检索结果-内蒙古大学图书馆

Interpreting convolutional neural network by joint evaluation of multiple feature maps and an improved NSGA-ii algorithm

引用

EXPERT SYSTEMS WITH applications 2024年第PartA期255卷

作者： Wang, Zhenwu Zhou, Yang Han, Mengjie Guo, Yinan China Univ Min & Technol Sch Artificial Intelligence Beijing 100083 Peoples R China Dalarna Univ Sch Informat & Engn S-79188 Falun Sweden China Univ Min & Technol Dept Intelligent Control & Robot Beijing 100083 Peoples R China Minist Educ China Key Lab Syst Control & Informat Proc Shanghai 200240 Peoples R China

The 'black box' characteristics of Convolutional neural networks (CNNs) present significant risks to their application scenarios, such as reliability, security, and division of responsibilities. Addressing the interpretability of CNN emerges as an urgent and critical issue in the field of machine learning. Recent research on CNN interpretability has either yielded unstable or inconsistent interpretations, or produced coarse-scale interpretable heatmaps, limiting their applicability in various scenarios. In this work, we propose a novel method of CNNs interpretation by incorporating a joint evaluation of multiple feature maps and employing multi-objective optimization (JE&MOO-CAM). Firstly, a method of joint evaluation for all feature maps is proposed to preserve the complete object instances and improve the overall activation values. Secondly, an interpretation method of CNNs under the MOO framework is proposed to avoid the instability and inconsistency of interpretation. Finally, the operators of selection, crossover, and mutation, along with the method of population initialization in NSGA-ii, are redesigned to properly express the characteristics of CNNs. The experimental results, including both qualitative and quantitative assessments along with a sanity check conducted on three classic CNN models-VGG16, AlexNet, and ResNet50-demonstrate the superior performance of the proposed JE&MOO-CAM model. This model not only accurately pinpoints the instances within the image requiring explanation but also preserves the integrity of these instances to the greatest extent possible. These capabilities signify that JE&MOO-CAM surpasses six other leading state-of-the-art methods across four established evaluation criteria.

关键词： Black box Convolutional neural network Interpretability Feature map Multi -objective optimization

来源：评论

学校读者我要写书评

暂无评论

A Cloud-Based Robot Framework for Indoor Object Identification Using Unsupervised Segmentation Technique and Convolution neural Network (CNN) 1

引用

34th International Conference on Industrial, Engineering and Other applications of Applied Intelligent Systems (IEA/AIE)

作者： Kabir, Raihan Watanobe, Yutaka Islam, Md Rashedul Univ Aizu Dept Comp Sci & Engn Fukushima Japan Univ Asia Pacific Dept Comp Sci & Engn Dhaka Bangladesh

ISBN: (数字)9783030794637

ISBN: (纸本)9783030794620;9783030794637

Nowadays autonomous indoor mobile robot is getting more attention in many application areas. A cloud-based multi-robot framework provides highspeed data processing and inter robot's communication efficiently for the indoor mobile robot system. However, efficient detection and recognition of the environmental objects are vital issues for indoor mobile robots. Thus, this paper proposes a cloud-based multi-robot system, where Indoor objects are detected using a new unsupervised object segmentation model and object identification using cloud-based Convolutional neural networks (CNN) model. In the object segmentation model, a segmentation algorithm is developed with the combination of Canny edge detection, Floodfill, and BoundingBox image processing technique for efficiently segmenting the objects of the indoor environment. After detecting objects, a cloud-based CNN model with SoftMax classifier is used for classifying objects. Besides, an iterative learning is introduced in our proposed model for identifying unknown objects. Some indoor images captured by the camera are used to test the proposed system. To validate the proposed model, a benchmarked object image dataset from an open resource repository is used in this paper to train the CNN model. The model shows good object detection and identification result and the cloud-based framework enhance the usability of the proposed system.

