检索结果-内蒙古大学图书馆

2nd International Conference on Artificial Intelligence and Machine Learning applications, AIMLA 2024

作者： Sathya, K. Esther, J. Kavitha, S. Kamalakumari, J. SRM Institute of Science and Technology Faculty of Science and Humanities Department of Computer Applications Chengalpattu Tamil Nadu Kattankulathur603203 India Tagore College of Arts and Science Department of Computer Science Chromepet Chennai India Agurchand Manmull Jain College Dept. Of. Computer Applications Meenambakkam Chennai India

ISBN: (纸本)9798350349221

The security of authentication system completely is connected with confidentiality and strength. Even if graphical authentication system eradicates the weakness of the text password, single-level password system is inadequate to protect our information. Hence, FacetPass a novel password technique is proposed with 4 × 4 of 16 facets arrangement with multiple colours. Facet touch, fading and swap is applied with automatic facial recognition approach which secures from exhaustive attack, technology-based recording, dictionary, and smudge attack. A scrutiny is systematically conducted on the threat of FacetPass in both usability and security with 113 physical users of various people from different age groups, and educational status. The performance of the FacetPass system exceeds the security and usability of other graphical password systems, including VAP codes, CD-GPs, and EvoPass. © 2024 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Artificial Neural Network-Based Steganography: Techniques, applications, and Challenges 3rd

Artificial Neural Network-Based Steganography: Techniques, A...

引用

3rd International Conference on Emerging Trends in Expert applications and Security, ICE-TEAS 2024

作者： Rajput, Prashant Vaisla, Kunwar Toyesh Singh Department of Computer Science Amramali Institute of Management and Computer Applications Shiksha Nagar Lamachaur Uttarakhand Haldwani India Uttarakhand Pauri India

ISBN: (纸本)9789819739905

This paper aims to the understanding and advancement of ANN-based steganography by providing a comprehensive overview of its techniques, applications, and challenges in modern secure communication systems and digital media processing. Artificial neural network (ANN)-based steganography has emerged as a promising approach for embedding secret information into digital media while preserving perceptual quality and resisting detection. This paper presents a comprehensive review of ANN-based steganography techniques, covering various aspects including methodologies, applications, and challenges. Through an in-depth analysis of recent research and advancements, this paper aims to provide insights into the state-of-the-art techniques, applications, and future directions of ANN-based steganography. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Steganography

来源：评论

学校读者我要写书评

暂无评论

Hyperparameter Optimization of Software Quality Model Using Improvised Genetic Algorithm and EEM 1

Hyperparameter Optimization of Software Quality Model Using ...

引用

1st IEEE International Conference on Advances in Computing, Communication and Networking, ICAC2N 2024

作者： Singh, Rakhi Sharma, Vishnu Kaushik, Neeraj Malhotra, Ritu Rauthan, Hemlata Delhi Institute of Higher Education Department of Computer Application Greater Noida India ITS Engineering College Department Of Computer Science and Engineering Greater Noida India Galgotias College of Engineering and Tehnology Department of Computer Applications Greater Noida India GNIOT Institute of Professional Studies Department of Computer Applications Greater Noida India Delhi Institute of Higher Education Department of Computer Applications Greater Noida India

ISBN: (纸本)9798350356816

Software quality analysis has become one of the topmost concerns in the modern world and requires the massive attention of developers and testers during software development. Software quality analysis is a multidimensional notion and one attribute may not describe the software product's overall quality. Software developer's objective is to build a software product that attains the highest quality which depends on multifarious attributes namely functional suitability, maintainability, etc. However, analysis of software product quality is challenging in both the development and maintenance phases. This research is aimed at hyperparameter optimization of the software quality model using an improvised genetic algorithm and an enhanced ensemble model (EEM) approach. In this research, there has been shown the optimal possibility of software quality model hyperparameter optimization using the modified architecture of genetic algorithm along with EEM. To validate the performance of this suggested approach, PROMISE Repository datasets have been utilized. As a result, this proposed approach achieves all performance metrics very optimal. The evaluated values of accuracy, precision, recall, and F1- score are 99.45%, 98.83%, 97.28%, and 99.37%, respectively. In the future, this approach may be integrated with modified architectures of software quality models for automated software product quality analysis. © 2024 IEEE.

关键词： Software quality

来源：评论

学校读者我要写书评

暂无评论

Improving Handwritten Stenography Recognition Using Domain Specific Encoding and Synthetic Data Augmentation

Improving Handwritten Stenography Recognition Using Domain S...

