检索结果-内蒙古大学图书馆

Self Sustainable Artificial Intelligence Systems (ICSSAS), International Conference on

作者： U Kumaran Gurupriya M Harshitha Reddy Thodathara Aryagopal Aditya Vijjapu Gattamaneni Harish Dept. of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (数字)9798350368413

ISBN: (纸本)9798350368420

computers have been seamlessly integrated into every domain including health care where one of its applications is in the storage of health care records such as medical images. Electronic healtheare records contain a lot of sensitive information about patients, such as the diseases, diagnosis, treatment plans, drugs administered or medicines prescribed and hence this vital information must not be disclosed at any cost as it can have huge repercussions. As each day passes, more vulnerabilities and threats surface and it is important to come up with secure systems and apt security measures to counter these threats and keep the attackers at bay. This study provides a holistic approach to secure and safeguard medical image records by addressing two problems, the first is image tamper detection using medical image deepfake detection to decipher whether the image has been modified or not, and the second is to employ various cryptographic techniques such as hashing, watermarking and digital signatures to protect the images from getting tampered itself.

关键词： Deepfakes Solid modeling Accuracy Three-dimensional displays Watermarking Predictive models Real-time systems Medical diagnostic imaging Digital signatures Surface treatment

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Approach towards Stratification of Opioid Patients Based on Data Analysis—A Study

Machine Learning Approach towards Stratification of Opioid P...

引用

International Conference on computing and Networking Technology (ICCNT)

作者： A. Siva Ramakrishna Praneeth Ch. Bayapa Reddy Ch. Vijaya Durga Reddy G. Revanth Sai Nalini Sampath Dept. of Computer Science & Engineering Amrita School of Computing Bengaluru Amrita Vishwa Vidyapeetham India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

This work investigates machine learning and deep learning methods for drug categorization in order to address the urgent problem of opioid abuse. Because of the intricacy of the issue, many approaches to anticipate opioid prescribing have not produced adequate results in terms of accuracy. The goal of this study is to use structured and unstructured data from the MIMIC-III database to categorize patients who are opioiddependent. To distinguish between purposeful and inadvertent opioid users, 41 pertinent variables were included in both classic machine learning and deep learning models. The findings show that deliberate users from structured data and inadvertent users from unstructured data may be predicted with greater accuracy. Furthermore, encouraging outcomes were obtained from the integration of these models via knowledge distillation. Additional clarification on the categorization of opioid patients was provided by ablation analysis. Utilizing cutting-edge methods such as knowledge distillation and attention processes, this study improves the accuracy of drug categorization and provides insightful information for managing the opioid problem.

关键词： Deep learning Accuracy Databases MIMICs Opioids Forestry

来源：评论

学校读者我要写书评

暂无评论

Comparative Study of Cryptographic Algorithms in Post Quantum computing Landscape

Comparative Study of Cryptographic Algorithms in Post Quantu...

引用

Data Intelligence and Cognitive Informatics (ICDICI), International Conference on

作者： Anshuman Sahoo Indira Kumar A K Shinu M. Rajagopal Dept. of Computer Science and Engineering Amrita School of Computing Bengaluru Amrita Vishwa Vidyapeetham India

ISBN: (数字)9798350389609

ISBN: (纸本)9798350389616

As the advent of quantum computing looms, the cryptographic landscape faces unprecedented challenges that could render traditional algorithms like AES, RSA, and ECC vulnerable. This paper delves into a comparative study of these classical cryptographic algorithms, examining their foundational principles and evaluating their resilience against quantum computing threats, particularly Shor’s and Grover’s algorithms. Through a combination of theoretical analysis and practical simulations, we assess the potential weaknesses and strengths of AES, RSA, and ECC in the post-quantum era. The study highlights the need for quantum-resistant cryptographic methods and explores how current algorithms can be adapted or replaced to withstand the sophisticated computational capabilities of quantum computers. By bridging the gap between classical and quantum cryptography, this research offers crucial insights into the future of secure digital communication, underscoring the urgency for innovation in cryptographic practices to safeguard data in an increasingly quantum-dominated world.

关键词： computers Technological innovation Quantum computing Computational modeling Elliptic curve cryptography Digital communication Cryptography Quantum cryptography Faces Resilience

来源：评论

学校读者我要写书评

暂无评论

Advanced Latency Compensation Techniques for Seamless Online Gaming Experiences

Advanced Latency Compensation Techniques for Seamless Online...

引用

International Conference for Convergence of Technology (I2CT)

作者： Vijayakumar Soorya Suhas S Bhat Sajjad Shaik Shinu M. Rajagopal Sreebha Bhaskaran Dept. of Computer Science Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (数字)9798350394474

ISBN: (纸本)9798350394481

Online multiplayer games have become increasingly popular in the modern world, attracting a worldwide audience and creating virtual communities that cut across national borders. This research offers strategies for improving multiplayer gaming experiences and addresses the issues of lag and synchronization in networked game environments by introducing a novel combination of latency exposure, latency concealing techniques and prediction models. The use of visual and auditory effects to conceal latency, the display of ping time for player awareness of latency, and the use of algorithms like k-Nearest Neighbors, Decision Trees, and Random Forests for player input prediction in the event of network outages are effective techniques for enhancing gaming experiences. In addition to providing a thorough understanding of the technological nuances of latency control in online multiplayer games, the research presents solutions for scenarios involving real-time gaming. By implementing these techniques, the study demonstrates significant improvements in player experience, characterized by reduced lag, enhanced fairness, and greater responsiveness across various game genres.

