Journal articles on the topic 'Hierarchical Spatio-Temporal Feature Maps'
To see the other types of publications on this topic, follow the link: Hierarchical Spatio-Temporal Feature Maps.
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'Hierarchical Spatio-Temporal Feature Maps.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Sheng, Jingwei, Li Zheng, Bingjiang Lyu, Zhehang Cen, Lang Qin, Li Hai Tan, Ming-Xiong Huang, Nai Ding, and Jia-Hong Gao. "The Cortical Maps of Hierarchical Linguistic Structures during Speech Perception." Cerebral Cortex 29, no. 8 (August 23, 2018): 3232–40. http://dx.doi.org/10.1093/cercor/bhy191.
Full textAbstract:
AbstractThe hierarchical nature of language requires human brain to internally parse connected-speech and incrementally construct abstract linguistic structures. Recent research revealed multiple neural processing timescales underlying grammar-based configuration of linguistic hierarchies. However, little is known about where in the whole cerebral cortex such temporally scaled neural processes occur. This study used novel magnetoencephalography source imaging techniques combined with a unique language stimulation paradigm to segregate cortical maps synchronized to 3 levels of linguistic units (i.e., words, phrases, and sentences). Notably, distinct ensembles of cortical loci were identified to feature structures at different levels. The superior temporal gyrus was found to be involved in processing all 3 linguistic levels while distinct ensembles of other brain regions were recruited to encode each linguistic level. Neural activities in the right motor cortex only followed the rhythm of monosyllabic words which have clear acoustic boundaries, whereas the left anterior temporal lobe and the left inferior frontal gyrus were selectively recruited in processing phrases or sentences. Our results ground a multi-timescale hierarchical neural processing of speech in neuroanatomical reality with specific sets of cortices responsible for different levels of linguistic units.
2
Sun, Tao, Yongjun Xu, Zhao Zhang, Lin Wu, and Fei Wang. "A Hierarchical Spatial-Temporal Embedding Method Based on Enhanced Trajectory Features for Ship Type Classification." Sensors 22, no. 3 (January 18, 2022): 711. http://dx.doi.org/10.3390/s22030711.
Full textAbstract:
Ship type classification is an essential task in maritime navigation domains, contributing to shipping monitoring, analysis, and forecasting. Presently, with the development of ship positioning and monitoring systems, many ship trajectory acquisitions make it possible to classify ships according to their movement pattern. Existing methods of ship classification based on trajectory include classical sequence analysis and deep learning methods. However, the real ship trajectories are unevenly distributed in geographical space, which leads to many problems in inferring the ship movement mode on the original ship trajectory. This paper proposes a hierarchical spatial-temporal embedding method based on enhanced trajectory features for ship type classification. We first preprocess the trajectory and combine the port information to transform the original ship trajectory into the moored records of ships, removing the unevenly distributed points in the trajectory data and enhancing key points’ semantic information. Then, we propose a Hierarchical Spatial-Temporal Embedding Method (Hi-STEM) for ship classification. Hi-STEM maps moored records in the original geographical space into the feature space and can efficiently find the classification plane in the feature space. Experiments are conducted on real-world datasets and compared with several existing methods. The result shows that our approach has high accuracy in ship classification on ship moored records. We make the source code and datasets publicly available.
3
Silva, Nilton Correia da, Osmar Abílio de Carvalho Júnior, Antonio Nuno de Castro Santa Rosa, Renato Fontes Guimarães, and Roberto Arnaldo Trancoso Gomes. "CHANGE DETECTION SOFTWARE USING SELF-ORGANIZING FEATURE MAPS." Revista Brasileira de Geofísica 30, no. 4 (December 1, 2012): 505. http://dx.doi.org/10.22564/rbgf.v30i4.237.
Full textAbstract:
Os mapas auto-organizáveis (SOFM) consistem em um tipo de rede neural artificial que permite a conversão de dados de alta dimensão, complexos e não lineares, em simples relações geométricas com baixa dimensionalidade. Este método também pode ser utilizado para a classificação de imagens de sensoriamento remoto, pois permite a compressão de dados de alta dimensão preservando as relações topológicas dos dados primários. Este trabalho objetiva desenvolver uma metodologia eficaz para a utilização de mapas auto-organizáveis na detecção de mudanças. No presente estudo o SOFM é utilizado para a classificação não supervisionada de dados de sensoriamento remoto, considerando os seguintes atributos: espaciais (x, y), espectrais e temporais. O método é empregado na região oeste da Bahia, que teve recentemente um aumento significativo em monoculturas. Testes foram realizados com os parâmetros do SOFM com o objetivo de refinar o mapa de detecção demudanças. O SOFM possibilita uma melhor seleção de células e dos correspondentes vetores de peso, que mostram o processo de ordenação e agrupamento hierárquicodos dados. Esta informação é essencial para identificar mudanças ao longo do tempo. Um programa em linguagem C ++ do método proposto foi desenvolvido. ABSTRACT. Self-organizing feature maps (SOFM) consist of a type of artificial neural network that allows the conversion from high-dimensional data into simple geometric relationships with low-dimensionality. This method can also be used for classification of remote sensing images because it allows the compression of high dimensional data while preserving the most important topological and metric relationships of the primary data. This paper aims to develop an effective methodology forusing self-organizing maps in change detection. In this study, SOFM is used for unsupervised classification of remote sensing data, considering the following attributes: spatial (x and y), spectral and temporal. The method is tested and simulated in the western region of Bahia that has observed a significant increase in mechanized agriculture. Tests were performed with the SOFM parameters for the purpose of fine tuning a change detection map. The SOFM provides the best selection of cell and corresponding adjustment of weight vectors, which show the process of ordering and hierarchical clustering of the data. This information is essential to identify changes over time. All algorithms were implemented in C++ language.Keywords: unsupervised classification; land cover; multitemporal analysis; remote sensing
4
Hu, Jie, Yunping Chen, Zhiwen Cai, Haodong Wei, Xinyu Zhang, Wei Zhou, Cong Wang, Liangzhi You, and Baodong Xu. "Mapping Diverse Paddy Rice Cropping Patterns in South China Using Harmonized Landsat and Sentinel-2 Data." Remote Sensing 15, no. 4 (February 14, 2023): 1034. http://dx.doi.org/10.3390/rs15041034.
Full textAbstract:
Paddy rice cropping patterns (PRCPs) play important roles in both agroecosystem modeling and food security. Although paddy rice maps have been generated over several regions using satellite observations, few studies have focused on mapping diverse smallholder PRCPs, which include crop rotation and are dominant cropping structures in South China. Here, an approach called the feature selection and hierarchical classification (FSHC) method was proposed to effectively identify paddy rice and its rotation types. Considering the cloudy and rainy weather in South China, a harmonized Landsat and Sentinel-2 (HLS) surface reflectance product was employed to increase high-quality observations. The FSHC method consists of three processes: cropping intensity mapping, feature selection, and decision tree (DT) model development. The FSHC performance was carefully evaluated using crop field samples obtained in 2018 and 2019. Results suggested that the derived cropping intensity map based on the Savitzky–Golay (S-G) filtered normalized difference vegetation index (NDVI) time series was reliable, with an overall accuracy greater than 93%. Additionally, the optimal spectral (i.e., normalized difference water index (NDWI) and land surface water index (LSWI)) and temporal (start-of-season (SOS) date) features for distinguishing different PRCPs were successfully identified, and these features are highly related to the critical growth stage of paddy rice. The developed DT model with three hierarchical levels based on optimal features performed satisfactorily, and the identification accuracy of each PRCP can be achieved approximately 85%. Furthermore, the FSHC method exhibited similar performances when mapping PRCPs in adjacent years. These results demonstrate that the proposed FSHC approach with HLS data can accurately extract diverse PRCPs over fragmented croplands; thus, this approach represents a promising opportunity for generating refined crop type maps.
