检索结果-内蒙古大学图书馆

6th International Conference on Computational Intelligence and Networks, CINE 2024

作者： Sidpara, Pragati Agarwal, Anshul Swain, Debabrata Gupta, Rajeev Kumar Bhilare, Amol Upkare, Makarand Pandit Deendayal Energy University Dept. of Computer Science and Engineering Gandhinagar India Vishwakarma Institute of Technology Vishwakarma Institute of Technology Dept. of Computer Engineering Pune India

ISBN: (纸本)9798331516796

The aim of this study is to develop an automatic system that uses deep learning techniques to detect cervical spine fractures from medical images. Using a DICOM (Digital imaging and communications in medicine) images of cervical spine, the system can identify a fracture and specify which vertebrae has a fracture. This process involves first processing provided DICOM images, then applying data augmentation techniques including metadata information, finally designing neural network architecture for feature extraction. We use a method called transfer learning, utilizing a pre-trained model like EfficientNet, which is used for feature extraction, while optimizing network parameters using AdanW optimizer and CosineAnnealingWarmup learning rate scheduler. The results demonstrate the successful training of neural network models to identify fracture and that fractured vertebrae, with commendable performance and accuracy level noted during evaluation on validation data. This study has important implications for medical imaging and healthcare industries, since automated fracture detection can increase diagnostic efficiency and accuracy. Moreover, such a system would provide good support to healthcare professionals, specifically radiologists, to identify cervical spine fracture easily. © 2024 IEEE.

关键词： Digital Imaging and Communications in Medicine (DICOM)

来源：评论

学校读者我要写书评

暂无评论

Free Space Optical Communication Using Principles of Quantum Mechanics 4

Free Space Optical Communication Using Principles of Quantum...

引用

4th International Conference on Innovations in computer Science, ICONICS 2024

作者： Angabeen, Tooba Asghar, Fatima Ali Zafar, Roohi Malik, Tahir Khan, Muhammad Mubashir Kamran, Muhammad NED University of Engineering and Technology Dept. of Physics Karachi Pakistan NED University of Engineering and Technology Dept. of Telecommunications Engineering Karachi Pakistan NED University of Engineering and Technology Dept. of Computer Science and Information Technology Karachi Pakistan

ISBN: (纸本)9798331504342

It all begun by the early 1970s through, the work of Stephen Wiesner and Gilles Brassard, who introduced the concept of quantum conjugate coding, and it has now stretched to a level where today's agile communication systems constitute a substantial challenge for data security and safety. A number of research has been performed to achieve secure communication among legitimate parties in which QKD (Quantum Key Distribution) is prominent. Quantum Key Distribution (QKD), also called Quantum Cryptography, enables two communicating parties to share secret cryptographic keys with security that is theoretically guaranteed by the laws of quantum mechanics, assuming ideal conditions. However, practical implementations may be vulnerable to certain attacks, and the security of QKD can be compromised by imperfections in hardware, side-channel attacks, or limitations in real-world setups. In a practical QKD setup, two stations send and receive encoded quantum particles and some classical information. The most rudimentary and well-known QKD protocol is BB84, developed by Bennet and Brassard in 1984. We have developed the simulation and achieved the secret shared key with and without an intruder. © 2024 IEEE.

关键词： Optical communication

来源：评论

学校读者我要写书评

暂无评论

Gauging Deep Learning Archetypal Effectiveness in Haematological Reclamation

引用

SN computer Science 2024年第7期5卷 963页

作者： Pradeep kumar, B.P. Ravikumar, J. Dept. of Computer Science and Design Atria Institute of Technology VTU Karnataka Bangalore India Dept. of Computer Science and Engineering Atria Institute of Technology VTU Karnataka Bangalore India

