检索结果-内蒙古大学图书馆

8th International Conference on Inventive Computation Technologies, ICICT 2025

作者： Ramya, R. Jebathangam, J. Department of Computer Science Vels Institute of Science Technology & Advanced Studies(VISTAS) Chennai India

ISBN: (数字)9798331512248

ISBN: (纸本)9798331512255

The escalating problem of plastic pollution in aquatic environments poses a significant threat to global ecosystems. Among the various forms of plastic debris, floating macroplastics are particularly persistent and visually conspicuous, demanding effective monitoring and quantification strategies. Traditional methods for surveying plastic pollution, such as manual collection and visual observation, are often labor-intensive, geographically limited, and struggle to provide the comprehensive data required for effective mitigation strategies. However, existing detection methods primarily rely on manual surveys or simplistic computer vision approaches, which can be inaccurate and inefficient. To enhance the detection efficiency of macroplastics in waterways, a deep learning-based model was utilized, incorporating CSPDarknet, Bidirectional Feature Pyramid Network (BiFPN), and YOLOv7. This comprehensive approach addresses the global challenges introduced by macroplastic pollution and assesses its implications for environmental sustainability and public health. The experimental findings reveal that the proposed model showcases remarkable effectiveness and impressive efficiency, enabling the seamless automated identification of macroplastics on the waterways. The model delivers impressive detection accuracy (mAP) of 93.2 percent and effectively adapts to variations in object size and image quality. The model generates remarkable and more effective results when compared with the existing methods. Furthermore, its accuracy has improved by 2.3 to 2.9 percent. © 2025 IEEE.

关键词： BiFPN computer Vision CSPDarknet53 Macroplastic Detection Object Detection YOLO V7

来源：评论

学校读者我要写书评

暂无评论

Clients Help Clients: Alternating Collaboration for Semi-Supervised Federated Learning 40

Clients Help Clients: Alternating Collaboration for Semi-Sup...

引用

40th IEEE International Conference on Data Engineering, ICDE 2024

作者： Jiang, Zhida Xu, Yang Xu, Hongli Wang, Zhiyuan Qiao, Chunming School of Computer Science and Technology University of Science and Technology of China China Suzhou Institute for Advanced Research University of Science and Technology of China China University at Buffalo Department of Computer Science and Engineering The State University of New York United States

ISBN: (纸本)9798350317152

Federated learning (FL) provides a distributed framework for multiple clients to collaboratively train models without exposing raw data. Most FL research assumes that all clients have fully labeled data, which is impractical for many real-world applications. To this end, we focus on semi-supervised FL (SSFL), where data samples of each client are partially labeled. However, existing SSFL methods ignore two inherent characteristics of FL: limited communication resources and heterogeneous data distribution, which severely hinder convergence stability and efficiency. This paper proposes a novel SSFL mechanism, called FedAC, to address the above two challenges by alternating client-to-client (C2C) collaboration. Specifically, we group all clients using different clustering strategies at two different training stages. During each global round, FedAC first performs similarity clustering based on local data distribution, which gathers the knowledge from similar clients to generate high-quality pseudo-labels for unlabeled data. Then the clients are re-grouped using dissimilarity clustering strategy to approximate the IID setting at the cluster level, thereby alleviating the bias induced by Non-IID data. FedAC adopts a reinforcement learning algorithm to achieve a balance between labeling assistance from similar clients and unbiased optimization from dissimilar clients. Extensive evaluations demonstrate that FedAC can improve model accuracy and save up to 59.65% of communication costs compared with existing benchmarks. © 2024 IEEE.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Parallel Repetition of k-Player Projection Games 27

Parallel Repetition of k-Player Projection Games

引用

27th International Conference on Approximation Algorithms for Combinatorial Optimization Problems, APPROX 2024 and the 28th International Conference on Randomization and Computation, RANDOM 2024

作者： Bhangale, Amey Braverman, Mark Khot, Subhash Liu, Yang P. Minzer, Dor Department of Computer Science and Engineering University of California RiversideCA United States Department of Computer Science Princeton University NJ United States Department of Computer Science Courant Institute of Mathematical Sciences New York University NY United States School of Mathematics Institute for Advanced Study PrincetonNJ United States Department of Mathematics Massachusetts Institute of Technology CambridgeMA United States

