检索结果-内蒙古大学图书馆

ADDITION: Detecting Adversarial Examples With image-Dependent Noise Reduction

IEEE TRANSACTIONS ON DEPENDABLE AND SECURE COMPUTING 2024年第3期21卷 1139-1154页

作者： Wang, Yuchen Li, Xiaoguang Yang, Li Ma, Jianfeng Li, Hui Xidian Univ Sch Comp Sci & Technol Xian 710071 Peoples R China Xidian Univ Sch Cyber Engn State Key Lab Integrated Serv Networks Xian 710071 Peoples R China Purdue Univ Dept Comp & Informat Technol W Lafayette IN 47907 USA Xidian Univ Sch Cyber Engn Xian 710071 Peoples R China

Notwithstanding the tremendous success of deep neural networks in a range of realms, previous studies have shown that these learning models are exposed to an inherent hazard called adversarial example - images to which an elaborate perturbation is maliciously added could deceive a network, which entails the study of countermeasures urgently. However, existing solutions suffer from some weaknesses, e.g., parameters are usually determined empirically in some processing-based detection methods might result in a sub-optimal effect, and the directly performed processing on images might affect the classification of benign samples, leading to increment of false positive. In this paper, we propose a novel image-DepenDent noIse reducTION (ADDITION) model based on deep learning for adversarial detection. The ADDITION model can adaptively convert the adversarial perturbation in each image to approximate Gaussian noise by injecting image-dependent additional noise, then perform noise reduction to eliminate the adversarial perturbation, and finally detect adversarial examples by examining the classification inconsistency between the input image and its denoised version. The ADDITION model is trained end-to-end on benign samples without any prior knowledge of adversarial attacks, and thus avoid time-consuming task of generating adversarial examples in practical use. We generate more than 220,000 adversarial examples based on six attack algorithms for evaluation and present state-of-the-art comparisons on three real-word datasets. Extensive experiments demonstrate that our proposed method achieves improved performance in both detection accuracy rate and false positive rate.

关键词： Perturbation methods Noise reduction Gaussian noise Adaptation models Neural networks Face recognition Robustness Adversarial attack adversarial detection deep neural network noise reduction

来源：评论

学校读者我要写书评

暂无评论

A real-time recognition gait framework for personal authentication via image-based neural network: accelerated by feature reduction in time and frequency domains

引用

JOURNAL OF real-time image processing 2023年第5期20卷 92页

作者： Huang, Xuan Dong, Ran Wu, Bo Sato, Kiminori Ikuno, Soichiro Wang, Zijun Nishimura, Shoji Waseda Univ Metaverse Res Inst Tokorozawa Saitama 3591192 Japan Chukyo Univ Sch Engn Toyota Aichi 4700393 Japan Tokyo Univ Technol Sch Comp Sci Hachioji Tokyo 1920982 Japan Waseda Univ Fac Human Sci Tokorozawa Saitama 3591192 Japan

In recent years, personal authentication based on attitude estimation-gait recognition authentication has become a popular research topic because of its long-range, non-invasive, non-contact, high-precision, and other advantages. However, at present, most relevant research prefers to use the acquired original data directly for iteration and learning. As a result, it takes too long to learn relevant models in the use scenarios with complicated data and heavy human traffic, such as airports and railway stations, where real-time identification cannot be completed while maintaining accuracy, and thus a scheme to improve the learning and recognition speed is needed. Therefore, in this paper, we proposed an innovative real-time MediaPipe-based gait analysis framework and a new Composite Filter Feature Selection (CFFS) method via key nodes, angles, and lengths calculating. Then, based on the proposed method, we extract the aimed features as a new dataset and verified it by 1D-CNN neural network. Furthermore, we also applied Hilbert-Huang transform to investigate these extracted gait features in the frequency domain, improving the performance of our proposed framework to achieve real time under higher recognition accuracy. The experimental results show that the innovative gait recognition framework and data processing technology can reduce the gait feature data, speed up the process of gait recognition, and still maintain the original recognition accuracy. It can also be applied to various large, enclosed spaces with the huge human flow, which has played a role in improving the safety factor, saving labor costs, and accelerating economic consumption.