关键词： Solid modeling Visualization Three-dimensional displays Games Predictive models Prediction algorithms Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Enhancing Liver Cirrhosis Prognosis: A Machine Learning and Explainable AI Approach 3

Enhancing Liver Cirrhosis Prognosis: A Machine Learning and ...

引用

3rd International Conference on Artificial Intelligence, Computational Electronics and Communication System, AICECS 2024

作者： Jeyabalan, Jeyalakshmi Karthikeyan Amrita School of Computing Amrita Vishwa Vidyapeetham Dept. of Computer Science Engineering Chennai India

ISBN: (数字)9798350391244

ISBN: (纸本)9798350391244

Liver cirrhosis is a final stage of many chronic liver diseases, accompanying with higher morbidity and mortality rates reduce quality of life. The aim of this study is to examine the predictive potential of predictive analytics for survival in patients diagnosed with liver cirrhosis using a large clinical dataset. The employ advanced machine learning tools, like XGBoost, LightGBM and CatBoost to predict survival rates and classify patients in different prognostic subgroups. The above data preprocessing strategy and ensemble model with soft voting and weighted XGBoost work well toward the performance. It achieves of 0.4264 Logarithmic loss and an F1 score of 0.826 over 10 cross-validation splits on a Tensorflow dataset compared to the state-of-the-art genome analysis tools, These values of SHapley Additive exPlanations (SHAP) are even more important to understand the features used in model decisions. These results reflect the promise of machine learning to enable personalized medicine and clinical decision-making in hepatology by improving upon current prognostic predictions. © 2024 IEEE.

关键词： Theranostics

来源：评论

学校读者我要写书评

暂无评论

Seamless Attendance Logging Application: A Technological Revolution in Logbook Capture

Seamless Attendance Logging Application: A Technological Rev...

引用

International Conference for Convergence of Technology (I2CT)

作者： Bhupathi Shwejan Raj Bolisetty Sujith Janagama Vamshi Krishna Anjali Dept. of Computer Science and Engineering Amrita School Of Computing Amrita Vishwa Vidyapeetham Amritapuri India

ISBN: (数字)9798350394474

ISBN: (纸本)9798350394481

In this age of swift technological progress, Most educational establishments seek novel approaches that may further boost productivity. One such challenge has been the manual attendance tracking system in colleges. This research paper presents the development and implementation of an automated college attendance system powered by deep learning-based text extraction models. The primary objective of this system is to remove the labor-intensive process of taking attendance, improve accuracy, and provide valuable insights into student attendance patterns. The research begins by utilizing state-of-the-art deep learning techniques to extract roll numbers from images of attendance sheets. A Convolutional neural network is utilized for situating and identifying text within images. The system then processes this data and marks students as present or absent based on predefined criteria. The findings demonstrate that the automated attendance system, with its high degree of precision, makes a major dent in the time and energy formerly needed for keeping attendance logs, streamlining the whole process significantly. Furthermore, by enabling the ongoing monitoring and analysis of data in real time, educators and administrators are empowered to make evidence-informed decisions about student attendance through insights continuously gained from observant assessment and evaluation.

关键词： Deep learning Productivity Recurrent neural networks Refining Manuals Streaming media Real-time systems

来源：评论

学校读者我要写书评

暂无评论

MAC Address Spoofing and its Impact on Network Security

MAC Address Spoofing and its Impact on Network Security

引用

Sustainable Expert Systems (ICSES), International Conference on

作者： Kumaran U B. Umah Neeharika Ayalasomayujala Akshith Kosanam G Vivek Dept. of Computer Science and Engineering Amrita School of Computing Bengaluru Amrita Vishwa Vidyapeetham India

ISBN: (数字)9798331540364

ISBN: (纸本)9798331540371

This research investigates the technique of MAC address spoofing, which allows users to bypass network restrictions by changing the unique identifier associated with their device's network interface. This research study aims to explore the methods and motivations behind MAC address spoofing attempts and assess their potential impact on network security. Here, participants are asked to provide the URL of the target web application and the desired MAC address to be spoofed. The application launches the browser with the modified MAC address, enabling the user to attempt to access the restricted application. The study's objectives include promoting responsible digital use, understanding the consequences of MAC address spoofing, and addressing the evolving security challenges in the digital age. By gaining insights into the techniques and motivations behind MAC address spoofing, this research contributes to enhancing network security and promoting responsible online behavior.

关键词： Uniform resource locators Education Ecosystems Organizations Impersonation attacks Network security Information age Object recognition Network interfaces Expert systems

来源：评论

学校读者我要写书评

暂无评论

Prompt Palate: A Prompt-Based Restaurant Recommendation System with Scheduling and Chatbot Integration

Prompt Palate: A Prompt-Based Restaurant Recommendation Syst...