We study parallel repetition of k-player games where the constraints satisfy the projection property. We prove exponential decay in the value of a parallel repetition of projection games with a value less than 1. ... 详细信息

ISBN: (纸本)9783959773485

关键词： Multiplayer games Parallel Repetition Projection games

来源：评论

学校读者我要写书评

暂无评论

Unsupervised spoken term discovery using pseudo lexical induction

引用

International Journal of Speech Technology 2023年第3期26卷 801-816页

作者： Sudhakar, P. Sreenivasa Rao, K. Mitra, Pabitra Advanced Technology Development Centre Indian Institute of Technology West Bengal Kharagpur721302 India Department of Computer Science and Engineering Indian Institute of Technology West Bengal Kharagpur721302 India

An unsupervised spoken term discovery task aims to capture the pattern similarities among spoken terms in the absence of annotation. Such an approach is useful for the untranscribed spoken content from low-resource or zero-resource languages. A challenge in the discovery task is to compute the similarities among spoken terms without annotation. Dynamic time warping (DTW) is one of the techniques that computes temporal alignment between two acoustic feature representations of the speech signal without annotation. However, the speech variabilities that arise in natural speech introduce a challenge to the DTW approach. As a result, the performance of the spoken term discovery task was degraded. In this study, we overcome the challenges and improve the performance of the discovery task in three stages. At first, the speaker-independent acoustic feature representation was obtained from the Self Organising Map (SOM) to reduce the variabilities. In the second stage, non-segmental pseudo-labels were generated for the spoken content using context-free grammar. Finally, the spoken term similarities were obtained by grouping the similar sequences using proposed Label Sequence Similarity Mapping and Language modelling algorithms. The performance of the proposed system was measured using the Zero-Speech challenge corpus in terms of matching, clustering and parsing qualities. The experimental results reveal that the proposed approach improves the performance by 34.2% and 22.4% in English and Xitsonga, respectively, across multiple speakers. In addition, the clustering performance of the spoken terms at the word level was improved by 4.2% in English. © 2023, The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature.

关键词： Pattern matching

来源：评论

学校读者我要写书评

暂无评论

advanced Cyber-Attack Detection in IoT Networks Using Deep Belief Networks and Gradient Boosting Mechanisms 4

Advanced Cyber-Attack Detection in IoT Networks Using Deep B...

引用

4th IEEE International Conference on Mobile Networks and Wireless Communications, ICMNWC 2024

作者： Mohandas, R. Elavarasi, M. Praveen, R.V.S. Chittapragada, Hemanand Nithiya, C. Prabagar, S. Chennai Institute of Technology Department of Electronics and Communication Engineering Chennai India Vels Institute of Science Technology & Advanced Studies Department of Bca - It Pallavaram India LTIMindtree Limited Digital Engineering and Assurance Hyderabad India Madanapalle Institute of Technology & Science Department of Computer Science and Engineering Madanapalle India R.M.K. College of Engineering and Technology Department of Electronics and Communication Engineering Puduvoyal India Alliance School of Advanced Computing Alliance University Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350352931

The rapid growth of Internet of Things (IoT) devices has increased security weaknesses, rendering networks vulnerable to advanced cyber-attacks. Traditional detection systems frequently encounter difficulties in real-time anomaly detection and resource limitations, leaving IoT systems exposed. This study presents a hybrid model that combines Deep Belief Networks (DBN) for hierarchical feature extraction with Gradient Boosting (GB) to improve classification accuracy. Driven by the increasing incidence and complexity of cyber threats, the study seeks to rectify significant deficiencies in IoT security by providing a scalable, efficient, and high-performance detection system. Experimental findings confirm the model's efficacy, attaining 98.5% accuracy, an F1-score of 0.97, and a recall of 0.97, markedly surpassing current methodologies. The study addresses the issues of protecting IoT networks, suggests a comprehensive detection methodology, and offers a comparative analysis of performance indicators, laying the groundwork for refined, versatile approaches to counter new threats in IoT ecosystems. © 2024 IEEE.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

Harvesting Knowledge: An Innovative Ontology Framework for Agricultural Advancement using NPL methodologies 3

Harvesting Knowledge: An Innovative Ontology Framework for A...

