检索结果-内蒙古大学图书馆

11th iapr tc3 workshop on artificial neural networks in pattern recognition (annpr)

作者： Fankhauser, Benjamin Bigler, Vidushi Riesen, Kaspar Univ Bern Inst Comp Sci Bern Switzerland Bern Univ Appl Sci Inst Optimisat & Data Anal Biel Switzerland

ISBN: (纸本)9783031716010;9783031716027

River water temperature modeling is a major task in climate research. State-of-the-art methods for water temperature modeling deploy a transductive design, which makes it difficult to generalize to unseen water stations during test time. In the present paper, we isolate one of the common building blocks - a central LSTM, trained for each water station - and propose an embedding scheme in order to increase both the prediction accuracy and the amount of shared parameters and thus the generalization. the proposed embeddings are learned during training time. In an empirical evaluation we show that our method is able to reduce the RMSE by about five percentage points compared to the state-of-the-art reference method while decreasing the tuneable parameters by several orders of magnitude. We also provide a sample analysis of the embedding space of the catchment area of one specific river. Looking at the results of this qualitative analysis, we come to the conclusion that deploying an embedding in water temperature models is not only convincing to decrease the RMSE of water temperature predictions, but also enables better explainable deep learning models. Moreover, the proposed embedding technique opens up various unexplored applications in water temperature research.

关键词： Water Temperature Embedding LSTM Recurrent neural Network

来源：评论

学校读者我要写书评

暂无评论

Research on the Identification of Common Economic Shellfish in Jiangsu Based on Fused-ResNet Network 11th

Research on the Identification of Common Economic Shellfish ...

引用

11th iapr tc3 workshop on artificial neural networks in pattern recognition (annpr)

作者： Liu, Zhiyuan Zhang, Beining Wu, Yangping Zhang, Zhidong Chen, Junjie Li, Hongjun Nantong Univ Sch Informat Sci & Technol Nantong 226019 Jiangsu Peoples R China Marine Fisheries Res Inst Jiangsu Prov Nantong 226007 Peoples R China Marine Econ Shellfish Res & Dev Ctr Jiangsu Prov Nantong Peoples R China

ISBN: (纸本)9783031716010;9783031716027

Shellfish hold significant economic value and are one of the major economic crops in coastal areas of China. To identify a rapid and effective method for distinguishing different Shellfish species in Jiangsu based on morphological differences, this paper proposes a recognition algorithm for common economic Shellfish in Jiangsu based on the Fused-ResNet network. Firstly, the basic structure of the ResNet network is introduced. then, to address the issues of similarity in shape, color, and texture among Shellfish, a Channel Spatial Attention (CSA) module is incorporated. Additionally, to more effectively differentiate the diversity of Shellfish, a transfer learning training strategy is adopted. Finally, the optimized model is applied to Shellfish recognition tasks. the proposed recognition method demonstrates universality under different targets and achieves a recognition accuracy of 98.8%. Moreover, the algorithm's low computational cost makes it more suitable for deployment on mobile devices, providing effective technical support for the rapid identification of economic Shellfish in Jiangsu.

关键词： Shellfish recognition Deep learning Fused-ResNet Network

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

Multi-modal Decoding of Reach-to-Grasping from EEG and EMG via neural networks 11th

Multi-modal Decoding of Reach-to-Grasping from EEG and EMG v...

引用

11th iapr tc3 workshop on artificial neural networks in pattern recognition (annpr)

作者： Borra, Davide Fraternali, Matteo Ravanelli, Mirco Magosso, Elisa 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

