检索结果-内蒙古大学图书馆

Data science, Agents & Artificial Intelligence (ICDsAAI), International Conference on

作者： R. Murugadoss Department of Artificial Intelligence and Data Science V.S.B. College of Engineering Technical Campus Coimbatore Tamil Nadu India

ISBN: (数字)9798331537555

ISBN: (纸本)9798331537562

Human-animal conflicts pose a significant challenge in forest zones and agricultural fields, leading to resource losses and threats to endangered wildlife. These conflicts have escalated in recent years, necessitating innovative solutions for continuous monitoring and intervention. This study presents a novel approach for mitigating such conflicts by leveraging image processing and Artificial Intelligence (AI). Motion detection techniques are employed to identify activity, and content-based image classification algorithms analyze the captured visuals. The proposed method integrates advanced feature extractors, data augmentation, and AI to develop a robust detection network. Additionally, the system enhances safety analysis and certification for high-speed trains by identifying objects and animals in real time. Using the COCO dataset for training and validation, the study demonstrates the potential of AI to streamline conventional safety measures and ensure the coexistence of humans and animals in ecologically sensitive areas.

关键词： Animals Wildlife Forestry Feature extraction Data augmentation Real-time systems safety Object recognition Artificial intelligence Monitoring

来源：评论

学校读者我要写书评

暂无评论

PID Control and Estimation of the Attitude Model Applied to Geostationary satellites 7th

PID Control and Estimation of the Attitude Model Applied to ...

引用

7th International Conference on Microelectronics, Electromagnetics and Telecommunication, ICMEET 2022

作者： Meena, Radhey shyam Talukdar, Rongeet Kannadasan, b. Nageswara Rao, G. shukla, Amogh Anand, Rohit Gupta, Ankur Department of Industrial and Management Engineering Indian Institute of Technology Kanpur India Alma Mater Studiorum—Università di Bologna Bologna Italy Department of Civil Engineering B. S. Abdur Rahman Crescent Institute of Science and Technology Vandalur Tamil Nadu Chennai India EEE Department Lakireddy Bali Reddy College of Engineering Mylavaram India JNTUK Andhra Pradesh Kakinada India School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Vellore India DSEU G. B. Pant Okhla-1 Campus New Delhi India Department of Computer Science and Engineering Vaish College of Engineering Haryana Rohtak India

ISBN: (纸本)9789811988646

The estimation of systems is based on the analysis of data obtained after experimenting about the behavior of a real process in response to an external disturbance to find a scheme that allows the mathematical stages to be modeled. This is the importance of its in-depth study, since if it is carried out correctly, re-directing resources to other fields is one of the many benefits of its applications. This research work seeks to highlight the importance of correcting the displacements that satellites in orbit may experience, due to the influence of various agents, both of their own functioning and those generated by the environment in which they operate. That is why, the technique of systems estimation should be presented as a very useful option because of the analysis tools of the MATLAb program. Putting-in orbit of a team of these characteristics implies investment of strong amounts of time, money, and technology;likewise maintaining its initial orientation leads to the analysis of new parameters without mentioning the great problem generated in the orbit of the Earth, if for reasons other than those considered "normal," this orientation varied and the implemented processes did not fulfill their function. The necessary driver for our project is a PID control since a control law can compensate with the integral and derivative actions. The necessary tool for the development of our controller is from MATLAb. With this tool, we can reach our goal, since it shows us the trajectory of the roots as well as the necessary graphs showing control characteristics such as the maximum overshoot, stabilization time, and percentage of system error, among others. © 2023, The Author(s), under exclusive license to springer Nature singapore Pte Ltd.

关键词： MATLAb

来源：评论

学校读者我要写书评

暂无评论

Effective segmentation and Classification of brain Tumour MRI Images Using YOLOv8 Technique

Effective Segmentation and Classification of Brain Tumour MR...

