检索结果-内蒙古大学图书馆

11th IEEE International Conference on Advances in Computing and Communications, ICACC 2024

作者： Bennila Thangammal, C. Poorna Saai, M. Muhammad Taufeeq Umar, N. Nithissh, S.S. Murugesh, K. Tharun Kumar, S. R. M. D. Engineering College Electronics and Communication Engineering Kavaraipettai India R. M. D. Engineering College Artificial Intelligence and Machine Learning Engineering Kavaraipettai India

ISBN: (纸本)9798350379136

Traditional practices in agriculture lack the proper guidance in regard to crop production and yields, making the processes inefficient with Poor use of resources. To address the above challenges, we proposed an IoT and machine learning-based system targeting on the improvement of precision farming. The technology incorporated into our system is a microcontroller, numerous soil sensors and a GSM for transmitting the data. The main focus of our study is accurate crop recommendations that depend on which crops are suitable for the farmer and his environment. This is done via, evaluating some of the key factors of the environment in terms of Nitrogen, Phosphorous, and potassium Content in the soil, its Ph Level, the temperature, humidity and TDS. The way it works is that an image or a video of the soil is taken while, at the same time, it monitors the real-time data of the soil parameters using the sensors. Then it sends this data to a GSM module with IoT technology which connects to a model website on the cloud. The information is then processed by enhanced machine learning formulas in order to determine the fertility level of the soils and the type of crops to be grown on the land. The processed data and recommendations are sent back to the device with enabled user interface to see the analyzed results on a display. Here our use of IoT with machine learning enables the system give accurate and recommendable crop data, making the most of the resources and maximizing crop production. It bypasses the shortcomings of conventional ways of agricultural methods offering a scalable and efficient solution for modern agriculture. © 2024 IEEE.

关键词： Smart agriculture

来源：评论

学校读者我要写书评

暂无评论

Agribot: An IoT and Deep learning-Based System Empowering Precision Farming 2

Agribot: An IoT and Deep Learning-Based System Empowering Pr...

引用

2nd International Conference on Emerging Trends in Information Technology and engineering, ic-ETITE 2024

作者： Thangammal, C. Bennila Poorna Saai, M. Muhammad Taufeeq Umar, N. Nithissh, S.S. Murugesh, K. R. M. D. Engineering College Electronics and Communication Engineering Kavaraipettai India R. M. D. Engineering College Artificial Intelligence and Machine Learning Engineering Kavaraipettai India

ISBN: (纸本)9798350328202

Farmers frequently encounter issues such as irregular weather patterns and ineffective resource management, particularly in irrigation practices. Offering them a centralized information platform equipped with vital data for monitoring and managing their fields has the potential to be a game changer. This paper describes an advanced smart agricultural system that combines both cutting-edge software and hardware modules to transform current farming practices. The hardware components, which include data collecting and soil quality assessment sensors, work together with machine learning models to provide accurate weather forecasts and crop recommendations. Our technology offers a high degree of precision in predicting and advising suitable crop choices based on real-time soil conditions by utilizing closely trained models. The user-friendly online interface offers safe authentication mechanisms, complete irrigation status updates, and crop-specific information. The system's distinctive strength comes in its ability to handle soil data, allowing it to provide individualized crop suggestions and exact planting directions. This research not only provides farmers with actionable knowledge but also represents a big step toward more sustainable and efficient farming practices. The study finishes with suggestions for potential future refinement avenues, highlighting the ongoing commitment to enhancing precision farming technologies. © 2024 IEEE.

关键词： Crops

来源：评论

学校读者我要写书评

暂无评论

A Deep learning Approach for Non - invasive Body Mass Index Calculation 1st

A Deep Learning Approach for Non - invasive Body Mass Index ...

