检索结果-内蒙古大学图书馆

2nd IEEE Mysore Sub Section International Conference, MysuruCon 2022

作者： Naik, Archana Koushik, K.A. Poorna Vikas, A.S. Reddy, Saicharan Manjunatha, N.M. Sooda, Kavitha Nitte Meenakshi Institute of Technology Department of Computer Science & Engineering Bagalore India B.M.S. College of Engineering Department of Computer Science & Engineering Bangalore India

ISBN: (数字)9781665497909

ISBN: (纸本)9781665497909

Poultry is the major economic food supplier industry in parallel with the agricultural sector. With good farm management practices, healthy poultry products are produced with the goal of satisfying the consumers as well as business profit. For producing healthy poultry chickens, environmental factors play a major role. Better chicken growth and yield can be achieved by standardizing environmental factors such as light, temperature, and humidity. To monitor the environmental factors, the Internet of Things is utilized. A prototype has been developed using sensors, which are installed inside the poultry to monitor the factors. Based on the sensor data, the managing and controlling processes are automated. The web page provides a real time reading of the sensor values, which are refreshed every 5 sec. Using the control options provided on the web page such as turn on light, open window, remote management of the system is made possible. The developed protype is tested on the farm. Remote control of the environment is achieved. © 2022 IEEE.

关键词： Websites

来源：评论

学校读者我要写书评

暂无评论

Advancing Image Forgery Detection: A CNN-Based Approach

Advancing Image Forgery Detection: A CNN-Based Approach

引用

International Conference on Computation System and Information technology for Sustainable Solutions (CSITSS)

作者： Nalini N Sai Rakshitha Nithyashree H V Rakshitha S L Motamarri Sai Shravan K Sai Uttej Dept. of Computer Science and Engineering Nitte Meenakshi Institute of Technology Bengaluru Karnataka India

ISBN: (数字)9798331505462

ISBN: (纸本)9798331505479

In the digital age, image forgery is a significant concern due to advanced editing tools. This study addresses the need for reliable forgery detection, focusing on copy-move, splicing, and retouching techniques. Using Convolutional Neural Networks (CNNs) known for learning hierarchical image features, the research developed a robust detection system. The CNN model, trained on a diverse dataset which has over 10,000+ images and it is split into test and train data for better classification results, detected subtle inconsistencies indicative of manipulation, achieving a peak accuracy of 94% over 50 training epochs. Test cases showed the system effectively detected forged images and identified forgery types, though it had shortcomings with invalid inputs. The CNN architecture employed convolutional and max-pooling layers with specific hyperparameters to enhance feature extraction. This paper offers a valuable tool for digital forensics experts, law enforcement, and journalists to ensure the authenticity of visual content.

关键词： Training Visualization Accuracy Law enforcement Splicing Digital forensics Feature extraction Forgery Real-time systems Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Humanoid Robot for Disaster Detection using Machine Learning 2

Humanoid Robot for Disaster Detection using Machine Learning

引用

2nd IEEE Mysore Sub Section International Conference, MysuruCon 2022

作者： Vellingiri, J. Trisheela, S. Vellore Institute of Technology School of Information Technology and Engineering Vellore India Nitte Meenakshi Institue of Technology Department of Computer Science and Engineering Bengaluru Yelahanka India