引用

Innovation and Novelty in engineering and Technology (INNOvA), International Conference on

作者： Aniket Prabhu Taradale suvarna Laxmikant Kattimani Department of Computer Science and Engineering B.L.D.E.A's V.P. Dr. P. G. Halakatti College of Engineering and Technology Vijayapura Karnataka India

ISBN: (数字)9798331505134

ISBN: (纸本)9798331505141

brain tumour classification is crucial for prompt diagnosis and life-saving treatment. A novel approach employing You Only Look Once (YOLO) technology for brain tumour segmentation and classification We used pre-existing data for tumour diagnosis and categorised in four main types: meningioma, glioma, pituitary, and no tumours. In diagnosis, segmentation is necessary to identify regions containing tumours seen in medical images such as MRI scans. Our method offers use of YOLO's real-time product search capabilities and makes them relevant for clinical use. The method achieves 95% Fl-score, 96.20% precision, 93.6% recall, and 97.2% mAP50 in identifying and segmenting tumour regions while using a large dataset of MRI scans as training. This method is superior to traditional segmentation methods as it provides a fast and accurate target detection method.

关键词： YOLO Training Image segmentation Technological innovation Accuracy Magnetic resonance imaging Resonance Real-time systems Medical diagnostic imaging Tumors

来源：评论

学校读者我要写书评

暂无评论

Experimental Analysis of Malware Detection and Classification system using Intelligent Deep Learning Methodology 4

Experimental Analysis of Malware Detection and Classificatio...

引用

4th IEEE International Conference on smart Technologies in Computing, Electrical and Electronics, ICsTCEE 2023

作者： Indumathi, K. Krishnaprasanna, R. Chamundeeswari, G. Preetha, M. Tamilvani, K. senthilkumar, b. Rajalakshmi Engineering College Department Of It Tamil Nadu Chennai India Sathyabama Institute Of Science And Technology Department Of Ece Tamil Nadu Chennai India Saveetha Engineering College Department Of Ece Tamil Nadu Chennai India Prince Shri Venkateshwara Padmavathy Engineering College Department Of Cse Tamil Nadu Chennai India Simats Saveetha School Of Engineering Department Of Biosciences Tamil Nadu Chennai India V.S.B. Engineering College Department Of Eee Tamil Nadu Karur India

ISBN: (纸本)9798350384628

computer system security relies heavily on the ability to identify and eliminate malware. signature-based approaches are widely used, although they are not able to effectively identify zero-day assaults or polymorphic infections. This is why there is a demand for detection methods based on deep learning and categorization. computers, smartphones, and apps are all fair game for malicious software. Malware is software that has to be watched out for since it might be a hazard for both computer users and internet-based systems. Malware was developed with the intention of stealing sensitive data from a user's computer or taking remote control of a user's device. Malware is software designed to disrupt or even destroy data on a user's computer. Malicious software can enter a computer in a number of ways, one of which occurs over a network that already has the virus installed. This project will investigate and deploy high-precision classification models using deep learning technologies from the discipline of computational intelligence to enhance the efficiency and accuracy of malware detection. Learning based Classification scheme for Improved Malware Detection (LCsIMD) is a unique technique described in this work and utilized as the primary training model. The suggested LCsIMD framework is trained with malware visualization tools. Models with higher classification accuracy can be found by transforming malware features into images and then modifying their characteristics and input procedures;similarly, prototypes with proposed model can benefit from the use of suitable characteristics and preprocessing methods. The final step is to generate characteristics for network-generated instances, which improves the precision of small-scale training. Every one of us desire to utilize malware that impacts various devices as a teaching example, as described above. The output efficiency of the suggested technique is cross-validated with the classic Neural Network (NN) model to assess

关键词： Malware

来源：评论

学校读者我要写书评

暂无评论

Robust Gray-scale Image Watermarkingusing symlet Wavelet Decomposition using Hybrid Approach 2

Robust Gray-Scale Image Watermarkingusing Symlet Wavelet Dec...

