检索结果-内蒙古大学图书馆

Facial Recognition with Aliveness Detection Using FaceNet and LivenessNet 1

Facial Recognition with Aliveness Detection Using FaceNet an...

1st International Conference on Computational Intelligence for Security, Communication and Sustainable Development, CISCSD 2024

作者： Bhaskar, S.V. Santhosh Krishna, B.V. Punyashree, C.D. Babu, Dabbara Sujith Darshan, S. Computer Science and Engineering New Horizon College of Engineering Bangalore India

ISBN: (纸本)9798350365405

Facial recognition technology has been widely used in many fields, issues with spoofing and presentation attacks continue to be major obstacles. In order to reduce the risks associated with photo impersonation, this paper suggests a novel facial recognition system that is coupled with aliveness detection techniques. Modern deep learning models, FaceNet for facial recognition and LivenessNet for aliveness detection, are integrated into an advanced facial recognition system that is presented in this paper. FaceNet is a neural network architecture that is used to extract and identify features from facial images with robustness. A specialized aliveness detection model called LivenessNet separates real-life live facial patterns from static or non-living sources. By utilizing FaceNet's capabilities, the suggested system creates high-dimensional embeddings that effectively capture distinct facial features, facilitating precise and dependable face matching. Simultaneously, LivenessNet uses real-time physiological cues, micro expressions, and small movements to verify that a live person is present, guaranteeing the authenticity of live faces during recognition. Through the integration of these models, the system provides a comprehensive solution that improves security in facial recognition applications by mitigating vulnerabilities related to impersonation through images or videos. Experiments conducted on various datasets show the effectiveness of the system, demonstrating its resilience to spoofing attempts and guaranteeing reliable face recognition with integrated aliveness detection. © 2024 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Big Data Analytics in loT Challenges and Opportunities 9

Big Data Analytics in loT Challenges and Opportunities

引用

9th International Conference on science, Technology, engineering and Mathematics, ICONSTEM 2024

作者： Kirubakaran, S. Vidhya, R. Prlya, V. Kalai ShyamPrakash, D. Dhotre, Sunita Balaji, N. Alangudi Cmr College of Engineering And Technology Department of Computer Science And Engineering Telangana Hyderabad501401 India Sri Krishna College of Technology Department of Computer Science And Engineering Tamil Nadu Coimbatore641042 India Rmk College of Engineering And Technology Department of Computer Science And Engineering Puduvoyal601206 India Sri Eshwar College of Engineering Deportmem of Computer Science And Business Systems Tamil Nadu Coimbatore641202 India College of Engineering Department of Computer Engineering Maharashtra Pune411043 India KoneruLakshmaiah Education Foundation Department of Computer Science And Engineering Andhra Pradesh Vaddeswaram522302 India

ISBN: (纸本)9798350365092

The intricate interplay between Big Data analytics and the Internet of effects is explored in this paper. The focus of this exploration is the integration of Big Data analytics into Internet of effects surroundings, probing into the complex geography and examining both the advantages and disadvantages. In the current period, where Internet of effects(loT) bias induce unknown quantities of data, the investigates the challenges associated with the collection and analysis of massive datasets. issues are under consideration, including data security, sequestration, scalability, and real-time processing. Again, openings lie in gaining pivotal perceptivity, enhancing decision- making processes, and fostering invention. This exploration provides a comprehensive understanding of the commerce between Big Data analytics and the Internet of effects(IoT), offering a precious resource for companies, academic institutions, and government officers seeking to navigate and acclimatize to this fleetly expanding confluence of technologies. © 2024 IEEE.

