检索结果-内蒙古大学图书馆

Intelligent Cyber Physical Systems and Internet of Things (ICoICI), International Conference on

作者： Jay Kant Pratap Singh Yadav Zainual Abdin Jaffery Laxman Singh Electrical Engineering Department Jamia Millia Islamia Central University New Delhi India Computer Science & Engg. (AI&ML) Department Krishna Group of Institutions Ghaziabad India

ISBN: (数字)9798331540661

ISBN: (纸本)9798331540678

Face recognition involves identifying or verifying a person based on their facial features. This study introduces a method using Legendre moments for feature extraction combined with an auto-associative memory approach, specifically a “Multi-connection Hopfield Neural Network” to enhance accuracy and robustness. The method uses a single image per person, optimizing both the computation time and memory usage. Tested on the ORL (Olivetti Research Laboratories) dataset, the approach achieved a 99.0% recognition rate, outperforming other state-of-the-art methods. Additionally, the system demonstrated resilience to noise, maintaining a 95.75 % rate with 50 % random noise.

关键词： Training Associative memory Accuracy Face recognition Noise Hopfield neural networks Feature extraction Robustness Noise measurement Resilience

来源：评论

学校读者我要写书评

暂无评论

Unmasking Deep Fakes: Detecting Low-Quality Forgeries through Unseen Artifacts

Unmasking Deep Fakes: Detecting Low-Quality Forgeries throug...

引用

Electronics and Sustainable Communication Systems (ICESC), 2020 International Conference on

作者： M. Venkateshwarlu M. Yashaswi Dhanya Shah R. Akash Reddy Department of Computer Science and Engineering(AI & ML) Vignan Institute of Technology and Science Nalgonda Telangana

ISBN: (数字)9798350379945

ISBN: (纸本)9798350379952

The spread of deepfakee-technology is a danger to the veracity of multimedia material, since it may be used to manipulate people's identities or spread false information. Low-quality forgeries continue to be difficult to detect because of their subtle artifacts, which elude traditional detection approaches. This is true even while deep fake detection algorithms have made significant progress in identifying high-quality forgeries. This research work presents a unique method for identifying hidden elements in low-quality forgeries, which may be used to uncover deep fakes. The proposed approach, which makes use of sophisticated machine learning algorithms and computer vision techniques, is centred on locating and taking advantage of distinctive artifacts that are introduced throughout the deep fake production process. This study provides a thorough analysis of these artefacts and show how well they can distinguish between real multimedia material and poor-quality deep fakes. The proposed technique is effective in properly detecting low-quality forgeries of photos, videos, and audio recordings. These findings are based on experiments conducted on a variety of datasets. Additionally, the proposed method's resilience is assessed against the cutting-edge deep fake creation techniques and emphasize its practical benefits in preventing the distribution of false information.

关键词： Deepfakes computer vision Machine learning algorithms Communication systems Neural networks Production Streaming media Forgery Detection algorithms Resilience

来源：评论

学校读者我要写书评

暂无评论

Dynamic and Energy-Efficient Resource Allocation using Bat Optimization in 5G Cloud Radio Access Networks 2

Dynamic and Energy-Efficient Resource Allocation using Bat O...

引用

2nd IEEE International Conference on Networks, Multimedia and Information Technology, NMITCON 2024

作者： Padmakala, S. Al-Farouni, Mohammed Rao, Deepak Dasaratha Saritha, Kambhampati Puneeth, R.P. Saveetha Institute of Medical And Technical Sciences Saveetha University Saveetha School of Engineering Department of Computer Science And Engineering Chennai India The Islamic University College of Technical Engineering Department of Computers Techniques Engineering Najaf Iraq Indian Institute of Technology Patna India Gokaraju Rangaraju Institute of Engineering and Technology Department of Ai & Ml Hyderabad Bachupally India Department of Computer Science and Engineering Karnataka India

