检索结果-内蒙古大学图书馆

5th International Conference on Intelligent Communication Technologies and Virtual Mobile Networks, ICICV 2024

作者： Kushwaha, Sumit Amuthachenthiru, K. Geetha, K. Narasimharao, Jonnadula Dileep Kumar, M. Gadde, Sai Sudha University Institute of Computing Chandigarh University Department of Computer Applications Punjab 140413 India Ramco Institute of Technology Department of Artificial Intelligence and Data Science Tamil Nadu Rajapalayam626117 India Srm Institute of Science and Technology Department of Computing Technologies Tamil Nadu Kattankulathur603 203 India Cmr Technical Campus Department of Computer Science and Engineering Telangana Hyderabad501401 India Hensard University Faculty of Management Sciences Bayelsa 561101 Nigeria Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering Telangana Vaddeswaram500075 India

ISBN: (纸本)9798350385649

Medical imaging modalities, including computed tomography (CT), magnetic resonance imaging (MRI), X-rays, and ultrasound, are extensively employed in the healthcare industry for diagnostic purposes. Noise, on the other hand, can disturb these approaches and lead to inaccurate diagnosis. Due to this problem, the significance of noise removal technologies has grown in the field of medical imaging, specifically for the examination and understanding of medical images and anatomical structures. To tackle these challenges, a variety of denoising techniques have been developed, such as the Weiner filter (WF), Gaussian filter, and median filter. This work employs a Deep Learning (DL) method known as Convolutional Autoencoder (CAE) to remove noise from medical images. We gather chest X-ray images for analysis and focus on common noise types that affect medical images, such as Poisson and Gaussian noise. We evaluate the effectiveness of the suggested denoising method CAE by comparing it to the commonly employed WF methodology. The Structural Similarity Index (SSIM) and Peak Signal-to-Noise Ratio (PSNR) are employed to assess and compare the performance of the WF and CAE in reducing Poisson and Gaussian noise. The study's findings indicate that the suggested denoising method based on CAE shows promising results in terms of improving quality. © 2024 IEEE.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Telecom Churn Analysis using Machine Learning in Smart Cities 1

Telecom Churn Analysis using Machine Learning in Smart Citie...

引用

1st International Conference in Advanced Innovation on Smart City, ICAISC 2023

作者： Sharma, Ashish Shukla, Prafullit Gourisaria, Mahendra Kumar Sharma, Bhisham Dhaou, Imed Ben GLA University Department of Computer Engineering & Applications UP Mathura India KIIT Deemed to Be University School of Computer Engineering Odisha Bhubaneswar India Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Dar Al-Hekma University Hekma School of Engineering Computing and Informatics Department of Computer Science Jeddah Saudi Arabia

ISBN: (纸本)9781665472753

With the increase in the Telecom industry, service providers are more attentive toward the action of becoming larger or more extensive to the subscriber base. For surviving in telecom companies, the continued possession of holding customers must be a big challenge. According to consideration in the telecom environment, the market price of obtaining the new purchaser is more than holding the existing purchaser. Through collecting knowledge from the telecom industry to analyze the association of the customer whether will leave or not the company. Such types of the Decision tree and Logistic regression model have been compared on the 3334 instances of the dataset. The classification model derived from logistic regression has an accuracy of 80% and the decision tree classifier with an accuracy of 97%. © 2023 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Career selection of students using hybridized distance measure based on picture fuzzy set and rough set theory

Decision Making: Applications in Management and Engineering

引用

Decision Making: applications in Management and engineering 2021年第1期4卷 104-126页

作者： Sahu, Rekha Dash, Satya R. Das, Sujit School of Computer Engineering KIIT University Bhubaneswar India School of Computer Applications KIIT University Bhubaneswar India Department of Computer Science and Engineering National Institute of Technology Warangal Warangal India

Since the future of the society depends upon the role of students, so suitable career selection methods for the students are considered to be an important problem to explore. It is assumed that if a student has the required capability and positive attitudes towards a subject, then the student will achieve more in that subject. To consider the uncertain issues involved with students' career selection, picture fuzzy set (PFS) and rough set based approaches are proposed in this study as they are found to be appropriate due to their inherent characteristics to deal with incomplete and imprecise information. For the purpose of selecting a suitable career, the article analyzes student's features in terms of career, memory, interest, knowledge, environment and attitude. We propose two hybridized distance measures using Hausdorff, Hamming and Euclidian distances under picture fuzzy environment where the evaluating information regarding students, subjects and student's features are given in picture fuzzy numbers. Then we present an algorithmic approach using the proposed distance measures and rough set theory. We apply rough set theory to determine whether a particular subject is suitable for a student even if there is controversy to select a stream. Lower and higher approximation with boundary region of rough set theory is used to manage the inconsistent situations. Finally, two case studies are demonstrated to validate the applicability of the proposed idea. © 2020 Regional Association for Security and crisis management. All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Research and Implementation of Data Mining for applications Involving Big Data 1

Research and Implementation of Data Mining for Applications ...

