检索结果-内蒙古大学图书馆

1st International Conference on Advanced Computing and Emerging Technologies, ACET 2024

作者： Dattangire, Rahul Vaidya, Ruchika Biradar, Divya Joon, Ashish Publicis Sapient Data Engineering HoustonTX77002 United States Department of Artificial Intelligence and Machine Learning Maharashtra Wardha442001 India University of Texas at Arlington Computer Science ArlingtonTX76019 United States Andhus Technologies Inc Software Developer PensacolaFL United States

ISBN: (纸本)9798350367720

Beyond being merely trendy terms in technology, machine learning (ML) and artificial intelligence (AI) have directly influenced every industry. This article thus demystifies the true meaning of these technologies by sifting through the sultry descriptions. Here, we explore how AI and ML enhance efficiency, decision-making, and problem-solving in various sectors including health, Agriculture, finance, and production as we discover real-world applications. Continuing with the discussion of implementation challenges, the aspects of bias, ethical pitfalls, and report cards are examined. In addition, the article also covered how the integration of AI as well as ML remains a way of improving processes, creating better user experiences, and spurring innovation. This paper, which is also based on case studies, discusses the relationship between social welfare and AI and the importance of AI's development and use being done responsibly. Considering all the discussed aspects, this volume provides a rather nuanced perspective on AI and ML, unmasking the myths around these concepts to reveal the fact that they have a highly significant impact on the current reality and its projected evolutions. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Improved Performance Analysis and Reactive Power Compensation of FACTS Devices Utilizing Fuzzy Logic 4

Improved Performance Analysis and Reactive Power Compensatio...

引用

4th International Conference on Smart Electronics and Communication, ICOSEC 2023

作者： Reddy, N.V. Uma New Horizon College of Engineering Department of Artificial Intelligence and Machine Learning Bengaluru India

ISBN: (纸本)9798350300888

In most cases, a STATCOM is utilized to provide support for electrical networks in the event that as a result, the network's power factor decreases and voltage regulation issues become chronic. Because the STATCOM relies on a voltage source converter (VSC), its power supply must be behind a reactor. Adding a suitable energy storage device across the DC capacitor can improve the active power capabilities. This will allow for increased power output. The amount of reactive power present at the STATCOM terminals depends on how much power is supplied. When compared to an SVC, a STATCOM has a quicker response time. This is mostly because to the rapid switching speeds made possible by the voltage source converter's switches, which results in a shorter response time. In addition, compared to an SVC, the STATCOM provides improved support for reactive power even at low AC voltages. On the other hand, these devices can only provide shunt compensation. This research study suggests a novel technique centered on the reduction of line losses in loop distribution systems as a means of overcoming this restriction. The Unified Power Flow Controller, often known as the UPFC, is applied in order to experimentally accomplish these conditions of lowest loss. In contrast to the STATCOM, the UPFC can do series and shunt compensation, which enables the user to exercise control over both voltage and current. To meet this goal, this research developed a fuzzy logic controller-based implementation of a STATCOM and UPFC for reactive power compensation in distribution networks. © 2023 IEEE.

关键词： Static synchronous compensators

来源：评论

学校读者我要写书评

暂无评论

Gene Family Classification Using machine learning: A Comparative Analysis

Gene Family Classification Using Machine Learning: A Compara...

引用

International Conference on Data Analytics and Management, ICDAM 2023

作者： Seth, Drishti Dharmanshu Mahajan, Kpa Khanna, Rohit Chugh, Gunjan Department of Artificial Intelligence and Machine Learning Maharaja Agrasen Institute of Technology Delhi India

ISBN: (纸本)9789819965526

Accurate classification of gene families is of utmost importance in comprehending the functional roles and evolutionary history of genes within a genome. The exponential growth of genomic data has heightened the urgency for efficient and effective methods to classify gene families from DNA sequences. In this research paper, we present a novel approach for classifying DNA sequences into seven gene families. Our approach is based on machine learning and uses k-mer counting as a feature engineering technique to predict the gene family of a given DNA sequence. We evaluated our approach on a large dataset of DNA sequences and achieved a high accuracy of 90.9% in classification performance. Our results demonstrate the potential of machine learning methods for advancing our understanding of DNA sequences and gene families and can provide valuable insights for biologists and geneticists. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2023.

关键词： machine learning

来源：评论

学校读者我要写书评

暂无评论

SightAssist: A Multi-facility machine learning Approach for Empowering the Visually Impaired 2nd

SightAssist: A Multi-facility Machine Learning Approach for...

