检索结果-内蒙古大学图书馆

Delayed dynamic-feedback controller design for multi-frequency vibration suppression

IFAC-PapersOnLine 2024年第27期58卷 196-201页

作者： Adrian Saldanha Adam Peichl Wim Michiels Tomas Vyhlidal Department of Computer Science KU Leuven Celestijnenlaan 200A 3001 Leuven Belgium Dept. Instrumentation and Control Engineering Faculty of Mechanical Engineering and Czech Institute of Informatics Robotics and Cybernetics Czech Technical University in Prague Prague 6 Czechia

We present a methodology for designing a dynamic controller with delayed output feedback for achieving non-collocated vibration suppression with a focus on the multi-frequency case. To synthesize the delay-based controller, we first remodel the system of equations as a delay-differential algebraic equation (DDAE) in such a way that existing tools for design of a static output feedback controller can be easily adapted. The problem of achieving non-collocated vibration suppression with sufficient damping is formulated as a constrained optimization problem of minimizing the spectral abscissa in the presence of zero-location constraints, with the constraints exhibiting polynomial dependence on its parameters. We transform the problem into an unconstrained one using elimination, following which we solve the resulting non-convex, non-smooth optimization problem.

关键词： vibration suppression time-delay DDAE

来源：评论

学校读者我要写书评

暂无评论

Fingerprint definition for song recognition using Machine Learning Algorithm

Fingerprint definition for song recognition using Machine Le...

引用

Smart Systems for applications in Electrical Sciences (ICSSES), International Conference on

作者： Arunakumari B N Shashidhar R Sahana B Jagadamba G A S Manjunath Roopa M Dept. of Computer Science and Engineering BMS Institute of Technology and Management Bengaluru India Dept. of Electronics & Communication Engineering JSS Science and Technology University Mysuru India Dept. of Electronics & Communication Engineering RV College of Engineering Bengaluru India Dept. of Information Science and Engineering Siddaganga Institte of Technology Tumkuru India Dept. Of Master of Computer Applications JSS Science and Technology University Mysuru India Dept. of Electronics & Communication Dayananda Sagar College of Engineering Bengaluru India

A condensed content-based signature that summarises an audio recording is known as an audio fingerprint. Audio The capability to recognize music regardless of design and without the use of meta-data or watermark embedding has made fingerprinting technologies popular. In. tegrity checking, watermark support, and content-based aural retrieval are additional applications for fingerprinting. The various methods of fingerprinting have been discussed using various justifications and terminologies, such as pattern matching, multimedia information retrieval, or cryptography. It is a distinct and condensed digest created using perceptually important elements of a video. Audio material can be monitored using fingerprinting technologies without requiring embedding of metadata or watermarks. However, audio fingerprinting has extra applications The algorithm is trained using thousands of mini audio speech commands. In order to improve the training efficiency, audio features are extracted during a pre-processing. The accuracy of the developed model is 83.7%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Detection of Multi-Class Multi-Label Ophthalmological Diseases in Retinal Fundus Images Using Machine Learning

Detection of Multi-Class Multi-Label Ophthalmological Diseas...

引用

Innovations and Challenges in Emerging Technologies (ICICET), International Conference on

作者： P. T. Karule Sujata B. Bhele Prasanna Palsodkar Poonam T. Agarkar Hirendra R. Hajare Prashant R. Patil Dept. of Electronics Engineering Yeshwantrao Chavan College of Engineering Nagpur M.S India Dept. of Electronics & Telecommunication Engineering Government College of Engineering Nagpur M.S India Dept. of Computer Science and Engineering Ballarpur Institute of Technology Chandrapur M.S India Dept. of Management Studies Smt. Radhikatai Pandav College of Engineering Nagpur M. S India

ISBN: (数字)9798350319019

ISBN: (纸本)9798350319026

Multi-disease diagnosis of fundus image is a great challenge even though sophisticated computer-aided tools are available and ophthalmologist experience is to par. Clinical tests capture abnormalities and anatomical structures for various diagnoses of the retinal image. The proposed work uses RFMiD (Retinal Fundus Multi-Disease Image Dataset) to classify ocular diseases using an efficient feature extraction framework and machine learning. The framework considers 8-12 diverse ophthalmological diseases from 3200 dataset images labeled with the help of two senior medical (retinal) experts. Experimental evaluation of the dataset using Random forest classified up to 10 diseases with an accuracy of 100% while 96.75% was obtained when 12 diseases were considered without augmenting the dataset images. The evaluation successfully determined the retinal infection due to fine-grained variability, appearance, and closeness in the presence of several lesions.

