检索结果-内蒙古大学图书馆

GAN-Based Image Restoration and Colorization 8th

GAN-Based Image Restoration and Colorization

8th International Conference on Emerging Research in Computing, Information, Communication and Applications, ERCICA 2023

作者： Kabeer, Aliyah Tanna, Manali Milinda, K.N. Rizwan, Mohammed Uzair Agarwal, Pooja Department of Computer Science and Engineering PES University Bangalore India

ISBN: (纸本)9789819976324

The importance of images in today’s society has made it essential for them to be of the highest quality and visually indicative of their essential traits and attributes. Significant research has been done individually on colorizing and restoring degraded images. Separate studies of Generative Adversarial Networks (GANs) have also been conducted in each of these fields. However, it’s rare to find GAN architectures that can focus on both the tasks at once. With an emphasis on nature photographs, this study proposes a unique GAN architecture that was trained on a customized image dataset including images of landscapes, flowers, and mountains combined with the GoPro Light dataset. The proposed methodology makes use of a combination of different loss functions that enable the model to focus on both tasks simultaneously. Alongside the L1 loss and adversarial loss traditionally used in GANs, the proposed model includes the perceptual loss that performs feature-wise comparisons between images to restore its inherent features. To prove that the GAN can perform both restoration and colorization, its performance has been compared with other models that perform each of the two tasks separately. The model is tested on the curated dataset and evaluated on image-specific metrics like peak signal-to-noise ratio (PSNR) and structural similarity Index (SSIM). The model gives results that compare well with existing models, and it can colorize and restore images that have been degraded with motion blur or camera misfocus—successfully striking a good balance between the two tasks. The paper concludes by providing insight into the future work that can be carried out. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Restoration

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-based Classification of Infant Cries for Parental Assistance: A Study using MFCC and CNN Technique 3

Deep Learning-based Classification of Infant Cries for Paren...

引用

3rd International Conference on Electronics and Renewable Systems, ICEARS 2025

作者： Mala, B.M. Darandale, Smitha Sandeep Gitam School of Technology Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798331509675

Worldwide Approximate count of 130 million babies were born per annum. Maintaining newborn babies is a great difficulty, mainly for first-time parents. However, intimations from experienced parents, books, and videos help to a certain extent but not significantly because of difficulty understanding the meaning of Infant cries. Researchers have proposed several techniques using machine learning and artificial intelligence. In this work, we try to leverage deep learning-based techniques such as convolutional neural networks (CNN) to identify the infant crying. Infant crying is further classified into four classes (inclusive of pain, hunger, sleepiness, and wet diaper). The MFCC (Mel-Frequency Cepstral Coefficients) technique is used for feature extraction, as it efficiently captures audio characteristics from crying sounds. In this study, will compare the various existing machine learning models with our proposed model. Among the models evaluated, MFCC combined with Convolutional Neural Networks (CNN) achieves the highest accuracy of 95.5%, for classifying the infant cry and reasoning. © 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

Towards True Decentralization: Development, Testing and Evaluation of a Novel Blockchain Consensus Protocol 1

引用

56th International Conference on Asia Pacific Advanced Network, APANConf 2023

作者： Wimal, Kesara Liyanage, Geethapriya School of Computer Science and Engineering University of Westminster London United Kingdom Department of Computer Science and Engineering University of Moratuwa Moratuwa Sri Lanka

ISBN: (数字)9783031511356

ISBN: (纸本)9783031511349

The blockchain technology that powers the Bitcoin network was unveiled to the world in 2008. After more than a decade of research and development, a number of blockchain systems have been put out by both industry and academics. This research undertaking brings attention to a significant issue that impacts both blockchain users and cryptocurrency investors. The concern regarding true decentralization in existing blockchain platforms has long been a prominent topic within the blockchain community. Although Proof of Work (PoW), Proof of Stake (PoS), and hybrid approaches are commonly employed in blockchain systems, both methods exhibit limitations concerning decentralization. Despite the emergence of alternative consensus protocols, none have thus far achieved complete decentralization. This project aims to devise and implement an innovative consensus protocol that circumvents tendencies toward centralization, accommodates any number of network participants, eliminates the requirement for specialized hardware, reduces energy consumption, and fosters network activities. The proposed protocol advocates for a democratic and equitable approach to blockchain consensus. A comprehensive evaluation is conducted to assess the degree of achieved decentralization. The solution successfully demonstrates genuine decentralization. The test results also indicate enhanced security, and high performance, while obviating the need for specialized hardware and reducing energy consumption. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

SlidEar: Exploring eSense in-Ear Wearable for Voice-Assisted Smart Slide Supervision 17

SlidEar: Exploring eSense in-Ear Wearable for Voice-Assisted...