This paper project an system for reclamation of medical images in an effective way for the extraction and retrieving of data from large archives is critical. This study aims to improve haematological image reclamation by combining visual-based image reclamation (VBIR) approaches with the GLCM algorithm, specifically for characteristics related to the prostate gland. While previous research has focused on computer-aided methods for Gleason grading, our technique focuses on early-stage feature reclamation across 14 paired glands. The experimental findings, including Bicubic Interpolation The resolution Enrichment with a standard deviation of 12.37, kurtosis of 122.83, and skewness of 2.92, demonstrate improved reclamation performance. Our suggested methodology uses a handmade learning approach that includes critical components such as GLCM contrast and correlation. This extensive feature extraction step includes descriptors for morphology, texture, fractals, and contextual information, which are then subjected to in-dept. statistical analysis to identify significant features. Using an RNN, our technique improves performance somewhat but significantly when compared to alternatives, with time required for execution offering insights into the intricate interaction of stages and the effect of sample variability. These findings not only encourage more research, but also help to advance standard reviews in haematological analysis of images. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Gland reclamation Gray-level co-occurrence matrix (GLCM) Haematological Haematological image Prostate gland

来源：评论

学校读者我要写书评

暂无评论

Personalized Movie Recommendation Based on User Preferences Using Optimized Sequential Transformer Model

Personalized Movie Recommendation Based on User Preferences ...

引用

2024 International Conference on Artificial Intelligence and Emerging technology, Global AI Summit 2024

作者： Ravikumar, R.N. Jain, Sanjay Sarkar, Manash Amity University Rajasthan Dept. of Computer Science and Engineering Jaipur India Atria Institute of Technology Dept. of Computer Science and Engineering Banglore India

ISBN: (纸本)9798350379716

This study explores the application of a Transformer based model to the 'MovieLens 1M' and 'MovieLens 10M' datasets provided by GroupLens, which includes one million and ten movie ratings. The Transformer model, known for its proficiency in handling sequence-to-sequence tasks, employs multi-head self-attention mechanisms and position-wise feed-forward networks. Our implementation, developed in PyTorch, benefits from its capacity for automatic differentiation and GPU acceleration, which significantly enhances the training efficiency. The model underwent rigorous hyperparameter tuning and optimization to adapt optimally to the characteristics of the dataset. Performance evaluation using the Normalized Discounted Cumulative Gain (NDCG) metric demonstrates that the Transformer model substantially outperforms a conventional popular recommendation system across various top-K rankings. Specifically, for the MovieLens 1M dataset, the Transformer model achieved NDCG scores of 0.0455, 0.0805, 0.0995, and 0.1273 at top 1, 3, 5, and 10, respectively. Comparatively, the popular recommendation system scored 0.0023, 0.0044, 0.0061, and 0.0091 at these same rankings. This trend of superior performance by the Transformer model is also consistent across the MovieLens 10M dataset, further confirming its effectiveness in ranking highly relevant items at the top of the list. Also, to address quality and utility of recommendations, MAP, Precision, Recall, F1 Score, Coverage and Serendipity metrics evaluated. These results underscore the effectiveness of Transformer models in extracting and leveraging complex patterns in sequence data, demonstrating a clear superiority over traditional methods in recommendation systems. This study highlights the potential of deep learning architectures to revolutionize fields reliant on understanding user preferences and sequential data interactions. © 2024 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

RenalNet: An End-to-End Hybrid Deep Learning and Ensemble Model for Accurate Kidney Disorder Classification 3

RenalNet: An End-to-End Hybrid Deep Learning and Ensemble Mo...

引用

3rd International Conference on Advancement in Electrical and Electronic engineering, ICAEEE 2024

作者： Haque, Fariha Siddique, Md Abu Ismail Shojol, Md. Shojeb Hossain Rajshahi University of Engineering & Technology Dept. of Electronics & Telecommunication Engineering Rajshahi Bangladesh Rajshahi University of Engineering & Technology Dept. of Electrical & Computer Engineering Rajshahi Bangladesh

