检索结果-内蒙古大学图书馆

Breast Cancer Detection and Classification from Mammogram Images Using Multi-model Shape Features

SN computer science 2022年第5期3卷 404页

作者： Gurudas, V.R. Shaila, S.G. Vadivel, A. Dayananda Sagar University Karnataka Bangalore India Department of Computer Science and Engineering GITAM School of Technology GITAM University Karnataka Bengaluru India

Nowadays, breast cancer has become one of the common diseases and is leading in causes of deaths in women. Early detection of breast cancer is very much needed and critical, and mammography is considered as one of the best-suited procedures. The masses are classified as benign or malignant tumors. The size and shape of the masses are characterized by its shapes as per BI-RADS (Breast Imaging-Reporting and Data System), which can discriminate benign and malignant effectively. In this paper, we propose a framework that automatically classifies the benign and malignant tumors in mammogram images. We have considered INBreast and CBIS-DDSM dataset experiments. The histogram-processing multi-level Otsu thresholding on the extracted Region of Interest (ROI) is applied as pre-processing steps for segmenting it. Eighteen features are extracted from the ROI and characterized structure, shape, size, and boundaries of mass present in images belong to both the datasets. The features extracted from the datasets are cross-validated for training and testing using stratified cross-validation techniques. The support vector machine (SVM) and artificial neural network (ANN) classifiers are trained and validated for benign and malignant tumor classification. The experimental results have achieved good results and are promising. © 2022, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Benign Breast cancer Classification Malignant Mammogram Mass Shape Size Tumor

来源：评论

学校读者我要写书评

暂无评论

Secure Metadata Curating the Agile Software Development Process and its Need for Blockchain Storage

Secure Metadata Curating the Agile Software Development Proc...

引用

2022 International Conference on Electronics and Renewable Systems, ICEARS 2022

作者： Parikshith Nayaka, S.K. Dayanand Lal, N. Gitam School of Technology Department of Computer Science and Engineering Karnataka Bengaluru India

ISBN: (纸本)9781665484251

The paper presents the use of Blockchain technology to record the sub-path way of Agile team using Scrum or Lean processes. The agile software development team shares a number of sequential transactions that affect the developmental flow of the software. The key to any agile team's success is the flow of information and coordination with collective responsibilities of the team. The main factors like the corporate culture, user involvement, team capabilities, project management process, project definition process, testing, objectives and goals, scheduling, budgeting, unambiguous requirements specification, selection of agile method and technology. The paper indicates that any manipulation of these main factors would lead to indifferent results and hence a proper documental control of the development process, which is accessible selectively but understood by all stake holders. The paper brings in Blockchain with smart contracts for successfully implementing and increasing profitability from agile software development in an organization along with effective grants, penalties and all stake holders' duties regulation. © 2022 IEEE.

关键词： Metadata

来源：评论

学校读者我要写书评

暂无评论

A hybrid model: PNM for improving prediction capability of classifier

引用

International Journal of Information Technology (Singapore) 2024年第1期16卷 483-491页

作者： Mehrotra, Shashi Muttum, Vinay Kumar Krishna, Redrouthu Vamsi Kumar, Vinod Varish, Naushad College of Computing Science and Information Technology Teerthanker Mahaveer University Uttar Pradesh Moradabad 244001 India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Guntur 522302 India School of Computing Science and Engineering GALGOTIAS University Greater Noida 203201 India Department of Computer Science and Engineering GITAM (Deemed to be University) Rudraram Telangana Hyderabad 502329 India

In recent years, the COVID-19 and its variant are more dangerous for people with some health complexity, such as breast cancer, diabetes, and heart disease. Diagnosis at the early stage of these diseases may save people from deadly diseases and infections. However, often these diseases are diagnosed very late. Classification algorithms are in use for the diagnosis of several diseases. Classification result significance is a major issue in many real-time domains which deal with class imbalance data. Class imbalance data is one of the primary challenges for the performance of classification models. Most sensitive and essential real-time domain data are class imbalances, resulting in poor classification performance. Due to the dominancy of the major class, the classification of the minor class may show high accuracy. Misclassification can not be accepted in medical cases, which can cost human life as well. The paper presents a hybrid model named PNM to address the class imbalance issue and thus improve the performance of the classifiers. This proposed sampling model integrates Principal Component Analysis and the Near-Miss sampling method. Experimental results show the efficiency of the PNM model for the class imbalance data. © 2023, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of computer Applications and Management.

关键词： Class imbalance Classification K-Nearest Neighbor Near-Miss Principal component analysis Support vector machine

来源：评论

学校读者我要写书评

暂无评论

An Effective Expectation of Diabetes Mellitus via Improved Support Vector Machine through Cloud Security

An Effective Expectation of Diabetes Mellitus via Improved S...

