检索结果-内蒙古大学图书馆

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

作者： Samarth, S. Sumukha Raghavan, M. Santhosh, T. Kowligi, Sahana J. Pooja, M.R. Department of Computer Science and Engineering Vidyavardhaka College of Engineering Mysuru India

ISBN: (纸本)9798331529635

This research study proposes a novel approach for behavioral tracking and anomaly detection in digital systems by using AI-driven models, particularly for applications in signal processing and digital computer environments. The proposed AI model combines techniques of behavioral tracking, aiming at identifying deviations in the operations of the system, while enhanced monitoring and anomaly identification are the focus. This methodology captures subtle deviations in user behavior and system signals to enhance real-time security and system integrity, thereby reducing the likelihood of unauthorized access and system misuse. © 2024 IEEE.

关键词： AI Models Anomaly Detection Behavioral Tracking Digital Systems

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Infant Cry Classification using Machine Learning and Deep Learning Techniques 1

Comparative Analysis of Infant Cry Classification using Mach...

引用

1st International Conference on Intelligent Systems and Computational Networks, ICISCN 2025

作者： Ramulu, Kothuri Parashu Jogannagari, Pranathi Reddy Indur Institute of Engineeing & Technology Department of Computer Science and Engineering Siddipet India University of Alabama at Birmingham Department of Computer Science Birmingham United States

ISBN: (纸本)9798331529246

Infant Cry Classification is the process of analyzing acoustic signals from an infant's cry for extracting relevant features to determine the cause of crying, and assess the infant's health condition. The process is typically divided into four main stages: pre-processing, feature extraction, feature fusion, and classification. In the feature extraction stage, spectrograms along with frequency transforms such as the Wavelet Transform, Cosine Transform, and Fourier Transforms are employed to capture important characteristics of the cry. The feature fusion stage is critical as it integrates information from various scales and contexts obtained during feature extraction, allowing for a more comprehensive representation of the cry's features. In current times, both Machine Learning (ML) and Deep Learning (DL) techniques are employed for classification. The ML techniques predominantly utilized in this process are: Multi-Class Support Vector Machines (SVM), Hyperparameter-Optimized SVM, Kernel-based SVM, Ensemble Boosting methods, Random Forest classifiers, K-Nearest Neighbors (K-NN), and Bayesian Optimization. In the case of DL architectures, models such as Style and Latent Guided Adversarial Networks (SLGAN), Multi-Layer Perceptron (MLP), Convolutional Neural Network - Sparse Convolution Net (CNN-SCNet), 1D CNN, and Dual-CNN are frequently employed to ensure high accuracy. The performance of these classification algorithms is evaluated in terms of the following metrics: sensitivity, specificity, accuracy, precision, and F-measure. © 2025 IEEE.

关键词： Cosine transforms

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection in Cybersecurity: Leveraging Machine Learning for Intrusion Detection

Anomaly Detection in Cybersecurity: Leveraging Machine Learn...

引用

2024 International Conference on Communication, computer sciences and engineering, IC3SE 2024

作者： Mittal, Aditi Gupta, Anushka Bhoomi Agarwal, Kadambri Abes Engineering College Department Of Computer Science And Engineering Ghaziabad India

ISBN: (纸本)9798350366846

An intrusion Detection system is a software that monitors the network traffic and alerts the administrators if any malicious request is found. The system is able to segregate between a malicious and non-malicious request using two methods one is signature-based and the other is by training a machine learning model which is also called the Anomaly-based method. In this paper, we have achieved the highest accuracy from all existing models i.e., 99.99%. We have been able to increase the accuracy of ML models as a result of our proposed model, which is an ensemble of Random Forest, Decision tree, and KNN. Along with this, we have also applied a deep learning model ANN which has led to the effect. Since we have used four different datasets, our model is trained with a large number of datasets which has also contributed to high accuracy. © 2024 IEEE.

关键词： Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

Facial Expression based Music Recommendation System using Deep Convolutional Neural Network 4

Facial Expression based Music Recommendation System using De...

引用

4th International Conference on Expert Clouds and Applications, ICOECA 2024

作者： Ashwini, P. Dammalapati, Pranav Ramineni, Nagajaswanth Adilakshmi, T. Vasavi College of Engineering Department of Computer Science and Engineering Hyderabad India

ISBN: (纸本)9798350385793

The proposed context-aware music recommendation system revolutionizes user experience by combining cutting-edge face recognition technology with Convolutional Neural Network (CNN) algorithms. To overcome the challenges faced by traditional voice analysis methodologies, this research study not only enhances mood detection accuracy but also significantly reduces the training duration. Utilizing the Streamlit library for the user interface ensures seamless interaction across various expertise levels. In the backend, the synergy among TensorFlow, Keras API, and foundational frameworks like NumPy empowers the proposed system to efficiently analyze extensive datasets, delivering personalized music recommendations in real-time. This integration of face recognition, CNN algorithms, and robust frameworks signifies a technological leap, reshaping the music recommendation landscape by acknowledging the dynamic nature of emotions and the diverse contexts in which users engage with music. © 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