关键词： Computer vision real time deep learning Machine learning Gait features Acceleration Neural network Data analytics

来源：评论

学校读者我要写书评

暂无评论

Explainable deep neural network for in-plain defect detection during additive manufacturing

引用

RAPID PROTOTYPING JOURNAL 2024年第1期30卷 49-59页

作者： Kumar, deepak Liu, Yongxin Song, Houbing Namilae, Sirish Embry Riddle Aeronaut Univ Aerosp Engn Dept Daytona Beach FL 32114 USA Embry Riddle Aeronaut Univ Math Dept Daytona Beach FL USA Univ Maryland Dept Comp Sci Baltomore MD USA

PurposeThe purpose of this study is to develop a deep learning framework for additive manufacturing (AM), that can detect different defect types without being trained on specific defect data sets and can be applied for real-time process ***/methodology/approachThis study develops an explainable artificial intelligence (AI) framework, a zero-bias deep neural network (DNN) model for real-time defect detection during the AM process. In this method, the last dense layer of the DNN is replaced by two consecutive parts, a regular dense layer denoted (L1) for dimensional reduction, and a similarity matching layer (L2) for equal weight and non-biased cosine similarity matching. Grayscale images of 3D printed samples acquired during printing were used as the input to the zero-bias *** study demonstrates that the approach is capable of successfully detecting multiple types of defects such as cracks, stringing and warping with high accuracy without any prior training on defective data sets, with an accuracy of 99.5%.Practical implicationsOnce the model is set up, the computational time for anomaly detection is lower than the speed of image acquisition indicating the potential for real-time process control. It can also be used to minimize manual processing in AI-enabled ***/valueTo the best of the authors' knowledge, this is the first study to use zero-bias DNN, an explainable AI approach for defect detection in AM.

关键词： Additive manufacturing Explainable AI deep neural network Anomaly detection Defect detection

来源：评论

学校读者我要写书评

暂无评论

deep Reinforcement learning for Efficient IoT Data Compression in Smart Railroad Management

引用

IEEE INTERNET OF THINGS JOURNAL 2024年第15期11卷 25494-25504页

作者： Chen, Xuan Yu, Qixuan Dai, Shuhong Sun, Pengfei Tang, Haichuan Cheng, Long Zhejiang Ind Polytech Coll Shaoxing 312068 Zhejiang Peoples R China North China Elect Power Univ Sch Control & Comp Engn Beijing 102200 Peoples R China Southwest Jiaotong Univ Sch Elect Engn Chengdu 611756 Peoples R China AI Lab CRRC Acad Beijing 100070 Peoples R China

Modern smart railroad management relies heavily on the Internet of Things (IoT)-enabled sensors to monitor train performance, resulting in the generation of extensive data streams. The ensuing data influx poses critical challenges in storage, processing, and transmission. This article presents a novel data compression method specifically designed for IoT-generated data within railroad management scenarios. Leveraging deep reinforcement learning (DRL), our approach intelligently compresses data from onboard IoT sensors. This not only streamlines data streams, ensuring essential information is retained and redundant data is pruned but also alleviates strain on resource-limited devices such as edge servers tasked with complex computations or aggregating large data sets for long-term trend analysis. Experimental results demonstrate that our approach can outperform current baselines with achieving an enhancement of more than 18% on compression rate in real-time configurations. This signifies a transformative solution for handling IoT-induced big data in contemporary railroad management systems.

关键词： Data compression Internet of Things real-time systems Servers Task analysis Market research image coding deep reinforcement learning (DRL) edge computing Internet of Things (IoT) smart railroad management

来源：评论

学校读者我要写书评

暂无评论

A real-time Prediction System for Molecular-level Information of Heavy Oil Based on Machine learning

引用

China Petroleum processing & Petrochemical Technology 2024年第2期26卷 121-134页

作者： Yuan Zhuang Wang Yuan Zhang Zhibo Yuan Yibo Yang Zhe Xu Wei Lin Yang Yan Hao Zhou Xin Zhao Hui Yang Chaohe State Key Laboratory of Chemical Safety SINOPEC Research Institute of Safety Engineering Co.LtdQingdaoShandong 266000People’s Republic of China State Key Laboratory of Heavy Oil Processing China University of PetroleumQingdaoShandong 266580People’s Republic of China College of Chemistry and Chemical Engineering Ocean University of ChinaQingdaoShandong 266100People’s Republic of China

Acquiring accurate molecular-level information about petroleum is crucial for refining and chemical enterprises to implement the“selection of the optimal processing route”*** the development of data prediction systems represented by machine learning,it has become possible for real-time prediction systems of petroleum fraction molecular information to replace analyses such as gas chromatography and mass ***,the biggest difficulty lies in acquiring the data required for training the neural *** address these issues,this work proposes an innovative method that utilizes the Aspen HYSYS and full two-dimensional gas chromatography-time-of-flight mass spectrometry to establish a comprehensive training ***,a deep neural network prediction model is developed for heavy distillate oil to predict its composition in terms of molecular *** training,the model accurately predicts the molecular composition of catalytically cracked raw oil in a *** validation and test sets exhibit R2 values of 0.99769 and 0.99807,respectively,and the average relative error of molecular composition prediction for raw materials of the catalytic cracking unit is less than 7%.Finally,the SHAP(SHapley Additive ExPlanation)interpretation method is used to disclose the relationship among different variables by performing global and local weight comparisons and correlation analyses.