关键词： Technological innovation Pathology Forestry Retina Feature extraction Data augmentation Ophthalmology

来源：评论

学校读者我要写书评

暂无评论

An Empirical Investigation on Electronic Government Services Continuance and Trust

An Empirical Investigation on Electronic Government Services...

引用

International Symposium on Technology and Society (ISTAS)

作者： Muhammad Ovais Ahmad Iftikhar Ahmad Iqra Sadaf Khan Dept. of Computer Science Karlstad University Karlstad Sweden Department of Computer Science and Information Technology University of Engineering and Technology Peshawar Pakistan Dept. of Management Studies Aalto University Espoo Finland

Trust is an important factor that contributes to citizens' willingness to continuance use of e-gov services. However, there is a lack of prior investigation about trust and continuance use of e-gov services in Pakistan - a developing country. We propose a model to investigate citizens' trust and e-gov services' continuous use intention to fill this research gap. Our study collected data from an online survey of 558 Pakistani citizens. Using partial least squares analysis, we found that disposition to trust positively correlates with both internet and government trust. Moreover, citizen satisfaction, trust, perceived usefulness, confirmation, and perceived risk all have significant impacts on the continuous use intention of e-gov services. This research extends and validates the Expectation-Confirmation Model by exploring key factors that influence e-gov continuance use intention. As such, our study offers valuable insights for policymakers and practitioners involved in e-gov service delivery in developing countries like Pakistan. The paper also discusses our findings' implications and identifies future research directions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MoodSync: Personalized Video Recommendation Based on User Face Emotion

MoodSync: Personalized Video Recommendation Based on User Fa...

引用

Disruptive Technologies (ICDT), International Conference on

作者： Anurag Singh Shaishav Gupta Harshit Satyawali Vikrant Sharma Shashank Awasthi Satvik Vats Dept. of Computer Science Graphic Era Hill University Dehradun Dehradun Uttarakhand India Department of Computer Science and Engineering G.L. Bajaj Institute of Management Greater Noida

Navigating the vast expanse of video content presents a challenge in discovering personalized, user-specific material. One way to tackle this issue is through a video search feature. However, while using keywords helps, it doesn't always give the best user experience. This abstract explores the use of facial emotion in contrast to watch history for better recommendation of videos to the user. YouTube is a widespread online video-sharing platform where users can upload, share, and view videos. Its recommendation system utilizes algorithms that analyses user behaviors, such as watch history, search patterns, and engagement metrics. Machine learning models, like collective filtering and deep neural networks, are employed to predict what content a user may enjoy. This personalized method enhances user experience, encourages longer engagement, and contributes to the platform's success in delivering applicable and engaging video content. We wanted to know what people liked, so we looked at how they felt when watching videos. With this knowledge, a new method of recommending videos that correspond with their feelings was developed. In real-time, our application reads users' facial expressions and recommends YouTube videos accordingly.

关键词：

来源：评论

学校读者我要写书评

暂无评论

XANNLight: A Novel Hybrid Ensemble Model for Accurate Health Insurance Prediction and Trend Forecasting 6

XANNLight: A Novel Hybrid Ensemble Model for Accurate Health...

引用

6th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2025

作者： Kafila Suneel, Sajja Thatipudi, Jayendra Gopal Jini Kumari, M. Penyameen, K. Sharma, Anubhav School of Business SR University Telangana Warangal India Institute of Aeronautical Engineering Dundigal Telangana Hyderabad500043 India Dept. of Computer Science University of North Texas United States Department of ECE Chennai Institute of Technology India Velammal College Of Engineering And Technology Madurai India Department of CSE IES institute of Technology and management IES University Mp Bhopal462044 India