Convolutional neural networks (CNNs) have revolutionized motor decoding from electroencephalographic (EEG) signals, showcasing their ability to outperform traditional machine learning, especially for Brain-Computer Interface (BCI) applications. By processing also other recording modalities (e.g., electromyography, EMG) together with EEG signals, motor decoding improved. However, multi-modal algorithms for decoding hand movements are mainly applied to simple movements (e.g., wrist flexion/extension), while their adoption for decoding complex movements (e.g., different grip types) is still under-investigated. In this study, we recorded EEG and EMG signals from 12 participants while they performed a delayed reach-to-grasping task towards one out of four possible objects (a handle, a pin, a card, and a ball), and we addressed multi-modal EEG+EMG decoding with a dual-branch CNN. Each branch of the CNN was based on EEGNet. the performance of the multi-modal approach was compared to mono-modal baselines (based on EEG or EMG only). the multi-modal EEG+EMG pipeline outperformed the EEG-based pipeline during movement initiation, while it outperformed the EMG-based pipeline in motor preparation. Finally, the multi-modal approach was capable of accurately discriminating between grip types widely during the task, especially from movement initiation. Our results further validate multi-modal decoding for potential future BCI applications, aiming at achieving a more natural user experience.

关键词： EEG EMG Multi-modal motor decoding Reach-to-grasping Convolutional neural networks Brain-Computer Interfaces

来源：评论

学校读者我要写书评

暂无评论

Deep Multiresolution Wavelet Transform for Speech Emotion Assessment of High-Risk Suicide Callers 11th

Deep Multiresolution Wavelet Transform for Speech Emotion As...

引用

11th iapr tc3 workshop on artificial neural networks in pattern recognition (annpr)

作者： Nfissi, Alaa Bouachir, Wassim Bouguila, Nizar Mishara, Brian Univ Quebec TELUQ Data Sci Lab Montreal PQ Canada Concordia Univ Concordia Inst Informat Syst Engn Montreal PQ Canada Univ Quebec Psychol Dept Montreal PQ Canada Ctr Res & Intervent Suicide Eth Issues & End Of L Montreal PQ Canada

ISBN: (纸本)9783031716010;9783031716027

this paper introduces an end-to-end (E2E) deep learning framework for speech emotion recognition (SER), aimed at assisting suicide helpline counselors during their interventions. Despite progress, SER still faces challenges such as system complexity, feature distinctiveness, and noise interference. Our approach uses a learnable architecture for fast discrete wavelet transform (FDWT) multi-resolution analysis, for directly extracting features from raw speech waveforms. It combines a 1D dilated convolutional neural network (1D dilated CNN) with spatial attention (SA) and bidirectional gated recurrent units (Bi-GRU) with temporal attention (TA) to capture spatial and temporal characteristics. the framework handles variable-length speech without segmentation, simplifying preprocessing. It introduces a learnable architecture for wavelet bases and coefficient denoising with a learnable asymmetric hard thresholding (LAHT) activation function, enhancing noise resilience and feature distinctiveness. We validate our model on the NSPL-CRISE dataset, which includes recordings from individuals with psychological challenges and potentially suicidal ideations. Our results show significant performance improvements over state-of-the-art SER methods, demonstrating the effectiveness of our multi-resolution deep learning framework in identifying emotional states related to suicide risk. the source code of our model is shared on: https://***/alaaNfissi/ DeepWaveSpeechEmotion- SuicideRiskAssessment.

关键词： Speech Emotion recognition (SER) Suicide Ideation Detection Deep Learning Framework Multi-Resolution Analysis Fast Discrete Wavelet Transform (FDWT) Bidirectional Gated Recurrent Units (Bi-GRU)

来源：评论

学校读者我要写书评

暂无评论

Automatic Interpretation of ¹⁸F- Fluorocholine PET/CT Findings in Patients with Primary Hyperparathyroidism: A Novel Dataset with Benchmarks 11th

Automatic Interpretation of <SUP>18</SUP>F- Fluorocholine PE...