5
Han, Te, Yuqi Tang, Xin Yang, Zefeng Lin, Bin Zou, and Huihui Feng. "Change Detection for Heterogeneous Remote Sensing Images with Improved Training of Hierarchical Extreme Learning Machine (HELM)." Remote Sensing 13, no. 23 (December 3, 2021): 4918. http://dx.doi.org/10.3390/rs13234918.
Full textAbstract:
To solve the problems of susceptibility to image noise, subjectivity of training sample selection, and inefficiency of state-of-the-art change detection methods with heterogeneous images, this study proposes a post-classification change detection method for heterogeneous images with improved training of hierarchical extreme learning machine (HELM). After smoothing the images to suppress noise, a sample selection method is defined to train the HELM for each image, in which the feature extraction is respectively implemented for heterogeneous images and the parameters need not be fine-tuned. Then, the multi-temporal feature maps extracted from the trained HELM are segmented to obtain classification maps and then compared to generate a change map with changed types. The proposed method is validated experimentally by using one set of synthetic aperture radar (SAR) images obtained from Sentinel-1, one set of optical images acquired from Google Earth, and two sets of heterogeneous SAR and optical images. The results show that compared to state-of-the-art change detection methods, the proposed method can improve the accuracy of change detection by more than 8% in terms of the kappa coefficient and greatly reduce run time regardless of the type of images used. Such enhancement reflects the robustness and superiority of the proposed method.
6
Sapienza, Davide, Davide Paganelli, Marco Prato, Marko Bertogna, and Matteo Spallanzani. "Deep learning-assisted analysis of automobiles handling performances." Communications in Applied and Industrial Mathematics 13, no. 1 (January 1, 2022): 78–95. http://dx.doi.org/10.2478/caim-2022-0007.
Full textAbstract:
Abstract The luxury car market has demanding product development standards aimed at providing state-of-the-art features in the automotive domain. Handling performance is amongst the most important properties that must be assessed when developing a new car model. In this work, we analyse the problem of predicting subjective evaluations of automobiles handling performances from objective records of driving sessions. A record is a multi-dimensional time series describing the temporal evolution of the mechanical state of an automobile. A categorical variable quantifies the evaluations of handling properties. We describe an original deep learning system, featuring a denoising autoencoder and hierarchical attention mechanisms, that we designed to solve this task. Attention mechanisms intrinsically compute probability distributions over their inputs’ components. Combining this feature with the saliency maps technique, our system can compute heatmaps that provide a visual aid to identify the physical events conditioning its predictions.
7
Ma, Andong, and Anthony M. Filippi. "A novel spatial recurrent neural network for hyperspectral imagery classification." Abstracts of the ICA 1 (July 15, 2019): 1. http://dx.doi.org/10.5194/ica-abs-1-233-2019.
Full textAbstract:
<p><strong>Abstract.</strong> Hyperspectral images (HSIs) contain hundreds of spectral bands, providing high-resolution spectral information pertaining to the Earth’s surface. Additionally, abundant spatial contextual information can also be obtained simultaneously from a HSI. To characterize the properties of ground objects, classification is the most widely-used technology in the field of remote sensing, where each pixel in a HSI is assigned to a pre-defined class. Over the past decade, deep learning has attracted increasing attention in the machine-learning and computer-vision domains, due to its favourable performances for various types of tasks, and it has been successfully introduced to the remote-sensing community. Instead of utilizing the shallow features within in a given image, which is the approach that is generally adopted in other conventional classification methods, deep-learning algorithms can extract hierarchical features from raw HSI data. Within the deep-learning framework, recurrent neural networks (RNNs), which are able to encode sequential features, have exhibited promising capabilities and have achieved encouraging performances, especially for the natural-language processing and speech-recognition communities. As multi-temporal remote-sensing images can be readily obtained from increasing numbers of satellite and unmanned aircraft systems, and since analysis of such multi-temporal data comprises a critical issue within numerous research subfields, including land-cover and land-change analyses, and land-resource management, RNNs have been applied in recent studies in order to extract temporal sequential features from multi-temporal remote-sensing images for the purpose of image classification. Apart from using multi-temporal image datasets, RNNs can also be utilized on a single image, where the spectral feature/band of each individual pixel can be taken as a sequential feature for the input layer of RNNs. However, the application of such sequential feature extraction that relies on a single image still needs to be further investigated since applying RNNs to spectral bands will directly introduce more parameters that need to be optimized, consequently increasing the total training time.</p><p>In this study, we propose a novel RNN-based HSI classification framework. In this framework, unlabelled pixels obtained from a single image are considered when constructing sequential features. Two spatial similarity measurements, referred to as pixel-matching and block-matching, respectively, are employed to extract pixels that are “similar” to the target pixel. Then, the sequential feature of the target pixel is constructed by exploiting several of the most “similar” pixels and ordering them based on their similarities to the target pixel. The aforementioned two schemes are advantageous, as unlabelled pixels within the given HSI are taken into consideration for similarity measurement and sequential feature construction for the RNN model. Moreover, the block-matching scheme also takes advantage of spatial contextual information, which has been widely utilized in spatial-spectral-based HSI classification methods. To evaluate the proposed methods, two benchmark HSIs are used, including a HSI collected over Pavia University, Italy by the airborne Reflective Optics System Imaging Spectrometer (ROSIS) sensor, and an image acquired over the Salinas Valley, California, USA via the Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) sensor. Spatio-temporally coincident ground-reference data accompanies each of these respective HSIs. In addition, the proposed methods are compared with three state-of-the-art algorithms, including support vector machine (SVM), the 1-dimensional convolutional neural network (1DCNN), and the 1-dimensional RNN (1DRNN).</p><p>Experimental results indicate that our proposed methods achieve markedly better classification performance compared with the baseline algorithms on both datasets. For example, for the Pavia University image, the block-matching based RNN achieves the highest overall classification accuracy, with 94.32% accuracy, which is 9.87% higher than the next most accurate algorithm of the aforementioned three baseline methods, which in this case is the 1DCNN, with 84.45% overall accuracy. More specifically, the block-matching method performs better than the pixel-matching method in terms of both quantitative and qualitative assessments. Based on visual assessment/interpretation of the classification maps, it is apparent that “salt-and-pepper” noise is markedly alleviated; with block-matching, smoother classified images are generated compared with pixel-matching-based methods and the three baseline algorithms. Such results demonstrate the effectiveness of utilizing spatial contextual information in the similarity measurement.</p>
8
Pantho, Md Jubaer Hossain, Pankaj Bhowmik, and Christophe Bobda. "Towards an Efficient CNN Inference Architecture Enabling In-Sensor Processing." Sensors 21, no. 6 (March 10, 2021): 1955. http://dx.doi.org/10.3390/s21061955.
