检索结果-内蒙古大学图书馆

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Zihao He Qianyu Shu Jinming Wen Hing Cheung So Department of Information Science and Technology Jinan University Guangzhou China School of Mathematical Sciences Sichuan Normal University Chengdu China Pazhou Lab Guangzhou China Department of Electrical Engineering City University of Hong Kong Hong Kong SAR China

In this work, we derive the proximity operator of an arctangent penalty, which is expressed using hyperbolic functions of sine and cosine. This penalty is then applied to sparse signal recovery, and an efficient arctangent regularization iterative thresholding (ARIT) algorithm is proposed, offering closed-form solutions for the subproblems associated with the arctangent penalty. Extensive experiments are conducted to compare the performance of ARIT with several existing iterative thresholding algorithms, and the results demonstrate that our algorithm achieves the best overall performance in terms of the probability of successful recovery, phase transition and running time.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Smart Droplet Microfluidic system for Single-Cell Selective Lysis and Real-Time Sorting Based on Micro-Injection and Image Recognition

SSRN

引用

SSRN 2023年

作者： Yu, Zhihang Jin, Jing Chen, Siyuan Shui, Lingling Chen, Huaying Shi, Liuyong Zhu, Yonggang Center for Microflows and Nanoflows School of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen518055 China Joint International Laboratory of Optofluidic Technology and System National Center for International Research on Green Optoelectronics School of Information and Optoelectronic Science and Engineering South China Normal University Guangzhou510006 China Mechanical and Electrical Engineering College Hainan University Haikou570228 China

Single-cell analysis has important implications for understanding the specificity of cells. To analyze the specificity of rare cells in complex biological samples such as blood and biopsies, selective lysis of single cells is pivotal but difficult. Microfluidics, particularly droplet microfluidics, has emerged as a promising tool for single-cell analysis. In this paper, we present a smart droplet microfluidic system that allows for single-cell selective lysis and real-time sorting, aided by the techniques of micro-injection and image recognition. A custom droplet and single-cell recognition program based on Python is proposed, which can also coordinate the operation of various parts of the microfluidic system. We have systematically investigated the effects of voltage and injection pressure applied to the oil-water interface on droplet micro-injection. An efficient and selective droplet injection scheme with the image feedback has been demonstrated. The droplet injection efficiency is found to increase dramatically from 2.5% to about 100%. Furthermore, we have proved that cell lysis solution can be selectively injected into target single-cell droplets. Then these droplets are shifted into the sorting area, with the sorting efficiency for K562 cells reaching up to 73%. The system function is finally explored by introducing complex cell samples, namely K562 cells and HUVECs, with a success rate of 75.2% in treating K562 cells as targets. This system enables automated single-cell selective lysis without the need for manual handling and sheds new light on the cooperation with other detection techniques for a broad range of single-cell analysis. © 2023, The Authors. All rights reserved.

关键词： Microfluidics

来源：评论

学校读者我要写书评

暂无评论

Use of Deep Learning Application in Medical Devices 4

Use of Deep Learning Application in Medical Devices

引用

4th International Conference on Inventive Research in Computing Applications, ICIRCA 2022

作者： Marakala, Vijaya Sriramakrishnan, G.V. Jakka, Geethamanikanta Shingadiya, Chetan J. Widiastuti, Hesti Prawita Ortiz, Geovanny Genaro Reivan College of Medicine University of Bisha Kingdom of Saudi Arabia Saudi Arabia Sikkim Manipal Institute of Technology Sikkim Manipal University Computer Science and Engineering India Information Technology University of the Cumberlands United States Computer Engineering R K University India Poltekkes Kemenkes Kaltim Indonesia Catholic University of Cuenca Laboratory of Basic Psychology Behavioral Analysis and Programmatic Development PAD-LAB. Ecuador Ecuador