引用

17th International Conference on COMmunication Systems and NETworkS, COMSNETS 2025

作者： Mondal, Susmita Zingre, Sameeran Ravishankar Chakraborty, Suchetana Indian Institute of Technology Department of Computer Science and Engineering Jodhpur India

ISBN: (纸本)9798331531195

In corporate settings, conferences, or classrooms, an orator relies on manual slide transitions, which can disrupt their presentation flow. Presentation devices can be inaccessible due to the physical limitations of individuals, reducing engagement with the audience. Traditionally used remote-controlled wireless presenters are hand-held devices that usually require a compatible connector slot for the presentation device and partially engage one hand of the orator. To ease the hand-free presentation of slides, we introduce SlidEar, a voice-assisted smart slide supervision successfully tested on eSense in-ear wearables. SlidEar leverages voice recognition fusion with wearable sensors to facilitate seamless slide operations. It allows real-time feedback on natural language commands during the presentation of slides. Compared with conventional methods, SlidEar enhances engagement and accessibility through hand-free in-ear placement and helps the orator focus on delivering their content without any disruption or distraction. The evaluation shows promising results that improve the presentation experience profusion. SlidEar significantly reduces errors and can be widely adopted in diverse presentation scenarios. © 2025 IEEE.

关键词： Speech recognition

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 Process Oriented Integration Model for Smart Health Services

引用

Intelligent Automation & Soft Computing 2023年第2期35卷 1369-1386页

作者： Farzana Kausar Gondal Syed Khuram Shahzad Muhammad Arfan Jaffar Muhammad Waseem Iqbal Department of Computer Science Superior UniversityLahore54600Pakistan Department of Informatics and Systems University of Management and TechnologyLahore54000Pakistan Faculty of Computer Science&IT Superior UniversityLahore54600Pakistan Department of Software Engineering Superior UniversityLahore54600Pakistan

Cities are facing challenges of high rise in population number and con-sequently need to be equipped with latest smart services to provide luxuries of life to its *** integrated solutions are also a need to deal with the social and environmental challenges,caused by increasing ***,the development of smart services’integrated network,within a city,is facing the bar-riers including;less efﬁcient collection and sharing of data,along with inadequate collaboration of software and *** to resolve these issues,this paper recommended a solution for a synchronous functionality in the smart services’integration process through modeling *** this integration modeling solution,atﬁrst,the service participants,processes and tasks of smart services are identiﬁed and then standard illustrations are developed for the better understand-ing of the integrated service group *** process modeling and notation(BPMN)language based models are developed and discussed for a devised case study,to test and experiment i.e.,for remote healthcare from a smart *** research is concluded with the integration process model application for the required data sharing among different service *** outcomes of the modeling are better understanding and attaining maximum automation that can be referenced and replicated.

关键词： Process modeling business process business process integration business process modeling and notation

来源：评论

学校读者我要写书评

暂无评论

Enhance Vertical Handover Security During Execution Phase in Mobile Networks

引用

computers, Materials & Continua 2022年第8期72卷 3863-3875页

作者： Omar Khattab Department of Computer Science and Engineering Kuwait College of Science and Technology(KCST)Kuwait

The Vertical Handover(VHO)is one of the most vital features provided for the heterogeneous mobile *** allows Mobile Users(MUs)to keep ongoing sessions without disruption while they continuously move between different Radio Access Technologies(RATs)such as Wireless Fidelity(Wi-Fi),Global System for Mobile Communication(GSM),Universal Mobile Telecommunications System(UMTS),Long Term Evolution(LTE)and Fifth Generation(5G).In order to fulfill this goal,the VHO must comply to three main phases:starting of collecting the required information and then passing it for decision phase to obtain the best available RAT for performing VHO by execution phase ***,the execution phase still encounters some security issues which are exploited by hackers in launching malicious attacks such as ransomware,fragmentation,header manipulation,smurf,host initialization,reconnaissance,eavesdropping,Denial of Service(DoS),spoofing,Man in the Middle(MITM)and *** paper thoroughly studies the recent security issues for hundreds VHO approaches found in the literature and comes up with a secure procedure to enhance VHO security during execution phase.A numerical analysis results of the proposed procedure are effectively evaluated in terms of security and signaling *** with the recent related work found in literature,the analysis demonstrates that the security is successfully improved by 20%whereas signaling cost is maintained as in non-proposed procedure.

