检索结果-内蒙古大学图书馆

SSRN 2023年第7期17卷 264-269页

作者： Bansal, Satish Jadon, Rakesh S. Gupta, Sanjay Kumar Prestige Institute of Management & Research Gwalior India Department of Computer Engineering Madhav Institute of Technology and Science Gwalior India SOS in Computer Science & Applications Jiwaji University Gwalior India

Breast cancer in women is a significant public health concern worldwide, with many cases going undiagnosed until the advanced stages. Early detection is crucial for proper treatment and improved outcomes. There are some pre-trained models used by authors for the detection of breast tumor, but these models require extensive computation power due to their many layers and parameters. To address this issue, it is required to proposed convolutional neural network (CNN) model with fewer training parameters for classification of ultrasound images dataset to determine that a particular image is either benign or malignant. In this paper, CNN model is proposed with changes in some hyperparameters like the number of filters, filter size, batch normalization, learning rate, epoch, and batch size, to achieve better accuracy with less computational power. The proposed model was compared to other pre-trained models, including ResNet50, Efficient Net, and VGG16, using two databases (database A for training and validation data, and database B for testing data). Our proposed classifier outperformed than pre-trained classifiers in terms of accuracy. © 2023, The Authors. All rights reserved.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Stock Price Prediction using Modified BPSO for Feature Selection with RNN Variants on Top Tech Companies

Stock Price Prediction using Modified BPSO for Feature Selec...

引用

2023 IEEE World Conference on Communication and Computing, WCONF 2023

作者： Gupta, Priyank Paharia, Nitin Gupta, Sanjay Kumar Jadon, Rakesh Singh Jiwaji University SOS Computer Science and Applications Gwalior India Prestige Institute of Management and Research Department of Computer Applications Gwalior India MITS Department of Computer Science and Engineering Gwalior India

ISBN: (纸本)9798350311204

The most often utilized data in recent years is time series data, used for things like stock market price prediction and others. Recent research has focused chiefly on stock market prediction using neural networks, and new techniques are being developed to improve these models' accuracy. One such method uses optimization algorithms like PSO, GWO, or GA. Other variants, such as Binary-PSO and Binary-GWO, are developed by further enhancing the original algorithms. The paper suggested a variant of BPSO called MBPSO / TBPSO that assigned binary values to the features during optimization using the 'tanh' activation function. The TBPSO is then applied individually for two, five, and ten years to the datasets of five leading Tech firms. The dataset, which comprises a variety of historical and technical indicators, is applied to different variants of RNN and finds the best results with the GRU model to forecast the closing stock price. What transpired proves that, when used for prediction on the GRU model and when choosing more features than BPSO, TBPSO provides us with features that will provide more accuracy. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Lips and Tongue Cancer Classification Using Deep Learning Neural Network 6

Lips and Tongue Cancer Classification Using Deep Learning Ne...

引用

6th International Conference on Information Systems and computer Networks, ISCON 2023

作者： Bansal, Satish Jadon, Rakesh S. Gupta, Sanjay Kumar Prestige Institute of Management and Research Gwalior India Mits Department of Computer Engineering Gwalior India Sos in Computer Science and Applications Jiwaji University Gwalior India

ISBN: (纸本)9798350346961

One of the major diseases in developing countries is Oral Cancer, caused by alcohol, tobacco product and smoking which creates uncontrolled and abnormal cells in parts of human body. Recent Convolution Neural Network (CNN) has helped in medical industry to used medical images for finding the different types of diseases. The objective of research to build new CNN model which use for analysis the oral cancer images and determine the cancerous and noncancerous image. In this paper, CNN technique and image processing are used to categorize cancer or non-cancer lips and tongue image dataset. Deep Learning approaches is used to develop and check the performance of proposed CNN model. For experiment small Kaggle dataset that contains cancerous and non-cancerous lips and tongue images and apply proposed CNN model (Oral_Cancer_Detection). The result of Oral_Cancer_Detection model is very effective and accurate with low complexity. The Oral_Cancer_Detection model found 94% accuracy in our experiment and achieved better accuracy results in less time.. © 2023 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Stock Price Prediction using Modified BPSO for Feature Selection with RNN Variants on Top Tech Companies

Stock Price Prediction using Modified BPSO for Feature Selec...

