检索结果-内蒙古大学图书馆

artificial neural networks in pattern recognition 1

丛书名： Lecture Notes in Computer Science

1000年

作者： Luca Pancioni Edmondo Trentin Friedhelm Schwenker

ISBN: (数字)9783319999784

ISBN: (纸本)9783319999777

This book constitutes the refereed proceedings of the 8th iapr TC3 International workshop on artificial neural networks in pattern recognition, ANNPR 2018, held in Siena, Italy, in September 2018.;The 29 revised full papers presented together with 2 invited papers were carefully reviewed and selected from 35 submissions. The papers present and discuss the latest research in all areas of neural network- and machine learning-based pattern recognition. They are organized in two sections: learning algorithms and architectures, and applications.;Chapter "Bounded Rational Decision-Making with Adaptive neural Network Priors" is available open access under a Creative Commons Attribution 4.0 International License via ***.

关键词： artificial Intelligence pattern recognition Image Processing and Computer Vision Natural Language Processing (NLP) Data Mining and Knowledge Discovery

来源：评论

学校读者我要写书评

暂无评论

Deep Learning in the Wild 8th

Deep Learning in the Wild

引用

8th iapr TC3 workshop on artificial neural networks in pattern recognition (ANNPR)

作者： Stadelmann, Thilo Amirian, Mohammadreza Arabaci, Ismail Arnold, Marek Duivesteijn, Gilbert Francois Elezi, Ismail Geiger, Melanie Lorwald, Stefan Meier, Benjamin Bruno Rombach, Katharina Tuggener, Lukas ZHAW Datalab Winterthur Switzerland Sch Engn Winterthur Switzerland Ulm Univ Inst Neural Informat Proc Ulm Germany ARGUS DATA INSIGHTS Schweiz AG Zurich Switzerland Deep Impact AG Winterthur Switzerland Ca Foscari Univ Venice DAIS Venice Italy Univ Neuchatel Inst Informat Neuchatel Switzerland PricewaterhouseCoopers AG Zurich Switzerland IDSIA Dalle Molle Inst Artificial Intelligence Manno Switzerland

ISBN: (纸本)9783319999784;9783319999777

Deep learning with neural networks is applied by an increasing number of people outside of classic research environments, due to the vast success of the methodology on a wide range of machine perception tasks. While this interest is fueled by beautiful success stories, practical work in deep learning on novel tasks without existing baselines remains challenging. This paper explores the specific challenges arising in the realm of real world tasks, based on case studies from research & development in conjunction with industry, and extracts lessons learned from them. It thus fills a gap between the publication of latest algorithmic and methodical developments, and the usually omitted nitty- gritty of how to make them work. Specifically, we give insight into deep learning projects on face matching, print media monitoring, industrial quality control, music scanning, strategy game playing, and automated machine learning, thereby providing best practices for deep learning in practice.

关键词： Data availability Deployment Loss & reward shaping Real world tasks

来源：评论

学校读者我要写书评

暂无评论

Using unsupervised learning of a finite Dirichlet mixture model to improve pattern recognition applications

引用

pattern recognition LETTERS 2005年第12期26卷 1916-1925页

作者： Bouguila, N Ziou, D Univ Sherbrooke Fac Sci Dept Informat Sherbrooke PQ J1K 2R1 Canada

Mixture modeling is the problem of identifying and modeling components in a given set of data. Gaussians are widely used in mixture modeling. At the same time, other models such as Dirichlet distributions have not received attention. In this paper, we present an unsupervised algorithm for learning a finite Dirichlet mixture model. The proposed approach for estimating the parameters of a Dirichlet mixture is based on the maximum likelihood (ML) expressed in a Riemannian space. Experimental results are presented for the following applications: summarization of texture image databases for efficient retrieval, and human skin color modeling and its application to skin detection in multimedia databases. (c) 2005 Elsevier B.V. All rights reserved.

关键词： Dirichlet distribution mixture modeling image summarization for efficient retrieval human skin detection

来源：评论

学校读者我要写书评

暂无评论

A Metaheuristic Optimization Based Deep Feature Selection for Oral Cancer Classification 11th

A Metaheuristic Optimization Based Deep Feature Selection fo...

