检索结果-内蒙古大学图书馆

Fake Face Detection Based on Fusion of Spatial Texture and High-Frequency Noise

Chinese Journal of Electronics 2025年第1期34卷 212-221页

作者： Dengyong Zhang Feifan Qi Jiahao Chen Jiaxin Chen Rongrong Gong Yuehong Tian Lebing Zhang Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation School of Computer and Communication Engineering Changsha University of Science and Technology School of Computer and Communication Engineering Changsha University of Science and Technology Changsha Social Work College Changkuangao Beijing Technology Co. Ltd. School of Computer and Artificial Intelligence Huaihua University

The rapid development of the Internet has led to the widespread dissemination of manipulated facial images, significantly impacting people's daily lives. With the continuous advancement of Deepfake technology, the generated counterfeit facial images have become increasingly challenging to distinguish. There is an urgent need for a more robust and convincing detection method. Current detection methods mainly operate in the spatial domain and transform the spatial domain into other domains for analysis. With the emergence of transformers, some researchers have also combined traditional convolutional networks with transformers for detection. This paper explores the artifacts left by Deepfakes in various domains and, based on this exploration, proposes a detection method that utilizes the steganalysis rich model to extract high-frequency noise to complement spatial features. We have designed two main modules to fully leverage the interaction between these two aspects based on traditional convolutional neural networks. The first is the multi-scale mixed feature attention module, which introduces artifacts from high-frequency noise into spatial textures, thereby enhancing the model's learning of spatial texture features. The second is the multi-scale channel attention module, which reduces the impact of background noise by weighting the features. Our proposed method was experimentally evaluated on mainstream datasets, and a significant amount of experimental results demonstrate the effectiveness of our approach in detecting Deepfake forged faces, outperforming the majority of existing methods.

关键词： Deepfakes Adaptation models Attention mechanisms Noise Transforms Transformers Feature extraction Internet Convolutional neural networks Faces

来源：评论

学校读者我要写书评

暂无评论

Automatic Skin Pathology Prognoser - Cutis Care

Automatic Skin Pathology Prognoser - Cutis Care

引用

2023 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2023

作者： Snekha, S. Sanjana, M. Sanjiv, S. Kishore Harshan Kumar, R. Ramya, J. Artificial Intelligence and Data Science St. Joseph's College of Engineering Chennai India

ISBN: (纸本)9798350319200

It takes a Physician, a family doctor, a specialist and a chief doctor to diagnose a skin disease and make a critical decision about the treatment process. It is important for a Doctor to spend enough time on a patient's diagnosis as it decides the course of treatment. The prevalence of skin diseases in the general population in different geographic regions of India varies from 7.9 to 60 percent. This ratio is increasing as the skin diseases are not considered seriously and handled very recklessly by people People are lazy to go visit a doctor until and unless it becomes something serious Diseases like Psoriasis first start like a small rash and can be treated and cured if found in a early stage whereas delaying makes it deadly. The aim is to automatically diagnose a skin disease just by scanning the affected part. © 2023 IEEE.

关键词： convolutional neural network cosine similarity data augmentation machine learning recommendation system Skin disease tf-idf

来源：评论

学校读者我要写书评

暂无评论

A Review on the Applications of Machine Learning and Deep Learning Techniques for Skin Cancer Detection 4

A Review on the Applications of Machine Learning and Deep Le...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Wanjari, Ketan Verma, Prateek Faculty of Engineering and Technology Department of Computer Science and Engineering Maharashtra Wardha442001 India Faculty of Engineering and Technology Department of Artificial Intelligence and Data Science Maharashtra Wardha442001 India