Full textAbstract:
The astounding development of optical sensing imaging technology, coupled with the impressive improvements in machine learning algorithms, has increased our ability to understand and extract information from scenic events. In most cases, Convolution neural networks (CNNs) are largely adopted to infer knowledge due to their surprising success in automation, surveillance, and many other application domains. However, the convolution operations’ overwhelming computation demand has somewhat limited their use in remote sensing edge devices. In these platforms, real-time processing remains a challenging task due to the tight constraints on resources and power. Here, the transfer and processing of non-relevant image pixels act as a bottleneck on the entire system. It is possible to overcome this bottleneck by exploiting the high bandwidth available at the sensor interface by designing a CNN inference architecture near the sensor. This paper presents an attention-based pixel processing architecture to facilitate the CNN inference near the image sensor. We propose an efficient computation method to reduce the dynamic power by decreasing the overall computation of the convolution operations. The proposed method reduces redundancies by using a hierarchical optimization approach. The approach minimizes power consumption for convolution operations by exploiting the Spatio-temporal redundancies found in the incoming feature maps and performs computations only on selected regions based on their relevance score. The proposed design addresses problems related to the mapping of computations onto an array of processing elements (PEs) and introduces a suitable network structure for communication. The PEs are highly optimized to provide low latency and power for CNN applications. While designing the model, we exploit the concepts of biological vision systems to reduce computation and energy. We prototype the model in a Virtex UltraScale+ FPGA and implement it in Application Specific Integrated Circuit (ASIC) using the TSMC 90nm technology library. The results suggest that the proposed architecture significantly reduces dynamic power consumption and achieves high-speed up surpassing existing embedded processors’ computational capabilities.
9
Chandrasekaran, V., M. Palaniswami, and T. M. Caelli. "Spatio-temporal feature maps using gated neuronal architecture." IEEE Transactions on Neural Networks 6, no. 5 (1995): 1119–31. http://dx.doi.org/10.1109/72.410356.
Full text
10
Hussain, I., J. Pilz, and G. Spoeck. "Hierarchical Bayesian space-time interpolation versus spatio-temporal BME approach." Advances in Geosciences 25 (March 30, 2010): 97–102. http://dx.doi.org/10.5194/adgeo-25-97-2010.
Full textAbstract:
Abstract. The restrictions of the analysis of natural processes which are observed at any point in space or time to a purely spatial or purely temporal domain may cause loss of information and larger prediction errors. Moreover, the arbitrary combinations of purely spatial and purely temporal models may not yield valid models for the space-time domain. For such processes the variation can be characterized by sophisticated spatio-temporal modeling. In the present study the composite spatio-temporal Bayesian maximum entropy (BME) method and transformed hierarchical Bayesian space-time interpolation are used in order to predict precipitation in Pakistan during the monsoon period. Monthly average precipitation data whose time domain is the monsoon period for the years 1974–2000 and whose spatial domain are various regions in Pakistan are considered. The prediction of space-time precipitation is applicable in many sectors of industry and economy in Pakistan especially; the agricultural sector. Mean field maps and prediction error maps for both methods are estimated and compared. In this paper it is shown that the transformed hierarchical Bayesian model is providing more accuracy and lower prediction error compared to the spatio-temporal Bayesian maximum entropy method; additionally, the transformed hierarchical Bayesian model also provides predictive distributions.
11
Inoue, Y., K. Tsuruoka, and M. Arikawa. "Spatio-Temporal Story Mapping Animation Based On Structured Causal Relationships Of Historical Events." ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XL-4 (April 23, 2014): 101–3. http://dx.doi.org/10.5194/isprsarchives-xl-4-101-2014.
Full textAbstract:
In this paper, we proposed a user interface that displays visual animations on geographic maps and timelines for depicting historical stories by representing causal relationships among events for time series. We have been developing an experimental software system for the spatial-temporal visualization of historical stories for tablet computers. Our proposed system makes people effectively learn historical stories using visual animations based on hierarchical structures of different scale timelines and maps.
12
Jiang, Haiyang, Yaozong Pan, Jian Zhang, and Haitao Yang. "Battlefield Target Aggregation Behavior Recognition Model Based on Multi-Scale Feature Fusion." Symmetry 11, no. 6 (June 5, 2019): 761. http://dx.doi.org/10.3390/sym11060761.
Full textAbstract:
In this paper, our goal is to improve the recognition accuracy of battlefield target aggregation behavior while maintaining the low computational cost of spatio-temporal depth neural networks. To this end, we propose a novel 3D-CNN (3D Convolutional Neural Networks) model, which extends the idea of multi-scale feature fusion to the spatio-temporal domain, and enhances the feature extraction ability of the network by combining feature maps of different convolutional layers. In order to reduce the computational complexity of the network, we further improved the multi-fiber network, and finally established an architecture—3D convolution Two-Stream model based on multi-scale feature fusion. Extensive experimental results on the simulation data show that our network significantly boosts the efficiency of existing convolutional neural networks in the aggregation behavior recognition, achieving the most advanced performance on the dataset constructed in this paper.
13
Zhao, Liang, Yuyang Gao, Jieping Ye, Feng Chen, Yanfang Ye, Chang-Tien Lu, and Naren Ramakrishnan. "Spatio-Temporal Event Forecasting Using Incremental Multi-Source Feature Learning." ACM Transactions on Knowledge Discovery from Data 16, no. 2 (April 30, 2022): 1–28. http://dx.doi.org/10.1145/3464976.
Full textAbstract:
The forecasting of significant societal events such as civil unrest and economic crisis is an interesting and challenging problem which requires both timeliness, precision, and comprehensiveness. Significant societal events are influenced and indicated jointly by multiple aspects of a society, including its economics, politics, and culture. Traditional forecasting methods based on a single data source find it hard to cover all these aspects comprehensively, thus limiting model performance. Multi-source event forecasting has proven promising but still suffers from several challenges, including (1) geographical hierarchies in multi-source data features, (2) hierarchical missing values, (3) characterization of structured feature sparsity, and (4) difficulty in model’s online update with incomplete multiple sources. This article proposes a novel feature learning model that concurrently addresses all the above challenges. Specifically, given multi-source data from different geographical levels, we design a new forecasting model by characterizing the lower-level features’ dependence on higher-level features. To handle the correlations amidst structured feature sets and deal with missing values among the coupled features, we propose a novel feature learning model based on an N th-order strong hierarchy and fused-overlapping group Lasso. An efficient algorithm is developed to optimize model parameters and ensure global optima. More importantly, to enable the model update in real time, the online learning algorithm is formulated and active set techniques are leveraged to resolve the crucial challenge when new patterns of missing features appear in real time. Extensive experiments on 10 datasets in different domains demonstrate the effectiveness and efficiency of the proposed models.
14
Wenger, Romain, Anne Puissant, Jonathan Weber, Lhassane Idoumghar, and Germain Forestier. "Multimodal and Multitemporal Land Use/Land Cover Semantic Segmentation on Sentinel-1 and Sentinel-2 Imagery: An Application on a MultiSenGE Dataset." Remote Sensing 15, no. 1 (December 27, 2022): 151. http://dx.doi.org/10.3390/rs15010151.