引用

2nd IEEE International Conference on Futuristic Technologies, INCOFT 2023

作者： savakar, Dayanand biradar, Pandurang Ghuli, Anand shirur, shreya Rani Channamma University Department of Computer Science Karnataka Belagavi India BLDEA's V.P.Dr.P.G.Halakatti College of Engineering & Technology Department of M.C.A Karnataka Vijayapur India

ISBN: (纸本)9798350308846

Amongst digital requirements, gray-scale image watermarking-capacity is the crucial issue that has to be effectively handled. A method of utilizing a blind watermarking scheme to insert a gray-scale image into another gray-scale image of a different size is proposed in order to mark the same. This method achieves a logically good perceptual analogy by measuring the appropriate (PsNR) and (ssIM) index. To extract LL bands, the technique uses sym 4 discrete wavelet transformation at a single level (DWT), where most of the image's features are kept. A trustworthy rectangular matrix of computationally viable areas of the updated image is then obtained using a singular value decomposition (svD), first utilized to obtain a set of elements sufficient to describe the full image. The technique is resistant to attacks from motion blur, JPEG compression, pepper and salt, Gaussian, speckle, median, and Gaussian lowpass filters, as well as attacks from sharpening and histogram equalization. An increasingly popular strategy for securing copyright protection and identifying data owners is watermarking. The representation of the image determines the watermark embedding techniques, and each domain has its own set of advantages and disadvantages. © 2023 IEEE.

关键词： DWT gray-scale image nonblind PsNR ssIM svD (keywords)

来源：评论

学校读者我要写书评

暂无评论

A Node MCU Enabled Comprehensive Remote Healthcare Evaluation system for Elder People Care and support

A Node MCU Enabled Comprehensive Remote Healthcare Evaluatio...

引用

2023 International Conference on Innovative Computing, Intelligent Communication and smart Electrical systems, ICsEs 2023

作者： sonia, R. Manikandan, s.K. Chinnammal, v. venkatanaresh, M. Harirajkumar, J. B S Abdur Rahman Crescent Institute of Science and Technology Department of Computer Applications Chennai Vandalur India Velalar College of Engineering and Technology Department of Biomedical Engineering Erode638012 India Rajalakshmi Institute of Technology Department of ECE Chennai India Mohan Babu University School of Engineering Department of ECE Erstwhile Sree Vidyanikethan Engineering College Andhra Pradesh Tirupati517102 India Sona College of Technology Department of Electronics and Instrumentation Engineering Salem India

ISBN: (纸本)9798350319200

The Internet of Things (IoT) has an opportunity to greatly improve our quality of life by providing immediate data that is acquired from an intelligent network of linked devices and then transferred via the internet. In this piece, we have discussed the Remote Medical Diagnosis system and the several life-threatening situations in which it possesses the potential to be a life-saving tool. sometimes people get sick in areas where there are no hospitals or other medical facilities and they don't make it when they don't get the treatment they need because they can't obtain it. sometimes they don't make it. This problem is made even more difficult in the rural areas of emerging countries. As part of the presentation, the temperature and heart rate of a person are both read and shown online. Through the use of a web browser, you will have immediate access to all of your medical records. An integrated TCP/IP protocol stack is required in order to send and receive sensor information, such as a patient's heart beat or electrocardiogram (ECG). Using several metrics and Electrocardiogram (ECG) readings, the NodeMCU EsP8266 WiFi module sends patient data to the remote monitoring site. This information may be accessed in real time. The patient's information and settings are stored on a distant Internet of Things server. In this instance, patient data is monitored using a smartphone that is linked to the cloud by a NodeMCU EsP8266. The NodeMCU EsP8266 comes equipped with its own built-in WiFi connectivity. Every user of the system, from doctors and nurses to patients themselves, has easy and rapid access to the system's database, where they may evaluate the findings. The findings of the analysis may be accessed by the patient or the doctor on an Internet of Things website or an Android application, respectively. © 2023 IEEE.