引用

International Conference on Computation System and Information Technology for Sustainable Solutions (CSITSS)

作者： Vidula N.A T.Hemanth Babu V. Gopi Kiran Roshni M. Balakrishnan Sreebha Bhaskaran Dept.of Computer Science & Engineering Amrita School of Computing Bengaluru Amrita Vishwa Vidyapeetham India

ISBN: (数字)9798331505462

ISBN: (纸本)9798331505479

In today's fast-paced world, individuals often find themselves craving a culinary adventure but struggle to decide on the perfect restaurant to satisfy their desires. Traditional restaurant search platforms typically offer rigid filters such as location, cuisine, and price range, limiting users' ability to explore options tailored to their specific cravings or preferences. We introduce Prompt Palate, a novel prompt-based restaurant recommendation system that uses natural language processing (NLP) techniques to address this challenge. Prompt Palate allows users to input their culinary desires via human-like prompts whose details and preferences are extracted through NLP algorithms. Moreover, the integration of a chatbot interface enhances user engagement and provides additional information about recommended restaurants. Users can engage in interactive conversations with the chatbot to learn more about menu offerings, ambiance, and special features of preferred restaurants. Additionally, the chatbot facilitates food ordering directly from the recommended restaurants, streamlining the dining or home delivery experience. To ensure a seamless and uncrowded dining experience, we incorporate intelligent scheduling algorithms for efficient table management, staff allocation, and delivery coordination. These algorithms optimize resource allocation, minimize wait times, and prevent overcrowding, thereby enhancing customer satisfaction.

关键词： Limiting Filters Scheduling algorithms Customer satisfaction Oral communication Chatbots Feature extraction Resource management Information technology Recommender systems

来源：评论

学校读者我要写书评

暂无评论

A fusion based approach for uneven illumination correction in retinal images using Gaussian Filtering method

引用

Procedia computer Science 2025年 260卷 991-999页

作者： Suchithra M Soman K P Dept of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Coimbatore-641112 India Center for Computational Engineering and Networking Amrita School of Artificial Intelligence Amrita Vishwa Vidyapeetham Coimbatore-641112 India

Enhancing the poor-quality retinal images is one of the inevitable pre-processing steps in retinal image analysis for the accurate diagnosis and treatment of different eye-related issues such as diabetic retinopathy, macular degeneration, glaucoma, etc. This paper presents a systematic approach to address this challenge by proportionally adjusting the red, green, and blue channels to ensure consistent luminance correction, enhancement, and color preservation. The core of our approach involves generating a luminance scaling matrix using a Gaussian low-pass filter applied to the red channel. This matrix is then used to correct the luminance proportion in each channel, resulting in new luminance-enhanced channels. We then applied Contrast Limited Adaptive Histogram Equalization(CLAHE) for enhancing the structural properties of the luminance corrected retina image. Our approach is effectively validated on two publically available datasets Diaretdb0 and Diaretdb1. We have tested the effectiveness of our proposed method using different evaluation metrics such as entropy, standard deviation, Natural Image Quality Evaluator(NIQE) and Perception-based Image Quality Evaluator(PIQE) measures and also confirms that our approach significantly improves the quality of retinal images, making them more suitable for accurate analysis and diagnosis.

关键词： Uneven illumination Gaussian Filtering image enhancement CLAHE

来源：评论

学校读者我要写书评

暂无评论

Gene Therapy Bio-factory: Mathematical Modeling of the Human Eye Pharmacokinetics 1

引用

1st Southern Georgia Mathematics Conference, SGMC 2021

作者： Carichino, Lucia Guidoboni, Giovanna Kansara, Viral Ciulla, Thomas Harris, Alon School of Mathematics and Statistics Rochester Institute of Technology RochesterNY United States College of Engineering and Computing Professor Electrical and Computer Engineering The University of Maine OronoME United States Clearside Biomedical Inc. AlpharettaGA United States Icahn School of Medicine at Mount Sinai New YorkNY United States

ISBN: (数字)9783031697104

ISBN: (纸本)9783031697098

Neovascular age-related macular degeneration (nAMD) is one of the leading causes of irreversible blindness in the industrialized world. In nAMD, abnormal blood vessel growth occurs under the macula, leading to exudation and scarring, distorting central vision. Current nAMD standard of care involves repeated intraocular injections of drugs that target the vascular endothelial growth factor (VEGF) signaling pathway (anti-VEGF drugs). These treatments have a high burden on patients, caregivers and physicians. Gene therapy based long-lasting production of anti-VEGF proteins in the eye (bio-factory approach) may address some of the limitations of current therapies. We adapt a previously developed three-compartment (retina, vitreous humor, aqueous humor) pharmacokinetic model in rabbits to simulate the pharmacokinetics of anti-VEGF proteins in the human eye delivered by intravitreal injection or produced via the gene therapy bio-factory approach. The model is used to estimate the protein levels in the vitreous humor and retina, and the retina anti-VEGF production rate starting from clinically measured anti-VEGF protein levels in the aqueous, using gene therapy. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Gene therapy

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：