检索结果-内蒙古大学图书馆

7th International Conference on Signal Processing and Machine Learning, SPML 2024

作者： Zhou, Zhen Li, Zuoyong Wang, Zhengyuan Teng, Shenghua Wang, Tao College of Electronic and Information Engineering Shandong University of Science and Technology Qingdao China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control School of Computer and Big Data Minjiang University Fuzhou China

ISBN: (纸本)9798400717192

Semi-supervised learning has garnered significant attention, particularly in medical image segmentation, owing to its capacity to leverage a large number of unlabeled data and a limited amount of labeled data to improve performance. However, most existing semi-supervised segmentation methods exhibit shortcomings in supervising unlabeled data, both in the label space due to potential noise in pseudo-labels, and the feature space due to indistinct class boundaries. To address the issues above, we propose Dual-view Label and Feature Supervision Network, termed DLFS-Net, to enhance label and feature supervision for unlabeled data. Our approach is based on a dual-view learning strategy that incorporates two modules: the Confidence Fusion Supervision Module (CFS) and the Dual-view Prototype Learning Module (DPL). Specifically, the CFS module generates weight matrices to integrate complementary information from two model outputs, producing more accurate pseudo-labels in the label space. The DPL module reduces intra-class variations in the feature space from two different views through prototype learning to generate clear class boundaries. Experiments on the LA and Pancreas-CT datasets demonstrate that our framework show solid gains (e.g.,1.76% Dice and 2.37% Jaccard improvement on Pancreas-CT dataset with 20% labeled data) compared with the state-of-the-art methods. © 2024 ACM.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Comparison of machine learning and deep learning methods for detection of liver abnormality 4th

Comparison of machine learning and deep learning methods for...

引用

4th Annual International Conference on Data Science, Machine Learning and Blockchain Technology, AICDMB 2023

作者： Vaidehi Nayantara, P. Kamath, Surekha Manjunath, K.N. Kadavigere, Rajagopal Department of Instrumentation and Control Engineering Manipal Institute of Technology Manipal India Department of Computer Science and Engineering Manipal Institute of Technology Manipal Academy of Higher Education Manipal India Kasturba Medical College Manipal Academy of Higher Education Manipal India

ISBN: (纸本)9781032426853

Liver is a vital organ that performs various essential functions. Liver cancer can have severe implications on human health, including death. To reduce the mortality rate, early detection of hepatic cancer is imperative. For rapid diagnosis and treatment planning, developing a computerized system that can aid in the diagnosis is essential. In this paper, machine learning and deep learning methods were compared for identifying abnormal liver from computed tomography images. The liver was segmented using DeepLabv3 + network. The machine learning method used, histogram and gray level co-occurrence matrix for feature extraction and support vector machine for classification. The deep learning methods investigated were ResNet, ShuffleNet and EfficientNet. Accuracy, sensitivity and specificity were used for performance evaluation. The results of our experiments showed that the deep learning methods outperformed the machine learning methods. Among the deep learning models, EfficientNet gave the highest accuracy of 87%. As future work, the abnormal liver can be further classified into benign and malignant classes. © 2024 The Author(s).

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Enhanced 3d Path Planning for Uavs Using Multi-Strategy Sand Cat Swarm Optimization

SSRN

引用

SSRN 2024年

作者： Chen, Baolong Wang, Fangchao Xu, Sitong Wang, Haocheng Zhang, Yu College Of Computer And Control Engineering Northeast Forestry University Heilongjiang Harbin150000 China

