检索结果-内蒙古大学图书馆

4th IEEE Global Conference for Advancement in technology, GCAT 2023

作者： Varun Prakash, J.M. Kodipalli, Ashwini Rao, Trupthi Kumaraswamy, S. Dept of Computer Science and Engineering Global Academy of Technology Karnataka Bangalore India Dept of Artificial Intelligence and Data Science Global Academy of Technology Karnataka Bengaluru India

ISBN: (纸本)9798350305258

In this paper, we propose a method for eyewear detection using Convolutional Neural Networks (CNNs). The objective of the study is to accurately classify images into two classes: "Glasses" and "No Glasses." The proposed approach is evaluated on a dataset comprising a total of 5000 images, with a training set consisting of 1947 images in the "Glasses" class and 1554 images in the "No Glasses" class. The testing set includes 834 images in the "Glasses" class and 665 images in the "No Glasses" class. We evaluate the eyewear detection performance using various evaluation metrics, including accuracy, precision, and recall. The outcomes demonstrate how well the suggested CNN-based technique for eyeglasses detection works. The trained model achieves an overall accuracy of 99.17%, with a precision of 0.76% and a recall of 0.44% on the testing set. The discovery advances the field of computer vision and creates new opportunities for improving eyeglasses detection methods through further additional study. © 2023 IEEE.

关键词： Accuracy Evaluation Computer Vision Convolutional Neural Network Eyewear detection Feature Extraction Image Classification

来源：评论

学校读者我要写书评

暂无评论

Resisting Visual Hacking: A Novel Graphical Password Authentication System 3

Resisting Visual Hacking: A Novel Graphical Password Authent...

引用

3rd International Conference on Pervasive Computing and Social Networking, ICPCSN 2023

作者： Jebakumar Immanuel, D. Ramalingam, V. Tharun Kumar, P. Iyer, Akash Narayanan, M.S. Karpagam Institute of Technology Department of Artificial Intelligence and Data Science Coimbatore641 105 India Sns College of Engineering Department of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350322842

Password-based authentication is a widely used method to ensure security and privacy in computer applications. However, the selection of weak passwords and insecure input methods by users is considered the 'weakest link' in the authentication process. Instead of employing arbitrary alphanumeric sequences, individuals tend to opt for passphrases that are either mnemonic or abbreviated in nature. With the proliferation of web and mobile applications, users can access these applications at any time and from anywhere with various devices. Although this convenience is highly desirable, it also increases the likelihood of passwords being exposed to Visual Hacking. The forms of attack may be executed through either direct visual observation or the utilization of external recording devices in order to obtain the user's login information. In response to this issue, our team has devised an authentication system that centers on graphical passwords and is made to combat the threat of Visual Hacking. The system incorporates a three-layered security mechanism, comprising color and pattern matching functionalities in conjunction with password verification. This makes it highly challenging for potential attackers to deduce or limit the password even amidst numerous camera-based hacking attempts. Additionally, we have created and put to the test a prototype of the system to assess its user-friendliness. Our experimental results indicate that our system can resist Visual Hacking more effectively than previous authentication systems while still maintaining a high degree of usability and security. © 2023 IEEE.

关键词： Pattern matching

来源：评论

学校读者我要写书评

暂无评论

A Domain Generalization Model Based on Multilevel Domain Adversarial Invariant Representation Learning 8

A Domain Generalization Model Based on Multilevel Domain Adv...

引用

8th International Conference on Intelligent Computing and Signal Processing, ICSP 2023

作者： Liu, Kun Wang, Ding Yang, Ying Wang, Jingkai Mao, Jingkun Hebei University of Technology School of Artificial Intelligence and Data Science Tianjin China Tianjin University of Technology School of Electrical Engineering and Automation Tianjin China

ISBN: (纸本)9798350302455

Due to the influence of various factors such as cross-scene shooting height, shooting time, imaging angle of view, weather, etc., the performance of the defect detection model degrades in cross-scene situations. In this paper, we proposed a domain generalization model based on multilevel domain adversarial invariant representation learning, which included the designed defect space feature and channel feature enhancement modules. Among them, the defect space feature enhancement module uses the shallow feature invariance score to guide the model to extract cross-scene invariant representations, and at the same time, design and use the defect importance information in the shallow features to enhance the representation of defects in the shallow features. The channel feature enhancement module assigns learning weights to different channels of each sample according to the similarity between the sample and the whole, and the importance of different feature channels to defects, so as to better guide the model to extract cross-scene invariant representations. The experimental verification on the photovoltaic cell data set collected in outdoor natural scenes shows that, proposed model has stronger generalization ability than existed domain generalization methods. © 2023 IEEE.