ISBN: (纸本)9798331522667

Health insurance is a critical industry that requires precise data analysis and predictive capabilities to ensure operational efficiency and cost management. In an era where large datasets are readily available, machine learning models have become indispensable for predicting claims and identifying trends in insurance data. The rapid growth of the health insurance industry has increased the need for accurate prediction models to optimize claim management and trend forecasting. This study presents XANNLight, a novel hybrid ensemble model that integrates Artificial Neural Networks (ANN) and LightGBM to predict health insurance claims with high precision. The proposed model handles complex, nonlinear relationships using ANN while LightGBM provides fast and accurate predictions for structured data. The dataset used for model training and evaluation consists of 1338 records, with features including age, sex, BMI, number of children, smoker status, and region. The model’s performance is evaluated based on accuracy, precision, recall, and F1 score. The XANNLight model achieves an accuracy of 98.12%, outperforming nine existing models, including Logistic Regression, Decision Tree, Random Forest, and Gradient Boosting, which achieved accuracy levels between 85% and 96%. Furthermore, XANNLight demonstrates superior precision (97.83%), recall (97.90%), and F1 score (97.86%). These results highlight the model's efficiency in processing large datasets and predicting insurance claims, making it an effective tool for health insurance companies aiming to enhance operational efficiency and cost management. © 2025 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Smart Locker 2.0: Leveraging IoT and Machine Learning for Secure, User-Friendly Public Storage

Smart Locker 2.0: Leveraging IoT and Machine Learning for Se...

引用

2025 International Conference on Artificial Intelligence and Data engineering, AIDE 2025

作者： Chandrappa, S. Prithviraj Aditya Pai, H. Rajesh, I.S. Manjunath Sargur Krishnamurthy, R. Sneha Shetty, R. Dept. of Computer Science and Engineering Bengaluru India NMAM Institute of Technology Nitte Dept. of Computer Science and Engineering India MIT Art Design and Technology University Department of CSE Pune India BMS Institute of Technology and Management Dept. of AI & ML Bengaluru India JP Morgan & Chase Co Houston United States NMAM Institute of Technology Dept. of Artificial Intelligence and Machine Learning Nitte India

ISBN: (数字)9798331527518

ISBN: (纸本)9798331527518

Smart locker systems are a revolutionary technology, combining advanced automation and connectivity to address increasingly demanding requirements for secure, efficient, and convenient storage solutions in numerous scenarios. These intelligent lockers use the latest technologies, such as the Internet of Things (IoT) and mobile applications, to revolutionize the way people store their belongings. Existing Smart Locker System lacks measurable results. To sustain its claims, we include key findings. For security, the system utilizes RFID authentication and biometric security, which reduces unauthorized access by 98% and blocks spoofing attacks. For convenience, a study with 50 users found 92% satisfaction, with 87% preferring it over traditional lockers due to faster access, averaging 3 seconds. For environmental benefits, the system cut power use by using sleep mechanism and saved paper usage by switching to cloud logs. Real-World tests achieved 98% user satisfaction with the university system proving its efficiency, security, and sustainability. This system expounds on multifaceted benefits and functionalities in smart lockers. First, it covers how these lockers provide better security compared to old lock-and-key systems. Using access controls reduces the risk of theft and illegal access to one's valuables and sensitive belongings by a great degree. It has an easy reservation, access, and management of personal lockers via a remote means;this proves to be seamless without needing any physical keys and contactless interactions, ideal for modern spaces considering hygiene and efficiency is top priority. Moreover, it goes on to analyze the flexibility of smart locker systems. From corporate offices to co-working spaces, universities, shopping malls, and public transportation hubs, these lockers cater to diverse user needs, creating flexible and scalable solutions adaptable to a variety of environments. © 2025 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Differential Co-expression Network Analysis to Investigate Sexual Dimorphism in Colon Cancer

Differential Co-expression Network Analysis to Investigate S...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Caterina Alfano Lorenzo Farina Manuela Petti PhD program in Network Oncology and Precision Medicine Sapienza University of Rome Rome Italy Dept. of Computer Control and Management Engineering PhD program in Network Oncology and Precision Medicine Sapienza University of Rome Rome Italy Dept. of Computer Control and Management Engineering Sapienza University of Rome Rome Italy

ISBN: (数字)9781665468190

ISBN: (纸本)9781665468206

Colorectal cancer is the third most diagnosed cancer in the world, but it has a higher mortality rate in men compared to women. However, we are not close to understanding how and why sex influences the outcome of the disease. This study focuses on mRNA expression profiles of colon cancer patients to look for molecular differences in the development of colon cancer between men and women. We used paired expression data (i.e., data collected in pairs of normal and cancer cells, by taking samples from the same individual), we identified differentially expressed genes (cancer vs normal) and computed co-expression and differential co-expression gene networks (men vs women). Doing so, we inferred the main changes and alterations happening in cancer tissues, and specifically how these changes were different among men and women. We found that the co-expression networks of women and men affected by colon cancer are quite different and we reported the genes that show the most differences in this comparison, checking if they could also be associated to sexual dimorphism or sexual hormones. Among these genes we found a interesting presence of genes associated to the Wnt signaling pathway which has been found to be regulated by estrogen and whose activation is strongly linked with colon cancer.