Full textAbstract:
In the context of global change, up-to-date land use land cover (LULC) maps is a major challenge to assess pressures on natural areas. These maps also allow us to assess the evolution of land cover and to quantify changes over time (such as urban sprawl), which is essential for having a precise understanding of a given territory. Few studies have combined information from Sentinel-1 and Sentinel-2 imagery, but merging radar and optical imagery has been shown to have several benefits for a range of study cases, such as semantic segmentation or classification. For this study, we used a newly produced dataset, MultiSenGE, which provides a set of multitemporal and multimodal patches over the Grand-Est region in France. To merge these data, we propose a CNN approach based on spatio-temporal and spatio-spectral feature fusion, ConvLSTM+Inception-S1S2. We used a U-Net base model and ConvLSTM extractor for spatio-temporal features and an inception module for the spatio-spectral features extractor. The results show that describing an overrepresented class is preferable to map urban fabrics (UF). Furthermore, the addition of an Inception module on a date allowing the extraction of spatio-spectral features improves the classification results. Spatio-spectro-temporal method (ConvLSTM+Inception-S1S2) achieves higher global weighted F1Score than all other methods tested.
15
Sarabu, Ashok, and Ajit Kumar Santra. "Spatio-Temporal Human Action Recognition Model using Deep Learning Techniques." International Journal on Recent and Innovation Trends in Computing and Communication 10, no. 2s (December 31, 2022): 229–36. http://dx.doi.org/10.17762/ijritcc.v10i2s.5932.
Full textAbstract:
Two-stream human recognition achieved great success in the development of video action recognition using deep learning. Recently many studies have shown that two-stream action recognition is a powerful feature extractor. The main contribution in this work is to develop a two-stream model based on spatial and temporal networks using convolutional neural networks with a convolution long-short term memory. The two-stream model with ImageNet pre-trained weights is used to retrieve spatial and temporal features. Output feature maps of the two-stream model are fused using sum fusion and fed as input to convolutional long-short-term memory. SoftMax function is used to get the final classification score. To avoid overfitting, we have adopted the data augmentation techniques. Finally, we demonstrated that the proposed model performs well in comparison to state-of-the-art two-stream models with an accuracy of 96.1% on UCF 101 dataset and 70.9% accuracy on the HMDB dataset.
16
Saha, Pramit, and Sidney Fels. "Hierarchical Deep Feature Learning for Decoding Imagined Speech from EEG." Proceedings of the AAAI Conference on Artificial Intelligence 33 (July 17, 2019): 10019–20. http://dx.doi.org/10.1609/aaai.v33i01.330110019.
Full textAbstract:
We propose a mixed deep neural network strategy, incorporating parallel combination of Convolutional (CNN) and Recurrent Neural Networks (RNN), cascaded with deep autoencoders and fully connected layers towards automatic identification of imagined speech from EEG. Instead of utilizing raw EEG channel data, we compute the joint variability of the channels in the form of a covariance matrix that provide spatio-temporal representations of EEG. The networks are trained hierarchically and the extracted features are passed onto the next network hierarchy until the final classification. Using a publicly available EEG based speech imagery database we demonstrate around 23.45% improvement of accuracy over the baseline method. Our approach demonstrates the promise of a mixed DNN approach for complex spatialtemporal classification problems.
17
Zhen, Peining, Hai-Bao Chen, Yuan Cheng, Zhigang Ji, Bin Liu, and Hao Yu. "Fast Video Facial Expression Recognition by a Deeply Tensor-Compressed LSTM Neural Network for Mobile Devices." ACM Transactions on Internet of Things 2, no. 4 (November 30, 2021): 1–26. http://dx.doi.org/10.1145/3464941.
Full textAbstract:
Mobile devices usually suffer from limited computation and storage resources, which seriously hinders them from deep neural network applications. In this article, we introduce a deeply tensor-compressed long short-term memory (LSTM) neural network for fast video-based facial expression recognition on mobile devices. First, a spatio-temporal facial expression recognition LSTM model is built by extracting time-series feature maps from facial clips. The LSTM-based spatio-temporal model is further deeply compressed by means of quantization and tensorization for mobile device implementation. Based on datasets of Extended Cohn-Kanade (CK+), MMI, and Acted Facial Expression in Wild 7.0, experimental results show that the proposed method achieves 97.96%, 97.33%, and 55.60% classification accuracy and significantly compresses the size of network model up to 221× with reduced training time per epoch by 60%. Our work is further implemented on the RK3399Pro mobile device with a Neural Process Engine. The latency of the feature extractor and LSTM predictor can be reduced 30.20× and 6.62× , respectively, on board with the leveraged compression methods. Furthermore, the spatio-temporal model costs only 57.19 MB of DRAM and 5.67W of power when running on the board.
18
Zhao, Peng, Fangai Liu, and Xuqiang Zhuang. "Speech Sentiment Analysis Using Hierarchical Conformer Networks." Applied Sciences 12, no. 16 (August 12, 2022): 8076. http://dx.doi.org/10.3390/app12168076.
Full textAbstract:
Multimodality has been widely used for sentiment analysis tasks, especially for speech sentiment analysis. Compared with the emotion expression of most text languages, speech is more intuitive for human emotion, as speech contains more and richer emotion features. Most of the current studies mainly involve the extraction of speech features, but the accuracy and prediction rate of the models still need to be improved. To improve the extraction and fusion of speech sentiment feature information, we present a new framework. The framework adopts a hierarchical conformer model and an attention-based GRU model to increase the accuracy of the model. The method has two main parts: a local feature learning group and a global feature learning group. The local feature learning group is mainly used to learn the spatio-temporal feature information of speech emotion features through the conformer model, and a combination of convolution and transformer is used to be able to enhance the extraction of long and short-term feature information. The global features are then extracted by the AUGRU model, and the fusion of features is performed by the attention mechanism to access the weights of feature information. Finally, the sentiment is identified by a fully connected network layer, and then classified by a central loss function and a softmax function. Compared with existing speech sentiment analysis models, we obtained better sentiment classification results on the IEMOCAP and RAVDESS benchmark datasets.
19
Isbister, James B., Akihiro Eguchi, Nasir Ahmad, Juan M. Galeazzi, Mark J. Buckley, and Simon Stringer. "A new approach to solving the feature-binding problem in primate vision." Interface Focus 8, no. 4 (June 15, 2018): 20180021. http://dx.doi.org/10.1098/rsfs.2018.0021.
Full textAbstract:
We discuss a recently proposed approach to solve the classic feature-binding problem in primate vision that uses neural dynamics known to be present within the visual cortex. Broadly, the feature-binding problem in the visual context concerns not only how a hierarchy of features such as edges and objects within a scene are represented, but also the hierarchical relationships between these features at every spatial scale across the visual field. This is necessary for the visual brain to be able to make sense of its visuospatial world. Solving this problem is an important step towards the development of artificial general intelligence. In neural network simulation studies, it has been found that neurons encoding the binding relations between visual features, known as binding neurons, emerge during visual training when key properties of the visual cortex are incorporated into the models. These biological network properties include (i) bottom-up, lateral and top-down synaptic connections, (ii) spiking neuronal dynamics, (iii) spike timing-dependent plasticity, and (iv) a random distribution of axonal transmission delays (of the order of several milliseconds) in the propagation of spikes between neurons. After training the network on a set of visual stimuli, modelling studies have reported observing the gradual emergence of polychronization through successive layers of the network, in which subpopulations of neurons have learned to emit their spikes in regularly repeating spatio-temporal patterns in response to specific visual stimuli. Such a subpopulation of neurons is known as a polychronous neuronal group (PNG). Some neurons embedded within these PNGs receive convergent inputs from neurons representing lower- and higher-level visual features, and thus appear to encode the hierarchical binding relationship between features. Neural activity with this kind of spatio-temporal structure robustly emerges in the higher network layers even when neurons in the input layer represent visual stimuli with spike timings that are randomized according to a Poisson distribution. The resulting hierarchical representation of visual scenes in such models, including the representation of hierarchical binding relations between lower- and higher-level visual features, is consistent with the hierarchical phenomenology or subjective experience of primate vision and is distinct from approaches interested in segmenting a visual scene into a finite set of objects.