引用

2025 International Conference on Visual Analytics and Data Visualization, ICVADV 2025

作者： Nivetha, S. Kamatchi, C. Bala Hindustan Institute of Technology and Science Department of Computer Applications India

ISBN: (纸本)9798331521394

Handwritten form of stenography recognition is a challenging task due to high variations in shorthand symbols and a lack of annotated datasets. A strong baseline for stenographic text recognition, leveraging the newly created LION dataset of shorthand manuscripts. To alleviate symbol ambiguity as well as low-resource constraints in this domain, incorporating stenographic domain expertise is proposed through encoding schemes and synthetic data generation. In the experiments, a Gated-CNN-BGRU architecture is used, trained with Connectionist Temporal Classification (CTC) loss. Pre-train on synthetic data and fine-tuning on real data greatly improve CER and WER. The experiments showed the effectiveness of stenography-specific encoding schemes in improving WER (Word Error Rate) over baseline models by up to 10% when using Melin-based encodings. This work opens pathways for transcribing historical stenographic manuscripts more effectively. © 2025 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Approach in Detecting Liver Cancer from Medical Images with Explainable AI (XAI) Technique 15

Deep Learning Approach in Detecting Liver Cancer from Medica...

引用

15th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2024

作者： Arjun Kumar, H. Aswin, R. Rahul Varma, U. Department of Computer Science and Applications Amrita School of Computing Amrita Vishwa Vidyapeetham Amritapuri India

ISBN: (纸本)9798331300579

Liver cancer is a pressing global health issue often diagnosed at advanced stages, leading to poor prognosis. Artificial intelligence (AI) has shown promise in improving liver cancer detection from medical images. However, the lack of interpretability in AI models hampers their clinical adop-tion. This research proposes a novel approach that combines U-Net, a deep learning model, with LIME(Local Interpretable Model-agnostic Explanations), Which is an explainable AI technique, to enhance liver cancer detection. The proposed model aims to provide explanations for its predictions,helping physicians comprehend and accept the decisions made by the *** findings support the development of AI in medical diagnostics by demonstrating the efficacy of the suggested method in identifying liver cancer and offering insightful information about the decision-making process. © Grenze Scientific Society, 2024.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Gastrointestinal Lung Cancer Disease Classification via Hybrid Deep Architecture Trained with Improved Pattern Features 5

Gastrointestinal Lung Cancer Disease Classification via Hybr...

引用

5th International Conference on Emerging Systems and Intelligent Computing, ESIC 2025

作者： Mallick, Pradeep Kumar Rout, Subhashree Padhy, Neelamadhab Mohanty, Jnyana Ranjan Beura, Mamata Du School of Computer Engineering Odisha Bhubaneswar India Giet University Department of Computer Science and Engineering Odisha Gunupur India Du School of Computer Applications Odisha Bhubaneswar India

ISBN: (纸本)9798331522100

In the initial stage of lung cancer, GI tract is not frequently the position of metastases. It may be challenging to distinguish pulmonary metastases from the gastrointestinal (GI) tract and primary lung cancer. The following stages are followed to classify the gastrointestinal lung cancer disease: Image acquisition, preprocessing, feature extraction, and classification. The process of collecting images is called image acquisition. As per the work, the benchmark dataset is under consideration. Gaussian filtering is used to preprocess the input image for further processing. Subsequently, the features that are retrieved in the Feature Extraction step include Shape feature, Multi texton features, Improved median Binary Pattern, and Local Gradient Increasing Pattern (LGIP). A hybrid model trained with the extracted features will be used for classification, which integrates Squeezenet and LSTM models. The results of the proposed work is compared over the conventional models in terms of different performance measures. © 2025 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Addressing Food Waste: Survey of Approaches, Technological Innovations and Sustainable Solutions 11

Addressing Food Waste: Survey of Approaches, Technological I...

引用

11th International Conference on Reliability, Infocom Technologies and Optimization, ICRITO 2024

作者： Nandeesh, Talari Rakhra, Manik Chowdary, Pullela Harish Amanpreetsingh Lovely Professional University Department of Computer Science and Engineering Punjab Phagwara India Lovely Professional University Department of Computer Applications Punjab Phagwara India

ISBN: (纸本)9798350350357

Food waste management in our local is to high for solution. This review article critically examines the complex issue of food waste, analyzing root causes and examining environmental and social impacts. The essay delves into the issue of waste across various phases of the food supply system, specifically concentrating on production, processing, distribution, retail, and consumption stages. Environmental impacts, particularly greenhouse gas emissions and resource scarcity, are scrutinized alongside social consequences such as increased food poverty and hunger. The review evaluates existing strategies and technologies to reduce food waste and proposes comprehensive, long-term solutions. © 2024 IEEE.