ISBN: (数字)9781665497909

ISBN: (纸本)9781665497909

The most recent advancements in science and technology have led to the creation and deployment of robots in a variety of applications encompassing all areas of human existence. This has been made possible as a result of recent scientific and technological advances. Because of this, it will be necessary for people and robots to collaborate on a wider scale. Evidence from the past reveals that robots are more often seen as friends rather than machines or tools. Nevertheless, Human-Robot Interaction (HRI) is not the same as the previously established Human-computer-Interaction (HCI), which offers insights into better comprehending and enhancing interactions with computer-based technology. The Human-Robot Interaction (HRI) study field is unique from the Human- computer Interaction (HCI) research field because HRI introduces autonomy, physical closeness, and the capacity to make choices for a robotic system. When taking into account the vast number of interactions that take place between humans and robots, there is an urgent need to standardise standards in order to guarantee that robotic technology is used in a responsible and principled manner. The work presented here exhibits an HRI framework and metric taxonomy for the robot design that are appropriate for a variety of applications. These were generated after an in-depth analysis of the relevant literature. For hobbyists, developers, and academics interested in constructing completely autonomous, consumer-focused social robots with perception and reasoning skills, the framework provides an end-to-end product design overview that may further be employed to reach technological readiness for an end-product. newline As a result of investments made in the field of robotics, a wider variety of robots are becoming available on the consumer market, which will lead to an exponential rise in the number of contacts between people and robots. © 2022 IEEE.

关键词： Infrared detectors

来源：评论

学校读者我要写书评

暂无评论

LULC Classification Based on Multi-Scale Convolutional Auto Encoder with Artificial Bee Colony 2

LULC Classification Based on Multi-Scale Convolutional Auto ...

引用

2nd IEEE International Conference on Data science and Network Security, ICDSNS 2024

作者： Kumar, Bura Vijay Husain, Saif O. Kulkarni, Megha Das, Abhijeet Gurumoorthy, Sasikumar School of Computer Science and Artificial Intelligence Sr University Warangal India College of Technical Engineering The Islamic University Department of Computers Techniques Engineering Najaf Iraq Nitte Meenakshi Institute of Technology Department of Civil Engineering Bengaluru India Department of Civil Engineering Odisha Bhubaneswar India School of Engineering and Technology Dhanalakshmi Srinivasan University Computer Science and Engineering Tiruchirappalli India

ISBN: (纸本)9798350373110

Monitoring Land Use and Land Cover (LULC) is beneficial to several applications like non- rural development, planning, agricultural, forest departments etc. which enables for global transformation. In recent years, satellite images have become rapid growth in land surveys and environmental planning's. In this research, for LULC classification introduced a framework called Multi-Scale Convolutional Auto Encoder with Artificial Bee Colony (MSCAE). This research is evaluated by images collected from Eurosat dataset. Once dataset is collected preprocessing techniques are employed such as normalization to improve the quality of images. After preprocessing, haralick texture is applied to extract Spatial, texture from preprocessed images. In the next phase, Artificial Bee Colony is implemented to consider optimal features to improve the performance. ABC uses bit vectors to select optimal features and fed to classifier based on fitness function which automatically improves the accuracy. These optimal features are provided to MSCAE classifier to classify LULC classes. The MSCAE incorporates convolutional kernel to understand and classify images effectively. The proposed method outperformed with accuracy of 98.2 % when compared to state-of-art methods such as Densnet-121, CNN and 1D CNN. © 2024 IEEE.

关键词： Environmental management

来源：评论

学校读者我要写书评

暂无评论

Virtual Machine Placement Using Adam White Shark Optimization Algorithm in Cloud Computing

引用

SN computer science 2024年第1期5卷 21页

作者： Supreeth, S. Bhargavi, S. Margam, Rakesh Annaiah, H. Nandalike, Rajesh School of Computer Science and Engineering REVA University Bengaluru India Department of Electronics and Communication Engineering S J C Institute of Technology Chikkaballapur India Healthcare IT Leader SecureKloud Technologies Inc Chicago United States Government Engineering College Karnataka Hassan India Nitte Meenakshi Institute of Technology Bengaluru India

The increasing demand for virtual machine (VM) request is caused due to the increasing number of users. Hence, the VM placement is considered as a critical task for attaining effective resource handling in cloud data centers (DCs). In general, the VM placement procedure deploys the set of VMs onto the set of physical machines (PMs) depending on specific criteria. In this research, the optimal solution for VM placement is computed by hybrid optimization with fitness parameters. Here, the fitness function is computed by combining several objectives including load, power, placement time and migration cost. In addition, VM placement is based on several system factors such as central processing unit (CPU), memory, and bandwidth, million instructions per second (MIPS) and processing elements. Besides, the hybrid optimization technique devised for performing the VM migration in this research is Adam white shark optimization-based VM placement (AWSO_VMP), which is formulated by modifying the white shark optimization (WSO) with the Adam optimizer. Thus, the performance of AWSO_VMP is assessed using load, power consumption and cost of migration, and the attained values of corresponding metrics are 0.133, 0.225 W and 0.116. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Adam optimizer Physical machines Virtual machine Virtual machine placement White shark optimization

