检索结果-内蒙古大学图书馆

OCEANS

作者： Xueyang Yu Cheng Chi Shuqiu Li Yu Li Haining Huang Guanqun Wang Institute of Acoustics Chinese Academy of Sciences Key Laboratory of Science and Technology on Advanced Underwater Acoustic Signal Processing Chinese Academy of Sciences University of Chinese Academy of Sciences

ISBN: (数字)9798350362077

ISBN: (纸本)9798350362084

Intelligent recognition of underwater acoustic targets is a crucial component of the intelligentization of underwater acoustic devices [1]–[3]. In recent years, with the development of computing technology, deep learning has become increasingly attractive in the recognition of underwater acoustic targets. Compared to traditional machine learning techniques, deep learning utilizes the strong nonlinearmodeling capability of deep neural networks, which enables the discovery of complex patterns hidden in large datasets and produces high-quality predictions or classification results [4], [5]. However, the complex acoustic channels, interference, and noise in the ocean often lead to the degradation or masking of some features of underwater acoustic signals, reducing the differentiation of signal characteristics between different types of targets. This, in turn, affects the capability of employed neural networks to extract features and classify underwater acoustic signals. Currently, the existing deep learning-based recognition methods of underwater targets are heavily influenced by noise and interference.

关键词： Deep learning Adaptive systems Target recognition Oceans Noise Interference Artificial neural networks

来源：评论

学校读者我要写书评

暂无评论

Balancing property optimization and constraint satisfaction for constrained multi-property molecular optimization

arXiv

引用

arXiv 2024年

作者： Xia, Xin Zhang, Yajie Zeng, Xiangxiang Zhang, Xingyi Zheng, Chunhou Su, Yansen The Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Artificial Intelligence Anhui University Hefei230601 China The Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei230601 China College of Computer Science and Electronic Engineering Hunan University Changsha410012 China

Molecular optimization, which aims to discover improved molecules from a vast chemical search space, is a critical step in chemical development. Various artificial intelligence technologies have demonstrated high effectiveness and efficiency on molecular optimization tasks. However, few of these technologies focus on balancing property optimization with constraint satisfaction, making it difficult to obtain high-quality molecules that not only possess desirable properties but also meet various constraints. To address this issue, we propose a constrained multi-property molecular optimization framework (CMOMO), which is a flexible and efficient method to simultaneously optimize multiple molecular properties while satisfying several druglike constraints. CMOMO improves multiple properties of molecules with constraints based on dynamic cooperative optimization, which dynamically handles the constraints across various scenarios. Besides, CMOMO evaluates multiple properties within discrete chemical spaces cooperatively with the evolution of molecules within an implicit molecular space to guide the evolutionary search. Experimental results show the superior performance of the proposed CMOMO over five state-of-the-art molecular optimization methods on two benchmark tasks of simultaneously optimizing multiple non-biological activity properties while satisfying two structural constraints. Furthermore, the practical applicability of CMOMO is verified on two practical tasks, where it identified a collection of candidate ligands of β2-adrenoceptor GPCR and candidate inhibitors of glycogen synthase kinase-3β with high properties and under drug-like constraints. Copyright © 2024, The Authors. All rights reserved.

关键词： Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

BD-YOLO: Optimising Insect Imbalance Data Detection Models

BD-YOLO: Optimising Insect Imbalance Data Detection Models

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Jian–Yi Wang Zhen–Hong Jia Gang Zhou Jia–Jia Wang School of Computer Science and Technology Xinjiang University Urumqi China Xinjiang Uygur Autonomous Region Signal Detection and Processing Key Laboratory Xinjiang University Urumqi China