关键词： Greenhouse gases

来源：评论

学校读者我要写书评

暂无评论

A holistic securing approach to speech steganography system with message embedding and pause optimization

引用

Multimedia Tools and applications 2025年 1-27页

作者： Kumar, Surendra Yadav, Arun Singh Dwivedi, Mridula Kumar, Mohit Department of Computer Engineering and Applications GLA University Uttar Pradesh Mathura281401 India Department of Computer Science University of Lucknow Uttar Pradesh Lucknow226007 India Lucknow India Department of IT Dr. B.R. Ambedkar National Institute of Technology Jalandhar India

Nowadays, prevention control of message sharing as well as security enhancement in speech transmission which occurs due to users having a passion for novel inventions, communication system benefits. In this paper, the main objective is to design a speech steganography framework with covert message data transmission including speech. The secret message data is encrypted with the help of the Hyperelliptic Curve Cryptography (HECC) algorithm to provide a maximum security environment. The designed speech steganography framework is integrated with the pause removal mechanism respectively. Since, the Stegospeech is sent into the channel, as the Stegospeech as of now obtained the secret Message data its transfer speed will increment. Then at that point, it needs high bandwidth for transmission as well as needs higher energy utilization. In this manner, to decrease the data transfer speed, the best procedure is to eliminate the undesirable pause in the speech, the pause removal strategy carried out utilizing the combinations of Ensemble Empirical Mode Decomposition (EEMD) with Hilbert-Huang Transform (HHT). Then, some techniques are used to embed the message into the speech like 4-level Discrete Wavelet Transformation (DWT), Matrix definition, and Single Value Decomposition (SVD). They are likewise utilized for the secret message extraction from speech signal as well as message information from the Stegospeech signal. The presented strategy is carried out and analyzed towards the different invasions in the output. The Correlation Coefficient (CC), the Peak Signal-To-Noise Ratio (PSNR), the Signal-To-Noise Ratio (SNR), the Number of Pixels Changing Rate (NPCR), and the Unified Average Changing Intensity (UACI) are some of the popular standards that are utilised when comparing two encrypted voice signals. The numbers 33.3% and 100%, respectively, for UACI and NPCR are considered to be optimum states. It is noticed that the presented technique provides better Statistical resul

关键词： Steganography

来源：评论

学校读者我要写书评

暂无评论

Personal Workout Trainer Using MediaPipe and OpenCV for Real-Time Guidance and Feedback

Personal Workout Trainer Using MediaPipe and OpenCV for Real...

引用

2025 International Conference on Visual Analytics and Data Visualization, ICVADV 2025

作者： Priyanka, S.P. Janit, Sophia Hindustan Institute of Technology and Science Department of Computer Applications India

ISBN: (纸本)9798331521394

Home workouts have gained significant popularity, but the lack of professional guidance often leads to improper exercise techniques, increasing the risk of injuries and reducing workout efficiency. To address this challenge, a virtual fitness tracker integrates cutting-edge technologies like OpenCV, MediaPipe, and Gemini LLMa to provide an intelligent and adaptive fitness solution. OpenCV processes video feeds to capture user movements accurately, while MediaPipe detects and tracks key body landmarks in real-time, ensuring precise pose estimation. By analyzing this data, Gemini LLM delivers personalized feedback, dynamically adjusting suggestions to correct user form and optimize performance. The system not only bridges the gap between professional trainers and home fitness but also enhances accessibility by offering an interactive and user-friendly experience. With capabilities like exercise repetition tracking, posture correction, and injury prevention, this solution transforms workouts into a safe, engaging, and results-driven experience. The approach demonstrates the potential of integrating computer vision and advanced language models to revolutionize personal fitness training. © 2025 IEEE.

关键词： computer vision Gemini LLM MediaPipe posture detection

来源：评论

学校读者我要写书评

暂无评论

XAI aided Comparative Analysis of X-ray and CT Scans 2024

XAI aided Comparative Analysis of X-ray and CT Scans

引用

16th International Conference on Contemporary Computing, IC3 2024

作者： Ullas, Gautham S. Krishna, S. Department of Computer Science and Applications Amrita School of Computing Amrita Vishwa Vidyapeetham Amritapuri India

ISBN: (纸本)9798400709722

Early diagnosis and treatment of pneumonia are critical, and they have a substantial influence on patient outcomes. We provide a thorough comparison of pneumonia diagnosis models using both conventional X-ray imaging and modern CT scans in this research study. In this work, we examine how well deep learning (DL) models do in accurately identifying pneumonia using both imaging modalities. Furthermore, we investigate the application of Explainable Artificial Intelligence (XAI) methodologies to better understand these models' decision-making procedures and establish confidence in their projections. The research utilizes a mix of dataset that includes CT and X-ray pictures of pneumonia patients that were obtained from several web sources. To determine how well deep learning models for each imaging modality identify pneumonia, we train and test them. We employ XAI approaches to clarify decision-making processes within the models, offering insights into the characteristics that influence the classification results. Our results provide insight into the relative effectiveness of pneumonia detection models in CT and X-ray scans through thorough testing and assessment. Additionally, the combination of XAI and Pneumonia detection model approach shows encouraging progress in improving the robustness and interpretability of models, opening the door for more dependable and beneficial diagnostic systems in the field of medical imaging. © 2024 Copyright held by the owner/author(s).

关键词： computerized tomography

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：