引用

2023 IEEE International Conference on Integrated Circuits and Communication Systems, ICICACS 2023

作者： Lal N, Dayanand Hema, K. Spoorthi, T. Chegoni, Ramesh Madhura, K.G. Gitam School of Technology Gitam University Department of Computer Science & Engineering India Cmr Technical Campus Department of It Kandlakoya India Nitte Meenakshi Institute of Technology Department of Artificial Intelligence and Machine Learning Bengaluru India

ISBN: (纸本)9798350398465

Nerve pain, eye difficulties, skin issues, renal problems, heart disease, depression, and a host of other illnesses are all linked to diabetes if left untreated. In an effort to lengthen the human lifespan, scientists all around the world have applied a variety of methods for early disease prediction. Diseases of the eyes, heart, and kidneys are prioritised because they can cause serious consequences and even death if left untreated. After conducting an in-depth analysis of the strategies used by several researchers, the following models were constructed and tested using the datasets most frequently favoured by leading scientists throughout the world. Diabetic retinopathy (DR) is an eye condition, and this research seeks to construct a hybrid learning model for early prediction of DR. The proposed approach combines elements of both Machine Learning and Deep Learning. Score Level Fusion is the last arbiter of the model's precision. Images from the first dataset of its sort reflecting the Indian population, the Indian Diabetic Retinopathy Imaging Dataset, were used to make the prediction. Predicting the DR and recommending the necessary treatment to patients is possible based on severity levels, which ultimately leads to the elimination of blindness. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Enhancing Spatial Steganography for Optimal Data Concealment with Image Quality Preservation

Enhancing Spatial Steganography for Optimal Data Concealment...

引用

Recent Innovation in Smart and Sustainable Technology (ICRISST), International Conference on

作者： Padma R Vamsidhar Yendapalli Department of Computer Science and Engineering GITAM School of Technology GITAM University Bangalore India

ISBN: (数字)9798350309140

ISBN: (纸本)9798350309157

In the domain of steganography, the act of concealing data within an image poses a significant challengebalancing between the precision of the carrier image and the capacity for embedding information. This article introduces an innovative spatial steganography approach employing evolutionary algorithms. Proposed method introduces novel approaches to strengthen the matching of the LSB between the carrier and the concealed image. This process leads to an up-scaled concealing efficiency while minimizing deformation. The technique involved optimized pixel traversal in both row and column wise directions, pixel relocation, pixel swapping confidential bits, and inverting confidential data. A generic steganography model rooted on evolutionary algorithms is formulated to explore optimal solutions. Experimental investigations of the RECS [11] and SDID [16] method confirm that the performance of the proposed method is comparatively better than the traditional methods in terms of higher Embedding rate by 29%, PSNR by 19%, and SSIM by 15% respectively.

关键词： Image quality Steganography Visualization Technological innovation Deformation Evolutionary computation Search problems Optimization

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Neurodegenerative disease detection using Artificial Intelligence

Comparative Analysis of Neurodegenerative disease detection ...

引用

Knowledge engineering and Communication Systems (ICKECS), International Conference on

作者： J Vidya Vamsidhar Yendapalli Department of Computer Science and Engineering GITAM School of Technology GITAM University Bengaluru India

ISBN: (数字)9798350359688

ISBN: (纸本)9798350359695

Neurodegeneration is one of the features of several debilitating diseases that are rising rapidly. As they are not curable and progressive, early detection may help the patients and the caretakers to maintain a good quality of life. Advancements in computational methods have made it possible to diagnose and classify NDD (neurodegenerative diseases) using the automated procedure, which will be more effective than manual detection. This paper aims to comprehensively describe the neurodegenerative disease classification using ML and DL techniques that may help the community working on early detection of the disease.

关键词： Knowledge engineering Deep learning Image segmentation Image analysis Communication systems Magnetic resonance imaging Manuals

来源：评论

学校读者我要写书评

暂无评论

A Mathematical Approach to Prevent and Control COVID-19 Outbreaks: The Improved M-E Model 7th

A Mathematical Approach to Prevent and Control COVID-19 Outb...

引用

7th International Conference on Soft Computing: Theories and Applications, SoCTA 2023

作者： Amiripalli, Shanmuk Srinivas Siva Rama Raju, S.V. Department of Computer Science and Engineering GST GITAM University AP Visakhapatnam530045 India Academic Support Department Abu Dhabi Polytechnic Abu Dhabi United Arab Emirates

ISBN: (纸本)9789819720309

The COVID-19 virus, the eighth in the family of Coronaviridae, will spread swiftly among people, birds, and other animals. This virus spreads mostly via human infections and primarily affects the respiratory and nervous systems. There were more patients reported to hospitals in Wuhan, China, in the month of December 2019. They recognized it as a brand-new Corona virus known as COVID-19. The uncontrolled virus presents humans with two significant problems. Inadequate medical resources are a result of the anomalous development of COVID-19 cases. Lockdowns and other emergency procedures are used as a precaution. We provide a preliminary mathematical model for COVID-19 control and prevention that is based on evolutionary graph theory in our first paper. The well-known social distance approach is used in the proposed model in a variety of ways. In present research an updated model was generated and named as an Improved M-E (Mathematical-Based Epidemic Model) to Prevent and Control COVID-19 through random clustering. Lockdown in many nations causes a drop in GDP and an increase in mental health issues among the population. The distribution of anti-virus has done based on clustering the total population into small groups based on location, relation, culture etc. In the next process identify the random person among the clusters and inject the anti-virus, so that the proposed model will generate quick recovery then the previous model. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Concrete Crack Detection Using Deep Convolutional Generative Adversarial Network 12th

Concrete Crack Detection Using Deep Convolutional Generative...