ISBN: (纸本)9798350372892

G networks represent the fifth iteration of cellular networks, thus aimed at resolving the challenges and constraints faced by the preceding 4G network. Cloud Radio Access Networks (CRAN) provides economical and EnergyEfficient (EE) solutions customized to the requirements of 5G networks. This research proposes an energy-efficient CRAN that automatically allocates Baseband Unit (BBU) resources to Remote Radio Unit (RRHs) based on traffic, increasing network throughput as well as reducing power usage. Bat Optimization Algorithm (BOA) is a Swarm Intelligence (SI) approach used to optimize Resource Allocation (RA) in CRAN by mapping BBURRHs. Through controlling the BBU's mode based on resource utilization, this research minimizes the Power Consumption (PC) in 5G CRAN. Moreover, the findings revealed that the proposed BOA-CRAN reduced the power usage upto 95% when compared to existing methods such as 5G CRAN, Green-RAN while increasing BBU efficiency. © 2024 IEEE.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach to Skin Cancer Detection using CNN, ResNet, and Hybrid Feature Extraction

A Novel Approach to Skin Cancer Detection using CNN, ResNet,...

引用

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

作者： T.Srinivasa Ravi Kiran Y.Sudha Madhuri P Venkata Bala Annapurna A. Lakshmanarao B.S.N. Murthy Department of Computer Science Parvathaneni Brahmayya Siddhartha College of Arts & Science Vijayawada AP India Department of CSE(AI&ML|DS) Anil Neerukonda Institute of Technology and Sciences Department of AI&ML Aditya University Surampalem India Department of IT Aditya University Surampalem India Bonam Venkata Chalamayya Engineering College Odalarevu Andhra Pradesh

ISBN: (数字)9798350368413

ISBN: (纸本)9798350368420

Skin cancer is a prevalent and potentially life-threatening condition, making early and accurate detection crucial for effective treatment. This work proposes a novel hybrid approach to skin cancer detection, integrating both deep learning and traditional ml techniques. Utilizing a dataset from Kaggle, the process began with initial classification using a Convolutional Neural Network (CNN) and achieved an accuracy of 90%. Features were then extracted using Histogram of Oriented Gradients (HOG), Local Binary Patterns (LBP), and ResNet, adding multiple layers of feature richness. These features were combined into a comprehensive hybrid feature vector and analyzed using ml models, including Random Forest, XGBoost, and AdaBoost. The Random Forest model achieved an accuracy of 96%, while XGBoost obtained an accuracy of 95. 60%. AdaBoost reached an accuracy of 95%. The proposed method demonstrated significant improvements in detection accuracy and robustness, highlighting its effectiveness in enhancing skin cancer detection.

关键词： Accuracy Soft sensors Feature extraction Vectors Skin Robustness Real-time systems Convolutional neural networks Random forests Skin cancer

来源：评论

学校读者我要写书评

暂无评论

Adaptive residual convolutional neural network for moiré image restoration

引用

International Journal of Information Technology (Singapore) 2025年第2期17卷 783-791页

作者： Malagi, Vindhya P. Naresh, E. Mithra, C. Suresh, B. V. N. V. Krishna Department of AI & amp ML Dayananda Sagar College of Engineering Bengaluru India Department of Information Technology Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India Department of Computer Science and Engineering School of Computing Vel Tech Rangarajan Dr. Sagunthala R & amp D Institute of Science and Technology Chennai 600062 India Computer Science & amp Engineering KLEF KL University Andhra Pradesh Vaddeswaram India

Restoring Moiré images presents significant challenges due to the complex interference patterns that obscure image details. These patterns often degrade the quality of images, making accurate restoration crucial for various applications. Effective Moiré image restoration requires advanced techniques to overcome the difficulties posed by these intricate artifacts. This study introduces an Adaptive Residual Convolutional Neural Network (RCNN) for Moiré image restoration, augmented with the Zebra Optimization Algorithm (ZOA) to enhance both feature extraction and restoration accuracy. The hybrid model leverages ZOA's capability to balance exploration and exploitation, optimizing network parameters to improve learning efficiency. Tested on the DIV2K dataset, this approach demonstrates significant improvements in handling complex Moiré patterns, as evidenced by enhanced Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM) values. © The Author(s) 2024.

关键词： Adaptive residual convolutional neural network Moiré images Peak signal-to-noise ratio Structural similarity index measure Zebra optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Cancer Diagnosis with Deep Learning: A Case Study Using U-Net 7

Revolutionizing Cancer Diagnosis with Deep Learning: A Case ...