引用

1st International Conference on Futuristic Technologies, INCOFT 2022

作者： Unni Krishnn, A. Singh, Kedar Nath Galgotias University Department of Computer Applications Uttar Pradesh Greater Noida India Noida Institute of Engineering and Technology Department of Computer Science and Engineering Uttar Pradesh Greater Noida India

ISBN: (纸本)9781665450461

Data mining is the process of removing obscured, undiscovered, but possibly valuable information from vast amounts of data. Huge Information altogether affects the advancement of significant worth and logical forward leaps. In this paper, information mining strategies and large information advancements are presented. Information mining endlessly issues with immense information are examined. Also, a few information mining innovative headways and huge information mining progressions are featured. The lifecycle of electronic items, which ranges from the plan and creation stages through the assistance stage, has seen broad utilization of information mining (DM) utilizing Large Information. It will be useful for scientists to foster solid examination subjects and recognize holes in the writing, yet it will likewise help specialists in the improvement of DM application framework by furnishing an exhaustive investigation of DM with Enormous Information and a survey of its application in the phases of its lifecycle. This paper starts with a short clarification of DM-related issues. Large Information is a tremendous assortment of information that is excessively complicated for traditional projects to deal with. Nowadays, it involves huge, multifaceted, and a ton of coordinated, semi-organized, and unstructured information as well as privileged information that is delivered and accumulated from numerous areas and assets. The model when gets implemented displays results on various model s based on different regions SanFrancisco, Chicago and Philadelphia from 2006-2011 © 2022 IEEE.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

HHO-UNet-IAA: Harris Hawks Optimization based novel UNet-inception attention architecture for glaucoma segmentation

引用

International Journal of Information Technology (Singapore) 2025年第5期17卷 2619-2628页

作者： Banerjee, Tathagat Khan, Yusera Farooq Rafiq, Tabasum Singh, Shalini Wason, Ritika Narula, Gagandeep Singh Vellore Institute of Technology Karnataka Bengaluru India Department of Computer Science and Engineering Shri Mata Vaishno Devi University J&K Katra India National Institute of Srinagar (NIT) Jammu and Kashmir Srinagar India Jaipur Engineering College and Research Centre (JECRC) Rajasthan Jaipur India Department of Computer Science and Applications Centre for Research and Innovations in Interdisciplinary Studies BVICAM Delhi New Delhi India Guru Gobind Singh Indraprastha University (GGSIPU) Delhi Dwarka India

An accurate diagnosis is significant in preventing blindness because ophthalmology is one of the most prevalent causes of blindness worldwide. Glaucoma is diagnosed with a scanning-laser-tomography examination of the optic nerve head. The manual delineation of the optic nerve head by a skilled ophthalmologist is required for the analysis that results in a diagnosis of the illness. Transfer learning based computerized glaucoma classification has achieved effective outcomes. This study presents and validates a novel heuristic-based UNet-Inception attention framework for glaucoma optic nerve segmentation and classification. The suggested technique is based on the concept of merging the benefits of two distinct networks, such as the UNet and Inception framework for automatic segmentation of Glaucoma, along with the blend of the Harris Hawks approach for selecting impact features and a hybrid loss function. Using a database of fundus images, the proposed design was evaluated and compared to several state-of-the-art methods. The integration of the UNet-Inception architecture with the Haris Hawk Optimisation technique in the field of ophthalmology image segmentation has shown potential for substantial enhancements in terms of accuracy, efficiency, and adaptability based on the performance evaluation of this study. With a median DSC of 0.9892 for the optical nerve head (ONH) segments and 0.98718 for delineating the optic nerve head layer (RNFL), the findings show that the suggested technique performs better than the other techniques in terms of segmented images. © Bharati Vidyapeeth's institute of computer applications and Management 2025.

关键词： Glaucoma ASSESSMENT Glaucoma segmentation Harris Hawks optimization Inception Model Transfer Learning

来源：评论

学校读者我要写书评

暂无评论

Detection of Encrypted and Malicious Network Traffic using Deep Learning 1

Detection of Encrypted and Malicious Network Traffic using D...