引用

11th iapr TC3 workshop on artificial neural networks in pattern recognition (ANNPR)

作者： Halder, Akash Laha, Sugata Bandyopadhyay, Saptarshi Schwenker, Friedhelm Sarkar, Ram Jadavpur Univ Dept Comp Sci & Engn Kolkata India Ulm Univ Inst Neural Informat Proc Ulm Germany

ISBN: (纸本)9783031716010;9783031716027

Oral cancer is a serious hazard to world health, with many new cases recorded each year. Researchers have been concentrating on developing medical image analysis-based computer-aided diagnostic (CAD) systems for oral cancer. To this end, we propose a novel model that we name GrayWolf Optimization (GWO) based deep Feature Selection Network (GFS-Net). Initially, we use an attention-aided NASNet Mobile, a convolutional neural network (CNN) architecture, to extract features from the input images. Next, we use a metaheuristic-based optimization algorithm, called GWO, to get rid of the extraneous features obtained from the CNN model. For the final classification task, the K-Nearest-Neighbours (KNN) classifier is applied with this optimal feature set. Our model is evaluated on two publicly accessible oral cancer datasets, histopathologic oral cancer identification dataset and oral cancer (lips and tongue) dataset, that yields classification accuracies of 92.86% and 93.94%, respectively. The code and additional results are available at https://***/stellarsb7/GFS-Net.

关键词： Oral Cancer Deep Learning Feature Selection Gray Wolf Optimization Attention Mechanism Medical Image

来源：评论

学校读者我要写书评

暂无评论

Medical Deepfake Detection using 3-Dimensional neural Learning 10th

Medical Deepfake Detection using 3-Dimensional Neural Learni...

引用

10th iapr TC3 workshop on artificial neural networks for pattern recognition (ANNPR)

作者： Sharafudeen, Misaj Chandra, S. S. Vinod Univ Kerala Dept Comp Sci Thiruvananthapuram Kerala India

ISBN: (纸本)9783031206498;9783031206504

In recent years, Generative Adversarial networks (GAN) have underlined the necessity for exercising caution in trusting digital information. Injection and removal of tumorous nodules from medical imaging modalities is one method of maneuvering deepfakes. The inability to acknowledge medical deepfakes can result in a substantial impact on healthcare procedures or even cause of death. With a systematic case study, this work seeks to address the detection of such assaults in lung CT (Computed Tomography) scans generated using CT-GANs. We experiment with machine learning methods and a novel 3-dimensional deep neural architecture on the topic of differentiating between tampered and untampered data. The proposed architecture on the CT-GAN dataset attained a remarkable accuracy of 91.57%, sensitivity of 91.42%, and specificity of 97.20%. Sectioned data cubes containing the affected region of interest seem to perform better compared to raw CT slices with a gain of approximately 20%. Furthermore, 3DCNN outperforms its 2dimensional counterpart as it extracts temporal features unlike the spatial relationship insufficient for medical data processing. The outcomes of this research reveal that nodule injection and removal manipulations in complicated CT slices may be recognized with a high degree of precision.

关键词： Deepfake detection Computed tomography Fake cancer nodules Machine learning Deep learning

来源：评论

学校读者我要写书评

暂无评论

Palmprint Classification via Filter Faces and Feature Extraction 11th

Palmprint Classification via Filter Faces and Feature Extrac...

引用

11th iapr TC3 workshop on artificial neural networks in pattern recognition (ANNPR)

作者： Chen, Guang Yi Krzyzak, Adam Valev, Ventzeslav Concordia Univ Dept Comp Sci & Software Engn Montreal PQ H3G 1M8 Canada Bulgarian Acad Sci Inst Math & Informat Sofia 1113 Bulgaria

ISBN: (纸本)9783031716010;9783031716027

Palmprint classification is a popular method for today's biometrics, and it can be combined with iris or fingerprint to identify a person's identification. In this paper, we propose a novel method for palmprint classification by using filter faces and feature extraction. We extract such features as histogram of oriented features (HOG) and local binary patterns (LBP). We select to use both nearest neighbor (NN) classifier and collaborative representation classifier (CRC) for palmprint classification. Experiments demonstrate that filter faces always improve the classification accuracy for palmprint classification no matter what features are used and how much noise is present in palmprint images. Based on our experiments, the HOG features are very robust to noise whereas the LBP features are very sensitive to noise. As a result, it is preferable to use the HOG features for noisy palmprint images and the LBP features for clean palmprint images to improve classification accuracy.

关键词： Histogram of oriented features (HOG) Local binary patterns (LBP) Filter faces (FF) Collaborative representation classifier (CRC) Nearest neighbor classifier (NN)

来源：评论

学校读者我要写书评

暂无评论

artificial neural networks in pattern recognition 1

引用

丛书名： Lecture Notes in Computer Science

1000年

作者： Neamat Gayar Friedhelm Schwenker Cheng Suen

ISBN: (数字)9783319116563

ISBN: (纸本)9783319116556

This book constitutes the refereed proceedings of the 6th iapr TC3 International workshop on artificial neural networks in pattern recognition, ANNPR 2014, held in Montreal, QC, Canada, in October 2014. The 24 revised full papers presented were carefully reviewed and selected from 37 submissions for inclusion in this volume. They cover a large range of topics in the field of learning algorithms and architectures and discussing the latest research, results, and ideas in these areas.

