检索结果-内蒙古大学图书馆

35th Conference on Computational Linguistics and Speech Processing, ROCLING 2023

作者： Lin, Joseph Lyu, Ren-Yuan Hsinchu County American School Hsinchu Taiwan Department of Computer Science and Information Engineering Chang Gung University Taoyuan Taiwan

ISBN: (纸本)9789869576963

In this paper, we explore compact convolutional neural networks (CNNs) for end-to-end keyword spotting from raw audio to final recognition results, without using traditional feature extraction based on spectrogram. Such fully CNN models reach 90.5% accuracy, an improvement of 12.15% over traditional methods with similar structures, which only achieve 78.35% accuracy, on the Speech Commands dataset. This shows that learned CNN features outperform predefined FFT-based transforms. The results show that compact end-toend CNNs enable efficient, accurate small vocabulary keyword spotting that is well-suited for resource-constrained edge devices. © 2023 ROCLING 2023 - Proceedings of the 35th Conference on Computational Linguistics and Speech Processing. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Impairment-Aware Symbolic Modulation for Automatic Signal Processing

Impairment-Aware Symbolic Modulation for Automatic Signal Pr...

引用

2024 International Conference on Optimization Computing and Wireless Communication, ICOCWC 2024

作者： Rengarajan, A. Agarwal, Ankita Bishnoi, Sunita Department of Computer Science and Information Technology Bangalore India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India Vivekananda Global University Department of Chemistry Jaipur India

ISBN: (纸本)9798350383348

Impairment-aware Symbolic Modulation for computerized sign Processing is a singular technique utilized in sign processing. This technique makes use of symbolic modulation to simulate sign degradations caused by natural or conventional impairments. The proposed method allows the signals to be modulated in a manner that's privy to impairments. The method uses a combination of neural networks and fuzzy common sense to perceive the most suitable modulated sign representation. This technique enables in improvement of sign intelligence with the aid of expanding the sign representation space. It similarly enables one to become aware of signal components accountable for the presence or absence of impairment and to conform to sign adjustments correctly. This method gives a green way of dealing with the diffusion of signal degradations and may be used to discover and classify alerts dependably. © 2024 IEEE.

关键词： Dependably Impairment Modulation Networks Processing Symbolic

来源：评论

学校读者我要写书评

暂无评论

Secure and Energy Concise Route Revamp Technique in Wireless Sensor Networks

引用

Intelligent Automation & Soft Computing 2023年第2期35卷 2337-2351页

作者： S.M.Udhaya Sankar Mary Subaja Christo P.S.Uma Priyadarsini Department of Information Technology Velammal Institute of TechnologyChennai601204India Department of Networking and Communication SRM Institute of Science and TechnologyKattankulathur603203India Department of Computer Science and Engineering Saveetha School of EngineeringSaveetha Institute of Medical and Technical SciencesChennai600124India

Energy conservation has become a signiﬁcant consideration in wireless sensor networks(WSN).In the sensor network,the sensor nodes have internal batteries,and as a result,they expire after a certain *** a result,expanding the life duration of sensing devices by improving data depletion in an effective and sustainable energy-efﬁcient way remains a ***,the clustering strategy employs to enhance or extend the life cycle of *** identify the supervisory head node(SH)or cluster head(CH)in every grouping considered the feasible strategy for power-saving route discovery in the clustering model,which diminishes the communication overhead in the ***,the critical issue was determining the best SH for ensuring timely communication *** secure and energy concise route revamp technology(SECRET)protocol involves selecting an energy-concise cluster head(ECH)and route revamping to optimize *** sensors transmit information over the ECH,which delivers the information to the base station via the determined optimal path using our strategy for effective data *** modeled our methods to accom-plish power-efﬁcient multi-hop ***,protected navigation helps to preserve energy when *** suggested solution improves energy savings,packet delivery ratio(PDR),route latency(RL),network lifetime(NL),and scalability.

关键词： Wireless sensor network wireless security wireless routing clustering ad hoc network

来源：评论

学校读者我要写书评

暂无评论

Regional Resilient Routing Algorithm for LEO Satellite Network 22

Regional Resilient Routing Algorithm for LEO Satellite Netwo...

引用

22nd International Conference on Optical Communications and Networks, ICOCN 2024

作者： Tang, Hongjing Zhang, Qi Li, Yuanfeng Xi, Xiangjun Feng, Weiying Yu, Wensheng Chai, Furong Sun, Meng Wang, Fu Tian, Feng Wang, Yongjun Tian, Qinghua Beijing100876 China National University of Defense Technology Science and Technology on Information Systems Engineering Laboratory Changsha410073 China School of Information and Electronics Beijing Institute of Technology Beijing100081 China Beihang University Beijing Materials Science and Engineering Beijing100091 China

A hierarchical deep reinforcement learning-based regional resilient satellite routing algorithm is proposed. The simulation result shows the proposed method improves the communication success rate of the network in th... 详细信息

ISBN: (纸本)9798350367652

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Investigation of Quality of Service in Various Mobility Protocols for Wireless Local Area Networks

Investigation of Quality of Service in Various Mobility Prot...