20
Gibbs, Zoe, Chris Groendyke, Brian Hartman, and Robert Richardson. "Modeling County-Level Spatio-Temporal Mortality Rates Using Dynamic Linear Models." Risks 8, no. 4 (November 5, 2020): 117. http://dx.doi.org/10.3390/risks8040117.
Full textAbstract:
The lifestyles and backgrounds of individuals across the United States differ widely. Some of these differences are easily measurable (ethnicity, age, income, etc.) while others are not (stress levels, empathy, diet, exercise, etc.). Though every person is unique, individuals living closer together likely have more similar lifestyles than individuals living hundreds of miles apart. Because lifestyle and environmental factors contribute to mortality, spatial correlation may be an important feature in mortality modeling. However, many of the current mortality models fail to account for spatial relationships. This paper introduces spatio-temporal trends into traditional mortality modeling using Bayesian hierarchical models with conditional auto-regressive (CAR) priors. We show that these priors, commonly used for areal data, are appropriate for modeling county-level spatial trends in mortality data covering the contiguous United States. We find that mortality rates of neighboring counties are highly correlated. Additionally, we find that mortality improvement or deterioration trends between neighboring counties are also highly correlated.
21
Ding, Ziluo, Rui Zhao, Jiyuan Zhang, Tianxiao Gao, Ruiqin Xiong, Zhaofei Yu, and Tiejun Huang. "Spatio-Temporal Recurrent Networks for Event-Based Optical Flow Estimation." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 1 (June 28, 2022): 525–33. http://dx.doi.org/10.1609/aaai.v36i1.19931.
Full textAbstract:
Event camera has offered promising alternative for visual perception, especially in high speed and high dynamic range scenes. Recently, many deep learning methods have shown great success in providing model-free solutions to many event-based problems, such as optical flow estimation. However, existing deep learning methods did not address the importance of temporal information well from the perspective of architecture design and cannot effectively extract spatio-temporal features. Another line of research that utilizes Spiking Neural Network suffers from training issues for deeper architecture. To address these points, a novel input representation is proposed that captures the events temporal distribution for signal enhancement. Moreover, we introduce a spatio-temporal recurrent encoding-decoding neural network architecture for event-based optical flow estimation, which utilizes Convolutional Gated Recurrent Units to extract feature maps from a series of event images. Besides, our architecture allows some traditional frame-based core modules, such as correlation layer and iterative residual refine scheme, to be incorporated. The network is end-to-end trained with self-supervised learning on the Multi-Vehicle Stereo Event Camera dataset. We have shown that it outperforms all the existing state-of-the-art methods by a large margin.
22
Adin, A., D. Lee, T. Goicoa, and María Dolores Ugarte. "A two-stage approach to estimate spatial and spatio-temporal disease risks in the presence of local discontinuities and clusters." Statistical Methods in Medical Research 28, no. 9 (April 13, 2018): 2595–613. http://dx.doi.org/10.1177/0962280218767975.
Full textAbstract:
Disease risk maps for areal unit data are often estimated from Poisson mixed models with local spatial smoothing, for example by incorporating random effects with a conditional autoregressive prior distribution. However, one of the limitations is that local discontinuities in the spatial pattern are not usually modelled, leading to over-smoothing of the risk maps and a masking of clusters of hot/coldspot areas. In this paper, we propose a novel two-stage approach to estimate and map disease risk in the presence of such local discontinuities and clusters. We propose approaches in both spatial and spatio-temporal domains, where for the latter the clusters can either be fixed or allowed to vary over time. In the first stage, we apply an agglomerative hierarchical clustering algorithm to training data to provide sets of potential clusters, and in the second stage, a two-level spatial or spatio-temporal model is applied to each potential cluster configuration. The superiority of the proposed approach with regard to a previous proposal is shown by simulation, and the methodology is applied to two important public health problems in Spain, namely stomach cancer mortality across Spain and brain cancer incidence in the Navarre and Basque Country regions of Spain.
23
Ha, Jinsol, Joongchol Shin, Hasil Park, and Joonki Paik. "Action Recognition Network Using Stacked Short-Term Deep Features and Bidirectional Moving Average." Applied Sciences 11, no. 12 (June 16, 2021): 5563. http://dx.doi.org/10.3390/app11125563.
Full textAbstract:
Action recognition requires the accurate analysis of action elements in the form of a video clip and a properly ordered sequence of the elements. To solve the two sub-problems, it is necessary to learn both spatio-temporal information and the temporal relationship between different action elements. Existing convolutional neural network (CNN)-based action recognition methods have focused on learning only spatial or temporal information without considering the temporal relation between action elements. In this paper, we create short-term pixel-difference images from the input video, and take the difference images as an input to a bidirectional exponential moving average sub-network to analyze the action elements and their temporal relations. The proposed method consists of: (i) generation of RGB and differential images, (ii) extraction of deep feature maps using an image classification sub-network, (iii) weight assignment to extracted feature maps using a bidirectional, exponential, moving average sub-network, and (iv) late fusion with a three-dimensional convolutional (C3D) sub-network to improve the accuracy of action recognition. Experimental results show that the proposed method achieves a higher performance level than existing baseline methods. In addition, the proposed action recognition network takes only 0.075 seconds per action class, which guarantees various high-speed or real-time applications, such as abnormal action classification, human–computer interaction, and intelligent visual surveillance.
24
Wang, Senzhang, Meiyue Zhang, Hao Miao, Zhaohui Peng, and Philip S. Yu. "Multivariate Correlation-aware Spatio-temporal Graph Convolutional Networks for Multi-scale Traffic Prediction." ACM Transactions on Intelligent Systems and Technology 13, no. 3 (June 30, 2022): 1–22. http://dx.doi.org/10.1145/3469087.
Full textAbstract:
Traffic flow prediction based on vehicle trajectories collected from the installed GPS devices is critically important to Intelligent Transportation Systems (ITS). One limitation of existing traffic prediction models is that they mostly focus on predicting road-segment level traffic conditions, which can be considered as a fine-grained prediction. In many scenarios, however, a coarse-grained prediction, such as predicting the traffic flows among different urban areas covering multiple road links, is also required to help government have a better understanding on traffic conditions from the macroscopic point of view. This is especially useful in the applications of urban planning and public transportation planning. Another limitation is that the correlations among different types of traffic-related features are largely ignored. For example, the traffic flow and traffic speed are usually negatively correlated. Existing works regard these traffic-related features as independent features without considering their correlations. In this article, we for the first time study the novel problem of multivariate correlation-aware multi-scale traffic flow predicting, and we propose a feature correlation-aware spatio-temporal graph convolutional networks named MC-STGCN to effectively address it. Specifically, given a road graph, we first construct a coarse-grained road graph based on both the topology closeness and the traffic flow similarity among the nodes (road links). Then a cross-scale spatial-temporal feature learning and fusion technique is proposed for dealing with both the fine- and coarse-grained traffic data. In the spatial domain, a cross-scale GCN is proposed to learn the multi-scale spatial features jointly and fuse them together. In the temporal domain, a cross-scale temporal network that is composed of a hierarchical attention is designed for effectively capturing intra- and inter-scale temporal correlations. To effectively capture the feature correlations, a feature correlation learning component is also designed. Finally, a structural constraint is introduced to make the predictions on the two scale traffic data consistent. We conduct extensive evaluations over two real traffic datasets, and the results demonstrate the superior performance of the proposal on both fine- and coarse-grained traffic predictions.
