检索结果-内蒙古大学图书馆

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

Underwater Acoustic Target Recognition via Combining Adaptive Line Enhancement and Deep Neural Network

Underwater Acoustic Target Recognition via Combining Adaptiv...

引用

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

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

Ship Detection Method Based on Frequency Enhanced MSER for High Resolution SAR Image 2

引用

2nd China International SAR Symposium, CISS 2021

作者： Sun, Kun Ma, Liang Wang, Fei Liang, Yi Xidian University National Laboratory of Radar Signal Processing Xi'an China Shanghai Radio Equipment Research Institue Shanghai China Shanghai Academy Spaceflight Technology Shanghai China

ISBN: (纸本)9787000000001

Synthetic aperture radar (SAR) ship detection is an important part of marine monitoring. With the development of SAR, traditional constant false alarm rate (CFAR) detectors suffer from multiscale situation. To solve this problem and achieve better performs, a ship detection method based on frequency enhanced MSER for high resolution SAR image is proposed in this paper. First, a frequency saliency method is used to enhance the contrast between ship targets and sea background. Then, candidate regions are proposed by the MSER method. Finally, generalized Gamma distribution ( GΓD ) is utilized to complete precise detection results. Experimental results demonstrate the effectiveness of the proposed method. © 2021 SISE.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

Classification of UAV and Ground Targets By Micro-Doppler Signatures Based on PD Surveillance radar

Classification of UAV and Ground Targets By Micro-Doppler Si...

引用

2021 CIE International Conference on radar, radar 2021

作者： Ma, Beili Chen, Baixiao Zhang, Zhengrong Diao, Dandan Fang, Liang Zhao, Fei Xidian University National Laboratory of Radar Signal Processing Xi'an China The 27th Institute of China Electronics Technology Group Corporation Department of Microwave Zhengzhou China

ISBN: (纸本)9781665498142

As typical of low flying altitude, small size and slow flying speed (LSS) targets, the detection and recognition of mini-sized unmanned aerial vehicle (U A V) by surveillance radar is of great significance. However, it is difficult to realize classification of UA V and ground targets based on pulse Doppler (PD) surveillance radar because of low resolution and short dwell time. Based on the method of multiple micro-Doppler signatures (m-Ds) association, classification of UA V and non-UAV targets is considered and studied in this paper. We first focus on the micro-Doppler signature of UAV targets by PD radar, including the echo model and the micro-Doppler spectrum distribution. To verify the proposed method, we investigate UAVs, human and vehicle using the developed PD surveillance radar in a series of experiments. And seven key features are extracted from both frequency domain and time-frequency domain. The experiment results show that the classification accuracy is found to be more than 90%. © 2021 IEEE.

关键词： Micro-Doppler Signature PD radar Time-Frequency Analysis UA V classification

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

A Modified Omega-K Algorithm for Bistatic Forward-Looking SAR Data Imaging

A Modified Omega-K Algorithm for Bistatic Forward-Looking SA...

引用

2021 CIE International Conference on radar, radar 2021

作者： Zhang, Tinghao Li, Yachao Song, Xuan Zhang, Tao Wu, Chunfeng Sun, Ziyue Xidian University National Laboratory of Radar Signal Processing Xi'an China Chengdu Aerospace Science and Technology Microelectronics System Research Institute Chengdu China University of Exeter BEng Electronic Enginnering Cornwall United Kingdom

ISBN: (纸本)9781665498142

Accurate two dimension frequency spectrum (2D FS) with acceleration, two-way range coupling terms, and spatial variant Doppler parameters are main problems to be solved in translational variant bistatic forward-looking SAR (TV BFSAR) with curved trajectory. For these issues, a modified Omega-K imaging algorithm is derived in this paper. The maximum usage of 2D FS based on method of series reversion (MSR) is achieved by linear range cell migration correction and 2D FS is linearized in bistatic range by using high-order polynomial fitting. Then, a method of azimuth resampling is introduced to implement compensation of spatial variant Doppler parameters. And the small-aperture data is focused in the azimuth frequency domain to avoid azimuth aliasing without padding zeros. Finally, the raw bistatic SAR data verifies the effectiveness of the proposed method © 2021 IEEE.

关键词： bistatic Omega-K algorithm space variance Translational variant bistatic forward-looking synthetic aperture radar (TV BFSAR)

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：