检索结果-内蒙古大学图书馆

2nd International Conference on Electrical, Electronics, Information and Communication Technologies, ICEEICT 2023

作者： Latha, R. Suhas, A.R. Pradeep Kumar, B.P. Ibrahim, M.Mohammed Sathiyapriya, V. HKBK College of Engineering Department of Electronics and Communication Engineering Bangalore India Sona College of Technology Department of Computer Science and Engineering Salem India Knowledge Institute of Technology Department of Computer Science and Engineering Salem India

ISBN: (纸本)9798350397635

Speech Enhancement (SE) aims to improve the quality of degraded speech while maintaining its intelligibility. The Wavelet Transform (WT) has become a powerful tool of signal analysis thereby widely used in signal detection and signal denoising. In this paper, we propose an effective means of SE by a hybrid threshold scheme using WT. The proposed methodology looks into both falling the noise and preserving edges of the speech signal unlike the conventional Hybrid Threshold (HT) and Soft Threshold (ST) in the wavelet domain. The threshold value in the wavelet domain is maintained constant for all sub-bands of the signal which reduces denoising efficiency. A novel speech augmentation technique built on the wavelet onsets and time adaption of introduced by calculating wavelet coefficients of the Teager Energy. Performance analysis of speech enhancement techniques using Wavelet coefficients and Teager Energy Operator (TEO) with hybrid threshold method is done. The experiment is carried out for speech data with various values of SNR vacillating from -10 to +10 db with Additive White Gaussian Noise (AWGN). © 2023 IEEE.

关键词： Speech enhancement

来源：评论

学校读者我要写书评

暂无评论

Rapid Detection of Pilgrims Whereabouts During Hajj and Umrah by Wireless Communication Framework : An application AI and Deep Learning 5

Rapid Detection of Pilgrims Whereabouts During Hajj and Umra...

引用

5th International Conference on Emerging Smart Computing and Informatics, ESCI 2023

作者： Alhameed, Mohammed Hossain, Mohammad Alamgir College of Computer Science and Information Technology Jazan University Jazan Saudi Arabia College of Cs and It Jazan University Department of Computer Science Jazan Saudi Arabia

ISBN: (纸本)9781665475242

Human injuries and deaths occur often during public events like concerts, religious services, and political rallies because of a lack of proper crowd safety oversight. A small disaster can trigger panic in a huge crowd. Many intelligent video surveillance solutions can identify things, but despite the recent developments in artificial intelligence approaches and deep learning processes, it is very probable to track congested crowds and their mobility to avoid future detection disasters. Searching for points of interest makes use of movement analytics and classification to provide a superior platform for monitoring large crowds. The purpose of point-of-interest explorations is to aid in the management of the safety of moveable crowd events by assisting in the prediction and prevention of future disasters through the classification and analysis of real-time information gathered from crowds. Current surveillance cameras are insufficient for monitoring large crowds in outdoor locations due to their inability to scale. We believe that by using our proposed crowd analysis strategy, we may help enhance the current state of crowd safety management. Among the many aspects of crowd motion, we pay special attention to the difficulties of determining the identity, velocity, and direction of individuals inside the group. We then used these crowd-level semantics to monitor test POI searches in both a controlled lab environment and a real-world crowd. Findings from this study imply that POI searching can be utilized to help prevent harmful circumstances brought on by the movement of large crowds by recognizing the characteristics of mobile crowds in real time. © 2023 IEEE.