引用

2nd International Conference on Data Science and Network Engineering, ICDSNE 2024

作者： Bandopadhyay, Saikat Dutta, Jhalak Das, Smita Datta, Soumyajit Ghosh, Debaditya Dey, Rohit Kumar Nandigrami, Jeet Department of Artificial Intelligence and Machine Learning Netaji Subhash Engineering College Kolkata India Department of Computer Science and Engineering Heritage Institute of Technology Kolkata India Department of Computer Science and Engineering National Institute of Technology Agartala India Department of Artificial Intelligence and Machine Learning Heritage Institute of Technology Kolkata India

ISBN: (纸本)9789819783359

Blindness or visual impairment ranks among the top ten disabilities affecting both men and women, impacting over 35 million individuals of all ages in India. Access to visual information is crucial for enhancing the independence and safety of blind and visually impaired individuals. There exists a compelling imperative to develop assistive technologies that can significantly improve their quality of life. This paper presents SightAssist, a multilingual software solution designed to address the challenges faced by the visually impaired community in India. SightAssist utilizes a camera-based approach to serve as a digital prosthetic eye and virtual assistant, capable of currency detection, facial recognition, and providing various functionalities to assist with daily activities. Initially, a custom-labeled dataset has been prepared using a pre-trained YOLO model. Gradually, dataset pre-processing, normalization, and semantic segmentation are employed to optimize model performance. Additionally, voice-based accessibility features have been integrated using the Web Speech API, enabling users to interact with the application through voice commands. The experimental results show the successful development of SightAssist and its potential to significantly improve the lives of visually impaired people. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Assistive technology

来源：评论

学校读者我要写书评

暂无评论

Improved fuzzy C means with deep learning-based MANET routing model for multimedia communication

引用

International Journal of Networking and Virtual Organisations 2024年第4期31卷 306-338页

作者： Biradar, Manjula A. Mallapur, Sujata Department of Computer Science and Engineering Sharnbasava University Sharan Nagar Karnataka Kalaburagi585105 India Department of Artificial Intelligence and Machine Learning Sharnbasava University Sharan Nagar Karnataka Kalaburagi585105 India

The rapid growth of wireless communication amazed the researchers to done multimedia communication via wireless networks. The significant rise of mobile ad-hoc networks (MANET) in wireless communication is widely researched by researchers for an efficient transmission of multimedia data. MANET works on non-infrastructure topology with high quality of service (QoS) for better user experience. Though, it suffers from limitations such as routing, limited bandwidth, dynamic mobile node nature, etc. That’s why, this research paper is dedicated to introduce a MANET routing model for multimedia communication by providing reliable retransmission for better communication. An optimal cluster-based routing via improved fuzzy C-means (FCM) clustering takes place before it gets started nodal energy prediction is done by modified deep CNN model. And optimal cluster head selection is done via self-improved coati optimisation (SICO) under certain constraints. Finally, it is finished off with reliable retransmission to enhance the reliability of communication. Further, the efficiency of the proposed model is proved by various analysis. Copyright © 2024 Inderscience Enterprises Ltd.

关键词： Mobile ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

Exploring Diverse Clustering Methods for Analyzing Gas Turbine Emissions 11

Exploring Diverse Clustering Methods for Analyzing Gas Turbi...

引用

11th IEEE Region 10 Humanitarian Technology Conference, R10-HTC 2023

作者： Dalvi, Tejas Patley, Medhansh Bhatt, Ved Dhiman, Harsh S. Bongale, Anupkumar Patil, Shruti Department of Artificial Intelligence and Machine Learning Pune India Maharashtra Pune412115 India

ISBN: (纸本)9798350326147

This research investigates alternative clustering al-gorithms for analysing gas turbine emissions, which can have environmental and health consequences. We learn about emission patterns and sources by grouping similar data points into clusters. We evaluate approaches such as k-means, hierarchical clustering, density-based clustering, and fuzzy clustering using actual emission data. Our data show that no single strategy consistently outperforms others in detecting patterns. We explore the advantages and disadvantages of each strategy, as well as its practical usefulness. This research assists environmental engineers, decision-makers, and gas turbine manufacturers in developing efficient emission control programs. © 2023 IEEE.

关键词： Emission control

来源：评论

学校读者我要写书评

暂无评论

Decoding Information: A Dual Modality Approach for Sign Language Recognition 1

Decoding Information: A Dual Modality Approach for Sign Lang...

引用

1st International Conference on Computing, Sciences and Communications, ICCSC 2024

作者： Khattar, Princika Mishra, Siya Tanwar, Rahul Verma, Ankit Bhatia, Suman Dr. Akhilesh Das Gupta Institute of Professional Studies Department of Artificial Intelligence and Machine Learning Delhi India

ISBN: (纸本)9798350353648

Sign language is an important transmission method through which people who have hearing impairments or have difficulty in hearing properly communicate with other people. In sign language, each sign or gesture is assigned a different meaning. But communicating through sign language can be challenging as there are still crowds that have no idea about it therefore to solve this issue there are many sign language recognition tools present but they can be used by people who have a basic idea of sign language. A dual modality approach has been proposed, so this tool can be used by both the users who know sign language as they can use the sign-to-text recognition model which uses Convolutional Neural Network (CNN), and the users who do not know sign language can use the audio to text converter model which uses Speech Recognition Python Module. It can be used by a broader community. Our model has been trained on 26 alphabets and has achieved an accuracy of 98%. © 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

Automated Plant Disease Detection: CNN for Corn Maize, Tomato, and Potato 7th

Automated Plant Disease Detection: CNN for Corn Maize, Tomat...

