检索结果-内蒙古大学图书馆

8th International Conference on Electronics, Communication and Aerospace technology, ICECA 2024

作者： Amune, Amruta Dhage, Rohit Rajendra Dhage, Sharvari Somani, Tanuj Mahesh Rokade, Mayur Bhivasen Rajguru, Varun Mohan Vishwakarma Institute of Technology Pune India Vishwakarma Institute of Technology Department of Artificial Intelligence and Data Science Pune India Vishwakarma Institute of Technology Department of Chemical Engineering Pune India

ISBN: (纸本)9798350367904

This research study presents a novel automated window shade control system developed using the ESP32 microcontroller. The system integrates a Light Dependent Resistor (LDR) sensor for measuring ambient light intensity with the ESP32's Real-Time Clock (RTC) module to achieve precise day/night detection. By combining LDR measurements with RTC data, the system effectively determines daytime and nighttime conditions, accommodating variations in natural light due to seasonal changes. This dual-parameter approach enhances the system's accuracy in regulating shade positions. Furthermore, the system includes timebased scheduling functionality, allowing users to program shade adjustments independently of real-time light conditions. This capability is facilitated by the ESP32's computational power, thereby increasing operational efficiency and user convenience. © 2024 IEEE.

关键词： Stepping motors

来源：评论

学校读者我要写书评

暂无评论

Feature selection of BOF steelmaking process data by using an improved grey wolf optimizer

引用

Journal of Iron and Steel Research International 2022年第8期29卷 1205-1223页

作者： Zong-xin Chen Hui Liu Long Qi Faculty of Information Engineering and Automation Kunming University of Science and TechnologyKunming 650500YunnanChina Yunnan Key Laboratory of Artificial Intelligence Kunming University of Science and TechnologyKunming 650500YunnanChina

Basic oxygen furnace(BOF)steelmaking end-point control using soft measurement models has essential value for economy and ***,the high-dimensional and redundant data of the BOF collected by the sensors will hinder the performance of *** traditional feature selection results based on meta-heuristic algorithms cannot meet the stability of actual industrial *** order to eliminate the negative impact of feature selection application in the BOF steelmaking,an improved grey wolf optimizer(IGWO)for feature selection was proposed,and it was applied to the BOF data ***,the proposed algorithm preset the size of the feature subset based on the new encoding scheme,rather than the traditional uncertain number ***,opposition-based learning was used to initialize the grey wolf population so that the initial population was closer to the potential optimal *** addition,a novel population update method retained the features closely related to the best three grey wolves and probabilistically updated irrelevant features through measurement or random *** methods were used to search feature subsets to maximize search capability and stability of algorithm on BOF steelmaking ***,the proposed algorithm was compared with other feature selection algorithms on the BOF data *** results show that the proposed IGWO can stably select the feature subsets that are conductive to the end-point regression accuracy control of BOF temperature and carbon content,which can improve the performance of the BOF steelmaking.

关键词： Basic oxygen furnace Feature selection Grey wolf optimization Regression Opposition-based learning

来源：评论

学校读者我要写书评

暂无评论

A Review on Web data Mining to Detect Online Spread of Terrorism Activity 2

A Review on Web Data Mining to Detect Online Spread of Terro...

引用

2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025

作者： Jha, Saurav Kumar Pacharaney, Utkarsha Faculty of Engineering and Technology Department of Artificial Intelligence and Data Science Maharashtra Wardha India Faculty of Engineering and Technology Department of Artificial Intelligence and Machine learning Maharashtra Wardha India

ISBN: (纸本)9798331505745

This research study outlines the significant contribution that web data mining can make in discovering and combating the dissemination of online terrorism. With terrorist groups using the internet more and more to deliver propaganda, recruit, and organize, there is a pressing need for efficient monitoring and analysis of web content. This article discusses different data mining methods that can be used to identify and study patterns suggestive of terrorist activity throughout networked digital environments. Specifically, the embedding of machine learning algorithms, i.e., Support Vector Machines (SVM), Random Forest and Gradient Boosting, is investigated with regard to its suitability to differentiate between benign and harmful online content. These algorithms can process large volumes of data, where features are extracted, including URL structures, domain ages, and keyword frequencies, to detect anticipate threats. According to the article, feature extraction plays a crucial role in improving detection system accuracy, enabling real-time surveillance of anomalous online activities. In addition, the review discusses the problems that researchers and law enforcement agencies have been encountering in using web data mining for counter-terrorism purposes. Ethical concerns around privacy and civil liberties are addressed and technical challenges, including the quality of data and the dynamic character of online content, are elaborated. Scenarios in which false positives arising in detection systems may occur are also considered, with emphasis on the need for ongoing algorithm and technique refinement. © 2025 IEEE.

