检索结果-内蒙古大学图书馆

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Singh, Ajay Dhanda, Namrata Tiwari, Sharda Verma, Rajat Amity University Uttar Pradesh Amity School of Engineering and Technology Lucknow India Babu Banarasi Das Northern India Institute of Technology Department of Computer Science and Engineering Lucknow India Pranveer Singh Institute of Technology Department of Computer Science and Engineering Kanpur India

ISBN: (纸本)9798350370249

This research explores the integration of machine learning into market segmentation, a strategy traditionally reliant on demographic, geographical, and psychographic traits. With the rise of big data, machine learning offers enhanced precision by uncovering intricate consumer behavior patterns often missed by conventional methods. The study involves reviewing relevant literature, preprocessing datasets, and developing machine learning models to evaluate their effectiveness in segmenting markets. Findings indicate that machine learning significantly improves segmentation accuracy, enabling businesses to predict behaviors and tailor marketing strategies more effectively. This research contributes by highlighting machine learning's potential to transform market segmentation and drive business growth. Future work should focus on real-world implementation of these models to validate their practicality and impact. © 2024 IEEE.

关键词： consumer behavior customer insights machine learning market segmentation predictive analytics targeted marketing

来源：评论

学校读者我要写书评

暂无评论

Cost-Effective Authenticated Solution (CAS) for 6G-Enabled Artificial Intelligence of Medical Things (AIoMT)

引用

IEEE Internet of Things Journal 2024年第13期11卷 23977-23984页

作者： Mahmood, Khalid Obaidat, Mohammad S. Shamshad, Salman Alenazi, Mohammed J. F. Kumar, Gulshan Anisi, Mohammad Hossein Conti, Mauro National Yunlin University of Science and Technology Graduate School of Intelligent Data Science Douliu64002 Taiwan The University of Jordan King Abdullah II School of Information Technology Amman11942 Jordan University of Science and Technology Beijing School of Communication and Computing Engineering Beijing100083 China Amity University Amity School of Engineering and Technology Noida201301 India University of Lahore Department of Software Engineering Lahore54590 Pakistan King Saud University College of Computer and Information Sciences Department of Computer Engineering Riyadh12311 Saudi Arabia University of Padua Department of Mathematics Padua35131 Italy Lovely Professional University Department of Computer Science and Engineering Phagwara144411 India University of Essex School of Computer Science and Electronic Engineering ColchesterCO4 3SQ United Kingdom

The Internet of Things (IoT) is a network of interconnected objects, which congregate and exchange gigantic amounts of data. Usually, predeployed embedded sensors sense this massive data. Soon, several applications of IoT are anticipated to exploit emerging 6G technology. Healthcare is one of them, where the 6G-inspired paradigm may facilitate the users to exchange information through hundreds of sensors under the assumption of Artificial Intelligence of Things (AIoT). Integration of medical sensors with AIoT is known as Artificial Intelligence of Medical Things (AIoMT). The secure and seamless interactions among 6G-enabled AIoMT users should be the primary challenge. Furthermore, resource-constrained wearable sensing devices, with their inability to execute complex security solutions, provide an ideal attraction for malicious entities to launch diverse attacks. These challenges have motivated us to design a cost-effective authenticated solution (CAS) for 6G-enabled AIoMT healthcare applications. Our CAS protocol not only prevents cyber threats like impersonation session key secrecy but it can also prevent physical threats like hardware tampering. We observe formal and informal security validations to endorse its robustness and effectiveness. Performance comparison reveals that the CAS protocol offers maximum security enrichment. Moreover, CAS is cost-effective as it has achieved 33% and 60% reduction in computation and communication overheads, respectively, compared to contemporary competing related protocols. © 2014 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Recommender Systems and Artificial Intelligence in Digital Marketing

Recommender Systems and Artificial Intelligence in Digital M...