引用

7th International Conference on Soft Computing: Theories and Applications, SoCTA 2023

作者： Angeline, R. Aruneshwaran, S. Department of Computer Science and Engineering with Specialization in Artificial Intelligence and Machine Learning SRM Institute of Science and Technology Ramapuram India

ISBN: (纸本)9789819720880

Plant ailments pose present a significant challenge to the worldwide food security and the agricultural sector. Swift and precise detection of these diseases is pivotal for effectively managing them and preventing crop yield reductions. Lately, advanced deep learning techniques, specifically Convolutional Neural Networks (CNNs), have exhibited encouraging outcomes across various tasks involving image recognition. This undertaking strives to create and execute a model founded on CNNs to prognosticate plant diseases through leaf images. The proposed strategy encompasses three main phases: compiling and preparing the data, developing the model architecture, and assessing performance. Initially, an extensive dataset of plant leaf images, encompassing leaves afflicted by diverse diseases, is assembled. The images undergo preprocessing to heighten quality and eliminate disturbances, ensuring a dependable model training process. Subsequently, a CNN structure is devised and trained to employ the dataset. The chosen CNN model adheres to a sequential design, where each layer possesses precisely one input and output. These layers are arranged sequentially to construct the entire network and incorporate multiple convolutional layers such as Conv2D, MaxPooling2D, Flatten, and Dense, enabling the learning of features from the input images. The findings underscore that the CNN-centered model for forecasting plant diseases attains remarkable training precision of 99.65%, accompanied by a testing precision of 99.44% and a validation precision of 98.61%, proficiently identifying prevalent ailments like common rust disease in corn plants, bacterial spot infection in tomato crops, and the early blight ailment in potato plants. In conclusion, the proposed CNN-driven prognostic model for plant diseases manifests encouraging outcomes in precisely recognizing these diseases from leaf images. The efficacious application of this model can assist farmers and agricultural specialists in inform

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

Advancements in Facial Image Processing for Human Age and Gender Identification 1

Advancements in Facial Image Processing for Human Age and Ge...

引用

1st International Conference on Computing, Sciences and Communications, ICCSC 2024

作者： Gupta, Shivangi Adhikari, Sachin Zaid, Md Shams Verma, Ankit Bhatia, Suman Dr. Akhilesh Das Gupta Institute of Professional Studies Department of Artificial Intelligence and Machine Learning Delhi India

ISBN: (纸本)9798350353648

With the increased usage of social media and associated cyber frauds, current scenario demands for authenticated information. This in turn necessitates for the valid and verified information of individuals from various resources which are available online. Various examples of cyber fraud include: fake banking transactions, unauthorized access to various organizations' resources, fake online proxy for absentees through biometric system etc. To counter such issues, in this paper we have targeted facial image processing for Precise age and correct gender recognition which are the most crucial factors in the digital era. Thus, in this study, we have constructed two distinct approaches to figure out human age and gender from facial with a satisfactory runtime and efficiency. Our method uses image processing to examine specific features from facial images of people in different age groups that have been adjusted. It then creates binary masks, performs edge detection, and measures wrinkle densities. To make assessing easier, we developed the ADIENCE facial database, containing images of males and females spanning various age ranges. The database holds twenty-six thousand plus photos featuring more than two thousand individuals sorted by gender and grouped into eight age categories. This special database has been used to train computer program for identification of individual's face based on their age and gender. This has been done by using Convolutional Neural Network (CNN) which makes it easier for program to recognize age and gender from pictures of people's faces. This is definitely going to help in various domains where security is top concern. This can also be helpful in healthcare domain for medical diagnoses. © 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

Image Super Resolution using U-Net architecture and SRGAN: Comparative Analysis 2

Image Super Resolution using U-Net architecture and SRGAN: C...

引用

2nd International Conference on Computer, Communication and Control, IC4 2024

作者： Dandekar, Pranali Bhojwani, Bhavika Balpande, Aarya Zanwar, Sanskar Deb, Ankan Shri Ramdeobaba College of Engineering and Management Department of Computer Science and Engineering [Artificial Intelligence and Machine Learning Nagpur India

ISBN: (纸本)9798350387933

Super-resolution is an important image processing task that improves the resolution of high-resolution images. Low resolution is used in many different fields, including medical imaging, satellite imagery, and computer vision. This paper presents a new approach to ultra-high resolution using the U-Net architecture, a deep learning framework known for its success in image segmentation and restoration *** this study, we propose an adaptive U-Net model specifically designed for ultra-high-resolution tasks. The architecture includes an encoder-decoder network with bypass connections, enabling multi-scale feature extraction and high-resolution detail reconstruction. Our model is trained on a diverse dataset of low- and high-resolution image pairs, allowing it to learn complex relationships and patterns in *** evaluate the performance of the U-Net based superresolution method using standard image quality metrics and qualitative visual evaluation. Test results show a significant improvement in image quality, with improved sharpness, texture, and detail recovery. Furthermore, our model outperforms state-of-the-art super-resolution methods in terms of signal-to-noise ratio (PSNR) and structural similarity index (SSIM). © 2024 IEEE.

关键词： Image segmentation

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：