With the continuous advancement of informatization and intelligence, the application of Unmanned Aerial Vehicles (UAVs) has become increasingly widespread. To improve the operational efficiency and safety of UAVs, 3D path planning has become an important research direction. However, existing path planning methods have some issues, such as overly idealized environmental models, difficulty in meeting practical task requirements, poor algorithm stability, and susceptibility to local optima. These issues limit the effectiveness of UAV *** paper proposes a UAV 3D path planning method based on a Multi-Strategy Improved Sand Cat Swarm Optimization (ISCSO) algorithm. First, elevation data of the UAV's operating area is extracted, and terrain modeling is performed using an interpolation-based graphing method to provide more accurate environmental data. Then, B-splines are used for flight path fitting, and a fitness function is constructed considering both energy consumption and flight safety to optimize path performance. To enhance the global search capability of the Sand Cat Swarm Optimization (SCSO) algorithm and avoid local optima, several improvements are proposed, including enhancing movement strategy, optimizing the exploration phase, and introducing a nonlinear adjustment *** a series of experiments, including path generation comparison, obstacle avoidance tests, and simulations in complex environments, the results show that the proposed method can efficiently complete tasks in complex forest environments. Compared with the original SCSO algorithm, the ISCSO algorithm generates paths that not only significantly reduce energy consumption but also improve flight safety, demonstrating the application potential and advantages of this method in 3D path planning for UAVs. © 2024, The Authors. All rights reserved.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Near-Source Attack for Isolated Networks with Covert Channel Transmission

Near-Source Attack for Isolated Networks with Covert Channel...

引用

IEEE International Conference on Cyber Security and Cloud Computing (CSCloud)

作者： Zhiqiang Ruan Yuchen Yang Lejia Chen College of Computer and Control Engineering Minjiang University Fuzhou China

This paper investigates a new attack method called "near-source attack". It leverages the broadcast frames of the 802.11 protocol to establish a hidden tunnel and bypass physical isolation networks or air-gapped networks. We first analyze and implement a common technology known as Ghost Tunnel, which allows the attacker to control the target host and transmit information without being detected. However, this method suffers from frame loss, repeated frame, and attack transparency. We then propose an improved solution to deliver malicious programs to the target host using a modified BadUSB hardware device. Once the attackers successfully get in the isolated networks, they can bypass security protection devices and exploit vulnerabilities of communication protocols, so that they can remote control of target devices and hidden data transmission. We further conducted experiments to verify the feasibility and effectiveness of this attack scheme. The results indicate that the attack logic is capable of inducing the target host to engage in covert communication. Finally, we give some defense measures for such attacks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Update Strategy for KCF

An Adaptive Update Strategy for KCF

引用

IEEE Asia-Pacific Conference on Antennas and Propagation (APCAP)

作者： Xiaochun Xu Nixuan Lin Dingrong Chen Min Liu Nanling Su College of Computer and Control Engineering Minjiang University Fuzhou China

Great advance has been achieved to improve the CF-based trackers, most of them ignore to improve update scheme. The update scheme plays an important role in tracking, which helps the tracker adapt the change of target. This paper presents an adaptive update strategy by introducing the peak to sidelobe ratio (PSR) for kernelized correlation filter (KCF) tracker. It helps the KCF based trackers adapt to appearance changes and achieves excellent tracking performance under complex changes. The extensive evaluations on OTB2015 benchmark show that our tracker significantly enhances the tracking performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design of temperature and humidity control device for substation terminal cabinet

Design of temperature and humidity control device for substa...

引用

IEEE International Conference on Automation, Electronics and Electrical engineering (AUTEEE)

作者： Chen Yumu Su Jingjing Zhang Zihan Song Chengpu Chen Xin Sheng Jiancheng College of Computer and Control Engineering Minjiang University Fuzhou China

Based on the substation outdoor box cabinet in the operation process, which is prone to condensation and overheating, this paper designs a temperature and humidity control device for outdoor box cabinet of substation based on STM32 micro-controller. The device uses STM32 as the main control unit, and uses DHT 11 temperature and humidity sensor to detect the temperature and humidity of the box cabinet, and compare the threshold value to judge the temperature and humidity in the box cabinet and control the heater and fan to effectively drive moisture and heat.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cancelable Speaker Identification System Based on Optical-Like Encryption Algorithms