25
Leonards, Ute, Julie Palix, Christoph Michel, and Vicente Ibanez. "Comparison of Early Cortical Networks in Efficient and Inefficient Visual Search: An Event-Related Potential Study." Journal of Cognitive Neuroscience 15, no. 7 (October 1, 2003): 1039–51. http://dx.doi.org/10.1162/089892903770007425.
Full textAbstract:
Functional magnetic resonance imaging studies have indicated that efficient feature search (FS) and inefficient conjunction search (CS) activate partially distinct frontoparietal cortical networks. However, it remains a matter of debate whether the differences in these networks reflect differences in the early processing during FS and CS. In addition, the relationship between the differences in the networks and spatial shifts of attention also remains unknown. We examined these issues by applying a spatio-temporal analysis method to high-resolution visual event-related potentials (ERPs) and investigated how spatio-temporal activation patterns differ for FS and CS tasks. Within the first 450 msec after stimulus onset, scalp potential distributions (ERP maps) revealed 7 different electric field configurations for each search task. Configuration changes occurred simultaneously in the two tasks, suggesting that contributing processes were not significantly delayed in one task compared to the other. Despite this high spatial and temporal correlation, two ERP maps (120–190 and 250–300 msec) differed between the FS and CS. Lateralized distributions were observed only in the ERP map at 250–300 msec for the FS. This distribution corresponds to that previously described as the N2pc component (a negativity in the time range of the N2 complex over posterior electrodes of the hemisphere contralateral to the target hemifield), which has been associated with the focusing of attention onto potential target items in the search display. Thus, our results indicate that the cortical networks involved in feature and conjunction searching partially differ as early as 120 msec after stimulus onset and that the differences between the networks employed during the early stages of FS and CS are not necessarily caused by spatial attention shifts.
26
Koh, Junho, Junhyung Lee, Youngwoo Lee, Jaekyum Kim, and Jun Won Choi. "MGTANet: Encoding Sequential LiDAR Points Using Long Short-Term Motion-Guided Temporal Attention for 3D Object Detection." Proceedings of the AAAI Conference on Artificial Intelligence 37, no. 1 (June 26, 2023): 1179–87. http://dx.doi.org/10.1609/aaai.v37i1.25200.
Full textAbstract:
Most scanning LiDAR sensors generate a sequence of point clouds in real-time. While conventional 3D object detectors use a set of unordered LiDAR points acquired over a fixed time interval, recent studies have revealed that substantial performance improvement can be achieved by exploiting the spatio-temporal context present in a sequence of LiDAR point sets. In this paper, we propose a novel 3D object detection architecture, which can encode LiDAR point cloud sequences acquired by multiple successive scans. The encoding process of the point cloud sequence is performed on two different time scales. We first design a short-term motion-aware voxel encoding that captures the short-term temporal changes of point clouds driven by the motion of objects in each voxel. We also propose long-term motion-guided bird’s eye view (BEV) feature enhancement that adaptively aligns and aggregates the BEV feature maps obtained by the short-term voxel encoding by utilizing the dynamic motion context inferred from the sequence of the feature maps. The experiments conducted on the public nuScenes benchmark demonstrate that the proposed 3D object detector offers significant improvements in performance compared to the baseline methods and that it sets a state-of-the-art performance for certain 3D object detection categories. Code is available at https://github.com/HYjhkoh/MGTANet.git.
27
Zhang, Shiwen, Hong Liu, Cheng Sun, Xingjin Wu, Pei Wen, Fei Yu, and Jin Zhang. "MSTA-SlowFast: A Student Behavior Detector for Classroom Environments." Sensors 23, no. 11 (May 30, 2023): 5205. http://dx.doi.org/10.3390/s23115205.
Full textAbstract:
Detecting students’ classroom behaviors from instructional videos is important for instructional assessment, analyzing students’ learning status, and improving teaching quality. To achieve effective detection of student classroom behavior based on videos, this paper proposes a classroom behavior detection model based on the improved SlowFast. First, a Multi-scale Spatial-Temporal Attention (MSTA) module is added to SlowFast to improve the ability of the model to extract multi-scale spatial and temporal information in the feature maps. Second, Efficient Temporal Attention (ETA) is introduced to make the model more focused on the salient features of the behavior in the temporal domain. Finally, a spatio-temporal-oriented student classroom behavior dataset is constructed. The experimental results show that, compared with SlowFast, our proposed MSTA-SlowFast has a better detection performance with mean average precision (mAP) improvement of 5.63% on the self-made classroom behavior detection dataset.
28
Arif, Sheeraz, Jing Wang, Tehseen Ul Hassan, and Zesong Fei. "3D-CNN-Based Fused Feature Maps with LSTM Applied to Action Recognition." Future Internet 11, no. 2 (February 13, 2019): 42. http://dx.doi.org/10.3390/fi11020042.
Full textAbstract:
Human activity recognition is an active field of research in computer vision with numerous applications. Recently, deep convolutional networks and recurrent neural networks (RNN) have received increasing attention in multimedia studies, and have yielded state-of-the-art results. In this research work, we propose a new framework which intelligently combines 3D-CNN and LSTM networks. First, we integrate discriminative information from a video into a map called a ‘motion map’ by using a deep 3-dimensional convolutional network (C3D). A motion map and the next video frame can be integrated into a new motion map, and this technique can be trained by increasing the training video length iteratively; then, the final acquired network can be used for generating the motion map of the whole video. Next, a linear weighted fusion scheme is used to fuse the network feature maps into spatio-temporal features. Finally, we use a Long-Short-Term-Memory (LSTM) encoder-decoder for final predictions. This method is simple to implement and retains discriminative and dynamic information. The improved results on benchmark public datasets prove the effectiveness and practicability of the proposed method.
29
Coly, Sylvain, Myriam Garrido, David Abrial, and Anne-Françoise Yao. "Bayesian hierarchical models for disease mapping applied to contagious pathologies." PLOS ONE 16, no. 1 (January 13, 2021): e0222898. http://dx.doi.org/10.1371/journal.pone.0222898.