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

Vision-based insect detection is an important task in smart agriculture. Field-collected insect image datasets usually show severe imbalances in categories. Previous models have insufficient accuracy as well as low real-time performance for detecting unbalanced data of insects. To address the issues described above, an improved framework Balance Detect YOLO(BD-YOLO) based on YOLOv8 is proposed in this paper. We innovatively designed Focaler-CPIoU loss to increase the weight of a few classes of samples to achieve the optimisation of pest imbalance data detection. We introduced lightweight convolutional MBConv to improve the recognition accuracy while reducing the number of model parameters. In order to verify the effectiveness of the method in this paper, we established an insect dataset containing six types of insects, in which the most numerous thrips is 431.5 times more than the least numerous chrysopaperla. The experimental results show that compared with YOLOv8, the mAP50 reaches 61.7% with a 73.1% reduction in the number of model parameters, an improvement of 5.4%, and an improvement of 769 in FPS. A feasible approach to optimise the detection of unbalanced number of insects is provided in this paper along with the ability to be deployed on lightweight hardware devices.

关键词： YOLO Smart agriculture Accuracy Insects Data models Real-time systems Hardware Optimization Monitoring Cybernetics

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient UAV-Based IoT Communications With WiFi Suppression in 5 GHz ISM Bands

Energy-Efficient UAV-Based IoT Communications With WiFi Supp...

引用

作者： Lin, Deping Zuo, Peiliang Peng, Tao Qian, Rongrong Wang, Wenbo Beijing University of Posts and Telecommunications Wireless Signal Processing and Network Laboratory Key Laboratory of Universal Wireless Communication Ministry of Education Beijing100876 China Beijing Institute of Electronic Science and Technology Department of Electronics and Communication Engineering Beijing100070 China Beijing University of Posts and Telecommunications School of Artificial Intelligence Beijing100876 China

Unmanned Aerial Vehicle (UAV) based communication is a promising technology for offering wireless communication services. UAVs can typically be adopted as aerial base stations to collect data from ground Internet of Things (IoT) devices. However, the Ground-to-Air link of UAV-based IoT communications is prone to be interfered by surrounding WiFi devices in the Industrial, Scientific, Medical (ISM) band. This paper aims to enable reliable uplink communications for IoT devices in 5 GHz ISM bands, thereby reducing the hover time and energy consumption of the UAV. To this end, we first study and design suppression frames suitable for WiFi devices. Then a suppression method is proposed, which is shown to be effective for all the tested devices, based on emulation performance verification of the frames for multiple commercial off-the-shelf (COTS) WiFi devices. Moreover, by taking the energy consumption of the UAV and multiple transmission parameters of the suppression method into account, we formulate an optimization problem for the desired uplink, which is designed to minimize the energy consumption of the UAV, under the constraints of satisfying the link channel capacity. Given that the optimization problem is non-convex mixed-integer nonlinear programming, this paper proposes an efficient algorithm that takes advantage of the suppression performance of the utilized frames. Numerical simulations demonstrate the performance of the proposed algorithm in terms of the WiFi device density, UAV weight, channel capacity requirement and parameters of the suppression method. The communication quality of the desired Ground-to-Air link is shown to be significantly improved, while the consumed energy is demonstrated to be obviously reduced. © 1967-2012 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Adaptive Noise Reduction Algorithm Based on SPP and NMF for Environmental Sound Event Recognition under Low-SNR Conditions

引用

Wireless Communications and Mobile Computing 2023年第1期2023卷

作者： Luo, Li-Yan Guo, Shu-Ting Wang, Mei Qiu, Hong-Bing Liu, Zheng-Hong Provincial Ministry of Education Key Laboratory of Cognitive Radio and Signal Processing Guilin University of Electronic Technology Guilin Guangxi541004 China Guangxi Key Laboratory of Wireless Broadband Communication and Signal Processing Guilin University of Electronic Technology Guilin Guangxi541004 China College of Information Science and Engineering Guilin University of Technology Guilin Guangxi541007 China