引用

1st International Conference on Advances in artificial intelligence and machine learning in Big Data Processing, AAIMB 2023

作者： Nandhan, S. Harish Zean, J. Remoon Mahi, A.R. Meena, R. Mahalakshmi, S. Department of Artificial Intelligence and Machine Learning Rajalakshmi Engineering College Chennai India

ISBN: (纸本)9783031730641

A person’s body mass index (BMI) is a vital indicator of their health. Through extensive research, it was determined that traditional methods of BMI calculation can be time-consuming. We developed a technique that uses deep learning to predict a person’s BMI, age, and gender from facial images. Our system uses Multi-Task Cascaded Convolutional Neural Networks (MTCNN) to detect faces by cropping the face out of an input image and detecting facial landmarks based on the 5-point facial landmark detection algorithm from the input image. The cutting-edge pre-trained models will be finetuned, including VGG-Faces, ResNet (Residual Neural Network), and VGG16 (Visual Geometric Groups with 16 layers) on a public dataset of 1530 prisoners from Polk County Prison. This dataset contains a multifarious range of faces, including different races, ages, and genders. The uploaded CSV file contains the heights, weights, and gender of the training images. After the image is passed into the network, it generates BMI, age, and gender predictions for the input image. This system uses an efficient face recognition mechanism to identify the age, gender, and BMI of a person using a multi-task BMI prediction model. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing Tactile Sensor Technology with Neuromorphic Models and machine learning 6

Enhancing Tactile Sensor Technology with Neuromorphic Models...

引用

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

作者： Lenka, Komali Jyothi, Pulaparthi Lakshmi Asha Brahma Ramesh, Kallakuri N.V.P.S. Lanka, Dasaradha Ramayya Srikanth, M. Rajesh, Jonnapalli Tulasi Dept of IT S.R.K.R.Engineering College India India AP Bhimavaram India Dept of Artificial intelligence and Machine learning Aditya University India Dept of IT SRKR Engineering College Bhimavaram India

ISBN: (纸本)9798331522667

This study presents a novel approach to enhancing touch sensor technology by utilizing machine learning techniques and neuromorphic models. Tactile sensing has struggled to accurately understand complex physical interactions, despite its significance for artificial touch and robotic dexterity. Our approach improves the classification of tactile data by using neuromorphic computing—models inspired by brain processing—to identify changes in the environment, variations in force, and textures. We evaluate our model on benchmark tactile datasets and demonstrate its superior sensory resolution and increased adaptability. For robotics, prosthetics, and human-machine interfaces, the results are very important because they show that neuromorphic tactile sensors improve the accuracy and speed of data classification. This study showcases the potential of neuromorphic models to improve tactile perception, paving the way for more advanced and adaptable sensory systems. © 2025 IEEE.

关键词： Prosthetics

来源：评论

学校读者我要写书评

暂无评论

Blockchain for Secure and Efficient Crowdfunding: An Optimized Particle Swarm Approach 9

Blockchain for Secure and Efficient Crowdfunding: An Optimiz...

引用

9th International Conference on Communication and Electronics Systems, ICCES 2024

作者： Lakshmanan, M. Mala, G.S. Anandha Poorni, R. Ilamurugan, G. Sriramkumar, R. Gnanavel, R. Dayananda Sagar University Department of Artificial Intelligence and Machine Learning Bangalore India Easwari Engineering College Anna Univeristy Department of Computer Science and Engineering Chennai India Sri Venkateswara College of Engineering Sriperumbudur India

ISBN: (纸本)9798350377972

Crowdfunding, a method of raising capital through collective contributions, often faces challenges related to transaction efficiency, security, and transparency. Blockchain addresses these issues by providing a decentralized, transparent, and secure environment for transactions, while smart contracts automate the fund release process based on predefined conditions. PSO, a nature-inspired optimization algorithm, is applied to optimize various crowdfunding parameters such as funding strategies, donor behavior, and campaign success. By combining PSO with blockchain, the proposed model improves both the speed and security of crowdfunding transactions. This research presents an innovative approach to enhancing crowdfunding platforms by integrating Particle Swarm Optimization (PSO) with blockchain technology. Proposed Model achieves a 30% reduction in transaction time and a 40% improvement in security. This is achieved through the use of a Merkle tree for secure data storage and smart contracts to ensure efficient and automated fund management. The integration of PSO further optimizes key parameters, such as fund distribution and reward allocation, leading to a more efficient and transparent platform. The combination of these technologies results in a crowdfunding experience that is not only faster but also more secure and reliable, enabling global, borderless funding while minimizing fraud and enhancing trust among participants. This research highlights the potential of OPSA-enabled blockchain solutions to transform the crowdfunding landscape, offering a more efficient, secure, and transparent funding platform. © 2024 IEEE.

关键词： Decentralized finance

来源：评论

学校读者我要写书评

暂无评论

Development of Punjabi Automatic Speech Recognition Application for Mobile Devices 7

Development of Punjabi Automatic Speech Recognition Applicat...

