检索结果-内蒙古大学图书馆

Deep Multi-Kernel Convolutional LSTM Networks and an Attention-Based Mechanism for Videos

IEEE TRANSACTIONS ON MULTIMEDIA 2020年第3期22卷 819-829页

作者： Agethen, Sebastian Hsu, Winston H. Natl Taiwan Univ Taipei 10617 Taiwan

Action recognition greatly benefits motion understanding in video analysis. Recurrent networks such as long short-term memory (LSTM) networks are a popular choice for motion-aware sequence learning tasks. Recently, a convolutional extension of LSTM was proposed, in which input-to-hidden and hidden-to-hidden transitions are modeled through convolution with a single kernel. This implies an unavoidable trade-off between effectiveness and efficiency. Herein, we propose a new enhancement to convolutional LSTM networks that supports accommodation of multiple convolutional kernels and layers. This resembles a Network-in-LSTM approach, which improves upon the aforementioned concern. In addition, we propose an attention-based mechanism that is specifically designed for our multi-kernel extension. We evaluated our proposed extensions in a supervised classification setting on the UCF-101 and Sports-1M datasets, with the findings showing that our enhancements improve accuracy. We also undertook qualitative analysis to reveal the characteristics of our system and the convolutional LSTM baseline.

关键词： Kernel Videos Task analysis Convolution Feature extraction YouTube Mathematical model computational and artificial intelligence neural networks feedforward neural networks recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Fourier transform-based data augmentation in deep learning for diabetic foot thermograph classification

引用

BIOCYBERNETICS AND BIOMEDICAL ENGINEERING 2022年第2期42卷 437-452页

作者： Anaya-Isaza, Andres Zequera-Diaz, Martha Pontificia Univ Javeriana Elect Dept BASPI FootLab Bogota 110231 Colombia INDIGO Res Bogota 110221 Colombia

Diabetes Mellitus (DM) belongs to the ten diseases group with the highest mortality rate globally, with an estimated 578 million cases by 2030, according to the World Health Organization (WHO). The disease manifests itself through different disorders, where vasculopathy shows a chronic relationship with diabetic ulceration events in distal extremities, being temperature a biomarker that can quantify the risk scale. According to the above, an analysis is performed with standing thermography images, finding temperature patterns that do not follow a particular distribution in patients with DM. Therefore, the modern medical literature has taken the use of Computer-Aided Diagnosis (CAD) systems as a plausible option to increase medical analysis capabilities. In this sense, we proposed to study three state-of-the-art deep learning (DL) architectures, experimenting with convolutional, residual, and attention (Transformers) approaches to classify subjects with DM from diabetic foot thermography images. The models were trained under three conditions of data augmentation. A novel method based on modifying the images through the change of the amplitude in the Fourier Transform is proposed, being the first work to perform such synergy in the characterization of risk in ulcers through thermographies. The results show that the proposed method allowed reaching the highest values, reaching a perfect classification through the convolutional neural network ResNet50v2, promising for limited data sets in thermal pattern classification problems.(c) 2022 The Author(s). Published by Elsevier B.V. on behalf of Nalecz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences. This is an open access article under the CC BY-NC-ND license (http://***/licenses/by-nc-nd/4.0/).

关键词： artificial intelligence Diabetes Image classification Machine learning Medical diagnostic imaging computational and artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Efficiency Monitoring of Engineering System Designer Work Based on Multi-System User Behavior Analysis with AI/ML Algorithms 62

Efficiency Monitoring of Engineering System Designer Work Ba...

引用

IEEE 62nd International Scientific Conference of the Power-and-Electrical-Engineering of Riga-Technical-University (RTUCON)

作者： Nikiforova, Oksana Rizhko, Ruslan Zabiniako, Vitaly Babris, Kristaps Kornienko, Jurijs Gasparovica-Asitc, Madara Riga Tech Univ Appl Comp Sci Dept Riga Latvia Olimps Ltd CAD & DMS Dept Riga Latvia ABC Software Ltd Res & Dev Dept Riga Latvia ABC Software Ltd Microsoft Solut Dept Riga Latvia ABC Software Ltd User Support Dept Riga Latvia

ISBN: (纸本)9781665438049

Efficiency monitoring is one of the important tasks in monitoring of employees activities, the solution of which is constantly in the focus of researchers and is still not supported by automated methods and universal tools. This task is especially relevant if the field of activity is narrowly specific, and solving such a task of efficiency monitoring is not a trivial accumulation of statistical data, but requires a unique method. However, potentially the method of evaluating the work efficiency of this specific field is not commonly used or adaptable in the analysis of a wide range of activities. The work of an engineering system designer is an example of such specific activities. This paper offers a method for construction of a unified model of behavior of users of specialized IT systems in the engineering design industry, which offers to evaluate the efficiency of work based on the development of a user profile that collects information about the designer's activities, sequence and times. The method defines the input data, the result output data, AI/ML algorithms for output data acquisition and is supported with the prototype system for the visual representation of the expected result, which is based on the input / output data regularities.

