检索结果-内蒙古大学图书馆

LP norm regularized deep CNN classifier based on biwolf optimization for mitosis detection in histopathology images

International Journal of Information Technology (Singapore) 2024年第6期16卷 3517-3536页

作者： Lijo, Jithy Janardhanan Subramanian, Saleema Department of Computer Science Christ University Karnataka Bengaluru India Department of Statistics and Data Science Christ University Karnataka Bengaluru India Department of Computer Science and Applications Christ Academy Institute for Advanced Studies Karnataka Bengaluru India

Mitosis detection, a crucial biomedical process, faces challenges like cell morphology variability, poor contrast, overcrowding, and limited annotated dataset availability. This research presents a novel method for mitosis detection in histopathological images highlighting two important contributions using a Bi-wolf optimization-based LP norm regularized deep Convolutional neural network (CNN) model. This hybrid optimization protocol is the key to the precise calibration of model parameters and effective training, which translates into optimal classifier performance. The results reveal that this model achieves high accuracy, sensitivity, and specificity values of 96.69%, 91.89%, and 97.74% respectively. © Bharati Vidyapeeth's institute of computer Applications and Management 2024.

关键词： Biwolf optimization Feature extraction LP Norm Regularized deep CNN Pre-processing Yolo V5

来源：评论

学校读者我要写书评

暂无评论

TrA-MHWR: Transformer-Enhanced Feature Extraction with Attention-Based Recognition for Offline Handwritten Malayalam Words 2

TrA-MHWR: Transformer-Enhanced Feature Extraction with Atten...

引用

2nd IEEE International Conference on Emerging Research in Computational science, ICERCS 2024

作者： Anju, A.T. Chacko, Binu P Mohamed Basheer, K.P. Sullamussalam Science College Department of Computer Science Malappuram India Prajyoti Niketan College Department of Computer Science Trisssur India Amal College of Advanced Studies Department of Computer Science Malappuram India

ISBN: (纸本)9798331534950

The article introduces TrA-MHWR a unique methodology transformer-based model designed to facilitate the recognition of handwritten Malayalam words in an offline setting. The model features remarkable ability to transform raw pixel data into meaningful linguistic units. Utilizing the power of Vision transformers and attention units, the model offers a sophisticated framework for robust and precise identification of handwritten Malayalam words in offline contexts. This study presents a comprehensive analysis of the architecture, training methodology, and evaluation results of TrA-MHWR, demonstrating its efficacy in pushing the boundaries related to the recognition of handwritten words in relation to Malayalam language. The proposed study uses DeiT model with a multi-head self-attention layer to improve feature sensitivity and achieved 98.82% accuracy. © 2024 IEEE.

关键词： Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Approaches for Early Detection and Prediction of Chronic Kidney Disease Using Machine Learning 5

Data-Driven Approaches for Early Detection and Prediction of...

引用

5th International Conference on Information Management and Machine Intelligence, ICIMMI 2023

作者： Mathai, Shibi Thirunavukkarasu, K.S. Department of Computer Science Vels Institute of Science Technology and Advanced Studies Pallavaram Chennai India

ISBN: (纸本)9798400709418

In recent years, the application of machine learning (ML) techniques for medical diagnostics has shown promising advancements. This study introduces a distinctive method for predicting chronic kidney disease (CKD) harnessing the prowess of ML. Our methodology encompasses an innovative data preprocessing approach, intricate feature engineering, and an amalgamation of ensemble techniques for model training. By evaluating our model on a dataset sourced from Kaggle, comprising 400 samples, we achieved an impressive accuracy of 98%, outperforming traditional methods. The findings underscore the potential of ML in revolutionizing CKD diagnostics, laying a foundation for further exploration in this domain. © 2023 ACM.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Named Entity Recognition for Protecting Sensitive Data using Hybrid CNN 5

Named Entity Recognition for Protecting Sensitive Data using...

引用

5th International Conference on Smart Systems and Inventive Technology, ICSSIT 2023

作者： Gowr, P. Sheela Kumar, N. Vels Institute of Science Technology and Advanced Studies Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9781665474672

Named entity recognition is a natural language processing technique that effectively recognizes and categorizes named entities in a document. The named entity recognition helps to bring out dynamic information about a document or gather critical data to store in a database. Deep learning helps to develop over time, while NLP examines the structure and standards of language and produces an automated system that can discern meaning from text. Mining the essential entities in a text helps identify related data, which is vital when functioning with enormous datasets. The proposed system has a feature that can retrieve and identify sensitive data such as PAN numbers, bank account numbers, and Aadhar numbers from unstructured text data.. The proposed model is designed using Hybrid CNN and it attains 95% F1-Score, 97.5% precision, and 98.3% recall. © 2023 IEEE.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Conglomerate Energy Efficient Elgamal Encryption Based Data Aggregation Cryptosystems in Wireless Sensor Network