引用

11th iapr tc3 workshop on artificial neural networks in pattern recognition (annpr)

作者： Sharma, Natasha Balogova, Sona Noskovicova, Lucia Montravers, Francoise Talbot, Jean-Noel Trentin, Edmondo Univ Siena Dipartimento Ingn Informaz & Sci Matemat Siena Italy Comenius Univ Dept Nucl Med Bratislava Slovakia St Elisabeth Oncol Inst Bratislava Slovakia Bory Hosp AS Bratislava Slovakia Hop Tenon Serv Med Nucl Paris France Inst Natl Sci & Tech Nucl INSTN Saclay France

ISBN: (纸本)9783031716010;9783031716027

Primary hyperparathyroidism (pHPT) is a prevalent endocrine disorder characterized by excessive production of parathyroid hormone due to hyperactive parathyroid glands. this paper aims to enhance the diagnostic accuracy of PET/CT using F-18-fluorocholine (FCH) by employing radiomic image analysis to differentiate hyperfunctioning parathyroid glands (HPTG) from thyroid gland (TG) normal or adenomatous tissue. To this aim, the paper contributes a novel, real-life dataset (made publicly available online for download) along with several benchmarks. First, we collected and labeled FCH PET/CT images from 92 patients with pHPT, extracting 56 s-order and higher-order radiomic features using the software LIFEx. these features were analyzed in 98 HPTG and 91 TG findings, comparing clinical characteristics via nonparametric Wilcoxon rank sum tests. then, several variants of pattern recognition models (k-nearest neighbor and random forest) and deep neural networks were applied to the task of discriminating between HPTG and TG over the dataset in order to fix baseline results for the Community to challenge. Moreover, two ensemble methods are proposed that combine the aforementioned classifiers, achieving an area under the curve of up to 92.30%. In conclusion, the present integration of radiomic features and machine learning provides a promising approach to the task, setting a benchmark for future research in the field.

关键词： Primary hyperparathyroidism F-18-fluorocholine PET/CT deep neural network ensemble method stacking

来源：评论

学校读者我要写书评

暂无评论

Feature extraction: A time window analysis based on the x-ite pain database 9th

Feature extraction: A time window analysis based on the x-it...

引用

9th iapr tc3 International workshop on artificial neural networks in pattern recognition, annpr 2020

作者： Ricken, Tobias Steinert, Adrian Bellmann, Peter Walter, Steffen Schwenker, Friedhelm Institute of Neural Information Processing Ulm University James-Franck-Ring Ulm89081 Germany Department of Medical Psychology Ulm University Frauensteige 6 Ulm89075 Germany

ISBN: (纸本)9783030583088

In this work, we analyse different temporal feature extraction window approaches, in combination with short-time heat and electric pain stimuli. thereby, we focus on the physiological signals of the Experimentally Induced thermal and Electrical (X-ITE) Pain Database. Each of our proposed approaches is evaluated based on the leave-one-subject-out cross-validation using the random forest method. Moreover, the effectiveness of each physiological signal is inspected separately, as well as by applying the feature fusion approach. thereby, we analyse different binary classification tasks, as well as four-class classification tasks. Our outcomes indicate that a shifted temporal feature extraction window increases the classification performance significantly, when pain is induced by thermal stimuli. Moreover, our evaluations point out that the outcomes differ significantly, when participants are exposed to electrical pain stimuli. For short-term electric pain stimuli, the best results are obtained without temporal shifts of the feature extraction windows. © Springer Nature Switzerland AG 2020.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Pain intensity recognition - an analysis of short-time sequences in a real-world scenario 9th

Pain intensity recognition - an analysis of short-time seque...

引用

9th iapr tc3 International workshop on artificial neural networks in pattern recognition, annpr 2020

作者： Bellmann, Peter thiam, Patrick Schwenker, Friedhelm Institute of Neural Information Processing Ulm University James-Franck-Ring Ulm89081 Germany Institute of Medical Systems Biology Ulm University Albert-Einstein-Allee 11 Ulm89081 Germany

