检索结果-内蒙古大学图书馆

2nd IEEE International Conference on IoT, Communication and Automation technology, ICICAT 2024

作者： Ranjith, Jinugu Al-Farouni, Mohammed Anitha, R. Poornima, Ediga Sharma, Kamal Kumar, Neelam Sanjeev CMR College of Engineering & Technology Department of CSE India The Islamic University College of Technical Engineering Department of Computers Techniques Engineering Najaf Iraq New Prince Shri Bhavani College of Engineering and Technology Department of IT Tamil Nadu Chennai600073 India GRIET Bachupally Department of AI&ML Telangana Hyderabad India GLA University Department of Mechanical Engineering Mathura India SRM Institute of Science & Technology Vadapalani Department of Computer Science & Engineering Chennai26 India

ISBN: (纸本)9798350368109

Supply chain management is one of the industries that benefit greatly from implementing blockchain technology since it supplies chains with a high level of transparency, security, and traceability. Nonetheless, keeping up to date with different regulatory requirements or specifications that change frequently and still meeting contract requirements still pose a major problem. In this paper, we introduce a new method in the dynamic compliance management of blockchain implemented supply chain system by the use of deep reinforcement learning (DRL) and Long Short-Term Memory (LSTM) networks. Through DRL, supply chains can obtain real-time insights in learning from the environment and apply the knowledge effectively to satisfy regulatory standards as well as contractual terms. The inclusion of the LSTM component allows the system to capture sequential dependency and long-horizon effects within the supply-chain data. To prove the efficiency of our strategy, we provide simulation results as well as the analysis of real-world applications that discuss the positive shift in percentages and potential increase in productivity. © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Customer Retention Using Machine Learning 10

Customer Retention Using Machine Learning

引用

10th IEEE Uttar Pradesh Section International Conference on Electrical, Electronics and computer engineering, UPCON 2023

作者： Das, Lipsa Salman, Rahama Sabeer, Shaista Ansari, Subuhi Kashif Aarif, Mohd Rana, Ajay Amity School of Engineering and Technology Amity University UP Greater Noida India Jazan University Department of Computer Science Saudi Arabia Global Research Network UP Noida India College of Computer Science & Information Technology Jazan University Department of Information Technology and Security Jazan Saudi Arabia College of Computer Science and Information Technology & Security Jazan University Jazan Saudi Arabia

ISBN: (纸本)9798350382471

Maintaining customer retention stands as a pivotal element in ensuring business success, given that the costs associated with acquiring new customers often surpass those linked to retaining existing ones. Recognizing the significance of retaining a loyal customer base, businesses prioritize strategies and initiatives that cultivate lasting relationships with their current clientele, understanding that sustained customer loyalty contributes substantially to long-term viability and profitability.. Machine learning techniques offer a promising approach to predicting customer behavior and developing personalized retention strategies. In this research paper, we explore the use of machine learning for customer retention, specifically focusing on predictive modeling and recommendation systems. We review recent literature on the topic, discussing different machine learning algorithms and techniques that have been applied to customer retention. We also present a case study of a company that has successfully implemented machine learning-based retention strategies, highlighting the benefits and challenges of this approach. Our findings suggest that machine learning can be an effective tool for improving customer retention, but its success depends on several factors, including data quality, model accuracy, and implementation strategy. Our conclusion involves an exploration of the consequences of our research for forthcoming studies and practical applications within business environments.. © 2023 IEEE.

关键词： customer behavior Customer retention machine learning predictive modelling

来源：评论

学校读者我要写书评

暂无评论

Game Data Visualization Using Artificial Intelligence Techniques 11th

Game Data Visualization Using Artificial Intelligence Techni...

引用

11th International Conference on Recent Trends in Computing, ICRTC 2022

作者： Mohapatra, Srikanta Kumar Sarangi, Prakash Kumar Sahu, Premananda Sharma, Santosh Kumar Sharma, Ochin Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Vardhaman College of Engineering Hyderabad India Department of Computer Science and Engineering SRMIST DELHI-NCR Modinagar Ghaziabad India Department of Computer Science and Engineering CVRCE Odisha Bhubaneswar India

ISBN: (纸本)9789811988240

Games usually have a tendency to have the properties of massive use of a location and excessive complexity, making them notable benchmarks for evaluating numerous strategies which consist of AI ones. Broadly talking, techniques are utilized in video games in a position to make them larger exciting, immersive, smarter, and many others. Both of these prove to be excellent types of AI recreation. Since there are few viewpoints on contemporary results in the activity AI discipline from the standpoint of the fundamental program, in our work we have taken a scientific look at a number of commonplace that seems to be up to software program fields of pastime AI: viable agents in non-player character studies and recreation stage technological know-how in procedural content material fabric generation. Here we have proposed a model which can provide the different game visualization in the form of terms and conditions using different AI-based algorithms. In addition, AI for everyday tasks and hybrid genius for different games are explored. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Visualization

来源：评论

学校读者我要写书评

暂无评论

Fault Diagnosis Method of Planetary Gearbox Based on Transfer Learning and EfficientNet 14

Fault Diagnosis Method of Planetary Gearbox Based on Transfe...

