检索结果-内蒙古大学图书馆

6th international conference on signal processing and machine learning, spml 2023

ISBN: (纸本)9798400707575

the proceedings contain 51 papers. the topics discussed include: communication signal modulation recognition based on inception-V3 transfer learning;research on methane telemetry method using differential-harmonic detection;deep learning-based binaural speech signal enhancement method;interference signal recognition processing based on convolutional neural network;ECG signal denoising based on wavelet threshold algorithm;application of UAV technology in aquaculture operation communication system;an efficient signal enhancement scheme for metamaterial-enhanced magnetic induction-based underground wireless sensor networks;learnable sparsity structured pruning for acoustic pre-trained models;research on positioning and dimension measurement of truck compartment based on semantic segmentation in automatic loading system;and restoration of Dunhuang murals on large-scale pretraining.

关键词：

来源：评论

学校读者我要写书评

暂无评论

conference Proceedings - 2023 6th international conference on machine learning and Natural Language processing, MLNLP 2023

Conference Proceedings - 2023 6th International Conference o...

引用

6th international conference on machine learning and Natural Language processing, MLNLP 2023

ISBN: (纸本)9798400709241

the proceedings contain 42 papers. the topics discussed include: offensive text classification based on Ernie’s dual channel composite model;fake news detection algorithm based on incorporating multi-level features;EEGCN: event evolutionary graph comparison network for multi-modal fake news detection;explainable similar legal cases retrieval based on Siamese network;robust sentiment classification based on the backdoor adjustment;prior knowledge augmentation network for aspect-based sentiment analysis;a multi-dimension and multi-granularity feature fusion method for Chinese microblog sentiment classification;optimization study on weapon-target assignment problem based on intuitionistic fuzzy marine predator algorithm;a novel ranking method for textual adversarial attack;reinforcement learning in natural language processing: a survey;and an application of co-plot analysis: a multidimensional scaling data visualization.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep learning-Based Binaural Speech signal Enhancement Method 23

Deep Learning-Based Binaural Speech Signal Enhancement Metho...

引用

6th international conference on signal processing and machine learning, spml 2023

作者： Wei, Cheng Zhiling, Yang Xiamen Ocean Vocational College Xiamen361102 China

ISBN: (纸本)9798400707575

the binaural speech signal enhancement decomposition structure is usually monolayered, with limited signal enhancement effect and low signal regularity. In such a context, this paper presents an analysis of the design and validation of a deep learning-based binaural speech signal enhancement method. With the method, the speech and noise features can be extracted according to the actual enhancement requirements and criteria, and signal time-frequency multi-stage decomposition and signal waveform reconstruction can be realized in the multi-stage form to break the limitation of signal enhancement effect and build a deep learning signal enhancement model. the IMCRA spectral subtraction combined processing has been adopted to realize signal enhancement. the test results show that after enhancing the selected binaural speech signals, the distortion of the speech signal enhanced could be significantly improved, with the noise side the signals eliminated, interference reduced, and signals enhanced regularly, which indicates that the enhancement method of such signal could achieve better effect in maintaining the stability of signals during the processing procedure and improving the signal frequency, and therefore is of great application value. © 2023 ACM.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Interference signal recognition processing based on convolutional neural network 23

Interference signal recognition processing based on convolut...

引用

6th international conference on signal processing and machine learning, spml 2023

作者： Li, Yi Ze Xiang, Ji Xijing University China

ISBN: (纸本)9798400707575

Modern wireless communication systems are faced with an increasingly complex electromagnetic environment and are affected by a variety of noise and interference signals. In the communication process, the communicating party can take corresponding anti-interference measures if it can effectively identify the type of interference signals. In order to enhance the correct rate of recognition, the paper applies deep learning to the field of communication anti-interference and proposes a method of interference signal recognition based on complex neural networks. A complex CNN interference recognition network is constructed on top of the existing CNN network and a complex residual network is designed to input interference signals into different network structures. the results show that: the interference recognition algorithm based on feature extraction outperforms the real CNN network;the overall performance of the convolutional neural network complex interference recognition network outperforms the real interference recognition network;the overall performance of the designed residual network is better than several other networks. © 2023 ACM.