关键词： Engineering management Information systems Information technology computational and artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Online Robust Fuzzy Clustering of Data with Omissions Using Similarity Measure of Special Type 15th

Online Robust Fuzzy Clustering of Data with Omissions Using ...

引用

15th International Scientific Conference on Intellectual Systems of Decision Making and Problems of computational intelligence (ISDMCI)

作者： Bodyanskiy, Yevgeniy Shafronenko, Alina Mashtalir, Sergii Kharkiv Natl Univ Radio Elect Kharkiv Ukraine

ISBN: (纸本)9783030264741

The task of clustering is important and the most difficult part of the overall problem of Data Mining because it is based on the self-learning paradigm, i.e. implies the absence of pre-tagged training sample. In real conditions, this task is complicated by the fact that in having data arrays some of the observations can be corrupted by anomalous outliers and some - contain missing data, that is, the "object-property" table has "empty" cells. In addition, data can be arrive in online mode on processing, especially for tasks related with Data Stream Mining and Big Data. In the paper the problem of fuzzy adaptive online clustering of data distorted by outliers that are sequentially fed to the processing when the original sample volume and the number of distorted observations are apriori unknown is considered. The probabilistic and possibilistic adaptive online clustering algorithms for such data, that are based on the similarity measure of a special type that weaken or overwhelming outliers are proposed. The computational experiment confirms the effectiveness of approach under consideration.

关键词： computational and artificial intelligence Fuzzy neural networks Machine learning Self-organizing neural network

来源：评论

学校读者我要写书评

暂无评论

An Algorithm of Fertilization Model Fitting Based On Mixed Intelligent Computation

An Algorithm of Fertilization Model Fitting Based On Mixed I...

引用

International Conference on Advanced Computer Control

作者： Li Miao Jian Zhang Hu Ze-Lin Yuan Yuan Li Lu-jiu Chinese Acad Sci Inst Intelligent Machines Hefei 230031 Anhui Peoples R China Anhui Acad Agr Sci Inst Soil & Fertilizer Hefei 230031 Anhui Peoples R China

ISBN: (纸本)9780769535166

During the process of pluralistic fertilization model construction, the unreasonable ratio of nitrogen, phosphorus and kalium easily results in the deviation of fertilizing model. This paper has proposed an adaptive algorithm of fertilization model fitting based mixed intelligent computing of GP/GA, and solved the issue of structure and parameters optimization of adaptive fertilization model. This algorithm has carried out the research of applying control factors to adjust the parameters of filling function, the appropriate ratio of nitrogen, phosphorus and kalium is regarded as control factors of heuristic search to adjust models, on the basis of history test data dynamical models are generated, and the optimization and correction of models based appropriate ratio of nutrients are achieved.

关键词： Testing Nitrogen Neural networks Mathematical model Soil Statistics Intelligent structures Equations computational and artificial intelligence Genetic programming

来源：评论

学校读者我要写书评

暂无评论

Comparison of Selected Machine Learning Algorithms for Sub-Pixel Imperviousness Change Assessment

Comparison of Selected Machine Learning Algorithms for Sub-P...

引用

Baltic Geodetic Congress (BGC Geomatics)

作者： Drzewiecki, Wojciech AGH Univ Sci & Technol Dept Geoinformat Photogrammetry & Remote Sensing Krakow Poland

ISBN: (纸本)9781509024216

The paper presents the comparison of nine machine learning algorithms for sub-pixel impervious surface area change assessment. Predictive models were tuned and trained using the caret package in R environment. Their performance was analyzed based on both cross-validation results and results obtained for validation dataset. A paired t-test was used to determine if the differences between model accuracies are statistically significant. In case of imperviousness mapping for individual time points the regression trees based models outperformed other ones both for cross-validation on calibration dataset and for validation dataset. The Cubist algorithm seems to be the best performed one. The best assessment method for ISA change cannot be unambiguously pointed out. Random Forest gave the lowest RMS errors, random kNN was the best one according to MAE measure and support vector machines with radial basis kernel gave the highest mean value of the R-2.

关键词： geoscience and remote sensing computational and artificial intelligence environmental monitoring land surface prediction methods

来源：评论

学校读者我要写书评

暂无评论

Deep Aggregation of Regional Convolutional Activations for Content Based Image Retrieval 21

Deep Aggregation of Regional Convolutional Activations for C...