关键词： artificial Intelligence pattern recognition Data Mining and Knowledge Discovery Image Processing and Computer Vision User Interfaces and Human Computer Interaction Computation by Abstract Devices

来源：评论

学校读者我要写书评

暂无评论

Explaining Network Decision Provides Insights on the Causal Interaction Between Brain Regions in a Motor Imagery Task 11th

Explaining Network Decision Provides Insights on the Causal ...

引用

11th iapr TC3 workshop on artificial neural networks in pattern recognition (ANNPR)

作者： Borra, Davide Ravanelli, Mirco Univ Bologna Dept Elect Elect & Informat Engn Guglielmo Marcon Cesena Campus Cesena Italy Concordia Univ Dept Comp Sci & Software Engn Montreal PQ Canada Mila Quebec AI Inst Montreal PQ Canada

ISBN: (纸本)9783031716010;9783031716027

neural decoding widely exploits machine learning for classifying electroencephalographic (EEG) signals for brain-computer interface applications. Recent advancements in neural decoding regards the use of brain functional connectivity estimates as input features and the adoption of convolutional neural networks (CNNs) to realize decoders. Moreover, explainable artificial intelligence (XAI) approaches based on CNNs are growing interest in the neuroscience community, for validating the knowledge learned by networks and for using the decoder not only to classify the EEG but also to analyze it in a data-driven way, without a priori assumptions. However, the adoption of connectivity estimates for neural decoding is still in its infancy, as adopts non-directed connectivity measures, limits the analysis of few interactions/frequency ranges, and exploits classic machine learning approaches without exploring CNNs. Moreover, XAI approaches have never been applied to analyze EEG-based functional connectivity. To overcome these limitations, we design and apply a CNN for processing directed connectivity measures estimated via spectral Granger causality. The CNN automatically learns features in the frequency and spatial domains, and it is coupled with an explanation technique (DeepLIFT) for highlighting the most relevant connectivity inflow and outflow associated to each decoded brain state. Our approach is applied to motor imagery decoding, and achieves state-of-the-art performance compared to existing networks. DeepLIFT relevance representations match the directional interactions known occurring when imagining movements, validating the features related to the brain network, as learned by the CNN.

关键词： Electroencephalogram Functional connectivity Convolutional neural networks Explainable AI Motor imagery

来源：评论

学校读者我要写书评

暂无评论

Kernel estimators and mixture models in artificial neural networks

Kernel estimators and mixture models in artificial neural ne...

引用

Proceedings of the 3rd workshop on neural networks: Academic/Industrial/NASA/Defense

作者： Priebe, Carey E. Marchette, David J. Rogers, George W. Solka, Jeffrey L. Naval Surface Warfare Cent Dahlgren United States

ISBN: (纸本)1565550072

For many pattern recognition problems, including unsupervised learning applications, a direct probability density estimate is more powerful than a posterior probability estimate. Kernel estimation and finite mixture models represent two well-known methods of performing probability density estimation. It is shown that kernel and mixture estimates can be performed in the neural network style (e.g. massively parallel, local computations.) The convergence properties of these estimates are well known, and thus a network performing such an estimate has inherently desirable asymptotic characteristics both in terms of functional estimation and optimal classification performance. Several common artificial neural network (ANN) paradigms, including adaptive resonance theory, radial basis functions, probabilistic neural nets, and adaptive kernel neural networks, can be described in terms of their pattern recognition capabilities, as kernel and mixture estimates.

关键词： neural networks

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Algorithms for Emotion recognition on Low Power Single Board Computers 1

引用

5th iapr TC 9 workshop on pattern recognition of Social Signals in Human-Computer-Interaction (MPRSS)

作者： Srinivasan, Venkatesh Meudt, Sascha Schwenker, Friedhelm Ulm Univ Inst Neural Informat Proc D-89081 Ulm Germany

ISBN: (数字)9783030209841

ISBN: (纸本)9783030209841;9783030209834

In the world of Human-Computer Interaction, a computer should have the ability to communicate with humans. One of the communication skill that a computer requires is to recognize the emotional state of the human. With the state-of-the-art computing systems along with Graphical Processing Units, a Deep neural Network can be realized by training on any publicly available dataset and learn the whole emotion estimation into one single network. In a real-time application, the inference of such a network may not need high computational power as training a network does. Several Single Board Computers (SBC) such as Raspberry Pi is now available with sufficient computational power wherein during inference;small Deep neural networks models could perform well enough with acceptable accuracy and processing delay. The paper deals in exploring SBC capabilities for DNN inference, where we prepare a target platform on which real-time camera sensor data is processed to detect face regions and succeed further with recognizing emotions. Several DNN architectures are evaluated on SBC considering processing delay, possible frame rates and classification accuracy on SBC. Finally, a neural Compute Stick (NCS) such as Intel's Movidius is used to look at the performance of SBC for Emotion classification.

关键词： Emotion recognition Deep neural networks Single Board Computers

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：