ISBN: (纸本)9798331523923

Skin cancer is the most commonly reported type of cancer globally and one of the few cancers that can be effectively treated if detected in its early stages. Recent advancements in artificial intelligence (AI) have significantly improved skin cancer diagnosis through Machine Learning (ML) and Deep Learning (DL) models. This review explores ML and DL methodologies, including Random Forest, Convolutional Neural Networks (CNNs), Inception Networks, ResNets, and Support Vector Machines (SVMs), which have been widely used for automated diagnosis. However, existing AI-based systems face several challenges, including the need for balanced datasets, model interpretability issues, computational complexity, and difficulties in generalizing across diverse populations. Moreover, multimodal detection systems and Explainable AI (XAI) present additional challenges in making AI-driven diagnoses more reliable and transparent. This article discusses these challenges while also highlighting emerging techniques that integrate multiple data sources and individualized diagnostic tools to enhance precision. By addressing these challenges, this review aims to provide insights into the practical advancements and future directions of AI in skin cancer detection and treatment. © 2025 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Transfer Learning and Fine-tuned CNN Architecture for Dog Breed Classification 3

Transfer Learning and Fine-tuned CNN Architecture for Dog Br...

引用

3rd International Conference on artificial intelligence For Internet of Things, AIIoT 2024

作者： Gunaranjan, K. Vijay, K. Naveen, P. St. Joseph's College of Engineering Department of Artificial Intelligence and Data Science Chennai India SRM institute of science and technology Department of computational intelligence Chennai India

ISBN: (纸本)9798350372120

This study presents a comprehensive approach to dog breed classification, leveraging transfer learning algorithms and Convolutional Neural Networks (CNNs). The dataset utilized for training and evaluation is sourced from the Dog Breed Identification dataset, encompassing 120 distinct breeds. A pre-trained CNN model is employed, and through the application of transfer learning, the proposed models achieve an impressive accuracy rate of 99%. The primary objective is to enable users to submit images of dogs, with the model accurately identifying the specific breed from the diverse dataset. The research underscores the efficacy of transfer learning and pretrained models in achieving exceptional accuracy for the nuanced task of dog breed classification, contributing to the advancements in image recognition within the context of diverse canine breeds. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

artificial intelligence Support for the Prompt Identification and Understanding of the Broader Spectrum of Autism in Children 5

Artificial Intelligence Support for the Prompt Identificatio...

引用

5th International Conference on IoT Based Control Networks and Intelligent Systems, ICICNIS 2024

作者： Julaiha, A.G. Noorul Hemamalini, S. Preiya, V. Sathya Sathyamoorthy, K. Priyanka, V. Rajalakshmi Institute of Technology Centre for Data Science Department of Computer Science & Engineering Chennai India Panimalar Engineering College Department of Artificial Intelligence & Data Science Chennai India Panimalar Engineering College Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798331518097

This research work presents a novel language intervention system for Tamil-speaking children with autism spectrum disorder (ASD). The system satisfies the considerable requirement for tools aimed at one more section of population that has actually been forgotten by mainstream economics. Traditional language learning applications often lack specificity for diverse linguistic contexts, focusing on general learning rather than the unique challenges faced by ASD children. The proposed solution leverages Deep Learning (DL) modules to transform partial spoken Tamil words into complete, child-friendly vocabulary. This system goes beyond simple word completion;it incorporates interactive features to engage children with ASD and promote active learning. Preliminary evaluations yielded promising results, suggesting the system's potential in enhancing communication skills among Tamil-speaking children with ASD. This paper research study reviews the limitations of existing language learning tools and the rationale behind employing a DL-based approach. We discuss the specific DL architecture (e.g., Recurrent Neural Networks) envisioned for the system and how it will be trained on a corpus of Tamil speech data. This study also investigate the potential advantages beyond vocabulary learning, such as improved sentence formulation and the development of practical language abilities. Future ambitions include broadening the system's scope to include more languages, refining the DL model through ongoing training with enriched datasets, and conducting extensive user research with varied ASD populations. Validation across demographics is critical to ensuring the system's efficiency and generality. This research has the potential to bridge the language acquisition gap for Tamil-speaking children with ASD, empowering them to develop crucial communication skills and fostering their social inclusion. © 2024 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Few-shot image semantic segmentation based on meta-learning: A review