关键词： Disasters

来源：评论

学校读者我要写书评

暂无评论

Hyperparameter Tuning Bidirectional Gated Recurrent Unit Model for Oral Cancer Classification

引用

computers, Materials & Continua 2022年第12期73卷 4541-4557页

作者： K.Shankar E.Laxmi Lydia Sachin Kumar Ali S.Abosinne Ahmed alkhayyat A.H.Abbas Sarmad Nozad Mahmood Department of Computer Science South Ural State UniversityChelyabinsk454080Russia Department of Computer Science and Engineering Vignan’s Institute of Information TechnologyVisakhapatnam530049India Computer Technical Engineering Department College of Technical Engineeringthe Islamic UniversityNajaf54001Iraq College of Technical Engineering the Islamic UniversityNajafIraq College of Information Technology Imam Ja’afar Al-Sadiq UniversityAl-Muthanna66002Iraq Computer Technology Engineering College of Engineering TechnologyAl-Kitab UniversityIraq

Oral Squamous Cell Carcinoma(OSCC)is a type of Head and Neck Squamous Cell Carcinoma(HNSCC)and it should be diagnosed at early stages to accomplish efficient treatment,increase the survival rate,and reduce death *** imaging is a wide-spread standard used for OSCC ***,it is a cumbersome process and demands expert’s ***,there is a need exists for automated detection ofOSCC using Artificial Intelligence(AI)and computer Vision(CV)*** this background,the current research article introduces Improved Slime Mould Algorithm with Artificial Intelligence Driven Oral Cancer Classification(ISMA-AIOCC)model on Histopathological images(HIs).The presented ISMA-AIOCC model is aimed at identification and categorization of oral cancer using *** the initial stage,linear smoothing filter is applied to eradicate the noise from ***,MobileNet model is employed to generate a useful set of feature ***,Bidirectional Gated Recurrent Unit(BGRU)model is exploited for classification *** the end,ISMA algorithm is utilized to fine tune the parameters involved in BGRU ***,ISMA algorithm is created by integrating traditional SMA and ChaoticOppositional Based Learning(COBL).The proposed ISMA-AIOCC model was validated for performance using benchmark dataset and the results pointed out the supremacy of ISMA-AIOCC model over other recent approaches.

关键词： computer aided diagnosis deep learning BGRU biomedical imaging oral cancer histopathological images

来源：评论

学校读者我要写书评

暂无评论

GearDB: A GC-free Key-Value Store on HM-SMR Drives with Gear Compaction 23

GearDB: A GC-free Key-Value Store on HM-SMR Drives with Gear...

引用

2023 ACM Turing Award Celebration Conference, CHINA 2023

作者： Yao, Ting Wan, Jiguang Huang, Ping Zhang, Yiwen Xie, Changsheng He, Xubin Huawei Cloud Computing Technologies Co. Ltd. China School of Computer Science and Technology Huazhong University of Science and Technology China College of Science and Technology Temple University United States

No abstract available.

ISBN: (纸本)9798400702334

No abstract available.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Approx T: Design Methodology for Approximate Multiplication Units via Taylor Expansion

引用

IEEE Transactions on computer-Aided Design of Integrated Circuits and systems 2025年

作者： Shangshang, Yao College of Computer Science and Technology National University of Defense Technology Changsha China

Approximate computing is emerging as a promising approach to devising energy-efficient IoT systems by exploiting the inherent error-tolerant nature of various applications. In this paper, we present Approx-T, to tackle several major challenges according to the prior state-of-the-art (SOTA) Approximate Multiplication Units (AMUs) -lack of comprehensive optimization formulation, asymmetric error distribution, non-adjustable runtime precision and exponentially growing area complexity when adding up error compensation levels. We innovatively conduct an in-depth study on approximate multiplier via Taylor-expansion to address these issues. (1) Incorporate Taylor's theorem into the design concept of approximate arithmetic multipliers. (2) Leverage the inherent symmetrical error distribution of Taylor series to conduct unbiased approximations. (3) Present a runtime configurable error compensation architecture with low-complexity arithmetic operations. We implemented both approximate unsigned and signed integer and floating multiplication arithmetic units and compared with the SOTA works. The experimental results demonstrate that Approx-T surpasses other designs in all metrics, encompassing precision, area utilization, and power consumption. Furthermore, when deployed on an embedded FPGA platform to assess a spectrum of edge computing tasks, Approx-T showcases remarkable performance. Particularly in CNN applications, it achieves up to a 10.7x enhancement in energy efficiency, while maintaining negligible impact on accuracy. © 1982-2012 IEEE.