引用

computer Systems Science & engineering 2022年第10期43卷 87-102页

作者： Safaa El-Gazar Walid El-Shafai Ghada El-Banby Hesham F.A.Hamed Gerges M.Salama Mohammed Abd-Elnaby Fathi E.Abd El-Samie Department of Electrical Engineering Faculty of EngineeringEgyptian-Russian UniversityCairoEgypt Department of Electronics and Electrical Communications Engineering Faculty of Electronic EngineeringMenoufia UniversityMenouf32952Egypt Security Engineering Laboratory Department of Computer SciencePrince Sultan UniversityRiyadh11586Saudi Arabia Department of Industrial Electronics and Control Engineering Faculty of Electronic EngineeringMenoufia UniversityMenouf32952Egypt Department of Computer Engineering College of Computers and Information TechnologyTaif UniversityTaif21944Saudi Arabia Department of Information Technology College of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversityRiyadh84428Saudi Arabia

Biometric authentication is a rapidly growing trend that is gaining increasing attention in the last *** achieves safe access to systems using biometrics instead of the traditional *** utilization of a biometric in its original format makes it usable only ***,a cancelable biometric template should be used,so that it can be replaced when it is *** biometrics aims to enhance the security and privacy of biometric *** encryption is an efficient technique to be used in order to generate cancelable biometric *** this paper,a highly-secure encryption algorithm is proposed to ensure secure biometric data in verification *** considered biometric in this paper is the speech *** speech signal is transformed into its ***,the spectrogram is encrypted using two cascaded optical encryption *** first algorithm is the Optical Scanning Holography(OSH)for its efficiency as an encryption *** OSH encrypted spectrogram is encrypted using Double Random Phase Encoding(DRPE)by implementing two Random Phase Masks(RPMs).After the two cascaded optical encryption algorithms,the cancelable template is *** verification is implemented through correlation estimation between enrolled and test templates in their encrypted *** the correlation value is larger than a threshold value,the user is *** threshold value can be determined from the genuine and imposter correlation distribution curves as the midpoint between the two *** implementation of optical encryption is adopted using its software rather than the optical *** efficiency of the proposed cancelable biometric algorithm is illustrated by the simulation *** can improve the biometric data security without deteriorating the recognition *** results give close-to-zero This values for the Equal Error Rate(EER)and close-to-one values for the Area under Receiver Operator Charact

关键词： Cancelable biometrics spectrogram OSH DRPE EER AROC

来源：评论

学校读者我要写书评

暂无评论

A Multi-Stage Goal-Driven Network for Pedestrian Trajectory Prediction 5

A Multi-Stage Goal-Driven Network for Pedestrian Trajectory ...

引用

5th International Conference on computer Vision, Image and Deep Learning, CVIDL 2024

作者： Wu, Xiuen Wang, Tao Cai, Yuanzheng Liang, Lingyu Papageorgiou, George Minjiang University Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Fuzhou China Fuzhou University College of Computer and Data Science Fuzhou China South China University of Technology School of Electronic and Information Engineering Guangzhou China European University Cyprus Department of Computer Science and Engineering Nicosia Cyprus

ISBN: (纸本)9798350373820

Pedestrian trajectory prediction plays a pivotal role in ensuring the safety and efficiency of various applications, including autonomous vehicles and traffic management systems. This paper proposes a novel method for pedestrian trajectory prediction, called multi-stage goal-driven network (MGNet). Diverging from prior approaches relying on stepwise recursive prediction and the singular forecasting of a long-term goal, MGNet directs trajectory generation by forecasting intermediate stage goals, thereby reducing prediction errors. The network comprises three main components: a conditional variational autoencoder (CVAE), an attention module, and a multi-stage goal evaluator. Trajectories are encoded using conditional variational autoencoders to acquire knowledge about the approximate distribution of pedestrians' future trajectories, and combined with an attention mechanism to capture the temporal dependency between trajectory sequences. The pivotal module is the multi-stage goal evaluator, which utilizes the encoded feature vectors to predict intermediate goals, effectively minimizing cumulative errors in the recursive inference process. The effectiveness of MGNet is demonstrated through comprehensive experiments on the JAAD and PIE datasets. Comparative evaluations against state-of-the-art algorithms reveal significant performance improvements achieved by our proposed method. © 2024 IEEE.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Resonance Compensation for Wireless Charging System Using a Dynamic Tuning Circuit Based on the Principle of controllable Magnetic Flux