引用

7th International Conference on Contemporary Computing and Informatics, IC3I 2024

作者： Goyal, Himanshu Rai Al-Farouni, Mohammed Deepak, A. Reddy, R. Akhilesh Yadav, Kanchan Revathi, V. Graphic Era Deemed to be University Department of Computer Science & Engineering Dehradun India The Islamic university College of technical engineering Department of computers Techniques engineering Najaf Iraq Saveetha Institute of Medical and Technical Sciences Saveetha University Saveetha School of Engineering Tamilnadu Chennai India Mlr Institute of Technology Department of CSE-AI&ML Telangana Hyderabad India Gla University Department of Electrical Engineering Mathura India New Horizon College of Engineering Department of Applied Sciences Bangalore India

ISBN: (纸本)9798350350067

The U-Net architecture is a convolutional neural network model that is well-known for its skills in biomedical image segmentation. This study investigates the revolutionary potential that the U-Net architecture presents in the context of cancer diagnosis. We guarantee that the input is of high quality by using sophisticated preprocessing methods, which we do by constructing a robust U-Net-based system that is specifically designed for the segmentation and classification of tumour regions in medical imaging data. An exhaustive examination that makes use of criteria such as the Dice similarity coefficient, precision, recall, and F1 score indicates that our model performs substantially better than conventional techniques when it comes to identifying and distinguishing malignant tissues. Case studies that cover a wide range of cancer types provide further validation of the flexibility and practical application of the system. These studies also highlight the significant influence that deep learning has on increasing diagnosis accuracy, lowering the risk of human error, and overall patient outcomes in the field of cancer treatment. © 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

Transfer Learning in Endoscopic Imaging: A Machine Vision Approach to GIT Disease Identification

Transfer Learning in Endoscopic Imaging: A Machine Vision Ap...

引用

Communications and computer science (InCCCS), International Conference on

作者： Jayavrinda Vrindavanam Pradeep Kumar Gaurav Kamath Abhilash S Bharadwaj Department of Computer Science and Engineering(AI & ML) Dayananda Sagar University Bengaluru India

ISBN: (数字)9798350358858

ISBN: (纸本)9798350358865

In the context of rapidly rising Gastro-Intestinal tract related diseases among the population, the study explores the use of ai and ml that can enable early detection of the GI tract related abnormalities. The study after a detailed review of the existing studies, proposes on transfer learning to fine tune model weights trained on large data sets for GI-tract applications. The study has implemented models such as EfficientNet, MobileNet V3 Large, ResNet-50, DenseNet-201 and CNN (Convolutional Neural Network) on the endoscopic images. The top performing model, EfifcientNet2S, showcased superior proficiency identifying the eight distinct GIT diseases. The paper highlights the scope of applying transfer learning neural network architectures in enhancing disease diagnosis as well as selecting optimal architectures for accurate and efficient medical image classification in gastrointestinal pathology.

关键词： Pathology Transfer learning Neural networks computer architecture Gastrointestinal tract Medical diagnosis Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Novel Image Caption Generation Based on CNN and RNN

A Novel Image Caption Generation Based on CNN and RNN

引用

Advances in Computing Research on science engineering and Technology (ACROSET), International Conference on

作者： Hemlata Parmar Manish Rai Utsav Krishan Murari Department of Computer Science and Engineering(AI&ML) Manipal University Jaipur Jaipur India Department of Journalism and Mass Communication Sharda University Greater Noida Greater Noida India

ISBN: (数字)9798350388800

ISBN: (纸本)9798350388817

The field of image comprehension has experienced notable advancements as a result of the emergence of deep learning techniques and advancements in computer vision technology. The effort of generating coherent and detailed textual descriptions for images, known as image labeling, is a significant challenge that requires the integration of natural language processing and image processing techniques. This abstract provides an in-depth analysis of approaches employed for generating photo labels, with a particular focus on current advancements within the sector. The generation of picture labels involves the use of two main components in the pipeline, namely syntax interpreter and a photographic converter. The picture encoder uses (CNNs) to process images. For extracting visual The field of image comprehension has experienced notable advancements as a result of the emergence of deep learning techniques and advancements in computer vision technology. The effort of generating coherent and detailed textual descriptions for images, known as image labeling, is a significant challenge that requires the integration of natural language processing and image processing techniques. For extracting visual details from input pictures. To generate labels on a individual basis, a language decoder employs (RNNs) like(LSTM) or (GRUs) to analyse the context representation of the image. The results obtained from this study underscore the advantages of employing (GRU) in comparison to (LSTM) for the purpose of generating labels and constructing sentences. In addition to this, recent advancements in transformer-based design, such as the transformer model, have shown promising statistics concerning labelling of pictures. The models have demonstrated the ability to effectively imitate the connections between visual and textual modalities, and they achieve this by leveraging the self-attention mechanism found in transformers, which allows for capturing long-range interdependencies. The production

