vellore Institute of Technology Chennai India

Deep learning-based character recognition of Tamil inscriptions plays a significant role in preserving the ancient Tamil language. The complexity of the task lies in the precise classification of the age-old Tamil letters (Vattezhuthu) into modern-day Tamil letter structures. Various methodologies and pre-processing techniques have been used for denoising the ancient Tamil manuscript to retrieve the Tamil text. Researchers have used various synthesized and scanned images of stone wall inscriptions, palm leaves manuscripts, and offline handwritten characters for their analysis. Over the years, Ancient Tamil scripts have deteriorated with time due to various natural calamities. Strong denoising and feature extraction methods are required to separate the letters accurately to tackle this issue. Techniques such as CNN(OCR), ResNet, SVM, KNN, HorVer method, etc., are utilized to digitize Tamil characters. This technique has successfully converted handwritten characters into digitalized text for multiple languages, including Tamil, Arabic, English, Latin, Chinese, German, etc. Different models have been evaluated based on their segmentation and recognition rates, accuracy, detection rate, precision, and confusion matrix. This paper will concentrate on Ancient Tamil character segmentation and recognition models. Besides, we will give an overview of the different models and datasets available. Lastly, we summarise the key challenges and the future scope related to the topic. Authors

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

COVINet: A hybrid model for classification of COVID and Non-COVID pneumonia in CT and X-Ray imagery

引用

International Journal of Cognitive Computing in engineering 2023年第1期4卷 149-159页

作者： Mittal, Vasu Kumar, Akhil School of Computer Science & Engineering Vellore Institute of Technology Chennai India

The COVID-19 pandemic has resulted in a significant increase in the number of pneumonia cases, including those caused by the Coronavirus. To detect COVID pneumonia, RT-PCR is used as the primary detection tool for COVID-19 pneumonia but chest imaging, including CT scans and X-Ray imagery, can also be used as a secondary important tool for the diagnosis of pneumonia, including COVID pneumonia. However, the interpretation of chest imaging in COVID-19 pneumonia can be challenging, as the signs of the disease on imaging may be subtle and may overlap with normal pneumonia. In this paper, we propose a hybrid model with the name COVINet which uses ResNet-101 as the feature extractor and classical K-Nearest Neighbors as the classifier that led us to give automated results for detecting COVID pneumonia in X-Rays and CT imagery. The proposed hybrid model achieved a classification accuracy of 98.6%. The model's precision, recall, and F1-Score values were also impressive, ranging from 98-99%. To back and support the proposed model, several CNN-based feature extractors and classical machine learning classifiers have been exploited. The outcome with exploited combinations suggests that our model can significantly enhance the accuracy and precision of detecting COVID-19 pneumonia on chest imaging, and this holds the potential of being a valuable resource for early identification and diagnosis of the illness by radiologists and medical practitioners. © 2023

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

FedGB: Federated Gradient Boosting for Robust Autism Detection 15

FedGB: Federated Gradient Boosting for Robust Autism Detecti...

引用

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

作者： Dhar, Akanksha Gupta, Ishita Anuradha, J. Vellore Institute of Technology Computer Science and Engineering Vellore India

ISBN: (纸本)9798350370249

Autism Spectrum Disorder (ASD) presents substantial problems in cognitive, language, and social skills. Early detection is critical for effective intervention, spurring research into Artificial Intelligence (AI) approaches for ASD detection. Federated Learning (FL) is a promising way to improve accuracy and privacy by training models jointly across distributed datasets. This study presents 'FedGB,' a Federated Gradient Boosting (FedGB) strategy that addresses the drawbacks of existing methods and improves ASD identification. Using FL and Gradient Boosting methods, 'FedGB' combines GridSearchCV for hyperparameter tweaking to ensure optimal performance and secrecy. Extensive experimentation on varied ASD datasets demonstrates higher performance compared to existing approaches, demonstrating 'FedGB''s effectiveness and dependability in improving ASD detection while maintaining privacy. © 2024 IEEE.

关键词： Autism Spectrum Disorder Epsilon Federated Learning Gradient Boost Classifier Grid Search CV Machine Learning

来源：评论

学校读者我要写书评

暂无评论

Click-Through Rate Analysis for Understanding User Behavior in Information Retrieval 15

Click-Through Rate Analysis for Understanding User Behavior ...

引用

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

作者： Azad, Hiteshwar Kumar Sharma, Rohan Verma, Rohan Vellore Institute of Technology Computer Science and Engineering Vellore India

ISBN: (纸本)9798350370249

Improving user satisfaction and personalization in information retrieval is an ongoing challenge. This research delves into user behavior analysis using click-through data, providing a deeper understanding of user intent beyond initial interactions. This article utilizes click-through analysis to uncover user preferences, resulting in search results that align more closely with user intent. These insights contribute to more refined search experiences, enhancing user satisfaction and personalization across digital platforms. The experimental outcomes demonstrate the effectiveness of the proposed approach for capturing user preferences and tailoring search results accordingly. © 2024 IEEE.