Full textAbstract:
Disease mapping aims to determine the underlying disease risk from scattered epidemiological data and to represent it on a smoothed colored map. This methodology is based on Bayesian inference and is classically dedicated to non-infectious diseases whose incidence is low and whose cases distribution is spatially (and eventually temporally) structured. Over the last decades, disease mapping has received many major improvements to extend its scope of application: integrating the temporal dimension, dealing with missing data, taking into account various a prioris (environmental and population covariates, assumptions concerning the repartition and the evolution of the risk), dealing with overdispersion, etc. We aim to adapt this approach to model rare infectious diseases proposing specific and generic variants of this methodology. In the context of a contagious disease, the outcome of a primary case can in addition generate secondary occurrences of the pathology in a close spatial and temporal neighborhood; this can result in local overdispersion and in higher spatial and temporal dependencies due to direct and/or indirect transmission. In consequence, we test models including a Negative Binomial distribution (instead of the usual Poisson distribution) to deal with local overdispersion. We also use a specific spatio-temporal link in order to better model the stronger spatial and temporal dependencies due to the transmission of the disease. We have proposed and tested 60 Bayesian hierarchical models on 400 simulated datasets and bovine tuberculosis real data. This analysis shows the relevance of the CAR (Conditional AutoRegressive) processes to deal with the structure of the risk. We can also conclude that the negative binomial models outperform the Poisson models with a Gaussian noise to handle overdispersion. In addition our study provided relevant maps which are congruent with the real risk (simulated data) and with the knowledge concerning bovine tuberculosis (real data).
30
Ullah, Mohib, Ahmed Mohammed, and Faouzi Alaya Cheikh. "PedNet: A Spatio-Temporal Deep Convolutional Neural Network for Pedestrian Segmentation." Journal of Imaging 4, no. 9 (September 4, 2018): 107. http://dx.doi.org/10.3390/jimaging4090107.
Full textAbstract:
Articulation modeling, feature extraction, and classification are the important components of pedestrian segmentation. Usually, these components are modeled independently from each other and then combined in a sequential way. However, this approach is prone to poor segmentation if any individual component is weakly designed. To cope with this problem, we proposed a spatio-temporal convolutional neural network named PedNet which exploits temporal information for spatial segmentation. The backbone of the PedNet consists of an encoder–decoder network for downsampling and upsampling the feature maps, respectively. The input to the network is a set of three frames and the output is a binary mask of the segmented regions in the middle frame. Irrespective of classical deep models where the convolution layers are followed by a fully connected layer for classification, PedNet is a Fully Convolutional Network (FCN). It is trained end-to-end and the segmentation is achieved without the need of any pre- or post-processing. The main characteristic of PedNet is its unique design where it performs segmentation on a frame-by-frame basis but it uses the temporal information from the previous and the future frame for segmenting the pedestrian in the current frame. Moreover, to combine the low-level features with the high-level semantic information learned by the deeper layers, we used long-skip connections from the encoder to decoder network and concatenate the output of low-level layers with the higher level layers. This approach helps to get segmentation map with sharp boundaries. To show the potential benefits of temporal information, we also visualized different layers of the network. The visualization showed that the network learned different information from the consecutive frames and then combined the information optimally to segment the middle frame. We evaluated our approach on eight challenging datasets where humans are involved in different activities with severe articulation (football, road crossing, surveillance). The most common CamVid dataset which is used for calculating the performance of the segmentation algorithm is evaluated against seven state-of-the-art methods. The performance is shown on precision/recall, F 1 , F 2 , and mIoU. The qualitative and quantitative results show that PedNet achieves promising results against state-of-the-art methods with substantial improvement in terms of all the performance metrics.
31
BONACORSI, M., C. PERGENT-MARTINI, N. BREAND, and G. PERGENT. "Is Posidonia oceanica regression a general feature in the Mediterranean Sea?" Mediterranean Marine Science 14, no. 1 (March 22, 2013): 193. http://dx.doi.org/10.12681/mms.334.
Full textAbstract:
Over the last few years, a widespread regression of Posidonia oceanica meadows has been noticed in the Mediterranean Sea. However, the magnitude of this decline is still debated. The objectives of this study are (i) to assess the spatio-temporal evolution of Posidonia oceanica around Cap Corse (Corsica) over time comparing available ancient maps (from 1960) with a new (2011) detailed map realized combining different techniques (aerial photographs, SSS, ROV, scuba diving); (ii) evaluate the reliability of ancient maps; (iii) discuss observed regression of the meadows in relation to human pressure along the 110 km of coast. Thus, the comparison with previous data shows that, apart from sites clearly identified with the actual evolution, there is a relative stability of the surfaces occupied by the seagrass Posidonia oceanica. The recorded differences seem more related to changes in mapping techniques. These results confirm that in areas characterized by a moderate anthropogenic impact, the Posidonia oceanica meadow has no significant regression and that the changes due to the evolution of mapping techniques are not negligible. However, others facts should be taken into account before extrapolating to the Mediterranean Sea (e.g. actually mapped surfaces) and assessing the amplitude of the actual regression.
32
Vinagre Díaz, Juan José, Rubén Fernández Pozo, Ana Belén Rodríguez González, Mark R. Wilby, and Carmen Sánchez Ávila. "Hierarchical Agglomerative Clustering of Bicycle Sharing Stations Based on Ultra-Light Edge Computing." Sensors 20, no. 12 (June 23, 2020): 3550. http://dx.doi.org/10.3390/s20123550.
Full textAbstract:
Bicycle sharing systems (BSSs) have established a new shared-economy mobility model. After a rapid growth they are evolving into a fully-functional mobile sensor platform for cities. The viability of BSSs is floored by their operational costs, mainly due to rebalancing operations. Rebalancing implies transporting bicycles to and from docking stations in order to guarantee the service. Rebalancing performs clustering to group docking stations by behaviour and proximity. In this paper we propose a Hierarchical Agglomerative Clustering based on an Ultra-Light Edge Computing Algorithm (HAC-ULECA). We eliminate the proximity and let Hierarchical Agglomerative Clustering (HAC) focus on behaviour. Behaviour is represented by ULECA as an activity profile based on the net flow of arrivals and departures in a docking station. This drastically reduces the computing requirements which allows ULECA to run as an edge computing functionality embedded into the physical layer of the Internet of Shared Bikes (IoSB) architecture. We have applied HAC-ULECA to real data from BiciMAD, the public BSS in Madrid (Spain). Our results, presented as dendograms, graphs, geographical maps, and colour maps, show that HAC-ULECA is capable of separating behaviour profiles related to business and residential areas and extracting meaningful spatio-temporal information about the BSS and the city’s mobility.
33
Li, Xing, Qian Huang, Yunfei Zhang, Tianjin Yang, and Zhijian Wang. "PointMapNet: Point Cloud Feature Map Network for 3D Human Action Recognition." Symmetry 15, no. 2 (January 30, 2023): 363. http://dx.doi.org/10.3390/sym15020363.
Full textAbstract:
3D human action recognition is crucial in broad industrial application scenarios such as robotics, video surveillance, autonomous driving, or intellectual education, etc. In this paper, we present a new point cloud sequence network called PointMapNet for 3D human action recognition. In PointMapNet, two point cloud feature maps symmetrical to depth feature maps are proposed to summarize appearance and motion representations from point cloud sequences. Specifically, we first convert the point cloud frames to virtual action frames using static point cloud techniques. The virtual action frame is a 1D vector used to characterize the structural details in the point cloud frame. Then, inspired by feature map-based human action recognition on depth sequences, two point cloud feature maps are symmetrically constructed to recognize human action from the point cloud sequence, i.e., Point Cloud Appearance Map (PCAM) and Point Cloud Motion Map (PCMM). To construct PCAM, an MLP-like network architecture is designed and used to capture the spatio-temporal appearance feature of the human action in a virtual action sequence. To construct PCMM, the MLP-like network architecture is used to capture the motion feature of the human action in a virtual action difference sequence. Finally, the two point cloud feature map descriptors are concatenated and fed to a fully connected classifier for human action recognition. In order to evaluate the performance of the proposed approach, extensive experiments are conducted. The proposed method achieves impressive results on three benchmark datasets, namely NTU RGB+D 60 (89.4% cross-subject and 96.7% cross-view), UTD-MHAD (91.61%), and MSR Action3D (91.91%). The experimental results outperform existing state-of-the-art point cloud sequence classification networks, demonstrating the effectiveness of our method.