关键词： Cloud robot Object identification Unsupervised segmentation Canny edge detection Convolutional neural networks (CNN) Indoor mobile robot

来源：评论

学校读者我要写书评

暂无评论

Exploring the trade-off between performance and annotation complexity in semantic segmentation

引用

ENGINEERING applications OF artificial INTELLIGENCE 2023年第PartB期123卷

作者： Fernandez-Moreno, Marta Lei, Bo Holm, Elizabeth A. Mesejo, Pablo Moreno, Raul Univ Granada Andalusian Res Inst Data Sci & Computat Intelligen Dept Comp Sci & Artificial Intelligence DaSCI Granada 18071 Spain TheNextPangea SL Gozon 33440 Asturias Spain Carnegie Mellon Univ Mat Sci & Engn Pittsburgh PA 15213 USA Natl Distance Educ Univ UNED Dept Comp Sci & Automat Control Juan Rosal 16 Madrid 28040 Spain

image semantic segmentation, a fundamental computer vision task, performs the pixel-wise classification of an image seeking to group pixels that share some semantic content. One of the main issues in semantic segmentation is the creation of fully annotated datasets where each image has one label per pixel. These annotations are highly time-consuming and, the more the labelling increases, the higher the percentage of human-entered errors grows. Segmentation methods based on less supervision can reduce both labelling time and noisy labels. However, when dealing with real-world applications, it is far from trivial to establish a method that minimizes labelling time while maximizing performance. Our main contribution is to present the first comprehensive study of state-of-the-art methods based on different levels of supervision. image processing baselines, unsupervised, weakly supervised and supervised approaches have been evaluated. We aim to guide anyone approaching a new real-world use case by providing a trade-off between performance and supervision complexity on datasets from different domains, such as street scenes (Camvid), microscopy (MetalDAM), satellite (FloodNet) and medical images (NuCLS). Our experimental results suggest that: (i) unsupervised and weak learning perform well on majority classes, which helps to speed up labelling;(ii) weakly supervised can outperform fully supervised methods on minority classes;(iii) not all weak learning methods are robust to the nature of the dataset, especially those based on image-level annotations;and (iv) among all weakly supervised methods, point-based are the best-performing ones, even competing with fully supervised methods. The code is available at https://***/martafdezmAM/lessen_ supervision.

关键词： Semantic segmentation Unsupervised learning Weakly supervised learning Deep convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Pipeline leak diagnosis based on leak-augmented scalograms and deep learning

引用

ENGINEERING applications OF COMPUTATIONAL FLUID MECHANICS 2023年第1期17卷

作者： Siddique, Muhammad Farooq Ahmad, Zahoor Kim, Jong-Myon Univ Ulsan Dept Elect Elect & Comp Engn Ulsan 44610 South Korea PD Technol Ulsan South Korea

This paper proposes a new framework for leak diagnosis in pipelines using leak-augmented scalograms and deep learning. Acoustic emission (AE) scalogram images obtained from the continuous wavelet transform have been useful for pipeline health diagnosis, particularly when combined with deep learning. However, background noise has a significant impact on AE signals, which can reduce the accuracy of pipeline health identification using classification models. To address this issue, a new type of scalograms called leak-augmented scalogram is introduced, which enhances the variation in colour intensities of AE scalogram images. The leak-augmented scalograms are obtained by pre-processing them using image-enhancing Gaussian and Laplacian filters. The proposed method utilizes convolutional neural networks (CNNs) and convolutional autoencoders (CAEs) for feature extraction. The CNN extracts patterns specific to local changes, while the CAE extracts holistic patterns from the leak-augmented scalograms. The resulting leak susceptible and leak holistic indicators are merged into a single feature pool and provided as input to a shallow artificial neural network (ANN) to evaluate pipeline health conditions. The proposed method achieves high classification as well as accuracy, precision, F-1 Score and recall, compared to existing state of the art methods.