引用

2024 International Conference on Optimization Computing and Wireless Communication, ICOCWC 2024

作者： Sharma, Deeplata Nachappa, M.N. Yadav, Rakesh Kumar Vivekananda Global University Department of Chemistry Jaipur India Department of Computer Science and Information Technology Bangalore India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India

ISBN: (纸本)9798350383348

This technical abstract examines the pleasantness of carriers (quality of service) in numerous mobility protocols for Wi-Fi neighborhood place networks (WLAN). Quality of service is a measure of the level of service provided with the aid of a network and influences the supply, throughput, latency, jitter, and packet loss of packages. The research investigates the impact of mobility on quality of service in WLAN surroundings. An evaluation of the two fundamental mobility protocols., mobile IP and Proxy cellular IP, is executed in theoretical simulation surroundings. The effects of the assessment show that cell IP wireless advanced the quality of service on scalability, handoff delay, and packet loss. Additionally, this analysis suggests that Proxy cellular IP can successfully assist mobility in WLANs while providing suitable ranges of quality of service. With the consequences of these studies, gadget directors and network architects now have a higher understanding of the impact of mobility on the quality of service of WLANs. © 2024 IEEE.

关键词： Consequences Fundamental Measure Mobility Network Surroundings

来源：评论

学校读者我要写书评

暂无评论

NotePlayer: Engaging Computational Notebooks for Dynamic Presentation of Analytical Processes 24

NotePlayer: Engaging Computational Notebooks for Dynamic Pre...

引用

37th Annual ACM Symposium on User Interface Software and Technology, UIST 2024

作者： Ouyang, Yang Shen, Leixian Wang, Yun Li, Quan School of Information Science and Technology ShanghaiTech University Shanghai China Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong Hong Kong Microsoft Research Asia Beijing China

ISBN: (纸本)9798400706288

Diverse presentation formats play a pivotal role in effectively conveying code and analytical processes during data analysis. One increasingly popular format is tutorial videos, particularly those based on Jupyter notebooks, which offer an intuitive interpretation of code and vivid explanations of analytical procedures. However, creating such videos requires a diverse skill set and significant manual effort, posing a barrier for many analysts. To bridge this gap, we introduce an innovative tool called NotePlayer, which connects notebook cells to video segments and incorporates a computational engine with language models to streamline video creation and editing. Our aim is to make the process more accessible and efficient for analysts. To inform the design of NotePlayer, we conducted a formative study and performed content analysis on a corpus of 38 Jupyter tutorial videos. This helped us identify key patterns and challenges encountered in existing tutorial videos, guiding the development of NotePlayer. Through a combination of a usage scenario and a user study, we validated the effectiveness of NotePlayer. The results show that the tool streamlines the video creation and facilitates the communication process for data analysts. © 2024 Owner/Author.

关键词： Video analysis

来源：评论

学校读者我要写书评

暂无评论

On Reliably Decodable information Bits of Linear Codes

On Reliably Decodable Information Bits of Linear Codes

引用

2023 IEEE International Symposium on information Theory, ISIT 2023

作者： Wang, Yixin Ma, Xiao Sun Yat-sen University School of Systems Science and Engineering Guangzhou510006 China Sun Yat-sen University School of Computer Science and Engineering Guangzhou510006 China Sun Yat-Sen University Guangdong Key Laboratory of Information Security Technology Guangzhou510006 China

ISBN: (纸本)9781665475549

It is well-known that a linearly coded vector over an erasure channel can be decoded uniquely if the sub-generator matrix formed by the unerased columns has full row rank. This property is generalized in this paper to a necessary and sufficient condition for an information bit to be retrieved uniquely from a received vector with erasures. We show that an information bit of a linear code can be uniquely decodable if and only if its corresponding row of the sub-generator matrix is linearly independent from the other rows. Then we prove that, for semi-random linear codes over binary-input output-symmetric (BIOS) memoryless channels, the information bits associated with the random part of the generator matrices can be decoded with arbitrarily small error probability as the codelength increases. This in turn is applied to prove the coding theorem for time-invariant convolutional codes. © 2023 IEEE.

关键词： Convolutional codes

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Diagnostic System using Deep Learning for Early Prediction of Pancreatic Cancer 10

An Enhanced Diagnostic System using Deep Learning for Early ...