关键词： Error compensation

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of a Scalable Federated Learning-Based Agricultural Network 4

Performance Analysis of a Scalable Federated Learning-Based ...

引用

4th IEEE International Conference on Emerging Techniques in Computational Intelligence, ICETCI 2024

作者： Chakraborty, Shatanik Sarkar, Maharnab Gayen, Avijit Jana, Angshuman Chakraborty, Nilotpal Meghnad Saha Institute of Technology Dept. of Computer Science & Engg. Kolkata India Govt. College Of Engineering & Textile Technology Dept. of Computer Science & Engg. Berhampore India Indian Institute of Information Technology Dept. of Computer Science & Engg. Guwahati India Techno India University Dept. of Computer Science & Engg. West Bengal India

ISBN: (纸本)9798350387063

Although agriculture is a substantial part of the Indian economy, it encounters several challenges. Precision agri-culture is a farming management strategy that aims to overcome these challenges. It optimizes several components of the farming process using data and technology, resulting in increased crop yields while reducing waste and raising total resource use effi-ciency. Thus, in its context, we present a study on the development of a Federated Learning-based Agricultural Network consisting of a popular federated learning algorithm FedAvg to perform image classification on an open dataset, Plant Village. In this work, we specifically analyze the performance of the proposed Federated Learning-based Agricultural Network in terms of its scalable deployment. The proposed network yields an average classification accuracy of 97.52 % on test data (C ≈ 70), and provides a host of other benefits it derives from its federated nature, such as upholding the privacy of local client data as only the model updates are shared between the clients and the aggregation server. The prime objective of our work has been to study and explore the possibility of applying federated learning in the agriculture sector so that more efficient and privacy- preserving smart farming networks could be developed. © 2024 IEEE.

关键词： Agribusiness

来源：评论

学校读者我要写书评

暂无评论

P4CTM: Compressed Traffic Pattern Matching Based on Programmable Data Plane 28

P4CTM: Compressed Traffic Pattern Matching Based on Programm...

引用

28th IEEE Symposium on computers and Communications, ISCC 2023

作者： Lin, Hang Lin, Weiwei Lin, Jing Zhu, Longlong Zhang, Dong Wu, Chunming College of Computer and Data Science Fuzhou University Fuzhou China Zhicheng College Fuzhou University Fuzhou China College of Computer Science and Technology Zhejiang University Hangzhou China

ISBN: (纸本)9798350300482

Pattern matching is an important technology applied to many security applications. Most network service providers choose to compress network traffic for better transmission, which brings the challenges of compressed traffic matching. However, existing works focus on improving the performance of uncompressed traffic matching or only realize the compressed traffic matching on end-host that can not keep pace with the dramatic increase in traffic. In this paper, we present P4CTM, a proof-of-concept method to conduct efficient compressed traffic matching on the programmable data plane. P4CTM uses the two-stage scan scheme to skip some bytes of compressed traffic, the 2-stride DFA combines with the compression algorithm to condense the state space, and the wildcard match to downsize the match action tables in the programmable data plane. The experiment indicates that P4CTM skips 83.10% bytes of compressed traffic, condenses the state space by order of magnitude, and reduces most of the table entries. © 2023 IEEE.

关键词： Pattern matching

来源：评论

学校读者我要写书评

暂无评论

A Critical Analysis and Classification of Breast Cancer Using Histopathology Images

A Critical Analysis and Classification of Breast Cancer Usin...