ISBN: (纸本)9798350388282

Kidney disorders are a major public health issue affecting millions worldwide. Renal calculi and cancer are prevalent, causing chronic kidney disease(CKD). Artificial intelligence can assist in the precise diagnosis of kidney *** developed an end-to-end system using a custom CNN model to extract informative features from kidney images. Multiple ML classifiers provide complementary perspectives. A High-Performance Filter(HPF) selects the top classifiers for an ensemble model. The interactive web interface enables real-time prediction. Our approach achieves excellent performance metrics with an accuracy of 99.98%. Overall, We demonstrate an automated system combining deep learning and ensembling for the accurate characterization of diverse kidney abnormalities, which can aid in the early detection and treatment of CKD. © 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

Converging Diagnostic Paths: A Unified Approach to Acid-Base Imbalances in COPD Patients 2

Converging Diagnostic Paths: A Unified Approach to Acid-Base...

引用

2nd IEEE International Conference on Interdisciplinary Approaches in technology and Management for Social Innovation, IATMSI 2024

作者： Kinikar, Atharva Shah, Manan Pune Institute of Computer Technology Dept. Information Technology Pune India Dwarkadas J Sanghvi Coe Dept. Computer Engineering Mumbai India

ISBN: (纸本)9798350360523

Chronic Obstructive Pulmonary Disease (COPD) significantly impacts patient quality of life and is a leading cause of morbidity and mortality. This paper introduces an innovative algorithm for diagnosing acid-base disorders in COPD patients, incorporating traditional and advanced methodologies like the Henderson-Hasselbalch equation and Bedside Stewart Method. The algorithm enhances the accuracy and speed of Arterial Blood Gas (ABG) analysis, crucial for COPD management. We present a comprehensive approach that includes a Gamblegram for visualizing acid-base balance and a sophisticated system architecture employing Optical Character Recognition (OCR) for efficient ABG report processing. Our findings demonstrate the algorithm's efficacy in providing rapid, detailed analysis, markedly reducing treatment initiation time. This advancement holds significant potential in revolutionizing COPD patient care by improving diagnostic accuracy and treatment strategies for acid-base disorders. © 2024 IEEE.

关键词： Gases

来源：评论

学校读者我要写书评

暂无评论

The Impact of Compiler Warnings on Code Quality in C++ Projects 32

The Impact of Compiler Warnings on Code Quality in C++ Proje...

引用

32nd IEEE/ACM International Conference on Program Comprehension, ICPC 2024

作者： Johansson, Albin Holmberg, Carl Neto, Francisco G. De Oliveira Leitner, Philipp Chalmers University of Technology Dept. of Computer Science and Engineering Gothenburg Sweden Chalmers - University of Gothenburg Dept. of Computer Science and Engineering Gothenburg Sweden

ISBN: (纸本)9798400705861

Modern compilers often offer a variety of warning flags, which developers can enable to get feedback on code that, while syntactically correct, may be problematic. In the case of C++, one example of such 'correct but problematic' code is code that leads to undefined behavior (UB). The usage of compiler warnings has long been suspected as a way to decrease bugs and increase code quality. However, empirical evidence that supports this hypothesis is rare. In this study, we present evidence from a study of 127 open source C++ projects. We categorize their usage of compiler warnings into five groups based on which warning flags are being used, and analyse the relationship between compiler warnings and five quality metrics (bugs, critical issues, vulnerabilities, code smells, and technical debt) using Bayesian analysis. We conclude that, in general, compiler warnings indeed correlate with, and potentially cause, higher code quality, with the clearest impact being on the number of critical issues in a project. Using stricter warning flags expectantly correlates with higher code quality in our study objects. However, there are substantial differences between projects, which we attribute to the project's individual development culture. That is, while warnings matter, other factors such as quality culture, are likely to be even more important to source code quality. © 2024 ACM.

关键词： Quality control

来源：评论

学校读者我要写书评

暂无评论

AI-Driven Power Gating for Enhanced Energy Efficiency in Superscalar Processors 31

AI-Driven Power Gating for Enhanced Energy Efficiency in Sup...