引用

2022 OPJU International technology Conference on Emerging Technologies for Sustainable Development, OTCON 2022

作者： Lashkari, Saahil Sharma, Shilpi Amity University Amity School of Engineering and Technology Department of Computer Science and Technology Uttar Pradesh Noida India

ISBN: (纸本)9781665492942

technology is advancing rapidly is today's day and age. Machine learning and artificial intelligence algotrithms in particular have seen huge leaps forward in the past few years. AI is being used everywhere, from education to medicine, from tourism to marketing. Recommender systems belong to a class of machine learning algorithms which are used to provide personalized recommendations to a user of a service, helping them make faster and better purchase decisions. Because of this recommender systems have reshaped the online marketplace drastically and have become essential to any online seller. Because of the same, it has become a popular data science domain and many researchers have developed various different types of algorithms and techniques to suit each type of implementation of the systems. In this paper, we discuss the various types of recommender systems, their importance and applications, and develop a small model for understanding. © 2023 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

POSMETER: proof-of-stake blockchain for enhanced smart meter data security

引用

International Journal of Information technology (Singapore) 2024年第2期16卷 1171-1184页

作者： Singhal, Divya Ahuja, Laxmi Seth, Ashish Amity Institute of Information Technology Amity University Noida Uttar Pradesh Noida India School of Computer Science and Information Engineering INHA University Tashkent Uzbekistan

As smart home appliances have grown in popularity;a large amount of data has been created on smart meters pertaining to various consumers. Due to privacy concerns, these smart meters are unable to share their information in deregulated smart grids. Both smart grid implementation and smart meter data handling are currently significant issues for end-user security and utility. The idea of integrating blockchain technology into the smart grid came from this severe problem. The development of safe payment methods in particular has motivated the diversification of blockchain as a way to offer security and promote end-user confidence. Data security and privacy are two important technological solutions used with smart meters. This study proposes an easy and secure smart meter data validation technique supported by Blockchain technology. The proof-of-stake blockchain consensus process is the most well-known and reliable since it protects the database. A unique Data pruning technique is developed in this research to enhance blockchain storage. The data is encrypted and decrypted by using an Advanced Encryption Standard (AES-256) approach. The information gathered from smart meters is finally validated using the blockchain proof of work technique. © The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of computer Applications and Management 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s);author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

关键词： Blockchain technology Data pruning Privacy Proof-of-stake Security Smart meter

来源：评论

学校读者我要写书评

暂无评论

Glaucoma Classification Using Enhanced Deep Transfer Learning Models with Hybrid ROI Cropped Optic Disc Technique

引用

SN computer science 2023年第6期4卷 722页

作者： Singh, Piyush Bhushan Singh, Pawan Dev, Harsh Chaurasia, Brijesh Kumar Amity School of Engineering and Technology Lucknow Amity University Uttar Pradesh Lucknow India Department of Computer Science and Engineering Pranveer Singh Institute of Technology Kanpur India

Glaucoma is a chronic, irrevocable eye ailment in which the optic nerve slowly deteriorates, impairing vision and quality of life. Specialists can diagnose clinical glaucoma;however, the procedures are either expensive or time-consuming. In this paper, we have proposed an enhanced version of various pre-trained CNN models (DenseNet, ResNet, VGG, Inception, and MobileNet) using batch normalization, inception module, and global pooling with the Swish activation function. We have used three datasets (ACREMA, LAG, and IEEE Fundus images) and pre-processed versions of these datasets in this work. Moreover, we have also proposed a hybrid region of interest (ROI) extraction approach in which we have extracted the region of interest using a combination of the Brightest Spot algorithm and Hough Circles implementation for pre-processing of the fundus images to improve the overall performance. We have also applied manual hyperparameter optimization for learning rate, batch size, SGD optimizer, and fine-tuning step. The proposed framework acquired an improved accuracy of 98–99% among all datasets used in our research. The extensive experimental simulation results indicate that the proposed framework is performing better than all the stand-alone models. The proposed hybrid model with DenseNet-169 acquired an accuracy of up to 99% using the ROI and the improved transfer learning model with customized layers on pre-processed IEEE dataset. The empirical results also validate the efficacy of our proposed model on pre-processed large dataset LAG, with the proposed hybrid approach, having 5824 fundus images and achieving up to 95% accuracy by customized DenseNet-169 model. The results show that the proposed framework using cutting-edge techniques can ensure its effectiveness. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： ConvBN DenseNet-169 Glaucoma Normal Optic disc Optic nerve head (ONH)

来源：评论

学校读者我要写书评

暂无评论

Towards Accurate Heart Disease Diagnosis: An Overview of Machine Learning Approaches 6

Towards Accurate Heart Disease Diagnosis: An Overview of Mac...