引用

IEEE Journal of Emerging and Selected Topics in Power Electronics 2025年

作者： Li, Zhenjie Liu, Yingkai Xue, Pengfei Bai, Yuhong Yin, Laicheng Liu, Yiqi Northeast Forestry University College of Computer and Control Engineering College of Mechanical and Electrical Engineering Harbin150040 China

The detuning of the resonant tank due to component tolerance and aging influences the working performance of the wireless charging system (WCS). This article proposes a dynamic tuning circuit (DTC) using the principle of controllable magnetic flux to reinstate the resonant state. It has a continuous capacitance regulation ability, high precision, low current/voltage stress, and excellent parametric active disturbance rejection ability. First, the DTC's circuit structure and working principle are analyzed in depth, especially its core part-controllable magnetic flux inductor (CMFI). Second, the DTC's parameter design method is analyzed. The DTC's parameter sensitivity analysis is also performed. Third, the DTC's closed-loop control strategy is illustrated along with the resonant state determination and dynamic tuning units' workflow and circuit. Then, simulation results verify the DTC's feasibility in tuning the resonant tank. Finally, a prototype for the series-series compensated WCS is built. When the load resistance varies, and the deviation of passive components in the primary-side resonant tank occurs, using the DTC to restore the desired resonant state, system output power increases significantly, along with the system efficiency decrease slightly, compared to the case without DTC. Furthermore, the measured average adjustment precision of the DTC is higher than 98.5%. © 2013 IEEE.

关键词： Disturbance rejection

来源：评论

学校读者我要写书评

暂无评论

Video Polyp Segmentation: A Deep Learning Perspective

引用

Machine Intelligence Research 2022年第6期19卷 531-549页

作者： Ge-Peng Ji Guobao Xiao Yu-Cheng Chou Deng-Ping Fan Kai Zhao Geng Chen Luc Van Gool Research School of Engineering Australian National UniversityCanberra 2601Australia College of Computer and Control Engineering Minjiang UniversityFuzhou 350108China Department of Computer Science Johns Hopkins UniversityBaltimore 21218USA Computer Vision Laboratory ETH ZürichZürich 8092Switzerland Department of Radiological Sciences University of CaliforniaLos Angeles 90095USA School of Computer Science and Engineering Northwestern Polytechnical UniversityXi′an 710072China

We present the first comprehensive video polyp segmentation(VPS)study in the deep learning *** the years,developments in VPS are not moving forward with ease due to the lack of a large-scale dataset with fine-grained segmentation *** address this issue,we first introduce a high-quality frame-by-frame annotated VPS dataset,named SUN-SEG,which contains 158690colonoscopy video frames from the well-known *** provide additional annotation covering diverse types,i.e.,attribute,object mask,boundary,scribble,and ***,we design a simple but efficient baseline,named PNS+,which consists of a global encoder,a local encoder,and normalized self-attention(NS)*** global and local encoders receive an anchor frame and multiple successive frames to extract long-term and short-term spatial-temporal representations,which are then progressively refined by two NS *** experiments show that PNS+achieves the best performance and real-time inference speed(170 fps),making it a promising solution for the VPS ***,we extensively evaluate 13 representative polyp/object segmentation models on our SUN-SEG dataset and provide attribute-based ***,we discuss several open issues and suggest possible research directions for the VPS *** project and dataset are publicly available at https://***/GewelsJI/VPS.

关键词： Video polyp segmentation(VPS) dataset self-attention colonoscopy abdomen

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：