引用

2023 7th International Conference On Computing, Communication, Control And Automation, ICCUBEA 2023

作者： Mittal, Puneet Sharma, Sukhwinder Manipal University Jaipur Department of Artificial Intelligence & Machine Learning Jaipur India Manipal University Jaipur Department of Data Science & Engineering Jaipur India

ISBN: (纸本)9798350304268

Speech recognition based mobile device applications are gaining popularity due to their ease of use, flexibility as well as ability to provide hands-free access to device features and functions for persons without hands or with disabilities like blindness. The increased accuracy of Automatic Speech Recognition (ASR) systems and support to multiple languages is further motivating the researchers to develop such applications. The development of an application for mobile device helps to validate the applicability of an ASR system in real world environment. An android based speech recognition application for calling and messaging features has been designed and developed in this paper. User can send message or call to any phone number or contact stored in the mobile phone using Punjabi speech. Punjabi based ASR system having pronunciation dictionary, acoustic model and language model is used to implement the underlying speech recognition for Punjabi speakers. Speech user interface has been designed using Android, while AndroidPocketSphinx has been used as speech decoder. The successfully running application has been tested for multiple male and female native Punjabi speakers, followed by thorough performance analysis. The results shown are quite optimistic with a very low combined error of 1.6% for all female speakers and 2.1% for all male speakers. The application gives 98.4% success rate or recognition accuracy for female speakers and 97.9% for male speakers for the underlying Punjabi based ASR system. © 2023 IEEE.

关键词： Acoustic model AndroidPocketSphinx ASR Language Model Pronunciation Dictionary Speech Recognition

来源：评论

学校读者我要写书评

暂无评论

Design of Protograph LDPC-Coded MIMO-VLC Systems with Generalized Spatial Modulation

引用

China Communications 2024年第3期21卷 118-136页

作者： Dai Lin Fang Yi Guan Yongliang Mohsen Guizani School of Information Engineering Guangdong University of TechnologyGuangzhou 51006China The State Key Laboratory of Integrated Services Networks Xidian UniversityXi’an 710126China School of Electrical and Electronic Engineering Nanyang Technological UniversitySingapore Department of Machine Learning Mohamed Bin Zayed University of Artificial Intelligence(MBZUAI)Abu DhabiUnited Arab Emirates

This paper investigates the bit-interleaved coded generalized spatial modulation(BICGSM) with iterative decoding(BICGSM-ID) for multiple-input multiple-output(MIMO) visible light communications(VLC). In the BICGSM-ID scheme, the information bits conveyed by the signal-domain(SiD) symbols and the spatial-domain(SpD) light emitting diode(LED)-index patterns are coded by a protograph low-density parity-check(P-LDPC) code. Specifically, we propose a signal-domain symbol expanding and re-allocating(SSER) method for constructing a type of novel generalized spatial modulation(GSM) constellations, referred to as SSERGSM constellations, so as to boost the performance of the BICGSM-ID MIMO-VLC ***, by applying a modified PEXIT(MPEXIT) algorithm, we further design a family of rate-compatible P-LDPC codes, referred to as enhanced accumulate-repeat-accumulate(EARA) codes,which possess both excellent decoding thresholds and linear-minimum-distance-growth property. Both analysis and simulation results illustrate that the proposed SSERGSM constellations and P-LDPC codes can remarkably improve the convergence and decoding performance of MIMO-VLC systems. Therefore, the proposed P-LDPC-coded SSERGSM-mapped BICGSMID configuration is envisioned as a promising transmission solution to satisfy the high-throughput requirement of MIMO-VLC applications.

关键词： bit-interleaved coded modulation generalized spatial modulation multiple-input multipleoutput protograph LDPC codes visible light communication

来源：评论

学校读者我要写书评

暂无评论

AI-Driven Vegetation Monitoring and Fire Risk Mitigation for Wildfire Prevention and Powerline Safety

AI-Driven Vegetation Monitoring and Fire Risk Mitigation for...