关键词： Defects

来源：评论

学校读者我要写书评

暂无评论

Giant Trevally Optimizer (GTO): Enhancing HVDC Transmission Capacity with Optimized Fault Current Limiters and HVDC Circuit Breaker Parameters 3

Giant Trevally Optimizer (GTO): Enhancing HVDC Transmission ...

引用

3rd International Conference on Electronics and Renewable Systems, ICEARS 2025

作者： Ramkumar, M. Siva Saranya, N. Gopan, Gokul Baig, Rahmath Ulla Josha Daniel, S. Babu, M. Sns College of Technology Department of Ece India Karpagam College of Engineering Department of Artificial Intelligence and Data Science India Department of Mechanical Engineering Chennai602105 India Cambridge Institute of Technology Department of Artificial Intelligence and Machine Learning K R Puram Bangalore560086 India Hindustan College of Engineering and Technology Department of Eee India Hindusthan College of Engineering and Technology Master of Engineering in Embedded Systems India

ISBN: (纸本)9798331509675

The multi-terminal HVDC system relies heavily on circuit breakers (CBs) and fault current limiters (FCLs) for protection and performance reliability. This research describes a new Giant Trevally optimizer-based strategy for improving the performance of 4-terminal HVDC systems by optimizing crucial circuit breakers and fault current limiters. The proposed method uses time domain estimation to correctly capture fault dynamics, such as traveling waves and reflection coefficients and finds the worst-case fault locations. The multi-objective optimization seeks to optimize the overcurrent, overvoltage handling, fault clearance time, and energy absorption in arresters. This technology provides an effective, dependable protection solution that reduces fault recovery time and increases system stability. The output pulse of the HVDC system shows very low THD results 1.98% for the minimum load condition, 0.87% for median load, and 0.04% for peak load conditions. The results established the simulation of the model in a MATLAB environment. © 2025 IEEE.

关键词： MATLAB

来源：评论

学校读者我要写书评

暂无评论

Fruit and Vegetable Grading with Transfer Learning and Convolutional Neural Networks for Better Productivity 3

Fruit and Vegetable Grading with Transfer Learning and Convo...

引用

3rd International Conference on Advanced Computing Technologies and Applications, ICACTA 2023

作者： Narvekar, Chhaya Rao, Madhuri Xavier Institute of Engineering Department of Information Technology Mumbai India Thadomal Shahani Engineering College Department of Artificial Intelligence and Data Science Mumbai India

ISBN: (纸本)9798350348347

Grading provides quality assurance by confirming that agricultural products match predetermined standards, which can boost consumer trust in the goods. Additionally, it aids in ensuring that consumers receive products that are risk-free and error-free. In this study, a fruit and vegetable grading system based on deep learning methods such as transfer learning and convolutional neural networks (CNN) is proposed. The suggested approach correctly categorizes various fruit and vegetable varieties according to their outward appearance. Objective is to ascertain the effect of various grading parameters, such as size, shape, and color, on the grading system's correctness. This study utilized labeled image dataset for training models. Transfer learning is utilized to enhance the performance and accuracy of the grading system by leveraging pre-trained CNN models. The experimental findings show that the suggested system outperforms existing fruit grading systems and achieves excellent accuracy to comprehend how grading and standardization affect farming's profitability. © 2023 IEEE.

关键词： Grading

来源：评论

学校读者我要写书评

暂无评论

Empowering smart traffic avoidance using Natural language processing 3

Empowering smart traffic avoidance using Natural language pr...

引用

3rd International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics, IITCEE 2025

作者： Kalaiselvi, V.K.G. Vishnu Chandar, K.R. Vishwa, G. Tirunagari, Sharanya Hariharan, Shanmugasundaram Krishnamoorthy, Murugaperumal Sri Sairam Engineering College Department of Information Technology Tamilnadu India Vardhaman College of Engineering Department of Artificial Intelligence and Data Science Hyderabad India Vardhaman College of Engineering Department of Electrical and Electronics Engineering Hyderabad India