关键词： heavy distillate oil molecular composition deep learning SHAP interpretation method

来源：评论

学校读者我要写书评

暂无评论

AdaptoMixNet: detection of foreign objects on power transmission lines under severe weather conditions

引用

JOURNAL OF real-time image processing 2024年第5期21卷 172页

作者： Jia, Xinghai Ji, Chao Zhang, Fan Liu, Junpeng Gao, Mingjiang Huang, Xinbo Xian Polytech Univ Xian 710048 Peoples R China Xian Key Lab Interconnected Sensing & Intelligent Xian 710048 Peoples R China Xidian Univ Xian 710126 Peoples R China

With the expansion of power transmission line scale, the surrounding environment is complex and susceptible to foreign objects, severely threatening its safe operation. The current algorithm lacks stability and real-time performance in small target detection and severe weather conditions. Therefore, this paper proposes a method for detecting foreign objects on power transmission lines under severe weather conditions based on AdaptoMixNet. First, an Adaptive Fusion Module (AFM) is introduced, which improves the model's accuracy and adaptability through multi-scale feature extraction, fine-grained information preservation, and enhancing context information. Second, an Adaptive Feature Pyramid Module (AEFPM) is proposed, which enhances the focus on local details while preserving global information, improving the stability and robustness of feature representation. Finally, the Neuron Expansion Recursion Adaptive Filter (CARAFE) is designed, which enhances feature extraction, adaptive filtering, and recursive mechanisms, improving detection accuracy, robustness, and computational efficiency. Experimental results show that the method of this paper exhibits excellent performance in the detection of foreign objects on power transmission lines under complex backgrounds and harsh weather conditions.

关键词： Power transmission lines deep learning Adverse weather CARAFE Adaptive

来源：评论

学校读者我要写书评

暂无评论

Universal Fourier Attack for time Series

IEEE OPEN JOURNAL OF SIGNAL PROCESSING

引用

IEEE OPEN JOURNAL OF SIGNAL processing 2024年 5卷 858-866页

作者： Coda, Elizabeth Clymer, Brad Desmet, Chance Watkins, Yijing Girard, Michael Pacific Northwest Natl Lab Richland WA 99354 USA

A wide variety of adversarial attacks have been proposed and explored using image and audio data. These attacks are notoriously easy to generate digitally when the attacker can directly manipulate the input to a model, but are much more difficult to implement in the real world. In this paper we present a universal, time invariant attack for general time series data such that the attack has a frequency spectrum primarily composed of the frequencies present in the original data. The universality of the attack makes it fast and easy to implement as no computation is required to add it to an input, while time invariance is useful for real world deployment. Additionally, the frequency constraint ensures the attack can withstand filtering defenses. We demonstrate the effectiveness of the attack on two different classification tasks through both digital and real world experiments, and show that the attack is robust against common transform-and-compare defense pipelines.

关键词： Training time-frequency analysis Predictive models time series analysis Recording Data models Wireless networks Adversarial machine learning deep learning time series automatic speech recognition artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

An automatic fine-grained violence detection system for animation based on modified faster R-CNN

引用

EXPERT SYSTEMS WITH APPLICATIONS 2024年 237卷

作者： Tang, Yixin Chen, Yu Sharifuzzaman, Sagar A. S. M. Li, Tie Sejong Univ Dept Cooperat Course Performance Film & Animat Seoul 05006 South Korea Sejong Univ Dept Comp Sci & Engn Seoul 05006 South Korea Sejong Univ Dept Intelligent Mechatron Engn Seoul 05006 South Korea Tiangong Univ Dept Comp Sci & Technol Tianjin Peoples R China

Animation drama and movies are important entertainment sources for children and young people. However, many of these entertainment videos introduce ideas such as violence, fighting, abuse, and car accidents, which are not suitable for children and young people. In order to prevent children from viewing these videos, different countries' government bodies put restrictions on age on these videos. Violence detection is mostly done using manual inspection, which is time and resource consuming and cannot achieve a very good result. Therefore, artificial technologies such as deep learning and machine learning can detect violence in a video. Bleeding is one of the distinct characteristics of violent actions presented in such videos. This paper aims to propose a system that can detect a given video's blood in real-time. Researchers have proposed different image processing-based techniques to detect violence, but their proposed systems lack precision and real-time detection. To this end, a deep learning-based approach is proposed to detect violence in a given video and images. A Faster R-CNN model is modified due to the sophisticated characteristics of the violence in the cartoon and animation images to achieve the highest performance. The backbone of the proposed violence detection model is changed to a modified RegNet model to extract the features from the frame. The standard inner lateral connection is replaced with the modulated deformable convolutional (MDC) layer to extract deformable feature maps. A novel distributed attention module (DAM) is proposed on the feature pyramid network to improve the performance of the feature extraction. The multiscale Region of interest (ROI) Align is adapted to improve the detection performance of violence in a different scenario. Moreover, the classification approach is integrated with the detection model to classify the different levels of violence in a given frame. We have explored state-of-the-art object detection methods such as F