关键词： Network analyzers Biochemistry Colon Bioinformatics Cancer

来源：评论

学校读者我要写书评

暂无评论

AI-Driven Precision Agriculture: Techniques for Monitoring Crop Health and Yield Optimization

AI-Driven Precision Agriculture: Techniques for Monitoring C...

引用

Technological Advancements in Computational Sciences (ICTACS), International Conference on

作者： Deepak Sharma M. Chitra Devi Vivek Veeraiah Manisha Kasar Deepshikha Aggarwal Tripti Sharma Jagannath University Jaipur Rajasthan India Dept. of Computer Science SRM Trichy Arts and Science College Tamil Nadu India Dept. of Computer Science Sri Siddhartha Academy of Higher Education Karnataka India Dept. ofCSE Bharati Vidyapeeth (Deemed to be University) College of Engineering Pune Maharashtra India Dept. of IT Jagan Institute of Management Studies Delhi India Dept. of CSE Rungta College of Engineering & Technology Bhilai Chhattisgarh India

ISBN: (数字)9798350387490

ISBN: (纸本)9798350387506

AI-driven precision agriculture is revolutionising the agricultural business by using advanced techniques to monitor crop health and optimize output. By integrating data from sensors, drones, and satellite photos with artificial intelligence, farmers may get up-to-date information on crop condition, soil health, and environmental factors. Through meticulous analysis of vast amounts of data, these artificial intelligence systems are capable of detecting the first signs of pests, diseases, and nutritional deficiencies. This enables timely interventions to enhance the overall health of crops. AI-driven predictive analytics manage the timing of irrigation, fertilisation, and harvesting to enhance productivity and guarantee optimum resource use. This approach addresses growing global need in case of food while also improving agricultural sustain ability and productivity. The Python script demonstrates integration of AI and IoT technologies into a Precision Agriculture System to optimize agricultural yields and monitor crop health. It generates a synthetic dataset with real-world parameters and evaluates the Random Forest Regressor model on training along with testing data. The simulation provides visual insights and performance metrics, highlighting the potential of AI and IoT in precision agriculture in case of enhanced decision-making along with productivity.

关键词： Precision agriculture Productivity Temperature sensors Temperature measurement Visualization Decision making Crops Artificial intelligence Monitoring Testing

来源：评论

学校读者我要写书评

暂无评论

ELCCFD: An Efficient and Enhanced Credit Card Fraud Detection using Enhanced Deep Learning Principle 5

ELCCFD: An Efficient and Enhanced Credit Card Fraud Detectio...

引用

5th International Conference on Image Processing and Capsule Networks, ICIPCN 2024

作者： Potluri, Pandarinath Suneel, Sajja Chandra, B. Muthukumaran, D. Upadhyaya, Makarand Rajesh Kanna, R. Sitarampuram Narsapuram West Godavari district department of CSE Swarnandhra college of engineering and technology 534275 India Telangana Hyderabad India Department of Management Studies AP India Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology India University of Bahrain College of Business Administration Dept. of Management & Marketing Bahrain Department of Computer Science India

ISBN: (纸本)9798350367171

Credit card fraud poses a serious threat to financial institutions and their customers;hence, stringent detection protocols are necessary. This study introduces an approach known as Enhanced Learning for Credit Card Fraud Detection (ELCCFD) to enhance the accuracy of credit card fraud detection. To improve the fraud detection process, the proposed method combines the strengths of Convolutional Neural Networks (CNNs), AlexNet architecture, and Gradient Boosting Machines (GBM). The proposed approach begins with cleaning up the credit card data to get useful features, then trains a Convolutional Neural Network (CNN) using AlexNet to figure out complex patterns and representations on its own. This study generates a complete set of features by merging the CNN's output with features generated using GBM. The final model is trained by using a combination of deep learning and other conventional machine learning techniques to achieve the best results. Experimental findings on benchmark datasets demonstrate the effectiveness of the ELCCFD methodology, achieving an accuracy rate of 98%. This study combines AlexNet with GBM to get a model to capture the complex patterns and is easier to understand with the feature importance analysis. With its strong accuracy and reliability, the proposed methodology offers a strong option to fight credit card fraud, and it shows the potential for actual use in financial systems. © 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

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：