引用

14th IEEE Global Reliability and Prognostics and Health Management Conference, PHM-Hangzhou 2023

作者： Li, Yin Gu, Yiliu Shi, Changwu Li, Ting School of Mechanical and Electrical Engineering Jiangxi University of Science and Technology Ganzhou China College of Computer Scienceand Electronic Engineering Hunan University Changsha China School of Automotive Jiangxi College of Applied Technology Ganzhou China

ISBN: (纸本)9798350301359

In the field of gear fault diagnosis, the traditional convolutional neural networks model has a single precision improvement method and has limitations. This paper proposes a planetary gearbox fault diagnosis model based on Gramian Angular Fields (GAF) image coding technology and TL-EfficientNet network model. The collected one-dimensional vibration signal is preprocessed and converted into GAF diagram. The EfficientNet is pre-trained on the ImageNet dataset, the trained feature weights are migrated to the EfficientNet network, and the samples are trained to complete the fault identification of the planetary gearbox. The experimental results show that the proposed method can effectively improve the fault diagnosis accuracy of planetary gearboxes, reaching 99.49%, and has faster convergence speed and better stability than a single method. At the same time, the TL+EfficientNet-B2 model has strong generalization and can be applied to other fault diagnosis with similar feature distribution data. © 2023 IEEE.

关键词： convolutional neural network fault diagnosis Gramian Angular Fields planetary gear box transfer learning

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Enabled Disease Diagnosis for Secure Internet of Medical Things

引用

computers, Materials & Continua 2022年第10期73卷 965-979页

作者： Sultan Ahmad Shakir Khan Mohamed Fahad Al.Ajmi Ashit Kumar Dutta L.Minh Dang Gyanendra Prasad Joshi Hyeonjoon Moon Department of Computer Science College of Computer Engineering and SciencesPrince Sattam Bin Abdulaziz UniversityAlkharj11942Saudi Arabia College of Computer and Information Sciences Imam Mohammad Ibn Saud Islamic University(IMSIU)Riyadh11432Saudi Arabia College of Pharmacy King Saud UniversityRiyadh11451Saudi Arabia Department of Computer Science and Information System College of Applied SciencesAlMaarefa UniversityRiyadh11597Saudi Arabia Department of Information Technology FPT UniversityHo Chi Minh CityVietnam Department of Computer Science and Engineering Sejong UniversitySeoul05006Korea

In recent times,Internet of Medical Things(IoMT)gained much attention in medical services and healthcare management *** healthcare sector generates massive volumes of data like personal details,historical medical data,hospitalization records,and discharging records,IoMT devices too evolved with potentials to handle such high quantities of *** and security of the data,gathered by IoMT gadgets,are major issues while transmitting or saving it in *** advancements made in Artificial Intelligence(AI)and encryption techniques find a way to handle massive quantities of medical data and achieve *** this view,the current study presents a new Optimal Privacy Preserving and Deep Learning(DL)-based Disease Diagnosis(OPPDL-DD)in IoMT ***,the proposed model enables IoMT devices to collect patient data which is then preprocessed to optimize *** order to decrease the computational difficulty during diagnosis,Radix Tree structure is *** addition,ElGamal public key cryptosystem with Rat Swarm Optimizer(EIG-RSO)is applied to encrypt the *** the transmission of encrypted data to cloud,respective decryption process occurs and the actual data gets ***,a hybridized methodology combining Gated Recurrent Unit(GRU)with Convolution Neural Network(CNN)is exploited as a classification model to diagnose the *** sets of simulations were conducted to highlight the performance of the proposed model on benchmark *** experimental outcomes ensure that the proposed model is superior to existing methods under different measures.