关键词： Acoustic emission signals Gaussian and laplace filters non-destructive testing method continuous wavelet transform artificial neural network leak-augmented scalograms

来源：评论

学校读者我要写书评

暂无评论

artificial Intelligence for Automatic Pain Assessment: Research Methods and Perspectives

引用

PAIN RESEARCH & MANAGEMENT 2023年第1期2023卷 6018736页

作者： Cascella, Marco Schiavo, Daniela Cuomo, Arturo Ottaiano, Alessandro Perri, Francesco Patrone, Renato Migliarelli, Sara Bignami, Elena Giovanna Vittori, Alessandro Cutugno, Francesco Ist Nazl Tumori IRCCS Fdn G Pascale Div Anesthesia & Pain Med I-80131 Naples Italy Ist Nazl Tumori Napoli IRCCS G Pascale SSD Innovat Therapies Abdominal Metastases Via M Semmola I-80131 Naples Italy Ist Nazl Tumori IRCCS Fdn G Pascale Head & Neck Oncol Unit I-80131 Naples Italy Univ Naples Federico II Dieti Dept Naples Italy Fdn Pascale IRCCS Napoli Ist Nazl Tumori IRCCS Div Hepatobiliary Surg Oncol Naples Italy Univ Sapienza Rome Fac Med & Psychol Dept Pharmacol Rome Italy Univ Parma Dept Med & Surg Anesthesiol Crit Care & Pain Med Div Parma Italy Osped Pediatr Bambino Gesu IRCCS Dept Anesthesia & Crit Care ARCO ROMA I-00165 Rome Italy Univ Naples Federico II Dept Elect Engn & Informat Technol I-80100 Naples Italy

Although proper pain evaluation is mandatory for establishing the appropriate therapy, self-reported pain level assessment has several limitations. Data-driven artificial intelligence (AI) methods can be employed for research on automatic pain assessment (APA). The goal is the development of objective, standardized, and generalizable instruments useful for pain assessment in different clinical contexts. The purpose of this article is to discuss the state of the art of research and perspectives on APA applications in both research and clinical scenarios. Principles of AI functioning will be addressed. For narrative purposes, AI-based methods are grouped into behavioral-based approaches and neurophysiology-based pain detection methods. Since pain is generally accompanied by spontaneous facial behaviors, several approaches for APA are based on image classification and feature extraction. Language features through natural language strategies, body postures, and respiratory-derived elements are other investigated behavioral-based approaches. Neurophysiology-based pain detection is obtained through electroencephalography, electromyography, electrodermal activity, and other biosignals. Recent approaches involve multimode strategies by combining behaviors with neurophysiological findings. Concerning methods, early studies were conducted by machine learning algorithms such as support vector machine, decision tree, and random forest classifiers. More recently, artificial neural networks such as convolutional and recurrent neural network algorithms are implemented, even in combination. Collaboration programs involving clinicians and computer scientists must be aimed at structuring and processing robust datasets that can be used in various settings, from acute to different chronic pain conditions. Finally, it is crucial to apply the concepts of explainability and ethics when examining AI applications for pain research and management.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Leveraging spatiotemporal information in meteorological image sequences: From feature engineering to neural networks

引用

ENVIRONMENTAL DATA SCIENCE 2023年 2卷 e31-e31页

作者： Bansal, Akansha S. Lee, Yoonjin Hilburn, Kyle Ebert-Uphoff, Imme Colorado State Univ Cooperat Inst Res Atmosphere Ft Collins CO 80523 USA Colorado State Univ Elect & Comp Engn Ft Collins CO 80523 USA