关键词： Crop protection

来源：评论

学校读者我要写书评

暂无评论

Handwritten Signature Verification using CNN

Handwritten Signature Verification using CNN

引用

artificial intelligence in Education and Industry 4.0 (IDICAIEI), DMIHER International Conference on

作者： Rutuja Nitin Lanjewar Radha Wasudeo Wande Swapnil Gundewar Faculty of Engineering and Technology Artificial Intelligence and Data Science Sawangi Maharashtra India Faculty of Engineering and Technology Artificial Intelligence and Machine Learning Sawangi Maharashtra India

ISBN: (数字)9798331528713

ISBN: (纸本)9798331528720

A signature is a special kind of a sign made or given by a person on an instrument or document to indicate that he or she fully understands everything written on the document, agrees with them or being bound to fulfill the obligations stated on the document. It is used to verify the genuineness of the writing, to indicate origin and to constrain the signer to the provisions thus provided in the writing. Thus, the field of signature verification is not only valuable for the sphere of commercial banking, used for tools against frauds and approval of transactions, but also for a lot of other fields. Employment of this method is widely seen in legal, financial and governmental sectors to avoid forgery of numerous contracts agreements, legal instruments and other related documents. This paper concentrates on the offline handwritten signature verification using CNN, an advanced deep learning architecture which is famous for its capability to work on image data. CNNs are more appropriate for this task concerning the following characteristics: they are capable to draw out significant features from the province of the images of signatures, and the features like the strokes, texture, and general structure of signatures and so on with the high classification accuracy of genuine and forged signatures. This approach makes the signature verification more efficient and accurate and provides a better and automated solution for many applications for which signature authentication is most essential.

关键词： Deep learning Handwriting recognition Accuracy Recurrent neural networks Instruments Writing Real-time systems Convolutional neural networks Optimization Residual neural networks

来源：评论

学校读者我要写书评

暂无评论

Learning in sinusoidal spaces with physics-informed neural networks

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on artificial intelligence 2024年第3期5卷 985-1000页

作者： Wong, Jian Cheng Ooi, Chin Chun Gupta, Abhishek Ong, Yew Soon Institute of High Performance Computing Agency for Science Technology and Research Singapore138632 Singapore School of Computer Science and Engineering Nanyang Technological University Singapore639798 Singapore Singapore Institute of Manufacturing Technology Agency for Science Technology and Research Singapore138632 Singapore Agency for Science Technology and Research Singapore138632 Singapore Data Science and Artificial Intelligence Research Centre School of Computer Science and Engineering Nanyang Technological University Singapore138632 Singapore

A physics-informed neural network (PINN) uses physics-Augmented loss functions, e.g., incorporating the residual term from governing partial differential equations (PDEs), to ensure its output is consistent with fundamental physics laws. However, it turns out to be difficult to train an accurate PINN model for many problems in practice. In this article, we present a novel perspective of the merits of learning in sinusoidal spaces with PINNs. By analyzing behavior at model initialization, we first show that a PINN of increasing expressiveness induces an initial bias around flat output functions. Notably, this initial solution can be very close to satisfying many physics PDEs, i.e., falling into a localminimum of the PINN loss that onlyminimizes PDE residuals, while still being far from the true solution that jointly minimizes PDE residuals and the initial and/or boundary conditions. It is difficult for gradient descent optimization to escape from such a local minimum trap, often causing the training to stall. We then prove that the sinusoidalmapping of inputs-in an architecture we label as sf-PINN-is effective to increase input gradient variability, thus avoiding being trapped in such deceptive local minimum. The level of variability can be effectively modulated to match high-frequency patterns in the problem at hand. A key facet of this article is the comprehensive empirical study that demonstrates the efficacy of learning in sinusoidal spaces with PINNs for a wide range of forward and inversemodeling problems spanning multiple physics domains. Impact Statement-Falling under the emerging field of physicsinformed machine learning, PINN models have tremendous potential as a unifying AI framework for assimilating physics theory and measurement data. However, they remain infeasible for broad science and engineering applications due to computational cost and training challenges, especially for more complex problems. Instead of focusing on empirical demonstration of appli