关键词： Internet of medical things privacy security encryption radix tree deep learning

来源：评论

学校读者我要写书评

暂无评论

PDDD-PreTrain:A Series of Commonly Used Pre-Trained Models Support Image-Based Plant Disease Diagnosis

引用

Plant Phenomics 2023年第2期5卷 313-332页

作者： Xinyu Dong Qi Wang Qianding Huang Qinglong Ge Kejun Zhao Xingcai Wu Xue Wu Liang Lei Gefei Hao State Key Laboratory of Public Big Data College of Computer Science and TechnologyGuizhou UniversityGuiyang 550025China The School of Physics and Optoelectronic Engineering Guangdong University of TechnologyGuangzhou 510006China National Key Laboratory of Green Pesticide Key Laboratory of Green Pesticide and Agricultural BioengineeringMinistry of EducationGuizhou UniversityGuiyang 550025China

Plant diseases threaten global food security by reducing crop yield;thus,diagnosing plant diseases is critical to agricultural *** intelligence technologies gradually replace traditional plant disease diagnosis methods due to their time-consuming,costly,inefficient,and subjective *** a mainstream AI method,deep learning has substantially improved plant disease detection and diagnosis for precision *** the meantime,most of the existing plant disease diagnosis methods usually adopt a pre-trained deep learning model to support diagnosing diseased ***,the commonly used pre-trained models are from the computer vision dataset,not the botany dataset,which barely provides the pre-trained models sufficient domain knowledge about plant ***,this pre-trained way makes the final diagnosis model more difficult to distinguish between different plant diseases and lowers the diagnostic *** address this issue,we propose a series of commonly used pre-trained models based on plant disease images to promote the performance of disease *** addition,we have experimented with the plant disease pre-trained model on plant disease diagnosis tasks such as plant disease identification,plant disease detection,plant disease segmentation,and other *** extended experiments prove that the plant disease pre-trained model can achieve higher accuracy than the existing pre-trained model with less training time,thereby supporting the better diagnosis of plant *** addition,our pre-trained models will be open-sourced at https://***/and Zenodo platform https://***/10.5281/zenodo.7856293.

关键词： diagnosis Plant thereby

来源：评论

学校读者我要写书评

暂无评论

Developing a Comprehensive Hybrid Model Utilizing Convolutional Neural Networks and Random Forest for the Advanced Classification of Tomato Rot Disease Severity Stages

Developing a Comprehensive Hybrid Model Utilizing Convolutio...

引用

2024 IEEE International Conference on Emerging Technologies in computer science for Interdisciplinary Applications, ICETCS 2024

作者： Satyarthi, Abhishek Upadhyay, Deepak Bharti, Dilip Kumar Manwal, Manika Kukreja, Vinay Sharma, Rishabh AI DS IIMT College of Engineering Greater Noida India Graphic Era Hill University Uttarakhand Dehradun248002 India Computer Science and Engineering-Data Science ABES Engineering College Ghaziabad India Graphic Era Deemed to Be University Uttrakhand Dehradun India Chitkara University Institute of Engineering and Technology Chitkara University Punjab India

ISBN: (纸本)9798350372502

This study proposed a relatively new hybrid model integrating Convolutional Neural Networks (CNN) and Random Forest (RF) for the classification of tomato fruit rot diseases into five different levels, according to graded severity levels. Breaking with the norm of the primitive and one-sided machine learning techniques in the strong categorization and the precise diagnosis of plant diseases, this research stands out for applying the deep learning potential of convolutional neural networks and the multifaceted strength of random forest for the extraction of features and the classification accordingly. The newly proposed mixed methodology, including data acquisition, preprocessing, training, and validation, indicates the hybrid model with excellent performance where the accuracy measurement was 93.5%. Besides, this portrays a significant change because it is already better compared to the current models, and it evidences its potential in the fight against weather variability and the improvement of disease management. The study results suggest that the integration of deep and ensemble learning methods in the agricultural sector is possible, wherefore their perspectives can become a base for future practical applications as a worthwhile goal. The work is substantial and represents a significant contribution to the field of agricultural informatics and plant pathology in that there is a robust tool for early disease detection and severity classification that will directly lead to quick and informative management decisions. © 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

Exploring 2D representation and transfer learning techniques for indoor localization

引用

Multimedia Tools and Applications 2025年 1-13页

作者： Kerdjidj, O. Himeur, Y. Atalla, S. Copiaco, A. Sohail, S.S. Amira, A. Fadli, F. Mansoor, W. Gawanmeh, A. Centre of Development of Advanced Techniques Algiers Algeria College of Engineering and Information Technology University of Dubai Dubai United Arab Emirates Department of Computer Science University of Sharjah Sharjah United Arab Emirates Institute of Artificial Intelligence De Montfort University Leicester United Kingdom School of Computing Science and Engineering VIT Bhopal University Kothri Kalan India Department of Architecture & Urban Planning Qatar University Doha2713 Qatar