Atmospheric processes involve both space and time. Thus, humans looking at atmospheric imagery can often spot important signals in an animated loop of an image sequence not apparent in an individual (static) image. Utilizing such signals with automated algorithms requires the ability to identify complex spatiotemporal patterns in image sequences. That is a very challenging task due to the endless possibilities of patterns in both space and time. Here, we review different concepts and techniques that are useful to extract spatiotemporal signals from meteorological image sequences to expand the effectiveness of AI algorithms for classification and prediction tasks. We first present two applications that motivate the need for these approaches in meteorology, namely the detection of convection from satellite imagery and solar forecasting. Then we provide an overview of concepts and techniques that are helpful for the interpretation of meteorological image sequences, such as (a) feature engineering methods using (i) meteorological knowledge, (ii) classic image processing, (iii) harmonic analysis, and (iv) topological data analysis;(b) ways to use convolutional neural networks for this purpose with emphasis on discussing different convolution filters (2D/3D/LSTM-convolution);and (c) a brief survey of several other concepts, including the concept of "attention" in neural networks and its utility for the interpretation of image sequences and strategies from self-supervised and transfer learning to reduce the need for large labeled datasets. We hope that presenting an overview of these tools -many of which are not new but underutilized in this context -will accelerate progress in this area.

关键词： artificial intelligence image sequence machine learning meteorological data satellite imagery spatiotemporal patterns

来源：评论

学校读者我要写书评

暂无评论

Editorial for Special Issue: Remote Sensing Based Building Extraction ii

引用

REMOTE SENSING 2023年第4期15卷 998-998页

作者： Tian, Jiaojiao Yan, Qin Awrangjeb, Mohammad Kallfelz (Sirmacek), Beril Demir, Nusret German Aerosp Ctr DLR Remote Sensing Technol Inst D-82234 Wessling Germany Chinese Acad Surveying & Mapping Beijing 100830 Peoples R China Griffith Univ Inst Integrated & Intelligent Syst Nathan Qld 4111 Australia Akdeniz Univ Dept Space Sci & Technol Remote Sensing Div TR-07058 Antalya Turkiye

Accurate building extraction from remotely sensed images is essential for topographic mapping, urban planning, disaster management, navigation, and many other applications [1]. The easily available very-high resolution 2D/3D dataset and the rapid development of image processing techniques, especially the convolutional neural networks (CNN) and deep learning techniques have further boosted the research on building-extraction-related topics. Especially in recent years, many research institutes and associations have provided open-source datasets and annotated training data to meet the demand for advanced artificial intelligence models, which brings new opportunities to develop advanced approaches for building extraction and monitoring. Hence, there are higher expectations of the efficiency, accuracy, and robustness of building extraction approaches. They should also meet the demand of processing large datasets at the city, national, and global levels. Moreover, challenges remain on transform learning and dealing with imperfect training data, as well as unexpected objects in urban scenes such as trees, clouds, and *** learning (DL) shows remarkable performance in extracting buildings from high-resolution remote sensing images. How to improve the performance of DL methods, especially the perception of spatial information, is worth further study. Paper [2] proposed a building extraction network (B-FGC-Net) with a feature highlighting, global awareness, and cross-level information fusion to achieve improved profitability of accurate extraction and information integration for both small- and large-scale buildings. Focusing on the promotion of the robustness of the interactive segmentation, Shu et al. [1] propose one Progress Guidance Representation Net (PGR-Net) to utilize the distance of newly added clicks to the boundary of the previous segmentation mask as an indication of the interactive segmentation progress, and this information is employed with the previous

关键词：

来源：评论

学校读者我要写书评

暂无评论

Memristor-based LSTM network with in situ training and its applications

引用

neural networks 2020年 131卷 300-311页

作者： Liu, Xiaoyang Zeng, Zhigang Wunsch, Donald C., ii Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China Educ Minist China Key Lab Image Proc & Intelligent Control Wuhan 430074 Peoples R China Missouri Univ Sci & Technol Dept Elect & Comp Engn Appl Computat Intelligence Lab Rolla MO 65401 USA