引用

3rd International Conference on Electrical, Electronics, Information and Communication Technologies, ICEEICT 2024

作者： Deepa, R. Das, Manisha Thilakavathy, P. Bennet Prabhu, A. Surendran, R. Srm Institute of Science and Technology School of Computing Department of Computing Technologies Chennai India Andhrapradesh Rajam India Vels Institute of Science and Engineering Vels Institute of Science Technology and Advanced Studies Computer Science and Engineering Chennai India Kone Elevator India Technology & Engineering Centre Tamil Nadu Chennai India Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350369083

This paper introduces Agricultural Advancement using NLP (AA-NLP) techniques as a strategy to overcome the limitations of traditional agricultural management information systems. There is a lot of unstructured data available but this situation makes agricultural research inefficient because of its knowledge extraction and usage failure. This problem is addressed by combining an ontology framework developed for agricultural information management with Natural Language Processing (NLP) methods. The solution, AA-NLP, utilizes modern NLP algorithms which extract, classify and evaluate agricultural information from many textual sources that include research papers, reports and online repositories. AA-NLP achieves effective information retrieval and exploitation through named entity identification, sentiment analysis and semantic similarity as well as other techniques to convert unstructured input into structured ontological representations. Applying AA-NLP has several benefits such as increased discoverability of relevant agricultural information, automatic classification of scientific findings, and generation of actionable insights for decision making in farming practices, crop management and formulation of agricultural policies. The effectiveness of AA-NLP was analyzed in this paper by measuring the precision associated with knowledge extraction and ontology creation through various performance metrics including accuracy, sustainability farming practices, agricultural productivity and precision. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Pseudo Random Binary Sequence using Lattice-based Hard Problem for Quantum Key Distribution 56

Pseudo Random Binary Sequence using Lattice-based Hard Probl...

引用

56th International Carnahan Conference on Security Technology, ICCST 2023

作者： Pandit, Anupama Arjun Mishra, Arun SoCE&MS Defence Institute of Advanced Technology Department of Computer Science & Engineering Pune India

ISBN: (纸本)9798350315875

Recently, there has been a growing interest among researchers in Pseudo-Random Binary Sequences (PRBS) for Quantum Key Distribution (QKD). QKD is a cryptographic protocol that distributes secret keys between senders and receivers, relying on random numbers to determine the basis for evaluating transmitted bits. Quantum Random Number Generators (QRNG) utilizing natural resources create random bit sequences for QKD. However, QRNGs are susceptible to natural noise, which compromises their security. Additionally, post-processing of QRNG-generated sequences is necessary to reduce noise, but this process slows down the random number generation speed in QKD. Non-deterministic Pseudo-Random Sequence Generators (ND-PRSG) may overcome the QRNG's constraints, post-processing, and speed. Lattice-based NDPRSG provides security and efficiency. The proposed work focuses on generating a uniform PRBS with non-deterministic entropy using Learning with Errors (LWE) and LFSR. NIST Statistical Tests are performed on generated PRBS for randomness analysis, and the results are reported. The proposed PRBS generation can be used for QKD, operating up to 20.17 Mbit/s. © 2023 IEEE.

关键词： Statistical tests

来源：评论

学校读者我要写书评

暂无评论

Data Collection and Preprocessing Management for Sugarcane Leaf Disease Identification Using by Spatial Relation-Assisted Contrast Enhancement (SRCE)

Data Collection and Preprocessing Management for Sugarcane L...

引用

Integrated Intelligence and Communication Systems (ICIICS), International Conference on

作者： S. Akhil R. Durga Department of Computer Science Vels Institute of Science Technology & Advanced Studies Chennai India

ISBN: (数字)9798331504960

ISBN: (纸本)9798331504977

Background: Sugarcane, an essential commodity for the global sugar industry, is very vulnerable to several illnesses that significantly impact its output and quality. Methods: The study uses Spatial Relation Assisted Contrast Enhancement (SRCE) to enhance contrast in images of harmed sugarcane leaves. SRCE selectively enhances contrast, allowing for better differentiation between healthy and diseased areas. It focuses on local neighborhoods, highlighting critical symptoms while preserving leaf structure and texture. The enhanced images were analyzed using machine learning classifiers to assess their effectiveness in disease detection. Result: The results demonstrated that SRCE significantly improved the detection accuracy compared to traditional contrast enhancement techniques. This method aids in early disease identification and supports precision agriculture practices by enabling timely interventions. The results of SRCE of CII, LIF, SSIM, and PSNR values are evaluated. Conclusion: Our findings suggest that SRCE can be a valuable agricultural monitoring and management tool, ultimately contributing to increased sugarcane yield and sustainability.