Emergency evacuation system

Emergency evacuation system

引用

International Conference on Artificial Intelligence, Blockchain, Computing and Security, ICABCS 2023

作者： Loganathan, V. Parveen Fathima, M. Poorvaja, A. Rajalakshmi, R. Department of Computer Science and Engineering Saveetha Engineering College Chennai India

ISBN: (纸本)9781032669663

As global population is increasing day by day, life expectancy rises, and the causes of death across the world is rapidly increasing. It is very common that we tend to rush to any known exit when fire breaks out but this is not necessarily the best option. Therefore, our project mainly focuses on developing a medium that notifies and alerts people to an exit that is comparatively safe. Our project uses IoT technology in order to track the fire location, then notify the people to leave out safely. The information regarding the risk is intimated to the people at the right time. Various sensors are used in order to detect gases, temperature etc. The information regarding the fire accident will be provided to the user in timely manner so that the people will be able to know about the risk that is likely to be happened. Thus, intimating the user regarding the risk by sending an alert message to their mobile phones can probably decrease the death rates of the people. © 2024, CRC Press/Balkema. All rights reserved.

关键词： Gas temperature

来源：评论

学校读者我要写书评

暂无评论

Voice Assisted Facial Emotion Recognition System For Blind Peoples With Tensorflow Model

Voice Assisted Facial Emotion Recognition System For Blind P...

引用

2024 IEEE International Students' Conference on electrical, Electronics and computer science, SCEECS 2024

作者： Ashmad Ahemed, S. Jayakumar, D. Ifet College of Engineering Department of Computer Science and Engineering Villupuram India

ISBN: (纸本)9798350348460

This research project presents the development of a novel Voice-Assisted Facial Emotion Recognition System tailored to address the unique needs of blind individuals. Leveraging the power of deep learning and the TensorFlow framework, the system employs computer vision techniques to detect and interpret facial emotions, enabling blind users to comprehend the emotional cues of those they interact with. The project encompasses data collection, preprocessing, model training, and evaluation, resulting in a robust TensorFlow model capable of real-time emotion recognition from facial images. A voice assistant integrates seamlessly into the system, offering spoken feedback to users, thus enhancing their understanding of emotional contexts during social interactions. The system prioritizes user accessibility and privacy, ensuring a user-friendly interface and adherence to data security standards. Extensive testing and user feedback are essential components of the project, allowing for continuous improvement and optimization to meet the specific needs of blind individuals. This research offers a promising solution to empower the visually impaired community by providing them with a valuable tool for enhanced social interaction and emotional understanding. Real-World Application, Emphasize the practicality and real-world applicability of the system, showcasing how it can make a meaningful impact on the daily lives of blind individuals by helping them navigate social and emotional contexts more effectively. Multimodal Interaction, Highlight the multimodal nature of the system, which combines visual facial emotion recognition with voice-based interaction to provide a comprehensive and accessible user experience. © 2024 IEEE.

关键词： Convolutional Neural Network Emotion identification Tensorflow

来源：评论

学校读者我要写书评

暂无评论

Virtual AI Mouse with Biometric Authentication

Virtual AI Mouse with Biometric Authentication

引用

2024 International Conference on Knowledge engineering and Communication Systems, ICKECS 2024

作者： Vishnu Praba, B. Vinothini, R. Jayarathna, M. Subramani, Kavitha Sravanthi, P. Panimalar Engineering College Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350359688

A recent study has introduced an AI-driven virtual mouse that has the potential to revolutionize Human-computer Interaction (HCI) through its powerful machine-learning capabilities. This mouse has a versatile and user-friendly pointing system that can be used with current devices, potentially transforming traditional input methods. By using our AI-powered solution, we can address accessibility issues, enhance user experience, and enable new digital connections. The AI-powered virtual mouse is revolutionizing the way people interact with devices by offering a hands-free alternative to human-computer interaction. There are concerns about privacy and security due to the extensive use of technology. This research proposes two upgrades to overcome these issues: biometric verification and encryption. These enhancements create a private and secure virtual mouse experience by reducing security threats and unauthorized access, which is especially helpful for sensitive tasks. This research effort bridges innovation with increased security, adding to the changing field of HCI. © 2024 IEEE.

关键词： Biometrics

来源：评论

学校读者我要写书评

暂无评论

Designing Optimal Parameters for Single-Axis Solar-Tracker through Analysis of Sun-Path and Tracking Vector Dynamics 6

Designing Optimal Parameters for Single-Axis Solar-Tracker t...