关键词： Gradient methods

来源：评论

学校读者我要写书评

暂无评论

Using Supervised Machine Learning Model For Predicting Fake Deliveries 6

Using Supervised Machine Learning Model For Predicting Fake ...

引用

6th International Conference on Computing and Informatics, ICCI 2024

作者： Sadek, Mohamed A. Fouad, Khaled M. Faculty of Information Technology and Computer Science Nile University Cairo Egypt Faculty of Computers and Artificial Intelligence Benha University Egypt Faculty of Computer Science and Engineering New Mansoura University Egypt

ISBN: (纸本)9798350373875

The home delivery service is a crucial part of the delivery process. Still, it has the highest financial and trustworthiness costs because it's the only part that directly touches the customer. If it works, the customer will be happy, and the company will make money, but if it doesn't, the customer will be skeptical, and the product will not be trusted. One big issue with the delivery process that this study will try to address is the prevalence of fraudulent or inaccurate deliveries. Making the most money possible from each journey is the primary goal of most riders. The delivery management system allows riders to falsely record orders as completed, allowing them to receive many orders simultaneously. Because the consumer usually gets a message or notification saying their item has been delivered when it hasn't, this weakens their faith in the organization and messes up the delivery process. Return to Origin (RTO) rates rose, and consumer confidence in the brand fell due to the fraudulent shipments. The suggested approach is based on ML models that are supervised. © 2024 IEEE.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

Dynamic-Matrix-Encryption Based Secure Strong PUF for Device Authentication Protocols 17

Dynamic-Matrix-Encryption Based Secure Strong PUF for Device...

引用

17th IEEE International Conference on Solid-State and Integrated Circuit technology, ICSICT 2024

作者： Zhao, Liangxiao Li, Gang Wang, Pengjun Ma, Xuejiao Zhou, Ziyu The College of Electrical and Electronic Engineering Wenzhou University Wenzhou325000 China School of Data Science and Artificial Intelligence Wenzhou University of Technology Wenzhou325035 China Ningbo University Faculty of Electrical Engineering and Computer Science Ningbo315211 China

ISBN: (纸本)9798350361834

Strong physical unsolvable function (PUF) has a wide range of applications in internet of things (IoT) security. However, it is vulnerable to machine learning (ML) modeling attacks. This paper proposes a strong PUF anti-ML attack method based on dynamic-matrix encryption. It obfuscates the challenge by multiplying the dynamic encryption matrix (DEM) with the challenge matrix synchronizing initial values during the registration phase of the device security authentication protocol prevents our obfuscation from being invalidated when the algorithms and structures motivating the obfuscation are made public. Each round of DEM is updated with respect to each previous round of challenge which is similar to the properties of sequential logic circuits in that the current response does not depend only on the current challenge but is related to previous challenge. Experimental results show that even if an attacker collects 1 million challenge response pairs, the prediction accuracies of the several ML attacks we use are below 53%, with negligible effects on randomness, reliability, and uniqueness. © 2024 IEEE.