关键词： signal interference

来源：评论

学校读者我要写书评

暂无评论

the Drone-vs-Bird Detection Grand Challenge at ICASSP 2023: A Review of Methods and Results

IEEE OPEN JOURNAL OF SIGNAL PROCESSING

引用

IEEE OPEN JOURNAL OF signal processing 2024年 5卷 766-779页

作者： Coluccia, Angelo Fascista, Alessio Sommer, Lars Schumann, Arne Dimou, Anastasios Zarpalas, Dimitrios Univ Salento Dept Innovat Engn I-73100 Lecce Italy Fraunhofer Ctr Machine Learning Fraunhofer IOSB D-76131 Karlsruhe Germany Ctr Res & Technol Hellas Informat Technol Inst Visual Comp Lab Thessaloniki 57001 Greece

this paper presents the 6th edition of the "Drone-vs-Bird" detection challenge, jointly organized with the WOSDETC workshop within the IEEE international conference on Acoustics, Speech and signal processing (ICASSP) 2023. the main objective of the challenge is to advance the current state-of-the-art in detecting the presence of one or more Unmanned Aerial Vehicles (UAVs) in real video scenes, while facing challenging conditions such as moving cameras, disturbing environmental factors, and the presence of birds flying in the foreground. For this purpose, a video dataset was provided for training the proposed solutions, and a separate test dataset was released a few days before the challenge deadline to assess their performance. the dataset has continually expanded over consecutive installments of the Drone-vs-Bird challenge and remains openly available to the research community, for non-commercial purposes. the challenge attracted novel signal processing solutions, mainly based on deep learning algorithms. the paper illustrates the results achieved by the teams that successfully participated in the 2023 challenge, offering a concise overview of the state-of-the-art in the field of drone detection using video signal processing. Additionally, the paper provides valuable insights into potential directions for future research, building upon the main pros and limitations of the solutions presented by the participating teams.

关键词： Deep learning drone detection image and video signal processing unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Optimization of Antenna Dimensions for Improved Frequency Response using machine learning: A Survey 6

Optimization of Antenna Dimensions for Improved Frequency Re...

引用

6th international conference on Communications signal processing and their Applications

作者： ElAbbasi, Mona K. Madi, Mervat Kabalan, Karim Y. Amer Univ Beirut Elect & Comp Engn Dept Beirut Lebanon Higher Coll Technol Elect & Elect Engn Sch Dept Abu Dhabi U Arab Emirates

ISBN: (纸本)9798350384826;9798350384819

machine learning techniques have widespread applications in optimization across various domains. this survey delves into their specific utilization in antenna design, where dimensions such as height and width play critical roles in performance metrics. Additionally, this study investigates the performance of several regression methods for predicting nonlinear relationships within antenna design variables affecting resonant frequency. Our analysis highlights the superiority of support vector regression (SVR), polynomial regression, and neural networks over linear regression and genetic algorithms in terms of predictive accuracy. In essence, the paper underscores the importance of selecting appropriate regression techniques based on the complexity of antenna design variables, recommending SVR, polynomial regression, and neural networks for modeling intricate patterns effectively and providing accurate predictions.

关键词： machine learning performance metrics support vector regression (SVR) polynomial regression neural networks linear regression genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Radar Sensing via Geometric machine learning over Riemannian Manifolds 6

Radar Sensing via Geometric Machine Learning over Riemannian...

引用

6th international conference on Communications signal processing and their Applications

作者： Sadique, Joarder Jafor Nasim, Imtiaz Ibrahim, Ahmed S. Florida Int Univ Dept Elect & Elect Engn Miami FL 33199 USA Idaho Natl Lab 1955 N Fremont Ave Idaho Falls ID 83415 USA

ISBN: (纸本)9798350384826;9798350384819

the imperative for autonomously detecting radar signals is paramount in the context of emerging shared-spectrum wireless networks, such as the Citizens Broadband Radio Service (CBRS) band. the dynamic allocation of this spectrum hinges upon a specialized sensor network tasked with identifying the presence of federal incumbent radar signals. In this paper, we propose a radar sensing strategy using received signals at base stations. More specifically, the sample covariance matrices of received signals lie over Riemannian manifolds (i.e., curved surfaces) thanks to their symmetric positive definite (SPD) properties. Consequently, we propose to use support vector machine (SVM) learning models over Riemannian manifolds for classification of radar existence. Our findings reveal that the model attains more than 90% radar detection accuracy considering signal-to-noise ratio (SNR) values up to 14 dB.

关键词： CBRS machine learning radar detection Riemannian manifold spectrum sensing

来源：评论

学校读者我要写书评

暂无评论

Enhancing Industrial Efficiency: Early Detection of Fan Failures with IoT Technology 6

Enhancing Industrial Efficiency: Early Detection of Fan Fail...