Indoor localization (IL) plays a critical role in various applications, including asset tracking, emergency response, and indoor navigation. Traditional methods relying on one-dimensional (1D) representations of received signal strength indicator (RSSI) data often suffer from limitations such as low accuracy, environmental sensitivity, and susceptibility to interference. To overcome these challenges, this paper proposes Scalogram-Based Transfer Learning for Indoor Localization (STL-IL), a novel framework that significantly enhances localization performance. The proposed approach transforms 1D RSSI signals into two-dimensional (2D) representations using scalogram-based time-frequency analysis, coupled with advanced transfer learning (TL) techniques. By leveraging the scalogram method to generate image representations of the data and employing diverse wavelet types. Furthermore, pre-trained deep learning models, including GoogleNet and SqueezeNet, are utilized to achieve state-of-the-art performance. Experimental results demonstrate that the STL-IL system achieves remarkable accuracy levels of 95% and 96% for SqueezeNet and GoogleNet, respectively. The proposed framework not only improves localization accuracy but also enhances robustness in dynamic and challenging environments, making it a promising solution for real-world indoor localization applications. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Robustness Challenges in Deep Learning: Strategies for Enhancing Model Resilience 2

Robustness Challenges in Deep Learning: Strategies for Enhan...

引用

2nd International Conference on Disruptive Technologies, ICDT 2024

作者： Joshi, Prakash Shaikh, M.Z. Varshney, Neeraj Dwivedy, Bhoopendra Raj Kumar Goel Institute of Technology Department of Computer Science & Engineering UP Ghaziabad India Shree Bhagubhai Mafatlal Polytechnic College Department of Electronics & Telecommunication Maharastra Mumbai India Gla University Department of Computer Engineering and Applications UP Mathura India Galgotias University Department of School of Computer Science & Engineering UP Greater Noida India

ISBN: (纸本)9798350371055

Deep knowledge is the main way the improvement of gadgets, gaining knowledge of generation for more than a few applications from facial popularity to self-reliant vehicles. Deep learning fashions have carried out outstanding successes, even outperforming people in complex obligations. However, robustness demanding situations of deep getting-to-know systems remain an essential difficulty. Deep studying fashions are at risk of malicious inputs that could result in misclassifications or denial-of-provider attacks. Robustness towards entering noise, in addition to robust extraction of beneficial capabilities from noisy datasets, are just a number of the main challenges for deep mastering systems. Current research has discovered a plethora of attack vectors that can be deployed against deep getting-to-know fashions along with 'adversarial' assaults, which contain manipulating the enter records in a particular manner to purpose models to misclassify items. Moreover, dataset bias and absence of right validation can cause structures that are not sturdy towards facts from a domain extraordinary from the facts used for education. A good way to enhance the robustness of deep learning models, researchers are exploring solutions that include countermeasures, specialized architectures, and higher education and checking out approaches. While progress has been made, the robustness challenges of deep learning remain an important study vicinity that should be addressed so one can fulfill the promise of this generation. © 2024 IEEE.

关键词： Architectures Discovered Extraordinary Manipulating Researchers

来源：评论

学校读者我要写书评

暂无评论

Service Application of Knowledge Graph in the Hotspot of Network Public Opinion Research 11

Service Application of Knowledge Graph in the Hotspot of Net...

引用

11th Joint International Information technology and Artificial Intelligence Conference, ITAIC 2023

作者： Liu, Huanpeng Meng, Qingchuan Hu, Dayong Dong, Yiran Zhu, Yulin Meng, Ge HeiLongJiang Province Cyberspace Research Center Harbin China College of Computer Science and Technology Harbin Engineering University Harbin China

ISBN: (纸本)9798350333664

Along with the development of the study of Internet public opinion, it is a hotspot to analyze the Internet under the circumstance of large data. Under such background, article drew out the hotspots of Internet public opinion from lots of public opinion documents by means of application of knowledge, and made visual analysis of the hotspots in Internet. It was found that the application of knowledge can increase the intuitive ability of the hotspots from 76.10 percent to 89.15 percent and enhance the comprehensive degree of the hotspots. Thus, it can draw a conclusion that the knowledge graph constructed can offer a more direct and integrated analytical service to the hotspots of Internet Public Opinion. © 2023 IEEE.

关键词： High-frequency Keywords Knowledge Graph Online Public Opinion Research Hotspots

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：