引用

1st IEEE International Conference on Ambient Intelligence, Knowledge Informatics and Industrial Electronics, AIKIIE 2023

作者： Reddy, Pundru Chandra Shaker Shirley Muller, Priya N Koka, Sridhar Sharma, Vikas Sharma, Nipun Mukherjee, Saptarshi School of Computer Science and Engineering Manipal University Jaipur Rajasthan Jaipur India Sathyabama Institute of Science and Technology Department of Mathematics Chennai India Andhra University Computer Science and Engineering Visakhapatnam India School of Computer Science & Applications Iimt University Uttar Pradesh Meerut India Presidency University Electronics and Communication Engineering Karnataka Bangalore India Maulana Abul Kalam Azad University of Technology West Bengal India

ISBN: (纸本)9798350316469

Network traffic has increased by a factor of ten due to the meteoric rise of the Internet. The prevalence of encryption methods makes it difficult to identify malicious traffic. Reason being, without being able to decipher encrypted traffic, conventional detection methods are useless. Recent work on detecting harmful encrypted traffic has concentrated on feature extraction and the selection of deep learning techniques rather than on breaking the encryption itself. For the most part, today's edge node devices are responsible for processing massive amounts of data, extracting critical elements of network traffic, and then sending that information on to a cloud server. However, how to more rapidly and precisely identify network traffic remains a hard topic, as mobile terminal tools performance in discovering and categorizing encrypted &malicious traffic lags after. We develop a model of a convolutional-neural-network (CNN) that integrates normalized and attention processes;this model is called I-D-CNN with hexadecimal data (HexCNN-ID). Global-Attention-Block (GAB) and Category-Attention-Block (CAB) are modules of the attention mechanism that help identify and categorize network traffic. Our algorithm is able to recognize most types of network-traffic, plus encrypted &malicious traffic data, by mining efficient load information from hexadecimal network traffic. An average accuracy of 98.8% was found during experimental testing. Our methodology has the potential to significantly enhance the reliability of traffic data recognition in networks. © 2023 IEEE.

关键词： Attention mechanism CNN deep learning Traffic Data Traffic detection

来源：评论

学校读者我要写书评

暂无评论

Model using GAN for Text to Image synthesis

Model using GAN for Text to Image synthesis

引用

2022 IEEE North Karnataka Subsection Flagship International Conference, NKCon 2022

作者： Patil, Kumari Reshma Biradar, Vidyadevi G Mohan, S.G. Dileep, M.R. Clara Kanmani, A. Pramanick, Monalisa Information Science Engineering Nitte Meenakshi Institute of Technology Bengaluru India Nitte Meenakshi Institute of Technology Master of Computer Applications Bengaluru India Information Science Engineering Presidency University Bengaluru India

ISBN: (纸本)9781665453424

Due to its remarkable data-generating capabilities, generative adversarial networks have gained significant relevance in unsupervised learning. Generative adversarial networks are very much useful in generating synthetic images from the given text description. The research work presented in this paper aims at developing a text-image synthesis model to generate high resolution synthetic images based on the scenario description given in input text. The paper proposes a novel model Df-GAN which is derived from VQGAN and CLIP using transfer learning. This model is evaluated on the COCO dataset. the experimental results show that the model can generate high resolution images. The model achieves FID score of 18.26 which is satisfactory. © 2022 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Performance Indicators To Improve The Quality in Indian Educational Institutions Using GRD Ensemble Methods 3

Comparative Analysis of Performance Indicators To Improve Th...

引用

3rd International Conference on Advance Computing and Innovative Technologies in engineering, ICACITE 2023

作者： Babu, B Kamraj D Hemavathy, P. Majeed, Ali Hussein Alkhafaji, Mohammed Ayad Nasser, Sarmad Jaafar Fouad, Laith Hindustan Institute of Technology and Science Department of Computer Applications India Hindustan Institute of Technology and Science Department of Information Technology India National University of Science and Technology Collage of Engineering Dhi Qar Iraq Al-Farahidi University Medical Laboratory Techniques Department Baghdad Iraq

ISBN: (纸本)9798350399264

The Indian government uses a mechanism called the National Institutional Ranking Framework (NIRF) to rate those institutions of higher education. The NIRF uses five metrics, including research and development, teaching and learning-resources, graduation-outcome, outreach and inclusivity, and perception, to rank institutions. However, there is ongoing debate about the comparability and accuracy of the NIRF metrics. This study aims to compare the NIRF metrics used for ranking higher education institutions in India. In this study, GRD stands for machine learning algorithms including Gradient Boosting, Random Forest, and Decision Tree are used together with a mixed-methods strategy that combines qualitative and quantitative research techniques. The findings of the study suggest that while the NIRF metrics have some strengths and limitations, they provide a valuable tool for ranking higher education institutions in India. The study's results will be useful for stakeholders in the education sector, including policy makers, higher education institutions, and stakeholders, gain a better understanding of the NIRF measures and their applicability for ranking higher education institutions in India. Finding the key performance indicators (KPIs) that can be used to assess and improve the calibre of instruction in Indian educational institutions. The study also emphasises the necessity of continuing data gathering and analysis to maintain the usefulness and efficacy of these KPIs. In the conclusion, this study delivers insightful information about how data analysis contributes to raising educational standards in India and offers actionable advice for institutions wishing to improve. © 2023 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

The Role of 5G Networks in Energy-Efficient Smart Cities Development using IoT 2

The Role of 5G Networks in Energy-Efficient Smart Cities Dev...