关键词： Android Application Elder People Care EsP8266 Health support Internet of Things IoT NodeMCU Remote Healthcare Remote server

来源：评论

学校读者我要写书评

暂无评论

Adaptive Federated Learning for Efficient Network Traffic Management in Edge Computing 4

Adaptive Federated Learning for Efficient Network Traffic Ma...

引用

4th International Conference on Ubiquitous Computing and Intelligent Information systems, ICUIs 2024

作者： babu, Kuricheti suresh venkatasubramanian, s. Kishore, s. sree, K. Kavya Ramya susanna, Ch.Lavanya Rao, Goda srinivasa Lakkshmanan, Ajanthaa Pace Institute of Technology and Sciences Department of Computer Science and Engineering AndhraPradesh Valluru India Saranathan college of engineering Department of Computer Science and Business Systems Trichy India B V Raju Institute Of Technology Department of Csbs Narsapur Telangana Medak502313 India Aditya University Department of Ai&ml Surampalem India Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering Andhra Pradesh Vaddeswaram India Kl University Department of Cse Vaddeswaram Andhra Pradesh Guntur India School of Computing Srm Institute of Science and Technology Department of Computing Technologies Kattankulathur Campus Kattankulathur603 203 India

ISBN: (纸本)9798331529635

With the increasing prevalence of edge computing environment, there is a need to establish effective network traffic management that are able to manage vast data while also protecting the privacy of users. The proposed method enhances efficiency of bandwidth, reduce the network latency and manages computational demands without managing data privacy. This is achieved by utilizing the design of edge devices. The adaptable nature of the method enables it to react in real time to different traffic situations. It optimizes the distribution of resources and improves the overall performance of the network. Additionally, it can reduce the possibility of centralized data exposure, providing robust privacy preservation through the allowance of local model training on edge devices. Finally, this method is superior. The employment of federated learning to network traffic management provide efficiency to optimize the traffic in edge computing which is both scalable and safe. This makes it suitable for a wide variety of applications that are utilized in next generation networks © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

smart Production and Manufacturing system Using Digital Twin Technology and Machine Learning

引用

sN computer science 2023年第5期4卷 1-10页

作者： Yadav, Ranjeet Roopa, Y. Mohana Lavanya, M. Ramesh, J.v.N. Chitra, N. Thulasi babu, Gadde Raghu Electronics and Communication Engineering Government Polytechnic Daman UT Administration of Dadra and Nagar Haveli and Daman and Diu Daman and Diu 396210 India Department of CSE Institute of Aeronautical Engineering Telangana Hyderabad India Department of CSE Sri Venkateswara College of Engineering & Technology (Autonomous) R.V.S. Nagar Andhra Pradesh Chittoor 517127 India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Guntur Dist. AP Vaddeswaram India Computer Science and Information Technology MLR Institute of Technology Hyderabad India Department of Mechanical Engineering VNR Vignana Jyothi Institute of Engineering and Technology Nizampet (S.O) Telangana Hyderabad 500090 India

Adoption of digital twin (DT) in smart factories, which simulates an actual system that is manufacturing conditions and updates them in real-time, increased the output and decreased the costs and energy use which were some ways that this manifested. Fast-changing consumer demands have caused a sharp increase in factory transition in addition to producing fewer life cycles of a product. such scenarios cannot be handled by conventional simulation and modeling techniques;we suggest a general framework for automating the creation of simulation models that are data-driven as the foundation for smart factory DTs. Our proposed framework stands out thanks to its data-driven methodology, which takes advantage of recent advances in machine learning and techniques for process mining, constant model validation, and updating. The framework's objective is to completely define and reduce the requirement for specialist knowledge to get the appropriate simulation models. A case study is used to demonstrate our framework. © 2023, The Author(s), under exclusive licence to springer Nature singapore Pte Ltd.