ISBN: (纸本)9798331515911

The integration of Natural Language Processing (NLP) into smart traffic systems offers a novel approach to enhancing real-time traffic management and optimization. This paper explores how NLP can be leveraged to interpret and analyze vast amounts of unstructured traffic-related data, such as social media updates, traffic reports, and incident logs. A key component of this approach is the use of a BERT (Bidirectional Encoder Representations from Transformers) classifier, which enables more accurate extraction and classification of relevant traffic information from textual data. By processing this data in real time, the BERT-based NLP system can provide more precise traffic predictions, identify congestion patterns, and optimize traffic flow dynamically. The study highlights the potential of NLP, particularly through the use of BERT, in improving the efficiency and responsiveness of traffic management systems, ultimately leading to reduced travel times, lower emissions, and enhanced urban mobility. The app also includes user-friendly interfaces that allow drivers and city planners to access real-time updates, personalized route recommendations, and predictive analytics. The system's adaptability ensures that it can respond quickly to unexpected incidents, such as accidents or road closures, further enhancing urban mobility. The study highlights the transformation potential of this app in improving the efficiency and responsiveness of traffic management systems, ultimately leading to reduced travel times, lower emissions, and a significant improvement in overall urban transportation experiences. © 2025 IEEE.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Pancreatic Cancer Prediction Machine Learning using Multi Fusion Model

Pancreatic Cancer Prediction Machine Learning using Multi Fu...

引用

2024 International Conference on Distributed Systems, Computer Networks and Cybersecurity, ICDSCNC 2024

作者： Sathiyapriya, V. Devi, K. Nethra Deepa, S. Marimuthu, M. Manikandan, P. Prabu, S. Knowledge Institute of Technology Department of Computer Science and Engineering Kakapalayam India Gnanamani College of Technology Department of Artificial Intelligence and Data Science Namakkal India Vellore Institute of Technology School of Computer Science and Engineering Chennai India Srm Institute of Science and Technology School of Computing Tiruchirappalli India

ISBN: (纸本)9798350375442

Pancreatic cancer poses a significant challenge in early detection and treatment due to its malignant nature within the digestive tract. Recent studies, such as those conducted by the Pancreatic Cancer Action Network, predict that pancreatic cancer will rank as the world's second leading cause of cancer-related deaths in 2020. Various methods have been explored in the literature to segment pancreatic tumors and detect lesions from CT images, crucial for assessing severity. One such method is the Min-Max segmentation algorithm, which effectively removes the jaundiced sclera region from affected eyes by analysing color gradients, offering more feasible and discriminative solutions. Additionally, the utilization of Whale Optimized feature-based selection aids in extracting optimal features for optimization purposes. Through an analysis of different classification algorithms and the implementation of a suggested technique for achieving optimum solutions and maximum accuracy, the proposed work is structured into two phases. Phase I involves pre-processing and artifact removal, followed by segmentation, while Phase II focuses on feature extraction, feature selection, and classification. The initial step of pre-processing the image facilitates pixel location using intensity measures, crucial for accurate tumor segmentation and minimizing false detection. Ultimately, the proposed approach aims to design and develop an optimal feature selection strategy for classifying pancreatic cancer tumors in PET/CT images, resulting in increased classification efficiency 92% and improved cancer tumor detection rates with compare other existing approaches. © 2024 IEEE.

关键词： Computerized tomography

来源：评论

学校读者我要写书评

暂无评论

A Novel Framework for Gauging Information Extracted from Smartphones Using Neutrosophic Logic

引用

Neutrosophic Sets and Systems 2025年 76卷 154-171页

作者： Abou Alzahab, R.M. Ismail, Amr Abd Elkhalik, S.H. Shams, M.Y. El-Bakry, H.M. Salama, A.A. Department of Mathematics and Computer Science Faculty of Science Port Said University Egypt Department of Cybersecurity College of Engineering and Information Technology Buraydah Private Colleges Buraydah51418 Saudi Arabia Department. of Communication and Computer Engineering Air Defense University Egypt Faculty of Artificial Intelligence Kafrelsheikh University Kafrelsheikh33516 Egypt Department of Information Systems. Faculty of Computer and Information Science Mansoura University Egypt

Smartphones contain a vast amount of information about their users, which can be used as evidence in criminal cases. However, the sheer volume of data can make it challenging for forensic investigators to identify and use the most relevant information. Neutrosophic logic is a generalization of fuzzy logic that allows for uncertainty and vagueness, making it a more potent tool for dealing with the ambiguity of real-world data. The proposed framework aims to identify and utilize the most relevant information for forensic investigators, making it easier to solve criminal cases using Neutrosophic logic. This novel approach provides a more powerful tool for dealing with the ambiguity of smartphone data, ultimately improving the accuracy and effectiveness of forensic investigations. Our research has utilized Neutrosophic logic to evaluate the degree of truth, falsity, or Indeterminacy of this information. Additionally, this study analyzes conversations between individuals using Excel’s fuzzy lookup add-in to determine the percentage of truth and false in each conversation. The results were compiled into a dataset and utilized a Neutrosophic Python code to evaluate the information. The results indicate the percentage of truth, false, and Indeterminacy in each conversation and which can be used to determine its admissibility as evidence and which not. © 2025, University of New Mexico. All rights reserved.