引用

6th International Conference on Recent Trends in Advance Computing, ICRTAC 2023

作者： Deshmukh, Varun Pathak, Sunil Bhattacharya, Pronaya Verma, Ashwin Amity University Department of Computer Science & Engineering Jaipur India Amity University Amity School of Engineering and Technology Research and Innovation Cell Department of Computer Science and Engineering Kolkata India Nirma University Department of Computer Science & Engineering Ahmedabad India

ISBN: (纸本)9798350394702

cardiovascular diseases, especially heart ailments, pose substantial health challenges globally, often exacerbated by unhealthy lifestyle habits. Recent technological advances in machine learning (ML) have emerged as a beacon of hope, presenting avenues for swift and efficient heart disease detection. Despite the voluminous health data accumulated daily, its vast analytical potential is frequently overlooked, creating a pronounced knowledge disparity. Thus, it becomes imperative to study recent ML approaches for accurate heart diagnosis, which allows to fetch critical insights. In this paper, we discussed a comparative analysis of ML algorithms, datasets for heart diseases, and compared ML algorithms in terms of metrics like precision, recall, F1 and accuracy. We considered the benchmark Cleveland Heart Dataset for analysis. We observed an accuracy of 84% by Artificial Neural Network (ANN), while Support Vector Machine (SVM) has the highest recall of 95%. The presented findings and analysis indicate the efficacy of the analysis in heart prediction using ML in real-world setups. © 2023 IEEE.

关键词： Heart

来源：评论

学校读者我要写书评

暂无评论

IoT Based Smart Plant Monitoring System 13

IoT Based Smart Plant Monitoring System

引用

13th International Conference on Cloud Computing, Data science and engineering, Confluence 2023

作者： Nehra, Vibha Sharma, Megha Sharma, Vaibhav Amity University Department of Computer Science and Engineering Uttar Pradesh India Amity University Amity School of Engineering and Technology Uttar Pradesh India

ISBN: (纸本)9781665462631

Agriculture is a vast area that needs to be studied. technology development has brought us to the situation where there are sophisticated agricultural tools and systems. About 80% of India's surface water is used for agriculture. Applying IoT becomes necessary to ensure proper use of water resources and high-quality output. Because optimal irrigation in fields can provide better crops, this paper presents an open-source technology-based smart system to predict irrigation requirements of a field using sensing of ground parameters like soil moisture, environmental conditions like temperature and humidity, and external parameters like obstacle detection or intruder alert using an infrared sensor. The proposed system is based on an algorithm that takes into account sensed data in addition to the previously mentioned parameters. The entire system has been created and deployed on a pilot scale, and it wirelessly collects sensor node data over the cloud using web services, while a both web and mobile based information visualization and decision support system offers real-time insights based on the analysis of the sensor. The analysis displayed clear differences between the monitored and unmonitored environment and how it affects the plant health in both short and long term. The graphs help in visualizing the differences between the environment at fixed time intervals. In the future, this system can be combined with other technologies to predict rainfall, manage pH levels, and secure the vast amounts of data created and saved over the cloud by sensors. This would improve the system's long-term viability and make it more independent of human operation. © 2023 IEEE.

关键词： Soil moisture

来源：评论

学校读者我要写书评

暂无评论

Forecasting Smart Grid Stability Using a Hybrid CNN Bi-LSTM Approach

引用

SN computer science 2024年第5期5卷 539页

作者： Singhal, Divya Ahuja, Laxmi Seth, Ashish Amity Institute of Information Technology Amity University Uttar Pradesh Noida India School of Computer Science & amp Information Engineering INHA University Tashkent Uzbekistan