关键词： Deep learning Visualization computer vision Reinforcement learning Syntactics Transformers Feature extraction Natural language processing Labeling Proposals

来源：评论

学校读者我要写书评

暂无评论

CbcErDL: Classification of breast cancer from mammograms using enhance image reduction and deep learning framework

引用

Multimedia Tools and Applications 2025年第15期84卷 15501-15526页

作者： Agrawal, Rohit Singh, Navneet Pratap Shelke, Nitin Arvind Tripathi, Kuldeep Narayan Singh, Ranjeet Kumar Department of Computer Science and Engineering Madhav Institute of Technology & Science Race Course Road MP Gwalior474005 India School of AI Bennett University Uttar Pradesh Greater Noida201310 India School of Computer Science and Engineering Bennett University TechZone 2 UP Greater Noida201310 India

Breast cancer is a major health concern for women worldwide, and early detection is vital to improve treatment outcomes. While existing techniques in mammogram classification have demonstrated promising results, their limitations become apparent when applied to larger datasets. The decline in performance with increased dataset size highlights the need for further research and advancements in the field to enhance the scalability and generalizability of these techniques. In this study, we propose a framework to classify breast cancer from mammograms using techniques such as mammogram enhancement, discrete cosine transform (DCT) dimensionality reduction, and deep convolutional neural network (DCNN). The first step is to improve the mammogram display to improve the visibility of key features and reduce noise. For this, we use 2-stage Contrast Limited Adaptive Histogram Equalization (CLAHE). DCT is then used to enhance mammograms to reduce residual data. It can provide effective reduction while preserving important diagnostic information. In this way, we reduce the computational complexity and increase the results of subsequent classification algorithms. Finally, DCNN is used on size-reduced DCT coefficients to learn feature discrimination and classification of mammograms. DCNN architectures have been optimized with various techniques to improve their performance, including regularization and hyperparameter tuning. We perform experiments on the DDSM dataset, a large dataset containing approximately 55,000 mammogram images, and demonstrate the effectiveness of the proposed method. We assess the proposed model’s performance by computing the precision, recall, accuracy, F1-Score, and area under the receiver operating characteristic curve (AUC). We achieve Precision and Recall values of 0.929 and 0.963, respectively. The classification accuracy of the proposed models is 0.963. Moreover, the F1-Score and AUC values are 0.962 and 0.987, respectively. These results are better a

关键词： Discrete cosine transforms

来源：评论

学校读者我要写书评

暂无评论

Multilingual Transformer for Dynamic Cricket Commentary Generation

Multilingual Transformer for Dynamic Cricket Commentary Gene...

引用

Computing and Data science (ICCDS), International Conference on

作者： Gaurav Kamath Udayabhaskara N Department of Computer Science and Engineering (AI and ML) Dayananda Sagar University Bangalore India

ISBN: (数字)9798350365337

ISBN: (纸本)9798350365344

The sport of Cricket is growing in popularity which necessitates the use of technology to adhere to popular game standards. Since this is a data rich and most elaborate game, understanding this for someone who's new to the game had been challenging. We are aiming to solve this unavailability of the game through native commentary to audience of all major languages. To outline our entire research work we ideate a Cricket Game ai through computer vision, use it to produce text commentary of game-play and perform Machine Translation(MT) to produce native commentary for a targeted language, As afirst part of the outlined process in this work we focus on the implementation of the machine translation component of this pipeline, evaluating various methods including Seq2seq and transformer based architectures. Our method of cross feeding Seq2Seq with Transformer model results in Bilingual Evaluation Understudy (BEL U) score on Validation set of 2.08.

关键词： Computational modeling Pipelines Games Data science Transformers Real-time systems Machine translation

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：