引用

IEEE 21st International Workshop on Multimedia Signal Processing (MMSP)

作者： Schall, Konstantin Barthel, Kai Uwe Hezel, Nico Jung, Klaus HTW Berlin Visual Comp Grp Berlin Germany

ISBN: (纸本)9781728118178

One of the key challenges of deep learning based image retrieval remains in aggregating convolutional activations into one highly representative feature vector. Ideally, this descriptor should encode semantic, spatial and low level information. Even though off-the-shelf pre-trained neural networks can already produce good representations in combination with aggregation methods, appropriate fine tuning for the task of image retrieval has shown to significantly boost retrieval performance. In this paper we present a simple yet effective supervised aggregation method built on top of existing regional pooling approaches. In addition to the maximum activation of a given region, we calculate regional average activations of extracted feature maps. Subsequently, weights for each of the pooled feature vectors are learned to perform a weighted aggregation to a single feature vector. Furthermore, we apply our newly proposed NRA loss function for deep metric learning to fine tune the backbone neural network and to learn the aggregation weights. Our method achieves state-of-the-art results for the INRIA Holidays data set and competitive results for the Oxford Buildings and Paris data sets while reducing the training time significantly.

关键词： computational and artificial intelligence Multi-layer neural network Image retrieval Content-based retrieval Machine learning Feature extraction Machine learning algorithms Nearest neighbor searches Computer vision

来源：评论

学校读者我要写书评

暂无评论

Intelligent Fake News Detection: A Systematic Mapping

引用

JOURNAL OF APPLIED SECURITY RESEARCH 2021年第2期16卷 168-189页

作者： Meneses Silva, Caio, V Fontes, Raphael Silva Colaco Junior, Methanias Univ Fed Sergipe Comp Dept Marechal Rondon Ave S-N BR-49100000 Sao Cristovao Sergipe Brazil

Context: The speed with which the Fake News spread today has encouraged work in various areas to minimize the damage and the public insecurity caused by their proliferation. Objective: To characterize and analyze Fake News threat detection. Method: Systematic Mapping, since the area youthfulness still prevents a complete meta-analysis. Results: The most used algorithms were LSTM (17.14%), Naive-Bayes and Similarity Algorithm (11.43%). Conclusions: There is still the absence of more controlled experiments in the Big Data context. Fake News is a national security problem, requiring effective solutions to combat it. Situations like the Covid-19 virus (coronavirus) reinforce this fact.

关键词： computational and artificial intelligence machine learning fake news public security

来源：评论

学校读者我要写书评

暂无评论

Combinatorial PCPs with Short Proofs

Combinatorial PCPs with Short Proofs

引用

27th Annual IEEE Conference on computational Complexity (CCC)

作者： Meir, Or Stanford Univ Dept Comp Sci Stanford CA 94305 USA

ISBN: (纸本)9780769547084;9781467316637

The PCP theorem (Arora et. al., J. ACM 45(1,3)) asserts the existence of proofs that can be verified by reading a very small part of the proof. Since the discovery of the theorem, there has been a considerable work on improving the theorem in terms of the length of the proofs, culminating in the construction of PCPs of quasi-linear length, by Ben-Sasson and Sudan (SICOMP 38(2)) and Dinur (J. ACM 54(3)). One common theme in the aforementioned PCP constructions is that they all rely heavily on sophisticated algebraic machinery. The aforementioned work of Dinur (J. ACM 54(3)) suggested an alternative approach for constructing PCPs, which gives a simpler and arguably more intuitive proof of the PCP theorem using combinatorial techniques. However, this combinatorial construction only yields PCPs of polynomial length, and is therefore inferior to the algebraic constructions in this respect. This gives rise to the natural question of whether the proof length of the algebraic constructions can be matched using the combinatorial approach. In this work, we provide a combinatorial construction of PCPs of length. n . (logn)(O(log log) (n)), coming very close to the state of the art algebraic constructions (whose proof length is n . (log n)(O(1))). To this end, we develop a few generic PCP techniques which may be interesting in their own right. It should be mentioned that our construction does use low degree polynomials at one point. However, our use of polynomials is confined to the construction of error correcting codes with a certain simple multiplication property, and it is conceivable that such codes can be constructed without the use of polynomials.

关键词： computational and artificial intelligence computational intelligence Computation theory computational complexity

来源：评论

学校读者我要写书评

暂无评论

Genetic Network Programming for artificial stock market

Genetic Network Programming for artificial stock market

引用

4th International Conference on Communications, Circuits and Systems (ICCCAS 2006)

作者： Yang Cheng Sun Shixin Xie Zhilong Univ Elect Sci & Technol China Sch Comp Sci & Engn Chengdu 610054 Peoples R China Southwestern Univ Finance & Econom Sch Elect Commerce Chengdu 610054 Peoples R China

ISBN: (纸本)0780395840

Combined with the idea of Austrian school of economics, this paper proposes a new multi-agent model for artificial stock market based on Genetic Network Programming. It focuses on applying the GNP approach to emulate investment behavior of agents and evolve their trading rules. Simultaneously, this model enhances the heterogeneity of agents, and searches for an optimal combination of parameter values based on GA. Simulation results confirm the effectiveness of this GNP-ASM model through comparison with empirical statistics.

关键词： Genetics Stock markets Economic indicators Economic forecasting Environmental economics Educational institutions Investments Intelligent agent computational and artificial intelligence Competitive intelligence

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：