来源：评论

学校读者我要写书评

暂无评论

Hand Sign Language Detection Using Deep Learning and computer Vision

Hand Sign Language Detection Using Deep Learning and Compute...

引用

Ambient Intelligence, Knowledge Informatics and Industrial Electronics (AIKIIE), International Conference on

作者： Sujata Joshi Bhaskar Sharma Dharmender Divyansh Tripathi Akshat Shah Computer Science and Engineering Nitte Meenakshi Institute of Technology Bengaluru India

This work presents an innovative system/app designed to assist individuals with visual or hearing impairments in communicating with the outside world using American Sign Language (ASL). By leveraging machine learning and image processing techniques, the proposed system captures and processes hand gestures, enabling the optimal transliteration of sign language alphabets and numbers into machine-readable English text. The system employs deep learning or random forest algorithms to classify the gestures, followed by mapping them to specific alphabets or numbers. The resulting text is presented audibly, bridging the communication gap and facilitating interactions between ASL users and those unfamiliar with sign language. Through the integration of technology, this work aims to enhance inclusivity and accessibility for individuals having disabilities, fostering greater engagement and interaction with the wider world.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improving Accuracy in Network Intrusion Detection via Machine Learning Algorithms: An In-Depth Examination

Improving Accuracy in Network Intrusion Detection via Machin...

引用

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

作者： Suriya Prakash, J. Trishlaa, S. Soniya, R. Lakshmanan, V. Kiran, S. Department of Cse Ramnagara India Rajarajeshwari College of Engineering Department of Artificial Intelligence and Machine Learning Bengaluru India Sri Eshwar College of Engineering Department of Computer Science and Engineering Coimbatore India Nitte Meenakshi Institute of Technology Department of Mathematics Bengaluru India

ISBN: (纸本)9798350375442

Intrusion detection is essential for securing computer networks by monitoring and analyzing activity to detect and respond to unauthorized access and malicious behavior. By examining network traffic and system logs, intrusion detection systems (IDS) help protect data integrity and availability, enabling swift responses to potential security incidents. In an ever-evolving cyber threat landscape, IDS plays a critical role in maintaining network security. This research investigates the performance of various machine learning algorithms for classification tasks using a dataset from Kyoto collected on December 31st, 2015. The algorithms explored include Naive Bayes, K-Nearest Neighbors (KNN), Extreme Gradient Boosting (XGBoost), AdaBoost, and CatBoost. Training and testing the model with different data splits (80/20, 70/30, 60/40) revealed that AdaBoost, LGBM, XGBoost, Decision Tree, Gradient Boosting, and Random Forest consistently delivered the highest accuracy. The study concludes that selecting the appropriate algorithms and data splits is crucial for enhancing IDS effectiveness, providing valuable insights for future research. Explore the code behind this study at https://***/Trishlaa07/Kyoto_2015_Dec_day31 © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Enhancing Decentralized Finance for Scalability, Interoperability, and User Experience

Enhancing Decentralized Finance for Scalability, Interoperab...

引用

International Conference on Computation System and Information technology for Sustainable Solutions (CSITSS)

作者： Nalini N Vishak Rao Karthik Rao Shobha P Dept. of Computer Science and Engineering Nitte Meenakshi Institute of Technology Bengaluru Karnataka India

ISBN: (数字)9798331505462

ISBN: (纸本)9798331505479

This research explores Decentralized Finance (DeFi) through the lens of enhanced applications, introducing the concept of Decentralized Finance Enhanced (DeFine). It examines the transformative potential of DeFi, analyzing its evolution and the innovative solutions driving its progress. The objective is to investigate how DeFine addresses scalability, interoperability, security, and user experience challenges in the DeFi ecosystem. Through case studies and analysis, this proposed work provides insights into the implications, opportunities, and risks associated with the adoption and maturation of DeFi enhancements.