关键词： Classification Analysis Click-Through Data Visualization Heatmap Visualization Machine Learning

来源：评论

学校读者我要写书评

暂无评论

Renaissance of Fuzzy and Fast Matching Entity with DSHS Algorithm

引用

SN computer science 2024年第6期5卷 734页

作者： Kari, Venkatram Amalanathan, Geetha Mary School of Computer Science and Engineering Vellore Institute of Technology University

Entity matching is a crucial aspect of data management systems, requiring the identification of real-world entities from diverse expressions. Despite the human ability to recognize equivalences among entities, machines struggle due to variations in expression. This challenge underscores the necessity for a robust framework capable of matching entities based on their attributes. While previous studies have explored transformation techniques, NLP, and deep learning, they often fall short in accuracy and scalability or overlook internal constraints. Such shortcomings result in costly rework and compromised business decisions. To address these issues, proposed “Deep Semantic Homophonic Synonymy” (DSHS) algorithm, a hybrid approach integrating rule-based, NLP, and deep learning techniques. By employing semantic matching, rule-based preprocessing, NLP enrichment, phonetic analysis, abbreviation variations, and spelling corrections, the DSHS algorithm effectively overcomes entity matching challenges. This solution, comprising six modules including Preprocessing, Transformation, Translation, Word Embedding, Attribute Similarity, and Classification, outperforms existing EM models in terms of accuracy and scalability. This solution is a comprehensive entity matching, offering significant advancements in the field and providing a reliable framework for resolving complex matching requirements. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Data pipeline Data sync up MDDR Message queue Schema registry

来源：评论

学校读者我要写书评

暂无评论

High Utility Periodic Frequent Pattern Mining in Multiple Sequences

引用

computer Modeling in engineering & sciences 2023年第10期137卷 733-759页

作者： Chien-Ming Chen Zhenzhou Zhang Jimmy Ming-Tai Wu Kuruva Lakshmanna College of Computer Science and Engineering Shandong University of Science and TechnologyQingdao266590China Department of Information Technology Vellore Institute of TechnologyVellore632014India

Periodic patternmining has become a popular research subject in recent years;this approach involves the discoveryof frequently recurring patterns in a transaction sequence. However, previous algorithms for periodic patternmining have ignored the utility (profit, value) of patterns. Additionally, these algorithms only identify periodicpatterns in a single sequence. However, identifying patterns of high utility that are common to a set of sequencesis more valuable. In several fields, identifying high-utility periodic frequent patterns in multiple sequences isimportant. In this study, an efficient algorithm called MHUPFPS was proposed to identify such patterns. To addressexisting problems, three new measures are defined: the utility, high support, and high-utility period sequenceratios. Further, a new upper bound, upSeqRa, and two new pruning properties were proposed. MHUPFPS usesa newly defined HUPFPS-list structure to significantly accelerate the reduction of the search space and improvethe overall performance of the algorithm. Furthermore, the proposed algorithmis evaluated using several *** experimental results indicate that the algorithm is accurate and effective in filtering several non-high-utilityperiodic frequent patterns.

关键词： Decision making frequent periodic pattern multi-sequence database sequential rules utility mining

来源：评论

学校读者我要写书评

暂无评论

Enhanced prediction of agricultural CO2 emission using ensemble machine learning-based imputation approach

引用

Neural Computing and Applications 2024年第36期36卷 22867-22887页

作者： Thendral, M. Sathya Abinaya, S. Devi, M. K. Kavitha Department of Computer Science and Engineering Thiagarajar College of Engineering Madurai625015 India School of Computer Science and Engineering Vellore Institute of Technology Chennai600127 India

The agricultural sector contributes significantly to greenhouse gas emissions, which cause global warming and climate change. Numerous mathematical models have been developed to predict the greenhouse gas emissions from agriculture. However, the database utilized for prediction has thousands of missing values and imbalanced data records due to various factors, such as environmental disasters, sensor failure, maintenance issues, and budgetary constraints. Many researchers have either completely discarded records with missing values or have only partially addressed the issue, leading to less precise predictions. This study proposes a machine learning-based ensemble approach that uses multiple imputation by chained equations (MICE), K-nearest neighbors (KNN), and MissForest techniques to impute the missing values by reducing uncertainties and improves robustness in predictions. Furthermore, Synthetic Minority Oversampling Technique (SMOTE R) addresses data imbalance in CO2 emissions prediction by generating synthetic data to balance the target variable's distribution in the regression problem. Thereby the proposed SMOTE R and ensemble imputation approach aims to improve prediction accuracy and reliability by tackling data completeness and distribution issues simultaneously. The experiments are conducted on the GRACEnet database shows that the proposed approach outperforms the existing work in measure of R2, MAE, and RMSE metrics. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Greenhouse gas emissions

来源：评论

学校读者我要写书评

暂无评论

Crafting Captivating Narratives: Enhancing Image Captioning Through Encoder-Decoder Architectures 2

Crafting Captivating Narratives: Enhancing Image Captioning ...