关键词： Scalability

来源：评论

学校读者我要写书评

暂无评论

DFP-YOLO: An Efficient Algorithm for Detecting Steel Surface Defects

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer science 2025年第6期52卷 1754-1763页

作者： Chai, Jiawei Zhou, Ziwei School of Electronic and Information Engineering University of Science and Technology Liaoning Liaoning Anshan114051 China School of Computer Science and Software Engineering University of Science and Technology Liaoning Liaoning Anshan114051 China

To enhance the accuracy of steel plate surface defect detection and minimize the incidence of misdetection and leakage, this paper proposes a DFP-YOLO algorithm based on YOLOv8n to achieve efficient detection of steel plate surface defects. Firstly, the C2f module of the backbone network and Neck layer is substituted by the DWR_DRB module to strengthen the ability of capturing defects at various scales and enhance the efficiency of model feature extraction. Secondly, the Feature Pyramid Share Convolution module is devised to extract multi-scale features through convolutional layers with different dilation rates, integrating local details with global contextual information for a better comprehension of complex scenes. Finally, a Powerful-IoU loss function is utilized to control the scale size of the auxiliary boundary to accelerate the detection speed and improve the model accuracy. The experimental results demonstrate that the proposed algorithm in this paper boosts the mean accuracy (mAP) of the steel plate surface defect detection task by 3.4% compared to the original YOLOv8n model, increases the accuracy by 8.8%, and raises the inference speed of the model by 49 frames per second when conducting DFP-YOLO detection on the dataset NEU-DET. Meanwhile, the generalization and robustness of the model are verified through tests on the industrial steel plate surface defects dataset GC10-DET and the larger public benchmark dataset PASCAL VOC 2012. © (2025), (International Association of Engineers). All rights reserved.

关键词： Surface defects

来源：评论

学校读者我要写书评

暂无评论

Contention-free dynamic task scheduling approach for network-on-chip based quad-core systems

引用

International Journal of Information Technology (Singapore) 2024年第2期16卷 1055-1062页

作者： Farooq, Mohd Zafar, Aasim Samad, Abdus Department of Computer Science Aligarh Muslim University Aligarh India Department of Computer Engineering Aligarh Muslim University Aligarh India

The use of multi-core based on Network-on-Chip (NoC) systems has increased in recent years due to its effectiveness in executing real-time applications using the latest technologies. Efficient core utilization demands smart mapping of tasks on processing cores. The communication between different tasks should be done through the best available route to minimize network congestion. However, selecting the best suitable path becomes more complex in the case of dynamic scheduling of tasks. This paper presents an improved dynamic mapping technique for mapping the tasks on cores and minimise communication cost by using the various available links simultaneously for quad-core systems. This technique tries to map the communicating tasks in the vicinity to reduce the communication overhead. The proposed algorithm reduces the average latency by approximately 15%. In addition, the developed technique has met the deadline in the majority of test cases. © The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of computer Applications and Management 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s);author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

关键词： Dynamic scheduling Link contention Network-on-Chip

来源：评论

学校读者我要写书评

暂无评论

Implications of Virtual Reality on Environmental Sustainability in Restaurants based on AI 10

Implications of Virtual Reality on Environmental Sustainabil...

引用

10th International Conference on Communication and Signal Processing, ICCSP 2024

作者： Adithya Narayanan, C. Bharath, E. Vijayakumar, R. Rajalakshmi Engineering College Department of Computer Science Engineering Chennai India

ISBN: (纸本)9798350353068

This talks about the various ways that augmented reality (AR) affects environmental sustainability in the restaurant business. When combined with artificial intelligence (AI), augmented reality has the power to completely change the restaurant industry by improving eco-friendly operations and changing many facets of their operations. This article examines how AR and AI might help restaurants become more environmentally sustainable. It focuses on important topics including menu design, waste management, customer interaction, and operational efficiency. Easy access to menus and simplicity are two important elements that make restaurant food ordering simpler. The eating experience for customers is entirely revolutionized by the HOLOGRAM menu. Current programs offer an application that eateries can utilize to include their menus into tablets with CONTROL & HOLOGRAM functionality, making it simpler for customers to swipe, swipe, and tap through menus. The objective of this project is to give the restaurants a tablet menu that suggests items using a novel recommendation algorithm. We store the database on a cloud-based server, which is safe & affordable. © 2024 IEEE.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Truck Bridge - Revolutionizing Transport Efficiency and Sustainability 4

Truck Bridge - Revolutionizing Transport Efficiency and Sust...