Nonnegative matrix factorization- (NMF-) based noise reduction methods can effectively improve the performance of environmental sound recognition. However, when the environmental sound overlaps highly with the noise, the spectral line loss and noise residue will occur in the low signal-to-noise ratio (SNR) condition. An adaptive noise reduction algorithm was proposed in this paper. First, noisy environmental sound is separated into estimated noise and environmental sound using NMF. Then, the estimated noise is used to calculate sound presence probability (SPP), which is adapted to decrease spectral line loss and achieve accurately estimated noise. Subsequently, the estimated noise combines with noisy environmental sound to obtain the estimated environmental sound. Finally, SPP is applied to reduce residual noise in the estimated environmental sound and reconstruct the environmental sound. The simulation results demonstrate that the proposed algorithm outperforms the traditional algorithms and NMF-based methods in terms of perceptual evaluation of speech quality (PESQ) and global SNR with increase of X% and X%, respectively. Moreover, the proposed method can effectively improve the environmental sound recognition rate. Particularly, the proposed method makes a 16.2% increase of F1-score in car horn recognition under the realistic acoustic condition. © 2023 Li-Yan Luo et al.

关键词： signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Target Spatial-Frequency Scattering Response Sparse Approximation using Multi-static Radar Observations

Target Spatial-Frequency Scattering Response Sparse Approxim...

引用

2021 CIE International Conference on Radar, Radar 2021

作者： Zhou, Shenghua Cai, Jiewen Huo, Chaoying Ma, Hui Peng, Xiaojun Xidian University National Laboratory of Radar Signal Processing Xi'an710071 China Science and Technology on Electromagnetic Scattering Laboratory Beijing100854 China

ISBN: (纸本)9781665498142

Inverse synthetic aperture radar (ISAR) can form an image of the target with a sequence of wideband coherent observations, but it is generally difficult to generalize ISAR images from other directions. In this paper, with observations of a noncoherent multistatic radar system to the same target, we study how to approximate the target spatial-frequency joint response by the scattering centers target model. We optimize the scattering intensities of the scatterers such that the target response at selected frequency ticks and spatial directions, under sparse constraints to select proper number of scattering centers. Numerical results with a 3D plane model indicates that the target response can be approximated by a few scattering centers in a good accuracy, even for spatial directions in which the target is not probed before. © 2021 IEEE.

关键词： frequency scattering diversity MIMO radar radar cross section radar target 3D imaging scattering centers target model spatial scattering diversity

来源：评论

学校读者我要写书评

暂无评论

Data Association with Passive Angle Measurements 10

Data Association with Passive Angle Measurements

引用

10th International Conference on Control, Automation and Information sciences, ICCAIS 2021

作者： Wang, Linhai Li, Zhuyu Zhou, Shenghua Zhang, Xinyu Xing, Xiaoyu Gou, Mingjiang Xidian University National Laboratory of Radar Signal Processing Xi'an710071 China Science and Technology on Electromagnetic Scattering Laboratory Beijing100854 China

ISBN: (纸本)9781665440295

Some passive sensors can measure only relative angles of signals and in a distributed sensor network, it is interesting to associate measurements of angles from distributed sensors and then to estimate the positions of signal sources. This paper studies the data association problem and the intersection localization problem for a distributed passive sensor network. Under the assumption that the locations of the sensors are known a priori, different signal directions of distributed passive sensors constitute different lines and those with sufficiently small minimal distances are deemed to be from the same signal sources. Meanwhile, for associated signals, the signal location estimate is the average position of the points over the lines with minimal distances to each other. The impacts of angle estimation accuracy and platform self-localization accuracy are analyzed in numerical results, indicating that this method can achieve a high data association and positioning performance with a low computation cost. © 2021 IEEE.

关键词： Sensor networks

来源：评论

学校读者我要写书评

暂无评论

A Long Synthetic Aperture Passive Localization Method Using Two Planes

A Long Synthetic Aperture Passive Localization Method Using ...