ISBN: (数字)9781665497077

ISBN: (纸本)9781665497077

Artificial Intelligence (AI) is a system that helps machines to march with human abilities within daily lifestyles. Deep learning supported by AI can be an effective application within healthcare sector. This research has explained various aspects of Deep learning application that can be a major area of concern for pushing the development process of Indian medical sector that have lack of infrastructure and lack of capacity, to take less time to optimise the medical diagnosis process. This research has also investigated the advantages and disadvantages that medical sector might face while using deep learning applications. Deep learning applications under AI systems are used to classify objects. CNN model, Machine-learning tools, and other tools that use deep learning approach are effective to diagnose any disease and in medical image analysis process. Deep learning techniques are also used to detect heart disease and manage the data regarding the patients of heart diseases. Secondary data collection method has been used and a thematic analysis has been conducted in this research to describe and find various challenges that might have been engaged within deep learning process used in medical sectors of India. It has been found that, Deep Learning is used widely for COVID-19 medical image processing through a fully connected CNN model. As a result, the main finding states that deep learning application creates a major scope for the improvement in Indian medical sector. © 2022 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

A Low-profile Ultrawideband Dual-polarized TCDA

A Low-profile Ultrawideband Dual-polarized TCDA

引用

Cross Strait Quad-Regional Radio science and Wireless technology Conference (CSRWTC)

作者： Liangliang Zhao Aidong Li Chufeng Hu Chuwei Li Mingxuan Zheng Hailiang Zhu Tao Ma Yongmao Wang Jiaping Hou Huiling Zhao School of Electronics and Information Northwestern polytechnical university (NPU) Xi'an China Science and Technology on UAV Laboratory Northwestern Polytechnic University (NPU) Xi'an China China Academy of Space Technology (CAST) Beijing China System Engineering Division Xi'an Electronic Engineering Research Institute Xi'an China The 43rd Research Institute of CETC Hefei China AVIC SHAANXI AERO ELECTRIC CO. LTD

ISBN: (数字)9798331507794

ISBN: (纸本)9798331507800

In this work, a low-profile dual-polarized tightly coupled dipole array antenna is proposed based on the multi-notch balun and the planar metasurface design. Through the simulation analysis, the antenna realizes the ultra bandwidth of 1.4-13.2 GHz, and the impedance characteristics matches greatly. Finally, the performance of this design is validated by the finite 5x5 tightly coupled array and the specific analysis is listed.

关键词： Wireless communication Dipole antennas Baluns Bandwidth Metasurfaces Impedance Antenna arrays Ultra wideband technology

来源：评论

学校读者我要写书评

暂无评论

GraphEye: A Novel Solution for Detecting Vulnerable Functions Based on Graph Attention Network

GraphEye: A Novel Solution for Detecting Vulnerable Function...

引用

IEEE International Conference on Data science in Cyberspace (DSC)

作者： Li Zhou Minhuan Huang Yujun Li Yuanping Nie Jin Li Yiwei Liu School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu China National Key Laboratory of Science and Technology on Information System Security BeijingChina School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China

ISBN: (纸本)9781665418164

With the continuous extension of the Industrial Internet, cyber incidents caused by software vulnerabilities have been increasing in recent years. However, software vulnerabilities detection is still heavily relying on code review done by experts, and how to automatically detect software vulnerabilities is an open problem so far. In this paper, we propose a novel solution named GraphEye to identify whether a function of C/C++ code has vulnerabilities, which can greatly alleviate the burden of code auditors. GraphEye is originated from the observation that the code property graph of a non-vulnerable function naturally differs from the code property graph of a vulnerable function with the same functionality. Hence, detecting vulnerable functions is attributed to the graph classification problem. GraphEye is comprised of VecCPG and GcGAT. VecCPG is a vectorization for the code property graph, which is proposed to characterize the key syntax and semantic features of the corresponding source code. GcGAT is a deep learning model based on the graph attention networks, which is proposed to solve the graph classification problem according to VecCPG. Finally, GraphEye is verified by the SARD Stack-based Buffer Overflow, Divide-Zero, Null Pointer Deference, Buffer Error, and Resource Error datasets, the corresponding F1 scores are 95.6%, 95.6%, 96.1%, 92.6%, and 96.1% respectively, which validate the effectiveness of the proposed solution.