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

Solidification modes and delta-ferrite of two types of 316L stainless steels:a combination of as-cast microstructure and HT-CLSM research

引用

Journal of Iron and Steel Research International 2025年第2期32卷 426-436页

作者： Yang Wang Chao Chen Xiao-yu Yang Zheng-rui Zhang Jian Wang Zhou Li Lei Chen Wang-zhong Mu College of Materials Science and Engineering Taiyuan University of TechnologyTaiyuan 030024ShanxiChina Department of Materials Science and Engineering KTH Royal Institute of TechnologyStockholm 10044Sweden College of Artificial Intelligence and Big Data for Medical Sciences Shandong First Medical University and Shandong Academy of Medical SciencesJinan 250117ShandongChina College of Mechanical Engineering Taiyuan University of TechnologyTaiyuan 030024ShanxiChina Key Laboratory of Electromagnetic Processing of Materials(Ministry of Education) Northeastern UniversityShenyang 110819LiaoningChina

In 316L austenitic stainless steel,the presence of ferrite phase severely affects the non-magnetic properties.316L austenitic stainless steel with low-alloy type(L-316L)and high-alloy type(H-316L)has been *** microstructure and solidification kinetics of the two as-cast grades were in situ observed by high temperature confocal laser scanning microscopy(HT-CLSM).There are significant differences in the as-cast microstructures of the two 316L stainless steel *** L-316L steel,ferrite morphology appears as the short rods with a ferrite content of 6.98%,forming a dual-phase microstructure consisting of austenite and ***,in H-316L steel,the ferrite appears as discontinuous network structures with a content of 4.41%,forming a microstructure composed of austenite and sigma(σ)*** alloying elements in H-316L steel exhibit a complex distribution,with Ni and Mo enriching at the austenite grain ***-CLSM experiments provide the real-time observation of the solidification processes of both 316L specimens and reveal distinct solidification modes:L-316L steel solidifies in an FA mode,whereas H-316L steel solidifies in an AF *** differences result in ferrite and austenite predominantly serving as the nucleation and growth phases,*** solidification mode observed by experiments is similar to the thermodynamic calculation *** L-316L steel solidified in the FA mode and showed minimal element segregation,which lead to a direct transformation of ferrite to austenite phase(δ→γ)during phase transformation after ***,the H-316L steel solidified in the AF mode and showed severe element segregation,which lead to Mo enrichment at grain boundaries and transformation of ferrite into sigma and austenite phases through the eutectoid reaction(δ→σ+γ).

关键词： 316L austenitic stainless steel As-cast microstructure High-temperature confocal laser scanning microscopy Solidification mode Ferrite Characterization

来源：评论

学校读者我要写书评

暂无评论

Understanding the Regional Differences in World Happiness Index Using Machine Learning

Understanding the Regional Differences in World Happiness In...

引用

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

作者： Timmapuram, Mayush Ramdas, Rithvik Vutkur, Sadhvik Reddy Mali, Yashwanth Reddy Vasanth, K. Chaitanya Bharathi Institute of Technology Artificial Intelligence and Data Science Hyderabad India Chaitanya Bharathi Institute of Technology Electronics and Communication Engineering Hyderabad India

ISBN: (纸本)9798350319200

The World Happiness Report, created by the Sustainable Development Solutions Network and influenced by Gallup World Poll data, responds to a global call for happiness and well-being to be prioritized as core governance measures. The survey highlights the science of happiness across a region or country by investigating personal and national variances in happiness. This study entails data collection, cleansing, and exploratory analysis to uncover variable correlations. It discovers key factors of national happiness levels through correlation heat map and feature selection. Following that, prediction models based on machine learning techniques, such as regression and decision trees, are developed to anticipate a country's happiness score based on the Quality-of-Life factors relating to social, economic, and health data. The aim of this study is to provide insights into elements that contribute to the happiness of a population and explore the various policies implemented by the governments of progressive countries which led to societal upliftment. The regression techniques employed by the study have performed excellently, with an R-squared value of 0.7867 and a Root Mean Square Error (RMSE) of 0.4797. Notably, the Quality of Life (QoL) indicator for the year 2023 was predicted using Support Vector Regression (SVR), which turned out to be the best approach overall. In a nutshell, this study demonstrates data science's ability to decipher complex societal issues, as seen through the perspective of happiness and well-being. © 2023 IEEE.

关键词： Deep Learning Machine Learning Quality of Life Wellbeing World Happiness Index

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：