关键词： Authentication Protocol

来源：评论

学校读者我要写书评

暂无评论

A Novel High-Efficiency Transaction Verification Scheme for Blockchain Systems

引用

Computer Modeling in engineering & sciences 2024年第5期139卷 1613-1633页

作者： Jingyu Zhang Pian Zhou Jin Wang Osama Alfarraj Saurabh Singh Min Zhu School of Computer&Communication Engineering Changsha University of Science&TechnologyChangsha410015China Science and Technology on Information Systems Engineering Laboratory School of Systems EngineeringNational University of Defense TechnologyChangsha410073China Computer Science Department King Saud UniversityRiyadh11437Saudi Arabia Department of Artificial Intelligence and Big Data Woosong UniversityDaejeon34606South Korea College of Information Science and Technology Zhejiang Shuren UniversityHangzhou310015China

Blockchain can realize the reliable storage of a large amount of data that is chronologically related and verifiable within the *** technology has been widely used and has developed rapidly in big data systems across various *** increasing number of users are participating in application systems that use blockchain as their underlying *** the number of transactions and the capital involved in blockchain grow,ensuring information security becomes *** the verification of transactional information security and privacy has emerged as a critical ***-based verification methods can effectively eliminate the need for centralized third-party ***,the efficiency of nodes in storing and verifying blockchain data faces unprecedented *** address this issue,this paper introduces an efficient verification scheme for transaction ***,it presents a node evaluation module to estimate the activity level of user nodes participating in transactions,accompanied by a probabilistic analysis for all ***,this paper optimizes the conventional transaction organization form,introduces a heterogeneous Merkle tree storage structure,and designs algorithms for constructing these heterogeneous *** analyses and simulation experiments conclusively demonstrate the superior performance of this *** verifying the same number of transactions,the heterogeneous Merkle tree transmits less data and is more efficient than traditional *** findings indicate that the heterogeneous Merkle tree structure is suitable for various blockchain applications,including the Internet of *** scheme can markedly enhance the efficiency of information verification and bolster the security of distributed systems.

关键词： Blockchain architecture transaction verification information security heterogeneous Merkle tree distributed systems

来源：评论

学校读者我要写书评

暂无评论

Pathological voice detection using optimized deep residual neural network and explainable artificial intelligence

引用

Multimedia Tools and Applications 2024年 1-27页

作者： Jegan, Roohum Jayagowri, R. Department of Electronics and Communication Engineering BMS College of Engineering Bull Temple Road Karnataka Bengaluru560019 India Department of Artificial Intelligence and Data Science SIES Graduate School of Technology Nerul Maharashtra Navi Mumbai400706 India

Voice disorders affect individuals’ vocal quality and communication abilities, which pose significant challenges for both individuals and healthcare providers. The accurate and timely detection of voice disorders is crucial in facilitating early intervention and effective treatment. This study proposes a new noninvasive approach for voice disorder detection based on an optimized deep residual neural network. Input speech samples are transformed into mel-spectrogram time-frequency images and applied to train the ResNet-50 transfer learning model. The spectrogram time-frequency representation effectively captures intricate patterns and features that might indicate the presence of voice disorders exploiting local and global characteristics. Four hyperparameters of the ResNet-50 model are optimized using the snake optimization algorithm, which delivers an optimum residual deep transfer learning (DTL) model with an enhanced voice pathology detection rate. The proposed snake-optimized ResNet-50 model is evaluated on four popular voice pathology datasets: AVPD, SVD, PdA and VOICED. The results demonstrate the efficacy of the optimized ResNet-50 framework in accurately classifying healthy and pathological voice samples with 98.13% accuracy. Comparisons with recent machine learning and deep learning models reveal the superiority of the proposed approach in terms of F1-score, sensitivity, specificity and accuracy. Finally, Gradient-weighted class activation mapping (Grad-CAM) explainable artificial intelligence (XAI) is utilized for visualizing and interpreting the decision-making process. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Transfer learning

来源：评论

学校读者我要写书评

暂无评论

A Review on Web data Mining to Detect Online Spread of Terrorism Activity

A Review on Web Data Mining to Detect Online Spread of Terro...

引用

Machine Learning and Autonomous Systems (ICMLAS), International Conference on

作者： Saurav Kumar Jha Utkarsha Pacharaney Department of Artificial Intelligence and Data Science Faculty of Engineering and Technology Wardha Maharashtra India Department of Artificial Intelligence and Machine learning Faculty of Engineering and Technology Wardha Maharashtra India

ISBN: (数字)9798331505745

ISBN: (纸本)9798331505752

关键词： Support vector machines Uniform resource locators Machine learning algorithms Reviews Law enforcement Terrorism Feature extraction Real-time systems data mining Internet of Things

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：