关键词： Violence Fine-grained Animation deep learning CNN Faster R -CNN

来源：评论

学校读者我要写书评

暂无评论

Development of deep learning Color Recognition Model for Color Measurement Processes

引用

JOURNAL OF ELECTRICAL ENGINEERING & TECHNOLOGY 2024年第4期19卷 2779-2785页

作者： Lee, Sanghun Kim, Ki-Sub Kang, Jeong Won KCC Cent Res Inst Yongin 16891 South Korea Univ Southern Calif Daniel J Epstein Dept Ind & Syst Engn Los Angeles CA 90007 USA Korea Natl Univ Transportat Dept Chem & Biol Engn Chungju South Korea Korea Natl Univ Transportat Dept IT Energy Convergence Chungju South Korea Korea Natl Univ Transportat Dept Transportat Syst Engn Uiwang South Korea

We present a deep learning color recognition model for the color measurement process in the paint industry. Currently, spectrophotometers are primarily used for color measurements owing to their accuracy. The measurement method involves manually injecting the sample into a spectrophotometer. Our proposed method uses a webcam with a deep learning model on the stand of a spectrophotometer. deep learning models are widely used for image and color detection. In this study, the "you only look once (YOLO)" algorithm is applied for real-time detection of color samples. Upon training various sample images using YOLO, the model could detect the sample area in real time using a webcam. An open source computer vision (OpenCV) library was used for the color recognition model, and the detected RGB color value was converted to the international commission on illumination color space (CIELAB) value, which is primarily used in the color measuring process. However, because of the mirror-like reflection of light from a surface with specular reflection, it is difficult to implement the color value using a camera. To address this problem, we compare several specular removal methods and propose the most suitable model for the color recognition model of color samples. The accuracy of the proposed model was verified by comparing the colors of various samples. Our proposed approach can easily detect samples and color values, which can contribute significantly to automatically calculating the exact amount of coloring required for the target color.

关键词： deep learning Object detection Color recognition Open source computer vision You only look once algorithm (YOLO)

来源：评论

学校读者我要写书评

暂无评论

image enhancement and blur pixel identification with optimization-enabled deep learning for image restoration

引用

SIGNAL image AND VIDEO processing 2024年第5期18卷 4525-4540页

作者： Premnath, S. P. Gowr, P. Sheela Ananth, J. P. Arumugam, Sajeev Ram Sri Krishna Coll Engn & Technol Elect & Commun Engn Coimbatore 641008 Tamil Nadu India Vels Inst Sci Technol & Adv Studies Dept Comp Sci & Engn Chennai 600117 TamilNadu India Sri Krishna Coll Engn & Technol Comp Sci & Engn Coimbatore 641008 Tamil Nadu India Sri Krishna Coll Engn & Technol Dept Artificial Intelligence & Data Sci Coimbatore 641008 Tamil Nadu India

image enhancement is the process of enhancing specific aspects of an image, such as its borders or contrast. The procedure of restoring a destroyed image is known as image restoration. A multitude of factors, such as low camera resolution, motion blur, noise, and others, can cause images to degrade throughout the acquisition process. Although image restoration techniques can remove haze from a degraded image, they are problematic for use in a real-time system since they necessitate numerous photographs from the same location. The suggested fractional Jaya Bat algorithm (FJBA) provides picture enhancement and blur pixel identification to address this issue. Firstly, the blur pixel identification is done using a deep residual network (DRN) trained with FJBA considering blurry image. FJBA is created by combining the Jaya Bat algorithm (JBA) and fractional notion (FC). Furthermore, a blurred image is deblurred using a fusion convolutional neural network (CNN) approach tuned through Pelican hunter optimization (PHO). PHO stands for Pelican optimization (PO) and hunter prey optimization (HPO). Lastly, the image is enhanced using the neural fuzzy system (NFS) and the image enhancement conditional generative adversarial network (IE-CGAN), which has been fine-tuned using FJBA. The proposed FJBA-NFS-IE-CGAN provided enhanced performance with the highest PSNR of 50.536 dB, SDME of 60.724 dB, and SSIM of 0.963, respectively.

关键词： Blur pixel identification deep learning image restoration Neuro-fuzzy system image enhancement

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：