引用

10th International Conference on Electrical Energy systems, ICEES 2024

作者： Bhargavi, Kumbham Prasad, M Lakshmi Arun, G. Shaker Reddy, Pundru Chandra Yuvalatha, S. Triveni, M Naga Telangana Hyderabad India Computer Science and Engineering Institute of Aeronautical Engineering Telangana Hyderabad India Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Computer Science and Engineering Chennai India SR University School of Computer Science and Artificial Intelligence Telangana Warangal India Anna University Bannari Amman Institute of Technology Computer Science and Business Systems Tamil Nadu India Telangana Hyderabad India

ISBN: (纸本)9798350353778

With a dismal 5-year survival-rate of approximately 7%, pancreatic-cancer(PC) remains one of the world's most lethal tumors. In order to improve patient survival rates, early detection of PC is essential. computerized-tomography(CT), MRI combined with MRCP, or a biopsy is necessary for the diagnosis of PC. The steps involved in the suggested CAD design process are as follows: picture preprocessing, segmentation, feature-extraction & classificatiion. Color conversion and the isotropic diffusion filter method are utilized for preprocessing. The next step is the segmentation processes' usage of the suggested Fuzzy K-NN Equality code. A classification tool that makes use of Deep Learning is feature extraction. Using the characteristics gathered from the pancreatic sample, tumor cells are categorized. The image classification criterion includes both the train values and the testing datasets. To identify pancreatic cancer, an algorithm called DCNN_DBN is employed, which combines Deep-Convolutional Neural-Networks with Deep-Belief-Networks. The results of the experiments show that the present CAD system has great promise and is safe for the automated diagnosis of benign & malignant tumors, with an accuracy rate of 99.8 percent. The use of this classifier greatly reduces the computational complexity. More anomalies in pancreatic cancer cells could be detected with an improved version of the proposed method. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

DualFed: Enjoying both Generalization and Personalization in Federated Learning via Hierachical Representations 24

DualFed: Enjoying both Generalization and Personalization in...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Zhu, Guogang Liu, Xuefeng Niu, Jianwei Tang, Shaojie Wu, Xinghao Zhang, Jiayuan State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China Zhongguancun Laboratory Beijing China Department of Management Science and Systems University at Buffalo BuffaloNY United States

ISBN: (纸本)9798400706868

In personalized federated learning (PFL), it is widely recognized that achieving both high model generalization and effective personalization poses a significant challenge due to their conflicting nature. As a result, existing PFL methods can only manage a trade-off between these two objectives. This raises an interesting question: Is it feasible to develop a model capable of achieving both objectives simultaneously? Our paper presents an affirmative answer, and the key lies in the observation that deep models inherently exhibit hierarchical architectures, which produce representations with various levels of generalization and personalization at different stages. A straightforward approach stemming from this observation is to select multiple representations from these layers and combine them to concurrently achieve generalization and personalization. However, the number of candidate representations is commonly huge, which makes this method infeasible due to high computational costs. To address this problem, we propose DualFed, a new method that can directly yield dual representations correspond to generalization and personalization respectively, thereby simplifying the optimization task. Specifically, DualFed inserts a personalized projection network between the encoder and classifier. The pre-projection representations are able to capture generalized information shareable across clients, and the post-projection representations are effective to capture task-specific information on local clients. This design minimizes the mutual interference between generalization and personalization, thereby achieving a win-win situation. Extensive experiments show that DualFed can outperform other FL methods. Code is available at https://***/GuogangZhu/DualFed. © 2024 ACM.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

A Smart of Classification and Regression Tree Algorithms for Detection of Land Cover from Hyper Spectral Data

A Smart of Classification and Regression Tree Algorithms for...

引用

2024 International Conference on Optimization Computing and Wireless Communication, ICOCWC 2024

作者： Chaudhary, Chetan Shankar, Shiv Shankar Menaka, C. Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India Vivekananda Global University Department of Mathematics Jaipur India Department of Computer Science and Information Technology Bangalore India

ISBN: (纸本)9798350383348

This paper offers a new approach for land cover detection using classification and regression tree (CART) algorithms for hyperspectral information. The underlying principle for the CART technique is to assemble a decision tree to categorize the far-flung sensing records primarily based on hard and fast model parameters. The proposed technique uses a genetic algorithm for great tuning the parameters for each department of the tree., which enables the CART algorithm to version the spatial variability of the land cowl effectively. Experimental effects on multiple take-a-look-at pictures verify the merits of the proposed CART algorithm in detecting land cowl as it should be from hyperspectral facts. The paper additionally demonstrates the robustness of the proposed algorithm in handling noise and the length of the characteristic area. The results display a full-size development in land cowl detection accuracy over the present methods. © 2024 IEEE.

关键词： algorithms classification demonstrates parameters underlying

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：