引用

31st IEEE International Conference on High Performance Computing, Data, and Analytics Workshops, HiPCW 2024

作者： Kalra, Naman Tudu, Jaynarayan T. Dept. of Electrical Engineering Indian Institute of Technology Tirupati India Dept. of Computer Science Engineering Indian Institute of Technology Tirupati India

ISBN: (纸本)9798331509118

Amid the rising demand for efficient processors, the challenge has always been to reduce power consumption without compromising performance. FinFET technology has significantly reduced leakage power issues, but dynamic power consumption at lower nodes has reemerged as a concern. Methodologies such as power/clock gating, DVFS, and voltage biasing have been proposed in the past. However, next-generation complex SoC designs at © 2024 IEEE

关键词： System-on-chip

来源：评论

学校读者我要写书评

暂无评论

A comprehensive step of XAI for Bengali and English text detection and recognition from natural scene images 2

A comprehensive step of XAI for Bengali and English text det...

引用

2nd International Conference on Networking, Embedded and Wireless Systems, ICNEWS 2024

作者： Dutta, Mithun Das, Utpol Kanti Das, Jugal Krishna Rangamati Science and Technology University Dept. of Computer Science and Engineering Rangamati Bangladesh Jahangirnagar University Dept. of Computer Science and Engineering Dhaka Bangladesh

ISBN: (纸本)9798350367461

A critical first step in many applications, including augmented reality, document analysis, and scene comprehension, is text detection from images. Even though text identification for the English language has advanced significantly, there are particular difficulties when applying these methods to languages such as Bengali because of variations in script, morphology, and typographic characteristics. This article offers a wonderful method for leveraging the Faster R-CNN framework to identify and categorize text from images that contain Bengali and English sentences. The study utilizes a dataset named "Bengali and English text image dataset (BETID)"that consists of images with text in both Bengali and English scripts, taken from a variety of sources such as books, documents, natural scenes, internet images, and landscapes. Pre-processing methods are used to improve the resilience and generalization of the model, including image scaling, normalization, and augmentation. The Faster R-CNN architecture is tuned and trained to identify text regions in images and categorize Bengali or English text. The performance of the text Classification model is evaluated using evaluation measures such as accuracy on the BETID dataset. The proposed Faster R-CNN model achieved an average of 97.90% accuracy, which is better than other deep learning models. Empirical findings showcase the capacity of transfer learning to alleviate data scarcity concerns and enhance text detection precision for low-resource languages such as Bengali.) © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Techniques for Predicting Ovarian Cancer in its Early Stages Using Biomarkers 6

Machine Learning Techniques for Predicting Ovarian Cancer in...

引用

6th International Conference on Electrical engineering and Information and Communication technology, ICEEICT 2024

作者： Alam, Mir Jafikul Anawar, Jannat-E Mohi Uddin, Khandaker Mohammad Rahman, Md. Hasibur Rahman, Md. Mahbubur Dhaka International University Dept. of Computer Science and Engineering Dhaka Bangladesh Southeast University Dept. of Computer Science and Engineering Dhaka Bangladesh Bangladesh University of Business and Technology Dept. of Computer Science and Engineering Dhaka Bangladesh

ISBN: (纸本)9798350385779

The deadliest gynecological cancer affecting women is ovarian cancer, currently incurable with no effective medication treatments. The key focus of this research is to assess insights for early diagnosis using statistical analysis and machine learning techniques on data from clinical trials obtained from 349 patients. Several techniques, including Random Forest, Decision Tree, Gaussian NB, AdaBoost, and Logistic regression, were applied to find the most reliable factor for ovarian cancer prediction. A clinically evaluated raw dataset of benign samples and malignant ovarian tumor patient data set is used to develop early-stage ovarian cancer predictions, and the effectiveness of ML models was examined utilizing metrics including F1-score, Accuracy, Precision, and Recall. The proposed study shows better outcomes, with the Random Forest classifier exhibiting the highest accuracy for validation at 99% based on the test data of ovarian cancer predictions. Even though early-stage ovarian cancer detection is generally unavailable, cancer diagnosis may be greatly aided by machine learning. © 2024 IEEE.

关键词： Machine learning

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：