引用

Journal of Intelligent and Fuzzy Systems 2024年第5-6期47卷 351-367页

作者： Liu, Yu Zhu, Ye Chong, Haoze Yu, Ming School of Electronic and Information Engineering Hebei University of Technology Tianjin China School of Artificial Intelligence and Data Science Hebei University of Technology Tianjin China College of Computer and Information Engineering Tianjin Agricultural University Tianjin China

Deep learning-based image semantic segmentation approaches heavily rely on large-scale training datasets with dense annotations and often suffer from scarce semantic labels for unseen categories. This limitation has spurred a research trend in Few-shot image Semantic Segmentation (FSS), which makes it possible to segment objects of new categories using only a few labeled samples. Although more and more FSS methods are emerging and gradually integrated into practical applications, a deep understanding of its achievements and issues is still missing. In this survey, we focus on the recent developments of FSS, specifically on FSS methods based on meta-learning. According to different network architectures, we summarize the related research into three classes, that are Convolutional Neural Network-based (CNN-based) models, Graph Neural Network-based (GNN-based) models, and Transformer-based models. Then, we explore the specific implementations of these models, including parameter-based methods, metric-based methods, attention-based methods, and optimization-based methods. Furthermore, we illustrate datasets and analyze the experimental results of various kinds of methods. Toward the end of the paper, we discuss the limitations of FSS and present its applications and challenges to provide further research directions. © 2024 - IOS Press. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Millibots: Integrating Deep Learning Algorithms for Autonomous Control in Small-Scale Robotics 15

Millibots: Integrating Deep Learning Algorithms for Autonomo...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Sneha, A. Angel Diwan, B. Stella Maris College Of Engineering Artificial Intelligence and Data Science Department Nagercoil India Joesphs College Of Engineering Department of Computer Science St Chennai India

ISBN: (纸本)9798350370249

Millibots, miniature robotic platforms, have emerged as pivotal tools in various domains, ranging from medical interventions to environmental monitoring. However, their diminutive size presents formidable challenges in achieving autonomous navigation and control. In this paper, we delve into the realm of millibots and propose a groundbreaking approach to tackle these challenges by integrating deep learning algorithms for autonomous control. Leveraging the power of deep learning, we address the intricate interplay between perception, decision-making, and locomotion in small-scale robotics. Our methodology not only overcomes the limitations inherent to millibots but also unlocks new frontiers in their application. Through a comprehensive review of related work, meticulous experimentation, and insightful analysis, we demonstrate the unparalleled efficacy of our approach. This paper not only accelerates the advancement of small-scale robotics but also envisions a new era of autonomous exploration and innovation. © 2024 IEEE.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Enhanced Cooling Techniques for Photovoltaic Panels using Arduino-Controlled Water Circulation Systems 5

Enhanced Cooling Techniques for Photovoltaic Panels using Ar...

引用

5th International Conference on IoT Based Control Networks and Intelligent Systems, ICICNIS 2024

作者： Srikanth, K. Shiva Bhargavi, K. Vinod Reddy, S. Natarajan, Karuppiah Devi, Tellapati Anuradha Hariharan, Shanmugasundaram Vardhaman College of Engineering Department of Electrical and Electronics Engineering Hyderabad India Vardhaman College of Engineering Department of Artificial Intelligence and Data Science Hyderabad India

ISBN: (纸本)9798331518097

Photovoltaic solar systems harness solar energy using panels with multiple solar cells. These cells are semiconductor that convert sunlight energy directly into electrical energy through the PV process. However, they only convert less than 20% of the incoming solar radiation into electricity, with the rest turning into heat. Temperature is a crucial factor affecting the power output of these systems. As temperatures rises, electrical power decreases. Effective cooling enhances energy production by preventing cells from overheating and potential damage. Studies show that the overall efficiency and output of the PV modules are inversely related to their temperature. The growing demand for these PV systems is driven by their ability to produce clean, environmental friendly electricity from sunlight. Lower temperatures improve performance and efficiency, reduce temperature-induced power losses, and extend the modules' lifespan, leading to better long-term results. © 2024 IEEE.