引用

International Symposium on Advanced Computing and Communication (ISACC)

作者： Harini B Gouri MP Manju M Department of Artificial Intelligence and Machine Learning Rajalakshmi Engineering College Chennai India

ISBN: (数字)9798331523893

ISBN: (纸本)9798331523909

Ensuring the safety and reliability of power lines is crucial for preventing forest fires caused by vegetation encroachment. Traditional monitoring methods are labor-intensive, costly, and error-prone, often resulting in delayed identification of potential hazards. ForestGuard, an AI-powered vegetation monitoring and fire risk management system, addresses these challenges by integrating advanced geospatial and machine learning technologies. The system uses high-resolution satellite imagery and YOLOv5 for near-real-time detection and classification of vegetation and potential hazards around power lines. Built with Python and QGIS, ForestGuard automates the creation of Digital Terrain Models (DTM) and Digital Surface Models (DSM) to assess vegetation height and proximity to power lines. Upon identifying hazardous conditions, the system promptly notifies relevant authorities, enabling rapid responses to mitigate risks. By reducing reliance on manual inspections and ensuring timely interventions, ForestGuard minimizes the likelihood of power outages and wildfires. This scalable and efficient solution demonstrates significant potential for enhancing proactive vegetation management and improving the safety and reliability of power line networks.

关键词： YOLO Wildfires Prevention and mitigation Vegetation mapping Forestry Vegetation Satellite images Reliability Monitoring Risk mitigation

来源：评论

学校读者我要写书评

暂无评论

引用

4th IEEE International Conference on Mobile Networks and Wireless Communications, ICMNWC 2024

作者： Mallikarjuna, Shruthi Bennur Raju, Channakrishna Sjce Jss Science and Technological University Department of Computer Science and Engineering Mysuru India Sri Siddhartha Institute of Technology Ssahe Department of Artificial Intelligence and Machine Learning Tumakuru India

ISBN: (纸本)9798350352931

Wireless Sensor Networks (WSN) are designed to monitor sensor nodes systems, with a focus on data processing, collection and transmission. Developments in wireless communication have extended the scope of WSNs to various domains such as underwater communication and Internet of Things (IoT). However, secure clustering and routing remain challenging due to increased vulnerability to attacks in IoT-WSN, which negatively impact communication and data integrity. This research proposes Similarity Preference Weight-Chimp Optimization Algorithm (SPW-ChOA) for secure clustering and routing in WSN-IoT. Trust, node degree, distance between Cluster Head (CH) and Base Station (BS), energy and distance are employed as fitness functions for Secure CH (SCH) selection. The factors considered for routing in SPW-ChOA include energy and distance. The performance of SPW-ChOA is evaluated in terms of residual energy, Packet Delivery Ratio (PDR), throughput and energy consumption, with the number of nodes varied at 500,1000,1500 and 2000. The proposed SPW-ChOA consumes lesser energy at 0.28 which compared to the existing Butterfly Optimization Algorithm (BOA) and Antlion Optimization Algorithm (AOA). © 2024 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

CRYPTOPASS - A Unified Password Manager

CRYPTOPASS - A Unified Password Manager

引用

2024 IEEE International Conference on Electronic Systems and Intelligent Computing, ICESIC 2024

作者： Samuel, Prithi Vijay, K. Dheephiga, A.M. Maarcus Reniero, L. SRM Institute of Science and Technology Kattankulathur Campus Department of Computational Intelligence India Rajalakshmi Engineering College Department of Artificial Intelligence and Machine Learning Chennai India Worldline Global Services Chennai India UST Chennai India

ISBN: (纸本)9798331522988

In the present scenario, many people are unaware of the security risks when they store their passwords or keys directly as a text file without encryption. This leaves your password exposed to hackers who can access them easily. This software aims to create only one strong password to ease the pressure of remembering passwords is very efficient for us as users. A dedicated password manager will store your passwords in an encrypted form, help you generate secure random passwords, offer a more powerful interface, and allow you to easily access your passwords across all the different computers, smartphones, and tablets you use. Keeping the above scenario in mind, this application is designed to enhance the security of user's data. This application is based on password vaults or password managers which are programs that keep your passwords in a secure location. When you use this software, the passwords are encrypted, and you use a single master password to access them. The basic idea is to create only one password to help to remember it as well as for efficient access. This increases the security of our accounts as well as the regulation of our passwords in a secure manner. The key components of reusability and flexibility are implemented in this project which makes the project even more user friendly and makes the user more comfortable towards using Cryptopass. © 2024 IEEE.

关键词： Cross-Platform Compatibility Cryptopass Master Password Password Encryption Password Vault Secure Access User-Friendly Interface

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：