引用

2021 CIE International Conference on Radar, Radar 2021

作者： Chen, Bowei Wang, Yuqi Sun, Guang-Cai Xing, Mengdao Zhang, Zijing Yang, Xiaoniu Xidian University National Laboratory of Radar Signal Processing Xi'an China Science and Technology on Communication Information Security Control Laboratory Jiaxing China

ISBN: (纸本)9781665498142

A long synthetic aperture passive localization algorithm is proposed in this paper. First of all, the Doppler change rate of signal can be measured by the image contrast and then, grid points are divided within the maximum possible latitude and longitude of the emitter location, the Doppler change rate at each grid point can be calculated by using known position and velocity of the receiver. The grid points at which the calculated Doppler change rate is equal to the value measured by the received signal form an isoline. Two receivers can draw two isolines on the ground and the intersection of the isolines gives estimate of the emitter location. © 2021 IEEE.

关键词： Azimuth focusing Doppler change rate Passive localization Synthetic aperture localization

来源：评论

学校读者我要写书评

暂无评论

Small Target Insect Detection Based on Improved YOLOv8n

Small Target Insect Detection Based on Improved YOLOv8n

引用

International Conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Jianyu Shi Yuan Jia Gang Zhou Jiajia Wang Zhenhong Jia School of Computer Science and Technology Xinjiang University Urumqi China Xinjiang Uygur Autonomous Region Signal Detection and Processing Key Laboratory School of Statistics Renmin University of China Beijing

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Insect pests greatly affect the growth and harvest of crops, and accurate identification of insect species is very important to the agricultural industry. The insect dataset has the problem that the target is too small to locate, detect, and identify. To solve this problem, We designed a modified YOLOv8n for detecting small target insects. First, we add a small object detection head to the network structure of the YOLOv8n (You Only Look Once) model. Then, we improve C2f and Conv in YOLOv8n, construct C2f-RFAConv by adding Receptive-Field Attention Convolutional Operation (RFAConv) into C2f for the first time, and replace the original convolution with RFAConv for feature extraction. Finally, we improve Wise-IoU (WIoU) loss function to solve the problem of small object detection difficulty. When the number of parameters is reduced, the performance of our model YOLOv8n-Improved on the Yellow Sticky Traps dataset and self-built dataset is greatly improved compared with YOLOv8n, and it also has great advantages compared with other models in the YOLO series. This work plays an important role in our efforts to achieve intelligent pest management in agriculture.

关键词： YOLO Smart agriculture Accuracy Head Convolution Insects signal processing algorithms Pesticides Feature extraction Speech processing

来源：评论

学校读者我要写书评

暂无评论

Prompt Fusion and Aspect-Oriented Filtration for Aspect-Based Multimodal Sentiment Analysis

Prompt Fusion and Aspect-Oriented Filtration for Aspect-Base...

引用

International Conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Jiachang Sun Xiuhong Li Fuxian Zhu School of Computer Science and Technology XinJiang University Urumqi China Xinjiang Key Laboratory of Signal Detection and Processing Urumqi China School of Economics and Management XinJiang University Urumqi China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Currently, aspect-based multimodal sentiment analysis (ABMSA) remains a highly hot research field, aiming to leverage various modalities such as images and text to determine the sentiment orientation of viewpoint entities. Although deep learning methods have made significant progress in this field, some challenges still exist: Image information unrelated to the viewpoint entity can introduce noise, insufficient interaction during modal fusion. To solve these problems, we propose a novel ABMSA model with prompt fusion and noise filtration. Specifically, we introduced an Image Noise Filtering (INF) module that can filter the extracted image features to reduce the noise introduced by the irrelevant between viewpoint entity and the image. Additionally, we implemented Multimodal Prompt Fusion (MPF) module to enhance the interaction between modalities, addressing the issue of minimal effective features related to viewpoint entity during the fusion stage of text and image features. Experimental results show that the model outperforms the baseline model on two public datasets, Twitter-2015 and Twitter-2017, demonstrating that our proposed approach effectively enhances the accuracy of aspect-based multimodal sentiment analysis tasks.

关键词： Deep learning Sentiment analysis Analytical models Accuracy Filtration Noise Feature extraction Information filters Acoustics Speech processing

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：