引用

2024 International Conference on Knowledge Engineering and Communication systems, ICKECS 2024

作者： Singh, Pritpal Kumar, Rakesh Gupta, Meenu Obaid, Ahmed J. Chandigarh University Department of Cse Punjab 140413 India National University of Science and Technology Faculty of Computer Science and Mathematics College of Technical Engineering Dept of Computer Science Dhi Qar Iraq

ISBN: (纸本)9798350359688

In Breast Cancer ML is instrumental in early detection through the analysis of mammographic and histopathological images, assessing individual risk factors, personalizing treatment plans based on genomic data, and providing decision support for healthcare professionals. ML also contributes to post-treatment monitoring, integrates diverse datasets for comprehensive insights, and accelerates research and drug discovery efforts. Overall, it enhances the accuracy, efficiency, and personalized nature of breast cancer care across the entire healthcare continuum. The paper presents a comparative review of recent techniques that use histopathological images for breast cancer classification. The study synthesizes findings from a range of research efforts employing diverse methodologies, including deep learning, ensemble techniques, and innovative model architectures. Researchers have explored the application of artificial neural networks, convolutional neural networks, and transfer learning in increasing the accuracy and objectivity of breast cancer classification. Additionally, novel approaches such as ViT-AMCNet, Ensembled Transfer Learning (ETL), and Curriculum Feature Alignment Network (CFAN) have been introduced, each contributing to the evolving landscape of histopathology image analysis. This review also includes a case study based on the EfficientNetB3 architecture that achieved a 98% accuracy in the diagnosis of breast cancer, with remarkable recall values of 0.95 and 0.97 for positive and negative cases, respectively, along with precision rates of 0.96 for positive cases and 0.95 for negative cases. The review highlights the significance of these approaches in addressing challenges related to feature extraction, nuclei segmentation, and classification accuracy, ultimately advancing our understanding of breast cancer pathology through the lens of computational methodologies. © 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

A Semantic Segmentation Method Based on Multilevel Relational Distillation 6

A Semantic Segmentation Method Based on Multilevel Relationa...

引用

6th International Conference on Communications, Information System and computer Engineering, CISCE 2024

作者： Xianghong, H. Leibo, Y. Wang, Heyuan Tianxiong, L. College of General Education Guangdong University of Science and Technology Guangdong Dongguan China School of Computer Science and Technology Wuhan University Science and Technology Hubei Wuhan China Hangzhou Easitech Co. Ltd. Development Department Zhejiang Hangzhou China

ISBN: (纸本)9798350353174

This article proposes a multilevel relational distillation method, which focuses more on the spatial structure relationship of feature maps compared to traditional detection distillation. Compared with advanced network models, it has a more obvious segmentation effect on small targets in complex scenes. On the ADE20K dataset, the accuracy reached 75.93%, and on the Cityscapes validation set, the average intersection to union ratio was 74.12%, proving that the model has improved on various datasets and has strong universality. © 2024 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Residual Tensor Train: A Quantum-Inspired Approach for Learning Multiple Multilinear Correlations

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2023年第5期4卷 1101-1113页

作者： Chen, Yiwei Pan, Yu Dong, Daoyi Zhejiang University Institute of Cyber-Systems and Control College of Control Science and Engineering Hangzhou310027 China Zhejiang University State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control College of Control Science and Engineering Hangzhou310027 China University of New South Wales School of Engineering and Information Technology CanberraACT2600 Australia

States of quantum many-body systems are defined in a high-dimensional Hilbert space, where rich and complex interactions among subsystems can be modeled. In machine learning, complex multiple multilinear correlations may also exist within input features. In this article, we present a quantum-inspired multilinear model, named residual tensor train (ResTT), to capture the multiple multilinear correlations of features, from low to high orders, within a single model. ResTT is able to build a robust decision boundary in a high-dimensional space for solving fitting and classification tasks. In particular, we prove that the fully connected layer and the Volterra series can be taken as special cases of ResTT. Furthermore, we derive the rule for weight initialization that stabilizes the training of ResTT based on a mean-field analysis. We prove that such a rule is much more relaxed than that of tensor train (TT), which means that ResTT can easily address the vanishing and exploding gradient problem that exists in the existing TT models. Numerical experiments demonstrate that ResTT outperforms the state-of-the-art tensor network and benchmark deep learning models on MNIST and Fashion-MNIST datasets. Moreover, ResTT achieves better performance than other statistical methods on two practical examples with limited data, which are known to have complex feature interactions. © 2020 IEEE.

关键词： Neural networks

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：