引用

2nd IEEE International Conference on Data science and Network Security, ICDSNS 2024

作者： Sahaaya Arul Mary, S.A. Pandey, Adamya Kumar Jha, Aadarsh Sharma, Kartikay Shohel, Mohmad Natarajan, B. School of Computer Science and Engineering Vellore Institute of Technology Vellore India School of Information Technology Vellore Institute of Technology Vellore India School of Computer Science and Engineering Vellore Institute of Technology Chennai India

ISBN: (纸本)9798350373110

This research work aims to develop an image captioning system utilizing deep learning techniques. The pre-trained VGG-16 model is employed to extract image features, while an innovative encoder-decoder architecture is used to generate descriptive captions. To ensure compatibility with the model, pre-processing techniques are applied to the dataset, which comprises images and their corresponding descriptions. Tokenization, vocabulary generation, and effectively utilizing a data generator are integral parts of the training process, facilitating the handling vast datasets. Multiple training epochs are employed to optimize the model's ability to associate captions with specific picture attributes. The model's performance is evaluated using BLEU-1 and BLEU-2 scores on a designated test set, providing quantitative insights into the quality of the generated captions. Additionally, this work includes a visualization component enabling users to input names of specific images, generating captions in real-time for comparative analysis with actual captions. This comprehensive approach integrates methodologies from computer vision and natural language processing, showcasing how deep learning can enhance the interpretability and comprehension of images akin to human perception. BLEU is a widely used, automated metric for evaluating image captioning models, offering objective and quantitative comparisons. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

DERNNet:Dual Encoding Recurrent Neural Network Based Secure Optimal Routing in WSN

引用

computer Systems science & engineering 2023年第5期45卷 1375-1392页

作者： A.Venkatesh S.Asha School of Computer Science and Engineering Vellore Institute of TechnologyChennaiIndia Centre for Cyber Physical Systems&School of Computer Science and Engineering Vellore Institute of TechnologyChennaiIndia

A Wireless Sensor Network(WSN)is constructed with numerous sensors over geographical *** basic challenge experienced while designing WSN is in increasing the network lifetime and use of low *** sensor nodes are resource constrained in nature,novel techniques are essential to improve lifetime of nodes in *** energy is considered as an important resource for sensor node which are battery powered *** WSN,energy is consumed mainly while data is being transferred among nodes in the *** research works are carried out focusing on preserving energy of nodes in the network and made network to live ***,this network is threatened by attacks like vampire attack where the network is loaded by fake ***,Dual Encoding Recurrent Neural network(DERNNet)is proposed for classifying the vampire nodes s node in the ***,the Grey Wolf Optimization(GWO)algorithm helps for transferring the data by determining best solutions to optimally select the aggregation points;thereby maximizing battery/lifetime of the network *** proposed method is evaluated with three standard approaches namely Knowledge and Intrusion Detection based Secure Atom Search Routing(KIDSASR),Risk-aware Reputation-based Trust(RaRTrust)model and Activation Function-based Trusted Neighbor Selection(AF-TNS)in terms of various *** existing methods may lead to wastage of energy due to vampire attack,which further reduce the lifetime and increase average energy consumed in the ***,the proposed DERNNet method achieves 31.4%of routing overhead,23%of end-to-end delay,78.6%of energy efficiency,94.8%of throughput,28.2%of average latency,92.4%of packet delivery ratio,85.2%of network lifetime,and 94.3%of classification accuracy.

关键词： Wireless sensor network vampire nodes lifetime optimal routing energy encryption decryption trust value optimization

来源：评论

学校读者我要写书评

暂无评论

Efficient Road Segmentation Techniques with Attention-Enhanced Conditional GANs

引用

SN computer science 2024年第1期5卷 176页

作者： George, Glenn Varghese Hussain, Mohammad Shahil Hussain, Rizwan Jenicka, S. School of Computer Science and Engineering (SCOPE) Vellore Institute of Technology (VIT) Vellore India

Road segmentation from aerial images is a challenging yet crucial task, underpinning significant applications in urban planning, navigation, and transportation systems. In this study, we employ a conditional Generative Adversarial Network (GAN) architecture that synergistically integrates the strengths of Attention U-Net and PatchGAN to address this task. The Attention U-Net, serving as the generator, is trained on the publicly available Massachusetts Roads dataset, with an emphasis on critical regions while concurrently disregarding the irrelevant ones, thereby enhancing the accuracy of road segmentation. Simultaneously, the PatchGAN discriminator ensures the generation of sharp, high-quality segmentations. Through this cooperative approach, we have achieved an overall accuracy of 98.2%, a recall of 82.30%, a precision of 78.66%, an Intersection over Union (IoU) of 67.19%, and an F1 score of 80.44% on our dataset. While these results are promising, they also highlight areas for improvement, particularly in reducing false positives and enhancing the identification of all road pixels, underscoring the potential for future refinements in this research domain. © 2024, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Aerial image analysis Attention U-Net Conditional generative adversarial network (CGAN) Deep learning-artificial neural network Road segmentation

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：