检索结果-内蒙古大学图书馆

2024 IEEE International Conference on computer Vision and Machine Intelligence, CVMI 2024

作者： Samridhi, Kumari Sinha, Bam Bahadur Das, Trinanjan Indian Institute of Information Technology Electronics and Communication Engineering Ranchi India National Institute of Technology Computer Science and Engineering Sikkim India Indian Institute of Information Technology Computer Science and Engineering Ranchi India

ISBN: (纸本)9798350376876

Recommender systems utilize algorithms and data to predict user preferences based on their past choices. While these systems can be highly accurate, this increased accuracy can sometimes lead to predictability and monotony. In the realm of big data, recommender systems are both prevalent and valuable. Research on these systems has intensified in recent years, accompanied by a growing number of datasets. This paper examines the application of Variational Autoencoder (VAE)-based recommender systems using the MovieLens 1M and BookCrossing datasets. The study primarily evaluates the performance of the VAE model using Root Mean Square Error (RMSE) as the key metric. The VAE model was trained on these datasets to predict user preferences and generate personalized recommendations. Experimental results revealed an RMSE of less than 1 for both datasets, indicating the model's proficiency in accurately estimating user ratings for items. These findings suggest that VAE-based recommender systems are promising for enhancing recommendation accuracy and personalization. This research contributes to the understanding of VAE models within the context of recommender systems and provides insights for future research and potential improvements in this field. © 2024 IEEE.

关键词： Data accuracy

来源：评论

学校读者我要写书评

暂无评论

Customized Graph-Cut Segmentation with Superpixels for Snowfall Detection on Solar Panels 4

Customized Graph-Cut Segmentation with Superpixels for Snowf...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Pavithra, V. Danisha, B.R. Divyadharshini, V. Koresh, H. James Deva Kpr Institute of Engineering and Technology Department of Computer Science and Engineering Coimbatore India Kpr Institute of Engineering and Technology Department of Electronics and Communication Engineering Coimbatore India

ISBN: (纸本)9798331523923

Snow accumulation on solar panels reduces their performance in energy generation regions. Hence certain image processing methods were developed for segmenting snow from the normal areas of solar panels. Graph Cut and Flood Fill are the popular semi-automatic method used for this application where it relies on detecting an efficient region for marking the segmentation process. Similarly, the manual intervention fails to provide consistent results in such methods. Therefore, a customized graph cut methodology is proposed in this work by combining super pixel-based feature extraction and k-means clustering. At first, the input images are preprocessed by dividing the pixels to form super pixels as a group to reduce the computational complexity without losing the meaningful information. Features like intensity, edge density, texture, and color are extracted from these super pixel groups for segmenting the snow-covered regions on a solar panel. Further, the extracted features are normalized by a k-means clustering algorithm for identifying the highest intensity regions to observe the snow-covered regions. A graph cut-based segmentation technique is applied at the end to ensure the precise boundary delineation. The work is also incorporated with several post-processing techniques for improving the segmentation mask quality. This proposed method is evaluated against Graph cut and flood fill and satisfied with an average dice similarity coefficient of 93.09% and 95.11%. © 2025 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Pricing mechanism for constrained driverless shared buses in a smart city

引用

Journal of Intelligent and Fuzzy Systems 2025年第1-2期48卷 109-122页

作者： Jin, Yong Yang, Huizhen School of Computer Science and Engineering Changshu Institute of Technology Changshu China Changshu Dawei Transportation Technology Co. Ltd Changshu China

The price of passengers is closely related to the travel cost of passengers and the revenue of driverless shared bus. Therefore, the design of pricing mechanism is important to improve the market efficiency of driverless shared bus scheduling. To address these issues, we formulate the social optimization passenger selection problem to maximize the social welfare such that number of passengers taking each driverless shared bus is no more than its capacity and all the driverless shared buses can arrive at the corresponding destinations before the deadlines of the passengers, and propose the auction-based truthful pricing mechanism, Driverless Shared Bus Pricing (DSBP) mechanism, for deadline tightened pricing problem of driverless shared buses. Through both rigorous theoretical analysis and extensive simulations, we demonstrate that the proposed mechanism achieves computational efficiency, individual rationality, truthfulness, and guaranteed approximation. © 2025 – IOS Press. All rights reserved.