引用

4th International Conference on Ubiquitous Computing and Intelligent Information Systems, ICUIS 2024

作者： Gopinath, N. Naga Prasath, S. Karthikeyan, G. Sathish Kumar, D. Srikanth, V. Sri Sairam Engineering College Computer Science and Engineering Chennai India

ISBN: (数字)9798331529635

ISBN: (纸本)9798331529635

This study introduces an application that aims to revolutionise the logistics sector by facilitating truck pooling, a transportation efficiency-enhancing method that links drivers and shippers travelling in parallel. The software helps shippers find trucks with available capacity, which lessens the number of empty trucks on the road and improves resource efficiency and environmental impact. A network of intelligent trailers that can be dynamically joined or unlinked from trucks as needed is another element of the technology. Because of its adaptability, trucks can transport more freight without making more trips, which improves operational effectiveness and boosts truckers' profits. The app has an advanced auction-based mechanism that offers shippers cost-effective choices in addition to truck pooling. The technology creates a competitive market by enabling truckers to bid on available loads at a predetermined time every day, which lowers transportation costs for consumers. The software provides instant auctions for a charge, offering flexibility and quick response times for people in need of immediate assistance. The application's 'shared auction' approach, which allows users to pool smaller loads with other users travelling in the same route, is one of its standout features. Shippers with longer routes or lower cargo volumes will benefit most from this cooperative approach, which allows them to split the cost of transportation and increase efficiency. In a shared auction, users can post their loads and be paired with suitable © 2024 IEEE.

关键词： Truck transportation

来源：评论

学校读者我要写书评

暂无评论

MeVs-deep CNN: optimized deep learning model for efficient lung cancer classification

引用

Multimedia Tools and Applications 2024年 1-32页

作者： Sewatkar, Ranjana M. Y, Asnath Victy Phamila School of Computer Science and Engineering VIT Chennai Vandalur-Kelambakkam Road Chennai Tamil Nadu600127 India

Lung cancer is a dangerous condition that impacts many people. The type and location of cancer are critical factors in determining the appropriate medical treatment. Early identification of cancer cells can save numerous lives, making the development of automated detection techniques essential. Although many methods have been proposed by researchers over the years, achieving high prediction accuracy remains a persistent challenge. Addressing this issue, this research employs Memory-Enabled Vulture Search Optimization based on Deep Convolutional Neural Networks (MeVs-deep CNN) to develop an autonomous, accurate lung cancer categorization system. The data is initially gathered from the PET/CT dataset and preprocessed using the Non-Local Means (NL-Means) approach. The proposed MeVs optimization approach is then used to segment the data. The feature extraction process incorporates statistical, texture, and intensity-based features and Resnet-101-based features, resulting in the creation of the final feature vector for cancer classification and the multi-level standardized convolutional fusion model. Subsequently, the MeVs-deep CNN leverages the MeVs optimization technique to automatically classify lung cancer. The key contribution of the research is the MeVs optimization, which effectively adjusts the classifier's parameters using the fitness function. The output is evaluated using metrics such as accuracy, sensitivity, specificity, AUC, and loss function. The efficiency of the MeVs-deep CNN is demonstrated through these metrics, achieving values of 97.08%, 97.93%, 96.42%, 95.88%, and 2.92% for training phase;95.78%, 95.34%, 96.42%, 93.48%, and 4.22% for testing percentage;96.33%, 95.20%, 97.65%, 94.83%, and 3.67% for k-fold train data;and 94.16%, 95.20%, 93.30%, 91.66%, and 5.84% for k-fold test data. These results demonstrate the effectiveness of the research. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 202

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Crafting Insights from Facial Feedback for Enhanced Understanding 5

Crafting Insights from Facial Feedback for Enhanced Understa...