ISBN: (纸本)9783030583088

Pain intensity recognition still constitutes a challenging classification task. In this work, we focus on the physiological signals of the publicly available BioVid Heat Pain Database, which was collected at Ulm University. the BioVid Heat Pain Database consists of different recordings of healthy test subjects that were exposed to various short-time heat stimuli. the results reported in the literature, which are based on those short-time sequences do not justify the implementation of automated pain detection systems, due to unsatisfactory accuracy rates. In the current study, we show that the outcomes, which are stated in the literature, most likely represent lower bound estimations. For this purpose, we transfer the classification task, which is provided by the BioVid Heat Pain Database, to a real-world scenario. More precise, according to an expected hospital setting, we analyse the automated pain intensity recognition approach in combination with different sets of short-time sequences. Our outcomes indicate, that in real-world applications, where the detection of pain intensity is based on more than one single short-time sequence, the accuracy values can be significantly improved. In the current study, the classification performance of bagged decision tree ensembles is evaluated, based on a person-independent scenario. © Springer Nature Switzerland AG 2020.

关键词： Database systems

来源：评论

学校读者我要写书评

暂无评论

Deep learning methods for image guidance in radiation therapy 9th

Deep learning methods for image guidance in radiation therap...

引用

9th iapr tc3 International workshop on artificial neural networks in pattern recognition, annpr 2020

作者： Paysan, Pascal Peterlik, Igor Roggen, Toon Zhu, Liangjia Wessels, Claas Schreier, Jan Buchacek, Martin Scheib, Stefan Varian Medical Systems Imaging Laboratory GmbH Taefernstr. 7 Daettwil5405 Switzerland

ISBN: (纸本)9783030583088

Image guidance became one of the most important key technologies in radiation therapy in the last two decades. Nowadays medical images play a key role in virtually every aspect of the common treatment workflows. Advances in imaging hardware and algorithmic processing are enablers for substantial treatment quality improvements like online adaptation of the treatment, accounting for anatomical changes of the day, or intra-fraction motion monitoring and organ position verification during treatment. Going through this rapid development, an important observation is that further improvements of various methods heavily rely on model knowledge. In a classical sense such model knowledge is for example provided by mathematically formulated physical assumptions to ill-posed problems or by expert systems and heuristics. Recently, it became evident that in various applications such classical approaches get outperformed by data driven machine learning methods. Especially worth to mention is that this not only holds true in terms of precision and computational performance but also in terms of complexity reduction and maintainability. In this paper we provide an overview about the different stages in the X-ray based imaging pipeline in radiation therapy where machine learning based algorithms show promising results or are already applied in clinical routine. © Springer Nature Switzerland AG 2020.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Feature Selection for recognition of Online Handwritten Bangla Characters

引用

neural PROCESSING LETTERS 2019年第3期50卷 2281-2304页

作者： Sen, Shibaprasad Mitra, Mridul Bhattacharyya, Ankan Sarkar, Ram Schwenker, Friedhelm Roy, Kaushik Future Inst Engn & Management Kolkata 700150 India Jadavpur Univ Kolkata 700032 India Univ Ulm Inst Neural Informat Proc D-89069 Ulm Germany West Bengal State Univ Kolkata 700126 India

Feature selection through optimization techniques provides an interesting approach to minimize computational time with enhanced prediction capability, and has better cognizance of data in any pattern recognition application. this paper is an extended version of previously published work (Sen et al. in: 7th iapr tc3 workshop on artificial neural networks in pattern recognition, Ulm, Germany, pp 246-256, 2016), where a quad-tree based image segmentation approach has been discussed to estimate some topological and shape based features (192-attributed) for the recognition of online handwritten Bangla characters. the previous work achieved a recognition accuracy of 98.5% on a database consisting of 10,000 handwritten Bangla characters. In this paper, parameters, used in the previous version during feature estimation, are tuned to improve the performance of the overall system. thereafter, krill-herd a bio-inspired, meta-heuristic algorithm has been applied to find the optimal feature vector by reducing the dimension of the original feature vector. the reduced feature vector has been fed to Sequential Minimal Optimization classifier for the recognition of the same online handwritten Bangla character database used in previous work. It has been observed that result obtained with this optimal feature set is almost equivalent as the result produced by the entire feature vector.

关键词： Feature selection Krill-herd optimization Online handwriting recognition Bangla script Quad-tree based image segmentation

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：