引用

International Journal of Engineering, Transactions B: Applications 2022年第2期35卷 417-424页

作者： Babu, T.G. Jayalakshmi, V. Department of Computer Applications Vels Institute of Science Technology and Advanced Studies Pallavaram Chennai India

Wireless sensor networks (WSN) are growing rapidly since the pastdecade mainly due to its efficiency and Ad-Hoc feature. The data aggregation has been extensively employed in WSN that also impacton the data transferring between the sensor nodes. The security issues, data integrity and confidentiality become vital during the deployment of sensor network in a hostile environment. The entire network comprises of sensors, base stations, gateways and nodes which are connected for the purpose of digital transmission. Many existing works have been evolved to address the security issues in WSN butall focused only on basic security features but lack to obtain reliable and effective results in terms of parameters like energy consumption, packet delivery ratio, and computational cost. T his paper focussed on the primary research area of data aggregation and the mode of transmission in an energy efficientway without congestion. To obtain the objective, an integration of Conglomerate ElGamal energy efficient protocol has been employed and the performance of the proposed system are evaluated. Since the resource constraint nodes of the wireless sensor network requires less energy to cope up with limited battery power, the main purpose of the work is to build an efficient security mechanism that enhances the performance of the network with less energy, minimum delay, and maximum throughput. The performance parameters like packet delivery ratio, throughput, estimation of alive nodes and dead nodes for different rounds has been performed in the study. Furthermore, the effectiveness of the proposed system has been compared with state of artmet hods in terms of residual energy and depicted that deliberat es the superior performance of the presented framework. © 2022 Materials and Energy Research Center. All rights reserved.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Alzheimer's Disease Classification using Transfer Learning and Data Augmentation 3

Deep Learning-Based Alzheimer's Disease Classification using...

引用

3rd IEEE International Conference on Intelligent Technologies, CONIT 2023

作者： Anand, Deva Gowr, P. Sheela Logesh, S. Anand, S.M. Vels Institute of Science Technology and Advanced Studies Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350338607

Alzheimer's disease is a pressing healthcare concern worldwide, highlighting the importance of early and accurate detection. Deep learning models, particularly those utilizing transfer learning, have shown promise for AD classification. This research study explores the effectiveness of transfer learning in training models based on deep learning for the classification of Alzheimer's condition. We trained several transfer models using DenseNet121, InceptionV3, Xception, and ResNet101. Based on performance evaluation, InceptionV3 was selected as the base model, outperforming in comparison to the accuracy of the other models. To enhance the accuracy of the InceptionV3 base model, we added capacity, tuned hyperparameters using Keras tuner, and utilized data augmentation techniques. The final model was trained on the Kaggle Alzheimer's Dataset, consisting of 4 classes of images, and achieving an AUC value of 87%. Our research demonstrates that transfer learning and other data augmentation approaches are useful in improving the accuracy of deep learning models for the categorization of Alzheimer's condition. This research has practical implications for improving public health outcomes, facilitating timely intervention and effective treatment. It contributes to the development of more accurate diagnostic tools for AD and can help address the challenges associated with this disease. © 2023 IEEE.

关键词： Neurodegenerative diseases

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study on the Application of Text Mining in Cybersecurity

引用

Recent Advances in computer science and Communications 2023年第3期16卷 80-93页

作者： Barik, Kousik Misra, Sanjay Konar, Karabi Kaushik, Manju Ahuja, Ravin Department of Computer Science JIS Institute of Advanced Studies & Research JIS University Kolkata India Department of Computer Science and Communication Ostfold University Halden Norway Department of Computer Engineering Amity University Jaipur India Center of ICT/ICE Research CUCRID Covenant University Ota Nigeria

Aims: This paper aims to conduct a Systematic Literature Review (SLR) of the relative applications of text mining in cybersecurity. Objectives: The amount of data generated worldwide has been attributed to a change in different activities associated with cyber security, and demands a high automation level. Methods: In the cyber security domain, text mining is an alternative for improving the usefulness of various activities that entail unstructured data. This study searched databases of 516 papers from 2015 to 2021. Out of which, 75 papers are selected for analysis. A detailed evaluation of the selected studies employs sources, techniques, and information extraction on cyber security applications. Results: This study extends gaps for future studies, such as text processing, availability of datasets, innovative methods, and intelligent text mining. Conclusion: This study concludes with interesting findings of employing text mining in cybersecurity applications;the researchers need to exploit all related techniques and algorithms in text mining to detect and protect the organization from Cybersecurity applications. © 2023 Bentham science Publishers.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning Technique Based Automated Feature Analysis of Gene Expression Data

Reinforcement Learning Technique Based Automated Feature Ana...