引用

6th international conference on Communications signal processing and their Applications

作者： Durgun, Mahmut Ozkorucu, Zubeyir Sukru Tokat Gaziosmanpasa Univ Dept Comp Engn Tokat Turkiye

ISBN: (纸本)9798350384826;9798350384819

the Internet of things is an innovative system that enables the integration of technological devices into daily life, enabling them to exchange data with each other and with other systems with the help of machine learning. Fan systems play a critical role in industrial facilities. they support the efficient operation of facilities by providing functions such as ventilation and cooling. Failures in these systems can cause operational interruptions and cost increases. By quickly detecting faults, production can be sustained and costs can be reduced. In this study, acceleration values collected from the fan motor with Arduino Nano33 BLE Sense device were analyzed and classification was performed with Decision Tree, Gradient Boosting machine and Convolutional Neural Networks. According to the results obtained, the best classification accuracy was obtained in the Decision Tree and Gradient Boosting machine methods. the three methods were also compared in terms of latency and size. In terms of latency, the best performance belongs to the Decision Tree and Gradient Boosting machine methods. In terms of size, the Decision Tree method has the smallest size.

关键词： fan failure machine learning classification

来源：评论

学校读者我要写书评

暂无评论

Joint Power Control and Device Scheduling in Federated learning with Energy Harvesting 6

Joint Power Control and Device Scheduling in Federated Learn...

引用

6th international conference on Communications signal processing and their Applications

作者： Zhang, Boyuan Lu, Ning Queens Univ Dept Elect & Comp Engn Kingston ON K7L 3N6 Canada

ISBN: (纸本)9798350384826;9798350384819

Federated learning (FL) is emerging as a promising approach for enabling collaborative machine learning without centralizing data, particularly within Internet of things (IoT) networks. Despite its potential, the challenge of reducing communication delay and energy consumption in client-server transmissions is considered a critical challenge in wireless network implementations of FL. Moreover, the capability of many IoT devices to harvest energy introduces a novel dimension to optimizing FL efficiency, which remains underexplored. In this paper, we present POLISH, a novel POwer controL and devIce ScHeduling algorithm derived from an optimization problem designed to navigate a tripartite trade-off between minimizing communication delay (specifically, the transmission time for model updates), reducing total energy consumption, and maximizing device participation. through simulations, POLISH has shown superior performance in reducing communication delay and energy consumption when compared to existing benchmarks, highlighting its effectiveness in enhancing FL performance in energy-constrained IoT networks.

关键词： Federated learning Energy Harvesting Power Control Device Scheduling

来源：评论

学校读者我要写书评

暂无评论

machine learning-assisted Partially Blind Handover Prediction in 5G Network Systems 6

Machine Learning-assisted Partially Blind Handover Predictio...

引用

6th international conference on Communications signal processing and their Applications

作者： Yazici, Ibrahim Gures, Emre Acibadem Turk Telekom R&D Dept Istanbul Turkiye Czech Tech Univ Fac Elect Engn Prague Czech Republic

ISBN: (纸本)9798350384826;9798350384819

Handover is the process of transferring a cellular call or data session from one base station to another. this process aims to establish reliable and uninterrupted connection, thereby providing satisfactory Quality of Service (QoS) and Quality of Experience (QoE) for users. 5G networks will use millimetre wave (mmWave) frequencies in addition to sub-6 GHz bands, which will make handover more challenging. this paper focuses on the problem of partially blind handovers which is a novel handover type. In this sense, we modify an extant algorithm used for the partially blind handovers [1] which the algorithm is based on machine learning. In our modified algorithm, we use the extant algorithm with a powerful boosting method that is Categorical Boosting (CatBoost). We compare our modified algorithm with a baseline algorithm, the originally proposed algorithm, Support Vector machine integrated original algorithm. Different settings of simulation time and number of users are considered in comparing the algorithms, and our modified algorithm outperforms the rest of the algorithms in majority of the settings with higher handover prediction rates as per obtained results. the obtained results clearly indicate that the integration of machine learning with partially blind handovers enables accurate predictions whether handover execution will be successful in collocated cells in a network in the real-world case. A noteworthy takeaway from the obtained results is that machine learning deployment with partially blind handovers will likely contribute to self-organizing networks (SONs) in 5G communication systems.

关键词： machine learning mmWave 5G handover blind handover self-organizing networks (SONs) Categorical Boosting (CatBoost) eXtreme Gradient Boosting (XGBoost)

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：