关键词： Smart city driverless shared bus pricing scheduling

来源：评论

学校读者我要写书评

暂无评论

Feature engineering Techniques for Stegware Analysis: An Extensive Survey 1

引用

1st International Conference on Intelligent Computing for Sustainable Development, ICICSD 2023

作者： Anitha, M. Azhagiri, M. Department of Computer Science and Engineering SRM Institute of Science and Technology Ramapuram Chennai India Department of Computer Science and Engineering SRM Institute of Science and Technology Ramapuram Chennai India

ISBN: (数字)9783031612985

ISBN: (纸本)9783031612978

The art of hiding secret text within an innocuous cover medium is steganography. Steganalysis is the counterpart of steganography which focuses on the detection and extraction of the secret text from the medium. Feature engineering is the crucial field in Stegware Analysis which intends to identify more specific features, focusing on the accuracy and efficiency. Feature engineering is a process in Machine learning where the features of any dataset are selected and extracted for further use. Feature engineering is the process of extracting, transforming and selecting the most relevant features form the data that aids in discriminating between the stego and cover image. This is because, most of the time, the data will be in a raw format. Any ML model needs the data to be pre-processed and kept ready to train the model. Thus, from the pool of raw data, the required data needs to be selected and can be used in training the model. Further, the data at point needs to be extracted to get the precise data. The scope of the work is to identify the various feature engineering techniques available in practice and efficiently use them to achieve high accuracy and precision in the system. The survey focuses on the several feature selection and extraction techniques like filter method, wrapper method and embedded methods. Correlation being one of the feature selection methods is focused;while statistical moments computes the mean, variance and skewness of the feature. The extraction method holds the Computation of Invariants and other such. Comparative study is made on both the methods to understand the concepts with ease. The work starts by taking a sample from the dataset and few feature extraction techniques are applied on the same. Then the original image is compared with the extracted images with the view of histogram. The paper gives valuable insights into the effectiveness of different feature engineering techniques using the dataset and underscores the importance of featu

关键词： Steganography

来源：评论

学校读者我要写书评

暂无评论

Automated Immune Cell Classification using Image Processing Techniques 6

Automated Immune Cell Classification using Image Processing ...

引用

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

作者： Sathiyaprasad, B. Reddy, Arva Hari Vardhan Abdurrahman, Usama Micheal, A. Annie Department of Computer Science and Engineering Sathyabama institute of science and technology Chennai India

ISBN: (纸本)9798331522667

Advances in immunological research are essential for elucidating immune responses and developing targeted therapeutic approaches. This study proposes an automated method for immune cell classification leveraging machine learning and image processing techniques. A novel framework is introduced, combining high-resolution imaging with computational algorithms to accurately classify various immune cell types from biological samples. The methodology incorporated preprocessing steps, like normalization and noise reduction. Then, deep learning models, such as CNNs and SVMs, will be applied for feature extraction and classification. These models were trained on annotated datasets derived from flow cytometry and microscopy, demonstrating better accuracy and reliability. Results demonstrate an improvement in processing speed and accuracy of classification over traditional approaches, which underlines the importance of automation in immunological diagnostics. The data obtained can be used in high-throughput immunotherapy and disease diagnostic screening;it allows for the identification of immune cell populations within a short period and therefore improves research efficiency. The work provides a basis for real-time analysis and incorporation of multiscale datasets that will help to better understand immunity and its associated disorders. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Revolution of Self-Learning in Education from Traditional Pedagogy

Revolution of Self-Learning in Education from Traditional Pe...