引用

2023 International Conference on Circuit Power and Computing Technologies, ICCPCT 2023

作者： Jayakrishnan, R. Meera, S. Vels Institute of Science Technology and Advanced Studies Computer Science & Engineering Tamil Nadu Chennai India Vels Institute of Science Technology and Advanced Studies Department of Computer Science & Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350333244

Immunohistochemistry and reverse transcription polymerase chain reaction, it is feasible to find molecular markers that are specific to cancer;nevertheless, there are no pathognomonic molecular markers available for the vast majority of solid tumors at this time. In this paper, we develop a Reinforcement learning Technique based automated feature analysis of gene expression data. This provides support for the idea that, on average, all the validation findings and training data from each epoch were utilized. This proposed method helps to acquiring knowledge at a more leisurely pace is, in the end, what makes episodic deep RL possible as a potential choice for students to pursue. To put it another way, the slow but steady accumulation of knowledge paves the path for the rapid extension of one existing body of information. The proposed methods provide 98 percent of the accuracy result than existing ANN and DNN. The proposed framework outperformed existing methods in terms of increase accuracy rate and reduced execution time than other methods © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Classification of Soil Moisture Content with the Application of Deep Learning

Classification of Soil Moisture Content with the Application...

引用

2024 International Conference on Integrated Circuits, Communication, and Computing Systems, ICIC3S 2024

作者： Ansari, Mohammad Shaharyar Gautam, Prateek Raj Centre for Advanced Studies AKTU Department of Computer Science and Engineering Lucknow India School of Computer Science UPES Uttarakhand Dehradun India

ISBN: (纸本)9798350364088

India is an agricultural-oriented nation where soil moisture plays a vital role in the growth of plants and crops. Measuring soil moisture and maintaining a balance in the soil moisture content help sustain water resources. The traditional method for calculating the soil moisture content is to calculate the weight of moisture soil and dry soil differences. With time passage, different techniques are introduced based on different sensors. Recently, machine learning and deep learning have emerged as powerful tools and can be used for the classification of different levels of soil moisture. Convolution Neural Network is a technique used in the field of deep learning for the classification of images. This algorithm is used to analyze the images on various factors like texture, color, hue, and shapes. In this research, images have been collected from the internet image search and stored in separate folders according to their class. CNN is applied to the created dataset and after tuning the hyperparameters model reaches an accuracy of 73%. © 2024 IEEE.

关键词： Soil moisture

来源：评论

学校读者我要写书评

暂无评论

Detection of Brain Tumor using Transfer Learning using Conventional Autoencoder with Long Short Term Memory Method 6

Detection of Brain Tumor using Transfer Learning using Conve...

引用

6th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2025

作者： Agalya, D. Kamalakkannan, S. Department of Computer Science School of Computing Sciences Vels Institute of Science Technology & Advanced Studies Pallavaram Chennai India Department of Information Technology School of Computing Sciences Vels Institute of Science Technology & Advanced Studies Pallavaram Chennai India

ISBN: (纸本)9798331522667

Brain tumor (BT) has generate a significant health challenge by putting pressure on healthy brain parts or spreading into other areas as well as blocking the flow of fluid around the brain. BT diagnosis is an extensive and time consumption process that depends primarily on radiologists experience and interpretive capabilities. For the area of medical imaging, automatic segmentation of images by means of Deep Learning (DL) approaches. The DL approaches assist in transforming the sector, resulted in improving precision and effectiveness of investigations. However, there are various feature extraction mechanisms available. Therefore, the Recurrent Neural Network (RNN) is utilized for feature extraction and image classification. In model execution, the data have trained in transforming the test image as well as data features for minimizing the domain shift is calculated through the Convolutional Autoencoder (CAE) for reconstruction loss. This research has concentrated in building a model with VGG16 as a single test that subjected at inference and existing method is adopted as neural networks for AE as Transfer Learning (TL) that performs an image analysis task such as segmentation and even set as an adopter for pre training the model. The AE used to train from the source dataset and perform as the adaptors in optimizing during testing using a test subject for effective computation. Moreover, the Long Short Term Memory (LSTM) is utilized as RNN model with CAE for providing improved detection of BT in healthcare industries. Hence, the proposed CAE with LSTM is compared with AE with Convolutional Neural Network (CNN) for evaluating BT detection using MRI dataset with various BT type classifications. © 2025 IEEE.

关键词： Image 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：