artificial neural networks (ANNs), such as the convolutional neural network (CNN) and long short-term memory (LSTM), have high complexity and contain large numbers of parameters. Memristor-based neural networks, which have the ability of in-memory and parallel computing, are therefore proposed to accelerate the operations of ANNs. In this paper, a memristor-based hardware realization of long short-term memory (LSTM) network with in situ training is presented. The designed memristor-based LSTM (MbLSTM) network is composed of memristor-based LSTM cell and memristor-based dense layer. Sigmoid and tanh (hyperbolic tangent) activation functions are approximately implemented through intentionally designing circuit parameters. A weight update scheme with row-parallel characteristic is put forward to update the conductance of memristors in crossbars. The highlights of MbLSTM include an effective hardware-based inference process and in situ training. The validity of MbLSTM is substantiated through classification tasks. The robustness of MbLSTM to conductance variations is also analyzed. (C) 2020 Elsevier Ltd. All rights reserved.

关键词： Memristor Memristor-based neural network Recurrent neural network Long short-term memory Sequence data processing

来源：评论

学校读者我要写书评

暂无评论

Recent progress in optoelectronic memristors for neuromorphic and in-memory computation

引用

NEUROMORPHIC COMPUTING AND ENGINEERING 2023年第2期3卷 022002-022002页

作者： Pereira, Maria Elias Martins, Rodrigo Fortunato, Elvira Barquinha, Pedro Kiazadeh, Asal NOVA Univ Lisbon NOVA Sch Sci & Technol & CEMOP Dept Mat Sci UNINOVA i3N-CENIMAT P-2829516 Caparica Portugal

Neuromorphic computing has been gaining momentum for the past decades and has been appointed as the replacer of the outworn technology in conventional computing systems. artificial neural networks (ANNs) can be composed by memristor crossbars in hardware and perform in-memory computing and storage, in a power, cost and area efficient way. In optoelectronic memristors (OEMs), resistive switching (RS) can be controlled by both optical and electronic signals. Using light as synaptic weigh modulator provides a high-speed non-destructive method, not dependent on electrical wires, that solves crosstalk issues. In particular, in artificial visual systems, OEMs can act as the artificial retina and combine optical sensing and high-level image processing. Therefore, several efforts have been made by the scientific community into developing OEMs that can meet the demands of each specific application. In this review, the recent advances in inorganic OEMs are summarized and discussed. The engineering of the device structure provides the means to manipulate RS performance and, thus, a comprehensive analysis is performed regarding the already proposed memristor materials structure and their specific characteristics. Moreover, their potential applications in logic gates, ANNs and, in more detail, on artificial visual systems are also assessed, taking into account the figures of merit described so far.

关键词： optoelectronic memristors (OEMs) photonic memristors resistive switching devices artificial neural networks (ANNs) artificial visual systems neuromorphic computing

来源：评论

学校读者我要写书评

暂无评论

Sign Language Recognition for Deaf and Dumb People Using Convolution neural Network

Journal of ICT Standardization

引用

Journal of ICT Standardization 2022年第3期10卷 411-426页

作者： Herbaz, Nourdine El Idrissi, Hassan Badri, Abdelmajid Faculty of Sciences and Techniques Mohammedia Hassan II University of Casablanca 28830 Morocco

Gesture recognition is an open phenomenon in computer vision, and one of the topics of current interest. Gesture recognition has many applications in the interpretation of sign language in deaf-mutes, one is in human-computer interaction, and the other is in immersive game technology. For this purpose, we have developed a model of image processing recognition of gestures, based on artificial neural networks, starting from data collection, identification, tracking and classification of gestures, to the display of the obtained results. We propose an approach to contribute to the translation of sign language into voice/text format. In this paper, we present a Moroccan sign language recognition system using a Convolutional neural Network (CNN). This system includes an important data set of more than 20 files. Each file contains 1,000 static images of each signal from several different angles that we collected with the camera. Different Sign Language models were evaluated and compared with the proposed CNN model. The proposed system achieved 99.33% and achieved the best performance with an accuracy rate of 98.7%. © 2022 River Publishers.

关键词： Gesture recognition

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：