引用

12th International Advanced Computing Conference, IACC 2022

作者： Padhi, Biswajit Reza, Motahar Shams, Md. Salman Sai, Arcot Navya Department of Mathematics GITAM Deemed to be University Hyderabad502329 India Department of Mechanical Engineering Jamia Millia Islamia Central University New Delhi110025 India Department of Computer Science and Engineering GITAM Deemed to be University Hyderabad502329 India

ISBN: (纸本)9783031356407

To solve the problems related to the small sample extent in intelligent crack detection, we are using the synthetic image sets generation method for concrete cracks are expected based on DCGANs. Since the initial dataset of the crack image is significantly less, that makes a bottleneck to building a deep learning model for better accuracy. DCGANs help generates massive synthetic data for the crack image. This GANS classifier can perform better using this synthetic data and improve the crack features recognition. DCGAN model hyper-parameters are optimized. Subsequently, we are using Adam optimizer to optimize the loss function. The projected technique has the compensations of DCGANs. Finally, a concrete crack classifier detection model based on the CNN is used to classify whether the image is crack or not. In the results, our model has an average accuracy of more than 90%, which is higher than any other method which is proposed before, to estimate using the similar test dataset. This method generates non-real crack images that are nearly similar to real images. That’s why solving the issue of lacking image datasets of cracks in specific concrete surface sections is not an issue. And one more thing, this system provides the data guarantee for the intelligent of concrete crack detection and decrease in concrete surface maintenance & crack detection costs. © 2023, Springer Nature Switzerland AG.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Selective Text Encryption Using RSA for E-governance Applications for Pdf Document

Selective Text Encryption Using RSA for E-governance Applic...

引用

International Conference on Network Security and Blockchain Technology, ICNSBT 2023

作者： Adhikari, Subhajit Karforma, Sunil Assistant Professor BSH Department Institute of Engineering and Management University of Engineering and Management Kolkata India Research Scholar Department of Computer Science University of Burdwan Burdwan India Faculty Department of Computer Science The University of Burdwan Burdwan India

ISBN: (纸本)9789819944323

When data travels through an insecure medium, security must be enforced. The confidentiality of the exchanged data must be guaranteed with the help of encryption techniques. Selective encryption is a very powerful tool for encrypting textual data in a resource constrained environment. In the context of e-governance, textual data is very important and must be protected from any kind of security threat using selective text encryption. In this paper, a fast and efficient selective encryption technique based on an RSA asymmetric key encoding approach is presented. After fetching the whole textual information in the encryption phase, the user will search for a particular word or phrase using regular expression. After that, the selected data will be encrypted using the RSA-1024-bit algorithm and written to a new encoded document with the remaining text data. In the phase of decoding the data, only the encoded text of the document is considered. The experimental result confirms that the encrypting method is secure in terms of statistical security tests and fast in terms of computation time. Our encoding method can be implemented to encrypt any multimedia data like images, audio, and videos. This proposed technique can be used in IOT devices where resources are limited. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

EXB_RNN: A Hybrid Ensemble Approach for Enhanced Aspect-Based Sentiment Analysis 6th

EXB_RNN: A Hybrid Ensemble Approach for Enhanced Aspect-Base...

引用

6th International Conference on Computational Intelligence in Pattern Recognition, CIPR 2024

作者： Ganesh, Devadi Rao, P. V. Venkateswara Reddy, N. Sudhakar Suneetha, Sampathirao Lakineni, Prasanna Kumar Yoganandh, Sampathirao Department of CSE GMR Institute of Technology AP Vizianagaram India Department of CSE GITAM School of Technology GITAM University AP Visakhapatnam India Department of CSE Sri Venkateswara College of Engineering AP Tirupathi India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation AP Vaddeswaram India ANITS AP Visakhapatnam India

ISBN: (纸本)9789819780891

Aspect-based sentiment analysis (ABSA) presents a notable challenge in the realm of sentiment analysis (SA) by emphasizing the identification of fine-grained opinion polarity directed toward particular aspects. This study introduces EXB_RNN, a novel ensemble learning framework for ABSA, adept at discerning nuanced opinion polarities toward specific aspects in texts. Integrating the strengths of ELMo, XLNet, and BERT for profound contextual word representations, bidirectional dependencies, and nuanced contextual embeddings, respectively, EXB_RNN leverages these transformer models as feature extractors for an RNN classifier. This classifier determines sentiment polarity for each aspect, employing a majority voting mechanism to enhance prediction accuracy. Demonstrating its effectiveness, EXB_RNN achieves outstanding accuracy metrics of 97.74%, 98.87%, 97.94%, and 99.05% across various Semeval and Twitter datasets, highlighting its robustness and precision in capturing aspect-level sentiments. This ensemble approach marks a significant advancement in ABSA, combining deep learning techniques to address the complexity of fine-grained sentiment analysis. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Sentiment analysis

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：