引用

2025 International Conference on Pervasive Computational Technologies, ICPCT 2025

作者： Aggarwal, Aarush Pannu, Husanbir Singh Kaur, Varleen Sidhu, Sanmeet Thapar Institute of Engineering and Technology Computer Science and Engineering Patiala India Thapar Institute of Engineering and Technology Centre for Training & Development Patiala India

ISBN: (纸本)9798331508685

The transition from traditional pedagogy to self-learning represents a significant shift in educational practice, propelled by technological advancements and the evolving needs of learners. This study explores the evolution from ancient Gurukul systems to modern digital learning platforms, incorporating data from student survey responses. The analysis reveals a marked preference for hybrid learning models (62.4%) and the widespread use of online resources among participants (91%). Supported by established learning theories and quantitative analysis, the findings indicate that self-learning enhances critical thinking, adaptability, and lifelong learning competencies. The results suggest a future where technology-integrated, personalised learning complements conventional classroom instruction, fostering more independent and proficient learners. © 2025 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Investigation of sustainable strategies with metaheuristic algorithm on surface roughness, cutting temperature, and chip morphology during machining of Ti6Al4V alloy

引用

International Journal of Machining and Machinability of Materials 2024年第3期26卷 223-243页

作者： Misra, Sutanu Kumar, Yogesh Paul, Goutam Pradhan, Buddhadeb Department of Mechanical Engineering University of Engineering and Management Kolkata India Department of Mechanical Engineering National Institute of Technology Patna Bihar Patna India Department of Computer Science and Engineering University of Engineering and Management Kolkata India

This research work explores the effects of dry, liquid N2-based cryogenic cooling and cryogenic plus MQL hybrid strategy on surface roughness, rake surface temperature, principal cutting-edge temperature, auxiliary cutting-edge temperature, and chip morphology to understand the machinability of Ti-6Al-4V alloy using sustainable manufacturing techniques. Here, a metaheuristic algorithm approach has been introduced to determine the experimental data’s accuracy, which is approximately 75% for further investigation. Logistic regression and support vector machine provided higher accuracy and best fitted with the dataset and problem formulation. During this work, it has been observed that chip morphology is influenced by cutting parameters and lubrication strategy. The cryogenic plus MQL hybrid approach is the best method over cryogenic cooling by decreasing the heat by 12% and giving 8% better surface quality. Copyright © 2024 Inderscience Enterprises Ltd.

关键词： Titanium alloys

来源：评论

学校读者我要写书评

暂无评论

Exploration of Semantic Priming Studies in Native Language of Children:Study on Bengali L1 and English L2 Bilingual Children

引用

SN computer science 2025年第2期6卷 1-18页

作者： Banerjee, Jaya Nithin, Kota Sai Sai, Uppalapati Hari Krishna Chakraborty, Baisakhi Basu, Anupam Department of Computer Science & Engineering National Institute of Technology West Bengal Durgapur 713209 India National Institute of Technology West Bengal Durgapur India Department of Computer Science & Engineering Indian Institute of Technology (IIT) Kharagpur 721302 India

Word Priming is an event in which prior subjection to a particular word impacts the reply of the individual to the upcoming correlated word. The response time is inferred to be less in identifying the target word preceded by an associated word compared to the word in seclusion or isolation as per the experiments undertaken on an Indian language where research incorporates Bengali-speaking children. Bengali is an important language of consideration on national and international platforms. A set of twenty-one school-going children with ages in the range of 7 to 10 years are subjected to a word priming assessment. Analysis established a positive impact of word prime in the reaction of a set of children aged seven to ten to certain listed words Due to the presence of word prime, the average error measure of the lower progressing answerers reduced by a significant 19.8%. With reference to the Bengali script, the average error measure is 10 percent. With the involvement of the word prime, the mean error measure is 1.6 percent. This paper proposes first of its kind of research studies and analysis with regard to the positive effect of word priming on the response time of target word identification on Bengali speaking bi-lingual dyslexic children to yield positive results. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Bengali Children English Learning impairment Priming Psycholinguistics Second language Word identification Word priming