引用

Communication & Computing (WCONF), World Conference on

作者： Priyank Gupta Nitin Paharia Sanjay Kumar Gupta Rakesh Singh Jadon SOS Computer Science and Applications Jiwaji University Gwalior India Department of Computer Applications Prestige Institute of Management and Research Gwalior India Department of Computer Science and Engineering MITS Gwalior India

The most often utilized data in recent years is time series data, used for things like stock market price prediction and others. Recent research has focused chiefly on stock market prediction using neural networks, and new techniques are being developed to improve these models' accuracy. One such method uses optimization algorithms like PSO, GWO, or GA. Other variants, such as Binary-PSO and Binary-GWO, are developed by further enhancing the original algorithms. The paper suggested a variant of BPSO called MBPSO / TBPSO that assigned binary values to the features during optimization using the “tanh” activation function. The TBPSO is then applied individually for two, five, and ten years to the datasets of five leading Tech firms. The dataset, which comprises a variety of historical and technical indicators, is applied to different variants of RNN and finds the best results with the GRU model to forecast the closing stock price. What transpired proves that, when used for prediction on the GRU model and when choosing more features than BPSO, TBPSO provides us with features that will provide more accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Lips and Tongue Cancer Classification Using Deep Learning Neural Network

Lips and Tongue Cancer Classification Using Deep Learning Ne...

引用

International Conference on Information Systems and computer Networks (ISCON)

作者： Satish Bansal Rakesh S Jadon Sanjay Kumar Gupta Prestige Institute of Management & Research Gwalior India Department of Computer Engineering MITS Gwalior India SOS in Computer Science & Applications Jiwaji University Gwalior India

关键词： Deep learning Industries Tongue Lips Computational modeling Image processing Neural networks

来源：评论

学校读者我要写书评

暂无评论

Improved symmetric key technique using randomization 1st

Improved symmetric key technique using randomization

引用

1st International Conference on Communication, Networks and Computing, CNC 2018

作者： Chaturvedi, Anshu Sengar, Hirendra Singh Department of Master of Computer Applications M.I.T.S. Gwalior474005 India SOS in Computer Science & Applications Jiwaji University Gwalior474011 India

ISBN: (纸本)9789811323713

Cryptography is the process of turning something readable into something unreadable. Nowadays, internet is being used by the people for exchanging information electronically. The rapid growth of internet increased the number of electronic transactions made by internet users. The information traveled over the internet is very much confidential which need to be secured from unauthorized access, resulted the need of cryptography. In this paper, an innovative technique has been proposed where the three symmetric keys were generated through a randomization process and used for encryption and decryption. Combination of three random keys was used in the encryption process which makes this technique unbreakable and secured against brute force attack and other similar attacks. This technique generates different-different ciphertext each time for the same message which also ensures the protection against various cryptanalytic attacks. This technique can be used to encrypt and decrypt the alphanumeric data in milliseconds which makes the technique more efficient. © Springer Nature Singapore Pte Ltd. 2019.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Algorithms for anonymity preservation in cloud computing 8

Algorithms for anonymity preservation in cloud computing

引用

8th International Conference on Communication Systems and Network Technologies, CSNT 2018

作者： Sarang, Rakesh Prasad SOS in Computer Science Applications Jiwaji University Gwalior M.P474001 India

ISBN: (纸本)9781538659564

Cloud computing is a new technology and modern concept of the world. Users store enormous amount of data on cloud storage for future use. Now a day's anonymity to the data stored in cloud is a feature and protection is a very major challenging mission in cloud computing. The objective of this paper is to provide the anonymity techniques algorithm for the cloud environment. We propose novel techniques such as, Tiered Blind and Anonymous Hierarchical Identity Based Encryption (TBAHIBE) and Spatial Keyword Search (SKS) for providing anonymity preservation to the data stored in cloud server. A spatial keyword search is a preservation that is optimized to database query and stored data in cloud ESHGR. This paper, presents the preceding analysis by considering the anonymity is provided for each data by using the TBAHIBE technique. We have designed a new anonymity algorithm for the cloud environment through an attempt to bring solutions of such problems. © 2018 IEEE.

关键词： Cryptography

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：