关键词： Scalability Ecosystems Finance Decentralized applications User experience Security Information technology Interoperability Contracts Lenses

来源：评论

学校读者我要写书评

暂无评论

Voice Controlled Smart Home System

Voice Controlled Smart Home System

引用

Network, Multimedia and Information technology (NMITCON) International Conference on

作者： K Manjula V Dhananjaya Computer Science & Engineering Nitte Meenakshi Institute of Technology Bangalore India Computer Science & Engineering Impact college of Engineering Bangalore India

ISBN: (数字)9798350372892

ISBN: (纸本)9798350372908

The Internet of Things (IoT) is a significant technological advancement that uses the internet to enable seamless communication between various devices, allowing people and objects to connect anytime and from anywhere. In this research, we present an intelligent smart automation model that can remotely operate household appliances and water the garden plants from anywhere in the world. “Home automation” is a quickly emerging technology that minimizes the work that humans must perform. Certain home automation systems are offered to people seeking luxurious, advanced home automation systems. This method is safe because it works best for the elderly and disabled people. However, certain people could find it more challenging to use certain systems because of their special demands. The system’s primary features are voice recognition and intelligent interaction. Our main objective is to develop an advanced home automation system that has combined Alexa with the ESP 8266 module to improve security, reduce power consumption and minimize user effort. The model includes two essential sensors, a soil moisture sensor, a temperature and humidity sensor. All hardware components in this model are cost-effective, readily available, and easily replaceable.

关键词： Temperature sensors Smart agriculture Home appliances Virtual assistants Soil moisture Smart homes Speech recognition Internet of Things Usability Intelligent sensors

来源：评论

学校读者我要写书评

暂无评论

Cyber Security in Healthcare with Artificial Intelligence 2

Cyber Security in Healthcare with Artificial Intelligence

引用

2nd IEEE Mysore Sub Section International Conference, MysuruCon 2022

作者： Mahendrakhan, K. Nagarathna, P. Hindusthan Institute of Technology Department of ECE Coimbatore India Department of Computer Science and Engineering Nitte Meenakshi Institute of Technology Bengaluru India

ISBN: (数字)9781665497909

ISBN: (纸本)9781665497909

The intelligent Internet of Things (IoT), -which provides an endless number of networking options for the examination of medical data, is improving the connection between technology and healthcare society. Deep networks have seen productive alterations in recent years, and the usage of health wearables has become more prevalent The Internet of Things, which was made possible by deep neural networks, resulted in innovative social breakthroughs in medicine and opened up new avenues for the investigation of healthcare data. Despite the progress that has been made, there are still a few issues that need to be resolved in terms of the quality of the service. The Grey Filter Bayesian Convolution Neural Network, or GFB- CNN, is a method of smart healthcare that is powered by Deep Neural Networks and takes the use of real-time data This technique is presented here as part of this study. In this paper, we proposed an all-encompassing Al-driven Internet of Things (IoT) eHealth architecture that makes use of an ICNN in order to increase accuracy and efficiency across the essential quality of service parameters. An extensive Mobile HEALTH (MHEALTH) dataset is analyzed in order to determine how effective the approach is in its intended use. This illustrative example investigates and covers all of the pertinent aspects of the recommended technique, from design concepts to matching accuracy, overhead costs, and the amount of time associated with state-of-the-art procedures. The ICNN strategy was evaluated in a variety of simulated environments alongside other approaches that are considered to be state of the art We show that our method effectively analyses health information investigations for cardiac indications by being able to differentiate between healthy and abnormal heart signals in an efficient manner at a cheap cost and in a short amount of time, both of which are necessary for sensing and data collection. © 2022 IEEE.

关键词： 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：