来源：评论

学校读者我要写书评

暂无评论

Enhancing Diabetic Retinopathy Diagnosis with ResNet-50-Based Transfer Learning: A Promising Approach

引用

Annals of Data science 2024年第1期11卷 1-24页

作者： Karthika, S. Durgadevi, M. Rani, T. Yamuna Department of Computer Science and Engineering SRM Institute of Science and Technology College of Engineering and Technology Vadapalani Campus Tamil Nadu Chennai India ACMS Railway Hospital ICF Chennai Tamil Nadu India

Diabetic retinopathy is considered the leading cause of blindness in the population. High blood sugar levels can damage the tiny blood vessels in the retina at any time, leading to retinal detachment and sometimes glaucoma blindness. Treatment involves maintaining the current visual quality of the patient, as the disease is irreversible. Early diagnosis and timely treatment are crucial to minimizing the risk of vision loss. However, existing DR recognition strategies face numerous challenges, such as limited training datasets, high training loss, high-dimensional features, and high misclassification rates, which can significantly affect classification accuracies. In this paper, we propose a ResNet-50-based transfer learning method for classifying DR, which leverages the knowledge and expertise gained from training on a large dataset such as ImageNet. Our method involves preprocessing and segmenting the input images, which are then fed into ResNet-50 for extracting optimal features. We freeze a few layers of the pre-trained ResNet-50 and add Global Average Pooling to generate feature maps. The reduced feature maps are then classified to categorize the type of diabetic retinopathy. We evaluated the proposed method on 40 Real-time fundus images gathered from ICF Hospital together with the APTOS-2019 dataset and used various metrics to evaluate its performance. The experimentation results revealed that the proposed method achieved an accuracy of 99.82%, a sensitivity of 99%, a specificity of 96%, and an AUC score of 0.99 compared to existing DR recognition techniques. Overall, our ResNet-50-based transfer learning method presents a promising approach for DR classification and addresses the existing challenges of DR recognition strategies. It has the potential to aid in early DR diagnosis, leading to timely treatment and improved visual outcomes for patients. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2023. Springer

关键词： Blood vessels

来源：评论

学校读者我要写书评

暂无评论

A comprehensive analysis of threat vectors in software-defined networking

引用

Multimedia Tools and Applications 2024年第39期83卷 86791-86832页

作者： Dahiya, Seema Sehrawat, Harkesh Kharb, Seema Siwach, Vikas University Institute of Engineering and Technology Maharshi Dayanand University Rohtak Rohtak India Department of Computer Science and Engineering SRM University Sonepat Sonipat India

In recent years, cyber-attacks have become more frequent and advanced, targeting critical infrastructure, businesses, homes, and government agencies. Detecting and preventing these attacks at the earliest stage possible is crucial to avoid serious harm, including data breaches. Researchers and experts in cybersecurity are looking to Software-Defined Networking (SDN) technologies as a solution to enhance real-time defense against cyber-attacks. SDN revolutionizes traditional networking by offering unprecedented flexibility and control over network resources, making it possible to adapt quickly to emerging threats. SDN provides logically centralized network control by separating the control plane from the data plane. This enables network programming and can block network activity when malicious movement is spotted. This paper presents a comprehensive analysis of threat vectors in SDN. It examines the various ways in which SDN networks are vulnerable to cyber-attacks, including network infrastructure, application layer, and SDN controller. The paper also evaluates the effectiveness of existing security measures and proposes future research directions to enhance SDN security. Overall, the paper highlights the potential of SDN as a powerful tool in the fight against cybercrime and emphasizes the importance of continued research and development to improve SDN security. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Internet of things

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：