关键词： Air-cooling System Module temperature Photovoltaic cell PV module Cooling methods Solar energy conversion Water Cooling System

来源：评论

学校读者我要写书评

暂无评论

Classification of Tuberculosis Bacilli from Microscopic Sputum Smear Images Using Swin Transformer

Classification of Tuberculosis Bacilli from Microscopic Sput...

引用

2025 International Conference on Multi-Agent Systems for Collaborative intelligence, ICMSCI 2025

作者： Vallabhaneni, Praneeth Satapathy, Ashutosh Indugula, Manisha Velagapudi Ramakrishna Siddhartha Engineering College Department of Artificial Intelligence and Data Science Vijayawada India Velagapudi Ramakrishna Siddhartha Engineering College Department of Computer Science and Engineering Vijayawada India

ISBN: (纸本)9798331509828

Tuberculosis (TB) has been a great challenge in the health world, and proper treatment requires proper diagnosis at the right time. This paper has classified the bacilli in sputum samples into single/simple and clump formations using deep-learning transformer techniques. The method starts with semantic segmentation, where TransUNet model has been used on sputum images to detect regions containing the bacilli. The superior visual task performer, the Swin Transformer, further classifies the regions identified. Accuracy, precision, recall, F1-score, and AUC-ROC are the metrics used to evaluate the model's performance. This classification contributes to TB diagnosis by quantifying bacterial load and categorizing infection severity. This type of differentiation may guide clinicians in developing more precise treatment strategies as the variability of infection severity may be observed in patients suffering from TB. Integrating the recent transformer models, such as Swin Transformer and TransUNet, into the microbiological diagnosis process will improve the speed of TB diagnosis, and automated bacterial classification will occur through an organized process. This study will help diagnose TB by improving the capacity of diagnosis, which subsequently helps in better decision-making regarding treatment and management, independent of human interpretation. The successful classification of TB bacilli resulted in an average accuracy of 93%, average precision of 93%, average recall of 92.5%, and average F1-score of 92.5%. © 2025 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Multi-Objective Genetic-Programming Hyper-Heuristic for Evolving Interpretable Flexible Job Shop Scheduling Rules 13

Multi-Objective Genetic-Programming Hyper-Heuristic for Evol...

引用

13th IEEE Congress on Evolutionary Computation, CEC 2024

作者： Pang, Junwei Mei, Yi Zhang, Mengjie Centre for Data Science and Artificial Intelligence School of Engineering and Computer Science Victoria University of Wellington PO Box 600 Wellington New Zealand

ISBN: (纸本)9798350308365

The job shop scheduling problem is an important combinatorial optimisation problem in the real world. Genetic programming hyper-heuristic has been successfully applied to automatically evolve effective dispatching rules to make a schedule in real time without much domain knowledge. However, the interpretability of GP-evolved rules has been largely neglected, which could lead to the lack of reliability and trustworthiness of the evolved rules in practice. Current work related to interpretable genetic programming algorithms primarily uses the model size as the interpretability metric. This could not fully reflect the interpretability of evolved rules. To overcome the limitation, we employ structural complexity and dimension gap as more comprehensive interpretability measures. In addition, a new multi-objective genetic programming algorithm, which applies the a non-dominated sorting method to solve the objective selection bias issue, is proposed to optimise the makespan (scheduling objective), structural complexity and dimension gap simultaneously. A variety of experiments demonstrates the competitive performance of our proposed algorithm based on effectiveness, convergence and diversity. Furthermore, the semantics of evolved dispatching rules are analysed to show their better interpretability. © 2024 IEEE.

关键词： Genetic programming

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：