引用

5th IEEE International Conference on Computing, Power, and Communication Technologies, IC2PCT 2024

作者： Mohamed, Maryam Saeed Hassan, Md Al Mahedi Fahim, Md Forkan Hossain Suleyman, Rukia Mohamed Mansur, Usman Muhammad Singh, Ajay Kumar School of Computer Science and Engineering India School of Science and Technology India

ISBN: (纸本)9798350383522

This research introduces an innovative approach to facial emotion detection by integrating the Haar Cascade front face XML file for face detection and training a Convolutional Neural Network (CNN) model on the CK plus dataset for accurate emotion classification. Implemented using Jupyter Notebook and Python 3.7, our model captures facial expressions through video or webcam input, reading frames frame by frame. Each frame undergoes transformation to match the model's input shape, facilitating precise emotion detection. The model predicts and records emotions based on facial angles, presenting the outcomes in a comprehensible pie chart upon program termination. The dataset, encompassing five emotion classes (disgust, happy, neutral, sad, surprise), forms the foundation for CNN model training, ensuring real-time emotion classification accuracy. This research not only offers a systematic flowchart for implementation but also contributes a valuable tool for emotion analysis with applications ranging from user experience design to mental health interventions. © 2024 IEEE.

关键词： Emotion Classification Facial esxpression analysis Feedback Haar Cascade neural networks

来源：评论

学校读者我要写书评

暂无评论

SLR Driven Heart Failure Prediction 2

SLR Driven Heart Failure Prediction

引用

2nd IEEE International Conference on Emerging Research in Computational science, ICERCS 2024

作者： Bhuvaneswari, R. Krishnakumar, R. Karthic, S. Rajalakshmi Engineering College Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798331534950

Heart failure is one of the serious worldwide health issue which requires early identification and treatment. The paper offers an ensemble machine learning model that incorporates various patient variables, such as demographics, medical history, clinical measurements, and laboratory findings, to predict heart failure risk accurately. The model improves prediction accuracy and rectifies class imbalances by combining decision trees, random forests, and gradient boosting with SMOTE techniques. It also gives interpretable insights through feature significance analysis, allowing medical professionals to identify high-risk patients for immediate treatments and specialized therapy. Validated on heart failure data, the proposed model SLR (SVM +Logistic Regression + Random Forest Classifier) demonstrates significant predictive metrics, indicating its potential to enhance heart failure risk prediction and contribute to better clinical decision-making. The proposed methodology achieves 91.7% accuracy for the prediction of heart failure as it aimed to combine the best machine learning models which suites this dataset. This SLR model achieves precision, recall, F1 score with 0.93, 0.82 and 0.93 respectively which exhibits the efficacy of this model. © 2024 IEEE.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

Indonesian Abstractive Text Summarization Using Stacked Embeddings and Transformer Decoder

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer science 2025年第4期52卷 1051-1061页

作者： Winarko, Edi Tanoto, Luis Reza, Muhammad Haidar Department of Computer Science and Electronics Universitas Gadjah Mada Indonesia

Document summarization can be categorized into two categories: extractive and abstractive summarization. Research in abstractive summarization is more limited than that of extractive summarization, especially for Indonesian documents. Most existing studies in Indonesian abstractive summarization rely on a single embedding approach in their encoder. This study aims to develop an abstractive Indonesian document summarization model using stacked embedding as an encoder and a Transformer-based decoder. Stacked embeddings offer the advantage of capturing a more comprehensive range of linguistic features, enhancing the model’s ability to generalize across different word forms and morphological variations. The stacked embedding combines Bidirectional Encoder Representation from Transformers (BERT), Byte Pair Embedding (BPE), Character Embedding (CE), and FastText (FT). We conduct experiments to find the effect of BERT layer selection and various stacked embedding as an encoder in the proposed summarization model. Using the Liputan6 dataset, the experimental results show that using all layers of BERT as an encoder gives the best performance for summarization. In addition, the stacked embedding of BERT, CE, and BPE gives the highest F1 score of 35.58 (ROUGE-1), 15.40 (ROUGE-2), and 32.80 (ROUGE-L) when trained with 50,000 data. In contrast, when trained with 75,000 data, the stacked embedding performance is below BERT embedding, which has an F1 score of 37.18 (ROUGE-1), 18.19 (ROUGE-2), and 34.28 (ROUGE-L). Our proposed model achieves performance close to state-of-the-art models despite using less than 40% of the training data in Liputan6 dataset. © (2025), (International Association of Engineers). All rights reserved.

关键词： Decoding

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

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

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：