关键词： Deep learning Codes Conferences Semantics Cyberspace Syntactics Data science

来源：评论

学校读者我要写书评

暂无评论

All-fiber Mode-division-multiplexed Recirculating-loop Transmission system with Ultralow-cost MIMO Algorithm

All-fiber Mode-division-multiplexed Recirculating-loop Trans...

引用

2023 Opto-Electronics and Communications Conference, OECC 2023

作者： Zhao, Tianfeng Wen, Feng Tang, Shenglong Tian, Feng Lao, Hailing Wu, Baojian Xu, Bo Qiu, Kun University of Electronic Science and Technology of China Key Lab of Optical Fiber Sensing and Communication Networks Ministry of Education Chengdu China Beijing University of Posts and Telecommunications State Key Laboratory of Information Photonics and Optical Communications Beijing Key Laboratory of Space-round Interconnection and Convergence School of Electronic Engineering Beijing China International Education College Beijing Vocational College of Agriculture Beijing China

We experimentally demonstrate an all-fiber few-mode recirculating loop system (AF-FMRLS) with the ultralow-cost transfer-learning multi-input and multi-output (TL-MIMO) equalizers. 20 round trips were tested with the ... 详细信息

ISBN: (纸本)9781665462136

关键词： Cost reduction

来源：评论

学校读者我要写书评

暂无评论

Understanding the Robustness of 3D Object Detection with Bird'View Representations in Autonomous Driving

Understanding the Robustness of 3D Object Detection with Bir...

引用

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023

作者： Zhu, Zijian Zhang, Yichi Chen, Hai Dong, Yinpeng Zhao, Shu Ding, Wenbo Zhong, Jiachen Zheng, Shibao Institute of Image Communication and Network Engineering Shanghai Jiao Tong University China Institute for Ai Tsinghua University BNRist Center Thbi Lab Dept. of Comp. Sci. and Tech. China School of Computer Science and Technology Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Information Materials and Intelligent Sensing Laboratory of Anhui Province China Saic Motor Ai Lab Zhongguancun Laboratory China

ISBN: (纸本)9798350301298

3D object detection is an essential perception task in autonomous driving to understand the environments. The Bird's-Eye-View (BEV) representations have significantly improved the performance of 3D detectors with camera inputs on popular benchmarks. However, there still lacks a systematic understanding of the robustness of these vision-dependent BEV models, which is closely related to the safety of autonomous driving systems. In this paper, we evaluate the natural and adversarial robustness of various representative models under extensive settings, to fully understand their behaviors influenced by explicit BEV features compared with those without BEV. In addition to the classic settings, we propose a 3D consistent patch attack by applying adversarial patches in the 3D space to guarantee the spatiotemporal consistency, which is more realistic for the scenario of autonomous driving. With substantial experiments, we draw several findings: 1) BEV models tend to be more stable than previous methods under different natural conditions and common corruptions due to the expressive spatial representations;2) BEV models are more vulnerable to adversarial noises, mainly caused by the redundant BEV features;3) Camera-LiDARfusion models have superior performance under different settings with multi-modal inputs, but BEV fusion model is still vulnerable to adversarial noises of both point cloud and image. These findings alert the safety issue in the applications of BEV detectors and could facilitate the development of more robust models. © 2023 IEEE.

关键词： Autonomous driving

来源：评论

学校读者我要写书评

暂无评论

Spatiotemporal Change Patterns and Driving Factors of Land Surface Temperature in the Yunnan-Kweichow Plateau from 2000 to 2020

SSRN

引用

SSRN 2023年

作者： He, Zhi-Wei Tang, Bo-Hui Faculty of Land Resources Engineering Kunming University of Science and Technology Kunming650093 China Key Laboratory of Plateau Remote Sensing Department of Education of Yunnan Province Kunming China State Key Lab of Resources and Environmental Information System Institute of Geographic Sciences and Natural Resources Research Chinese Academy of Sciences Beijing100101 China