关键词： Data-driven Digital twin Energy consumption smart factories

来源：评论

学校读者我要写书评

暂无评论

American sign Language Recognition system for Numerical and Alphabets

American Sign Language Recognition System for Numerical and ...

引用

Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication engineering (RMKMATE), International Conference on

作者： D sathyanarayanan T. srinivasa Reddy A. sathish P. Geetha J.R. Arunkumar s. Prem Kumar Deepak Department of Computer Science and Engineering B V Raju Institute of Technology Narsapur Telangana India Department of Computer Science and Engineering Potti Sriramulu Chalivudi Mallikarjuna Rao College of Engineering and Technology Vijayawada India Department of Computer Science and Engineering Roever Engineering College Perambalur Department of Artificial Intelligence and Data Science K.Ramakrishnan College of Engineering SamayapuramTrichy Department of Computer Science and Engineering Modern Institute of Technology and Research Centre Alwar Rajasthan Department of Computer Science and Engineering B V Raju Institute of Technology Narsapur Telangana State

sign language is a helpful visual technique that can be utilized by individuals who have difficulty communicating verbally. This language is used frequently by people as well. However, the vast majority of individuals don't understand sign language very well, and as a result, they frequently struggle when attempting to communicate with someone who is fluent in it. The community of people who have trouble speaking or hearing will benefit from an initiative called the sign Language Recognition system. It is extremely challenging for deaf mutes to communicate, which is why we require a linguistic framework to understand what it is that they are attempting to express. In light of this, we present in this research an American sign Language (AsL) handwriting translator that is built on convolutional neural networks. Instructing computers to recognize specific characters is one way to accomplish this goal. The support vector Machine (svM) and the Convolutional Neural Network are two types of artificial neural networks that are being utilized in our project we have suggest the identification of American sign Language. In addition, the Decision Tree and voting Classifier are applied to the dataset in order to do an analysis. We have demonstrated the design and execution of an American sign Language (AsL) translator that also incorporates fingerspelling as a direct consequence of this.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Network Traffic Prediction using Deep Learning Models: Reducing Latency in High-Demand scenarios

Network Traffic Prediction using Deep Learning Models: Reduc...

引用

2025 International Conference on Computing for sustainability and Intelligent Future, COMP-sIF 2025

作者： sagar, b.J. Job Karuna Divya, M.v. Kale, Namita Anand, Neetu Gaurav, Kumar shashidhara, shrividya Joginpally B.R Engineering College Department of Cse Telangana Hyderabad India East West Institute of Technology Department of Computer Science Bangalore India MET'S Institute Of Engineering Department of Information Technology Nashik India Maharaja Surajmal Institute Department of Computer Applications Delhi India Bms Institute of Technology and Management Department of Cse Bangalore India

ISBN: (纸本)9798331538538

The availability of the internet and enhanced applications, more specifically, the utilization of more devices in networks, and improved computational applications has created complexity in the control of network traffic. Network traffic forecasting is an essential component in low-latency networks, as well as in real-time applications that deserve excellent service quality and efficient resource allocation. This study therefore focuses on identifying whether deep learning models can further improve the accuracy in forecasting traffic flows in a network. Therefore, with the help of LsTM networks and Convolutional Neural Networks, the work will build temporal dependencies and spatial correlations of network traffic data. There are major and minor adaptations to some classic methodologies that conform the proposed framework;moreover, it is applied to two real datasets to highlight the capacity of the model in anticipating traffic congestion with a higher level of accuracy than the traditional methodologies. Evaluation of models in dynamic network conditions is done through common parameters such as prediction accuracy, lowered latency, and scalability. saved models show that deep learning-based solutions reduce latency at high loads much more effectively, which will help network administrators in finding efficient solutions. This study demonstrate how deep learning can aid in the prediction of traffics, and the manner in which it is changing the efficiency and effectiveness of modern-day network systems. It makes the foundation for improved understanding of traffic patterns in order to apply it to optimize future generation of communication networks. © 2025 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：