引用

2nd International Conference on Applied Artificial Intelligence and Computing, ICAAIC 2023

作者： Govindasamy, Chinnaraj Dayana, T.R Nisha Vasu, V. Tamilarasi, A. Prakash, R.B.R. Kalaivani, R. Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Tamilnadu Chennai602105 India Vels Institute of Science Technology and Advance Studies Department of Computer Science India St. Claret College Department of Commerce Jalahalli Karnataka Bengaluru560013 India Kongu Engineering College Department of Computer Applications Perundurai India Electrical and Electronics Engineering Koneru Lakshmaiah Education Foundation vaddeswaram522302 India AP/ECE Erode Sengunthar Engineering College India

ISBN: (纸本)9781665456302

In theory, residents in 'smart cities' would have access to a wide range of amenities designed to enhance their daily lives by making better use of public resources and providing a more satisfying experience overall. The efficiency of these services depends on the information sharing across disparate systems serving similar functions. Large amounts of data with a variety of sophisticated, application-specific needs will likely be sent throughout the information exchange process. By better management of public resources and a focus on resident comfort, infrastructure upkeep, and environmental sustainability, 'smart cities,' which rely on ICT, aim to raise the bar on service quality. Fifth-generation (5G) wireless mobile communication paves the way for a new kind of communication network that can connect everyone and everything. Impacting economies and communities, 5G will offer the connectivity infrastructure required by many smart city applications. A glimpse into the future of urban areas may be seen in the rise of 'smart cities' and the IoT. The integration of many systems aimed to monitor varied components of the smart city may be utilized to generate a more sustainable and securer city. This research study presents a construction that mixes the data from diverse systems. In order to lessen the quantity of produced traffic in the 5G network and subsequently the energy consumption, suggest the usage of data aggregation in each antenna. A summary of 5G communication networks and different 5G technologies utilized in smart cities to promote sustainability is provided. The sustainability metrics for 5G networks are then examined across the environmental, social policy, and economic aspects, as well as sub-dimensions such as energy efficiency, energy usage, carbon footprint, contamination, cost, health, safety, and security. The findings indicate that while in an effort to address sustainability in 5G technology and intelligent buildings, the bulk of research publicat

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

Optimizing Supply Chain Operations through Machine Learning: Opportunities and Challenges

Optimizing Supply Chain Operations through Machine Learning:...

引用

2025 International Conference on Pervasive Computational Technologies, ICPCT 2025

作者： Santhakumar, D. Soundararajan, Gopalakrishnan Chintala, Suman Bharath, E. Murthy Inumula, Krishna Chouhan, Kuldeep Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Thandalam Tamil Nadu Chennai602105 India Muscat College Ruwi Oman Business Intelligence Architect United States C K College of Engineering & Technology Anna University Department of Artificial Intelligence & Data Science Tamil Nadu Cuddalore India Maharashtra Pune411057 India Sharda School of Engineering and Technology Sharda University Department of Computer Science and Applications Greater Noida201310 India

ISBN: (纸本)9798331508685

In order to create enduring partnerships that are essential to attaining long-term economic success, supply chain management, or SCM, is essential. Strict standards and decision-making procedures are necessary for efficient SCM, and they have a big influence on the final results. In order to efficiently manage inventory levels and logistical procedures, this study offers a complex ML system that combines demand forecasts and optimisation methods. For predicting demand, the approach uses a Generative Adversarial Networks (GAN) model, taking advantage of its capacity to process time-series data and identify intricate trends. The algorithm achieves an impressive 96.4% forecasting of demand accuracy by examining extensive historical sales data and a variety of supply chain variables. In order to optimise inventory rules, the investigation also uses optimisation techniques, particularly Genetic Algorithms (GA) in conjunction with Simulated Annealing (SA). The model demonstrated significant improvements when implemented to an actual commercial logistics system. Notably, it reduced storage expenses by 19% and increased order fulfillment rates by 24%, proving its capacity for combining service standards with financial efficiency. The findings highlight the significant impact of ML on improving supply chain efficiency and show how it can result in significant cost savings and improve service quality. © 2025 IEEE.

关键词： Simulated annealing

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：