In this study, the spatiotemporal change patterns and driving factors of land surface temperature (LST) on the Yunnan-Kweichow Plateau (YKP) during 2000-2020 are investigated by using the Daily 1-km all-weather land surface temperature dataset for the Chinese landmass and its surrounding areas (TRIMS LST) provided by National Tibetan Plateau Data Center. The main findings are as follows: Annual mean LST increases at an increasing rate of 0.016 K/year. Annual mean daytime LST is slightly decreasing with a rate of 0.009 K/year. Annual mean nighttime LST is significant increasing with a trend of 0.042 K/year;The trend and seasonal components of the daily mean LST have five and four breakpoints, respectively;The LST lapse rates (TLR) at nighttime are generally higher than those at daytime over the YKP. Summer nighttime has the highest TLR of 0.59 K/100m, while winter daytime shows the lowest TLR of 0.18 K/100m;The controlling effects of seven factors selected are generally stronger in the nighttime than those in the daytime. Elevation and air temperature predominate in the spatiotemporal distribution of LST over the YKP during the daytime and nighttime, respectively. This study contributes to the mitigation and adaptation to climate change of LST in the plateau and plays a theoretical reference role in formulating corresponding policies for environmental protection. © 2023, The Authors. All rights reserved.

关键词： Time series analysis

来源：评论

学校读者我要写书评

暂无评论

A Legal News Summarisation Model Based on RoBERTa, T5 and Dilated Gated CNN

A Legal News Summarisation Model Based on RoBERTa, T5 and Di...

引用

International Conference on Tools for Artificial Intelligence (ICTAI)

作者： Weijian Qin Xudong Luo School of Computer Science and Engineering Guangxi Normal University Guilin China Guangxi Key Lab of Multi-source Information Mining and Security Guilin China Key Lab of Education Blockchain and Intelligent Technology Ministry of Education of PRC Guilin China

Summarising legal news is crucial for monitoring judicial sentiments and managing emergencies, by distilling accurate, concise and comprehensive insights from extensive, complex legal texts to enhance the efficiency of managing public opinions. However, current methods are limited in handling long-form texts. To address this, we propose a novel two-phase sentence-level summarisation model. It first converts paragraphs into sentence vectors using RoBERTa and average pooling layer, then selects the more relevant sentences using a Dilated Gated CNN layer. These extracted sentences are treated as a corpus for the T5 PEGASUS model to generate refined summaries. Experiments show our model significantly outperforms baselines on ROUGE metrics by effectively capturing relevant information from lengthy, intricate legal opinions to produce high-quality summaries.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Segment-Level Cross-Modal Knowledge Transfer for Speech Sentiment Analysis 4

Segment-Level Cross-Modal Knowledge Transfer for Speech Sent...

引用

4th IEEE International Conference on Computer and Communication engineering technology, CCET 2021

作者： Zhang, Sheng Chen, Jincai Li, Minglei Li, Taisong Lu, Ping Wang, Zhu Huazhong University of Science and Technology Wuhan National Laboratory for Optoelectronics Wuhan430074 China Key Laboratory of Information Storage System Engineering Research Center of Data Storage Systems and Technology Ministry of Education of China Wuhan430074 China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China Huawei Cloud Bu Shenzhen518129 China Huawei Technology Co. Ltd. Shenzhen518129 China

ISBN: (纸本)9781665438902

Speech sentiments are inherently dynamic. However, most of the existing methods for speech sentiment analysis follow the paradigm: one single hard label for an entire utterance, which results in that segment-level fine-grained sentiment information is unavailable and sentiment dynamics can not be considered. In addition, due to the ambiguity of sentiments, it is difficult and time-consuming to annotate an utterance at the segment level. In this work, to alleviate the above issues, we propose to use sentiment profiles (SPs), which give a time series of the segment-level soft labels to capture the fine-grained sentiment cues across an utterance. To obtain a large number of labeled data with segment-level annotations, we propose a cross-modal knowledge transfer method at the segment level to transfer facial expression knowledge from images to audio segments. Further, we propose the sentiment profile refinery (SPR) to iteratively update sentiment profiles to improve the accuracy of SPs and overcome the noise problem in the cross-modal knowledge transfer method. Our experiments on the CH-SIMS dataset with the iQIYI-VID dataset as unlabeled data show that our method can effectively exploit additional unlabeled audio-visual data and achieve state-of-the-art performance. © 2021 IEEE.

关键词： Sentiment analysis

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：