关键词： Precision agriculture Accuracy Machine learning algorithms Crops Production Sugar industry Real-time systems Reliability Sustainable development Diseases

来源：评论

学校读者我要写书评

暂无评论

Impact of Music Signals on the Human Mind and Body: Need of Natural/Green Music Signals 5

Impact of Music Signals on the Human Mind and Body: Need of ...

引用

5th International Conference on Information Management and Machine Intelligence, ICIMMI 2023

作者： Batra, Neha Lakra, Sachin Department of Computer Science & Technology Manav Rachna University Department of Computer Science & Engineering Manav Rachna International Institute of Research & Studies Haryana Faridabad India Department of Computer Science & Technology Manav Rachna University Haryana Faridabad India

ISBN: (纸本)9798400709418

Music not only gives pleasure to the mind or brain but also helps in relaxing the whole body. studies have shown the impact of music on the Human Mind, Soul, and Body. Music has an unusual capability to conjure influential sentiments. It is mainly interesting because, unlike many other stimuli that induce emotions, such as aroma, flavor or facial manifestation, music has no evident core living or subsistence value. Further, fluctuations in certain physiological and psychological methods have been categorized in response to music signals. The paper reviews the impact of music of different genres and analyzes its impact on the human mind and body. Based on the impact of music reviewed, it is proposed to further study natural/green music produced by music instruments that are made of natural material as this natural music will be more amenable to the human mind and body. © 2023 ACM.

关键词： Physiological models

来源：评论

学校读者我要写书评

暂无评论

Automated Heart Disease Diagnosis and Monitoring System Using Similarity-Navigated Graph Neural Networks with Leopard Seal Optimization in IoT Healthcare Applications 4

Automated Heart Disease Diagnosis and Monitoring System Usin...

引用

4th International Conference on Sustainable Expert Systems, ICSES 2024

作者： Raja, V. Sripathi Rawat, Ruchira Pandit, Karuna Dhumpati, Raghu Vekariya, Vipul Vijitha, S. B V Raju Institute of Technology Department of Biomedical Engineering Telangana Narsapur502313 India Graphic Era Deemed to be University Department of Computer Science & Engineering Uttarakhand Dehradun248002 India Department of Information Science and Engineering Nitte Karkala Karnataka Udupi District India Bahrain Polytechnic Isa Town Department of Computer Science and Engineering Isa Town3339 Bahrain Parul Institute of Engineering and Technology Parul University Department of Computer Science and Engineering Post Limda Gujarat Waghodia391760 India Vels Institute of Science Technology and Advanced Studies Department of computer science and Engineering Pallavaram Tamil Nadu Chennai600043 India

ISBN: (纸本)9798331540364

One of the leading causes of death worldwide continues to be heart disease;therefore, early detection and precise diagnosis are essential to better patient outcomes. The conventional methods of diagnosing chemotherapy-induced nail changes involve a great deal of laboratory testing, which is more than exhaustive. In order to tackle these obstacles, this research introduces a novel methodology for the automated diagnosis and continuous tracking of heart diseases in the IoT -based health care system, integrated with deep learning algorithms. The proposed system includes several state-of-the art techniques to improve diagnostic reliability and speed. First of all, min-max normalization is used as a pre-processing technique that aims at pre-scaling the data of patients to a consistent level and, as a result, enhancing the performance of the model. The Mud Ring Algorithm is then used for feature selection, whereby the best features are chosen together with the reduction in dimensionality to decrease computational intensity, thus improving diagnostic accuracy. The core diagnostic engine is based on Similarity Navigated Graph Neural Networks (SNGNN) and has been enhanced with Leopard Seal Optimization (LSO), a new meta-method motivated by the hunting patterns of leopard seals. This combination enables the system to relate various features and give the correct prognosis for heart diseases. These techniques, applied within the IoT framework, enable real-time monitoring and diagnosis and therefore have the benefit of being a scalable solution for modern health care systems. The results show that the proposed method for providing diagnosis of heart disease is accurate, timely, and reliable and thus has the potential to revolutionize patient management in healthcare based on the IoT. © 2024 IEEE.

关键词： Chemotherapy

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：