引用

6th International Conference on electrical engineering and Information and Communication Technology, ICEEICT 2024

作者： Akhtaruzzaman, M. Islam, Md Shofiqul Shahryer, Fahim Arif, Muammer Din Mollik, Md. Sazib Rahman, Muhammad Towfiqur Rahman, Md. Mahbubur Hasan, Mohammad Kamrul Ahmed, Shugata Ashrafuzzaman, Md. Department of Computer Science and Engineering Dhaka1216 Bangladesh Department of Mechanical Engineering Dhaka1216 Bangladesh Department of Electrical and Electronic Engineering Dhaka Bangladesh Department of Computer Science and Engineering Dhaka Bangladesh Faculty of Information Science and Technology Bangi Malaysia Department of Robotics and Mechatronics Engineering Bangladesh Sdn. Bhd. Cyberjaya Malaysia

ISBN: (纸本)9798350385779

The persistent challenges faced by sun-tracking systems include inefficient power production, wastage of energy, ineffective control, and high costs. Most of the existing systems are either static or dual-axis tracking which lead to inefficient output or increasing energy wastage and cost overheads. Though, single-axis tracking system has some benefits over the static or dual-axis tracking, most of the systems do not analyze the selection of optimal sun-path which again leads to inefficient and inadequate absorption of sunlight. Addressing the issues, this article presents a design of optimal parameters for single-axis solar-tracking by analyzing the sun-path and tracking vector dynamics. The study mainly focuses on analyzing solar-tracking dynamics, variations in sunray angles, Azimuth and Elevation dynamics throughout the day for the twelve months, Sun-vector calculation for local coordinates, joint rotational-axis, and joint motion control using a Proportional-Derivative controller. Additionally, the article outlines a conceptual architecture for automated control, monitoring, and power distribution for the potential development of a sustainable smart city. The proposed strategy addresses the issues of the optimal design of a single-axis solar-tracker, thus ensuring the reduction of cost overhead and energy wastage. © 2024 IEEE.

关键词： Dynamics

来源：评论

学校读者我要写书评

暂无评论

Systematic analysis of on-premise and cloud services

引用

International Journal of Cloud Computing 2024年第3期13卷 214-242页

作者： Ali, Asif Laghari, Asif Ali Kandhro, Irfan Ahmed Kumar, Kamlesh Younus, Salman Department of Computer Science Sindh Madressatul Islam University Karachi Pakistan Department of Software Engineering Sindh Madressatul Islam University Karachi Pakistan

There are two key distinctions between cloud and on-premise (OP) software, the cost for each varies and so does the level of control. As organisations explore to reduce costs, many data and rules are migrating to multiple clouds like GCP, AWS, AZURE, and so on. Cloud service providers provide the extensibility, resilience, and quickness that traditional OP deployments usually lose. This paper presents a comparative analysis of on-premise and cloud computing differs by outline, arrangement, administration, and devices for associations and clients. This comparison shows that cloud computing provides more flexible infrastructure and better service of data processing on-premise. In today’s enterprise IT world, there are many factors that a business must consider when deciding whether a cloud infrastructure is the right choice. As there are many mid-level organisations that I personally know which fails to adapt cloud solutions, instead rely on their proven legacy and on-premises applications and software to do business. Therefore, it is very challenging to decide for business, if either a cloud infrastructure is right choice or not. In this article, which have covered many areas and analyses of on-premise and cloud, which will help mid-level organisations to make the decision of choosing cloud solutions for their running business applications. Copyright © 2024 Inderscience Enterprises Ltd.

关键词： Cloud computing

来源：评论

学校读者我要写书评

暂无评论

Detecting the violence from video using computer vision under 2dspatio temporal representations

Detecting the violence from video using computer vision unde...

引用

International Conference on Artificial Intelligence, Blockchain, Computing and Security, ICABCS 2023

作者： Srividhya, M. Ramyadevi, R. Vijaya Chamundeeswari, V. Department of Computer Science and Engineering Saveetha Engineering College Chennai India

ISBN: (纸本)9781032669663

A current hot topic in computer vision is action recognition in videos, particularly for the detection of aggression. The complexity of the 2D + t data produced by the proliferation of videos by a security camera or television material is what makes this work interesting. Modern techniques learn using 3D neural network approaches, which require data to train to produce discriminating features. This research intends to address topics such as cutting-edge techniques for video violence detection, datasets for real-time video violence detection framework development, and discussion and identification of unresolved concerns in the given subject. To overcome these restrictions, we offer throughout this piece a technique for putting videos into categories for violence recognition with a traditional 2D CNN. The methods comprise two parts.: (I) From an input video, we first construct several 2D spatial-temporal representations, (II) According to speculation, the new representations will feed CNN’s test/training data. The methodology by combining the separate conclusions from the video’s various 2D spatial-temporal representations and the categorization decision is made. An experiment on publicly available datasets with violent video demonstrates the usefulness of the suggested approach. © 2024, CRC Press/Balkema. All rights reserved.

关键词： computer vision

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：