关键词： Vertical handover security mobile networks wireless networks heterogeneous wireless networks

来源：评论

学校读者我要写书评

暂无评论

Blockchain Technology: Revolutionizing Trust, Transparency, and Transaction Efficiency

Blockchain Technology: Revolutionizing Trust, Transparency, ...

引用

2024 International Conference on Knowledge engineering and Communication Systems, ICKECS 2024

作者： Lal, Roop Chhabra, Arzoo Singla, Sanjay Sharma, Deepansh Chandigarh University Department of Computer Science and Engineering Mohali India

ISBN: (纸本)9798350359688

Blockchain technology is playing a transformative role in reshaping how trust is established, information is shared transparently, and transactions are conducted efficiently. This research paper explores the current state of blockchain, drawing insights from globally top-cited papers. Utilizing the Web service, we uncover key exploration themes such as profitable benefit, blockchain technology, initial coin offerings, fintech revolution, and participating frugality. The study takes a close look at the decentralized, secure, and fault-tolerant nature of blockchain, tracing its history, architecture, and consensus algorithms. Security and privacy aspects of blockchain are also examined, including agreement algorithms, hash-chained storage, mixing protocols, and zero-knowledge attestations. Additionally, the paper explores the evolving technology landscape of blockchain, considering its groups, service modes, and operational conditions. This comprehensive review not only addresses gaps in current research but also highlights future directions and challenges, showcasing the transformative potential of blockchain technology for both society and industry. © 2024 IEEE.

关键词： Distributed ledger

来源：评论

学校读者我要写书评

暂无评论

A Knowledge Discovery Framework for Maritime Intelligence on Dark Vessels 17

A Knowledge Discovery Framework for Maritime Intelligence on...

引用

17th International Conference on COMmunication Systems and NETworkS, COMSNETS 2025

作者： Jayaswal, Bharat Ghosh, Soumya K. Indian Institute of Technology Department of Computer Science and Engineering Kharagpur India

ISBN: (纸本)9798331531195

Maritime Intelligence is essential for safeguarding maritime interests of coastal nations. Traditionally, vessel movements are tracked using self-reported positions via Automatic Identification System (AIS) transponders. However, vessels engaged in illicit activities often disable their AIS transponders to evade detection, thereby going dark. Satellite-based sensors, such as Synthetic Aperture Radar (SAR) and Visible Infrared Imaging Radiometer Suite (VIIRS) can be used to detect Dark Vessels. However, extraction of actionable insights for maritime intelligence on Dark Vessels is posed with several challenges. The spatial estimation of activities of vessels over various time periods is complicated due to spatial and temporal overlaps in satellite scans. This poster presents our ideas on knowledge discovery framework that integrates spatial analytics methods to gain actionable insights on Dark Vessels. Preliminary results are shown on Global Fishing Watch (GFW) Dataset of Dark Vessels. © 2025 IEEE.

关键词： Radar imaging

来源：评论

学校读者我要写书评

暂无评论

Predictive Insights for Enhancing Customer Retention in Banking: Integrating Power BI and Random Forest 3rd

Predictive Insights for Enhancing Customer Retention in Bank...

引用

3rd International Conference on Machine Vision and Augmented Intelligence, MAI 2023

作者： Sumanasri, A. Vyshnavi, M. Manogna, R. Nikhila Keerthi, Kelam Kesavarshini, A. Pande, Sagar Dhanraj School of Computer Science Engineering VIT-AP University Andhra Pradesh Amaravati India Department of Computer Science and Engineering School of Engineering and Technology Pimpri Chinchwad University Maharashtra Pune India

ISBN: (纸本)9789819743582

The main goal of the study is to solve the problem of losing customers or clients in various financial organizations, especially in the banking sector. It investigates the use of Random Forest algorithm and the Power BI dashboard which helps to forecast churn and improve retention strategies. Historical data—transactions, demographics, and usage patterns—is collected and a thorough analyzation is done with the help of Power BI to provide a dynamic dashboard that provides insights in real-time. Combining data analytics technologies and predictive skills with their retention initiatives can help banks increase their efficacy and efficiency. Economic loss and operational difficulties are brought on by customer attrition. The outcome of this study suggests a method for forecasting customer attrition in banks that combines Power BI’s amazing data visualization techniques with Random Forest’s highly accurate predictive skills. The Random Forest algorithm integrates multiple decision trees to make predictions in a precise and expandable way. Moreover, it has the capability of handling large data sets. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Sales

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：