The prediction of smart grid stability is paramount for identifying contributors to network instabilities, yet it remains a challenging endeavor. To predict the stability of smart grid systems, researchers offer a novel method in this paper that uses a hybrid Convolutional Neural Network Bidirectional Long Short-Term Memory (CNN Bi-LSTM) model. By combining CNN's capacity to extract spatial characteristics with Bi-LSTM's capacity to record temporal dependencies, the suggested method overcomes the drawbacks of earlier techniques and provides a complete stability prediction solution. The research uses data transformation and normalization techniques to analyze data efficiently. To ensure fair handling of data, min–max normalization is utilized to reduce biases resulting from the Smart Grid database’s predilection for high-importance entries. This normalization process enhances algorithmic effectiveness by standardizing data sizes. The data analysis process begins with thorough exploration, allowing users to flexibly uncover preliminary patterns, primary points of interest, and distinctive attributes within the sizable dataset. Leveraging the Convolutional Neural Network framework, features are extracted, and the dimensionality problem stemming from the expanding smart grid systems is addressed using a principal component analysis-based feature selection technique. Finally, we introduce a novel Bidirectional Long Short-Term Memory technique tailored specifically for forecasting smart grid network stability. The proposed approach achieves superior accuracy, boasting a remarkable 96.9% accuracy rate compared to existing methods. This hybrid CNN Bi-LSTM methodology not only improves prediction accuracy but also enhances our understanding of smart grid dynamics, paving the way for more reliable and efficient energy management systems. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Bi-LSTM CNN Grid Stability Smart Grid Stability

来源：评论

学校读者我要写书评

暂无评论

Deep Convolutional Network Based Machine Intelligence Model for Satellite Cloud Image Classification

引用

Big Data Mining and Analytics 2023年第1期6卷 32-43页

作者： Kalyan Kumar Jena Sourav Kumar Bhoi Soumya Ranjan Nayak Ranjit Panigrahi Akash Kumar Bhoi Department of Computer Science and Engineering Parala Maharaja Engineering CollegeBerhampur 761003India Amity School of Engineering and Technology Amity UniversityUttar Pradesh 201303India Department of Computer Applications Sikkim Manipal Institute of TechnologySikkim Manipal UniversitySikkim 737102India Directorate of Research Sikkim Manipal UniversityGangtokSikkim 737102India

As a huge number of satellites revolve around the earth,a great probability exists to observe and determine the change phenomena on the earth through the analysis of satellite images on a real-time ***,classifying satellite images plays strong assistance in remote sensing communities for predicting tropical *** this article,a classification approach is proposed using Deep Convolutional Neural Network(DCNN),comprising numerous layers,which extract the features through a downsampling process for classifying satellite cloud *** is trained marvelously on cloud images with an impressive amount of prediction *** time decreases for testing images,whereas prediction accuracy increases using an appropriate deep convolutional network with a huge number of training dataset *** satellite images are taken from the Meteorological&Oceanographic Satellite Data Archival Centre,the organization is responsible for availing satellite cloud images of India and its *** proposed cloud image classification shows 94% prediction accuracy with the DCNN framework.

关键词： satellite images satellite image classification cyclone prediction Deep Convolutional Neural Network(DCNN) features layers down-sampling process

来源：评论

学校读者我要写书评

暂无评论

Survey on One-Shot Learning for Image Recognition using Machine Learning and Deep Learning Techniques 5

Survey on One-Shot Learning for Image Recognition using Mach...

引用

5th International Conference on Smart Electronics and Communication, ICOSEC 2024

作者： Kadam, Ganesh Vitthal Dubey, Ghanshyam Prasad Computer Science Amity School of Engineering & Technology Gwalior Maharajpura Madhya Pradesh Gwalior474005 India Amity School of Engineering & Technology ASET-CSE Maharajpura Madhya Pradesh Gwalior474005 India

ISBN: (纸本)9798331504403

Despite their success, the traditional deep neural networks are unable to rapidly generalize from a limited number of samples. To address the issue of large training data requirements with deep neural networks, one-shot learning restricting the number of data in each category is developed to attain enhanced results. Specifically, the traditional neural networks lead to over-fitting problems in training with a limited number of samples. In contrast, Machine Learning algorithms are capable of one-shot learning from limited samples like humans have the ability of oneshot learning. Hence, it is necessary to analyze one-shot object recognition techniques prevalent in image processing systems. This study will explore different one-shot learning techniques and methods from the state-of-the-art models and examine the merits and challenges of the approach with 25 literature papers. The effectiveness of the existing approaches will be evaluated by various techniques, datasets, and performance metrics are discussed in detail. At last, the paper discusses the potential future studies and challenges in achieving better detection accuracy. © 2024 IEEE.

关键词： Zero-shot learning

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：