34
Kang, Samuel, Young-Min Seo, and Yong-Suk Choi. "Video Super Resolution Using a Selective Edge Aggregation Network." Applied Sciences 12, no. 5 (February 27, 2022): 2492. http://dx.doi.org/10.3390/app12052492.
Full textAbstract:
An edge map is a feature map representing the contours of the object in the image. There was a Single Image Super Resolution (SISR) method using the edge map, which achieved a notable SSIM performance improvement. Unlike SISR, Video Super Resolution (VSR) uses video, which consists of consecutive images with temporal features. Therefore, some VSR models adopted motion estimation and motion compensation to apply spatio-temporal feature maps. Unlike the models above, we tried a different method by adding edge structure information and its related post-processing to the existing model. Our model “Video Super Resolution Using a Selective Edge Aggregation Network (SEAN)” consists of a total of two stages. First, the model selectively generates an edge map using the target frame and also the neighboring frame. At this stage, we adopt the magnitude loss function so that the output of SEAN more clearly learns the contours of each object. Second, the final output is generated using the refinement (post-processing) module. SEAN shows more distinct object contours and better color correction compared to other existing models.
35
Demirkus, Meltem, Doina Precup, James J. Clark, and Tal Arbel. "Hierarchical Spatio-Temporal Probabilistic Graphical Model with Multiple Feature Fusion for Binary Facial Attribute Classification in Real-World Face Videos." IEEE Transactions on Pattern Analysis and Machine Intelligence 38, no. 6 (June 1, 2016): 1185–203. http://dx.doi.org/10.1109/tpami.2015.2481396.
Full text
36
DI DOMENICO, ANTONELLA, and GIOVANNI LAGUARDIA. "APPLICATION OF PERCOLATION THEORY AND RG METHOD TO SOIL MOISTURE DYNAMICS." International Journal of Modern Physics B 23, no. 28n29 (November 20, 2009): 5391–401. http://dx.doi.org/10.1142/s0217979209063717.
Full textAbstract:
In this work, we present a review of the results obtained in the exploitation of percolation theory and the renormalization group method in the study of soil moisture spatial patterns. In order to capture critical point in soil moisture spatio-temporal dynamics, we developed an algorithm consisting of three steps: (i) dichotomization, i.e., transforming the soil moisture maps into binary maps; (ii) identification of the largest wet cluster; (iii) scaling transformation, i.e., applying an ad hoc implemented coarse-graining procedure to the binary maps. The methodology was explored by means of several applications on soil moisture data coming from field measurement, remote sensing, and hydrological modelling over a wide range of spatial scales. From the relations between the occupation probability in soil moisture spatial patterns and the normalized size of the largest cluster at different scales, as well as the scaling behaviour, it is possible to argue that also for this physical system the critical point theory applies. The critical probability seems to be a structural feature of the catchment, being insensitive to the scale of the analysis, as well as to the parameterization of the methodology.
37
Qiu, Chunping, Michael Schmitt, Lichao Mou, Pedram Ghamisi, and Xiao Zhu. "Feature Importance Analysis for Local Climate Zone Classification Using a Residual Convolutional Neural Network with Multi-Source Datasets." Remote Sensing 10, no. 10 (October 1, 2018): 1572. http://dx.doi.org/10.3390/rs10101572.
Full textAbstract:
Global Local Climate Zone (LCZ) maps, indicating urban structures and land use, are crucial for Urban Heat Island (UHI) studies and also as starting points to better understand the spatio-temporal dynamics of cities worldwide. However, reliable LCZ maps are not available on a global scale, hindering scientific progress across a range of disciplines that study the functionality of sustainable cities. As a first step towards large-scale LCZ mapping, this paper tries to provide guidance about data/feature choice. To this end, we evaluate the spectral reflectance and spectral indices of the globally available Sentinel-2 and Landsat-8 imagery, as well as the Global Urban Footprint (GUF) dataset, the OpenStreetMap layers buildings and land use and the Visible Infrared Imager Radiometer Suite (VIIRS)-based Nighttime Light (NTL) data, regarding their relevance for discriminating different Local Climate Zones (LCZs). Using a Residual convolutional neural Network (ResNet), a systematic analysis of feature importance is performed with a manually-labeled dataset containing nine cities located in Europe. Based on the investigation of the data and feature choice, we propose a framework to fully exploit the available datasets. The results show that GUF, OSM and NTL can contribute to the classification accuracy of some LCZs with relatively few samples, and it is suggested that Landsat-8 and Sentinel-2 spectral reflectances should be jointly used, for example in a majority voting manner, as proven by the improvement from the proposed framework, for large-scale LCZ mapping.
38
Abdullah, Abu Yousuf Md, Arif Masrur, Mohammed Sarfaraz Gani Adnan, Md Abdullah Al Baky, Quazi K. Hassan, and Ashraf Dewan. "Spatio-temporal Patterns of Land Use/Land Cover Change in the Heterogeneous Coastal Region of Bangladesh between 1990 and 2017." Remote Sensing 11, no. 7 (April 2, 2019): 790. http://dx.doi.org/10.3390/rs11070790.
Full textAbstract:
Although a detailed analysis of land use and land cover (LULC) change is essential in providing a greater understanding of increased human-environment interactions across the coastal region of Bangladesh, substantial challenges still exist for accurately classifying coastal LULC. This is due to the existence of high-level landscape heterogeneity and unavailability of good quality remotely sensed data. This study, the first of a kind, implemented a unique methodological approach to this challenge. Using freely available Landsat imagery, eXtreme Gradient Boosting (XGBoost)-based informative feature selection and Random Forest classification is used to elucidate spatio-temporal patterns of LULC across coastal areas over a 28-year period (1990-2017). We show that the XGBoost feature selection approach effectively addresses the issue of high landscape heterogeneity and spectral complexities in the image data, successfully augmenting the RF model performance (providing a mean user’s accuracy > 0.82). Multi-temporal LULC maps reveal that Bangladesh’s coastal areas experienced a net increase in agricultural land (5.44%), built-up (4.91%) and river (4.52%) areas over the past 28 years. While vegetation cover experienced a net decrease (8.26%), an increasing vegetation trend was observed in the years since 2000, primarily due to the Bangladesh government’s afforestation initiatives across the southern coastal belts. These findings provide a comprehensive picture of coastal LULC patterns, which will be useful for policy makers and resource managers to incorporate into coastal land use and environmental management practices. This work also provides useful methodological insights for future research to effectively address the spatial and spectral complexities of remotely sensed data used in classifying the LULC of a heterogeneous landscape.
39
Fan, Kun, Chungin Joung, and Seungjun Baek. "Sequence-to-Sequence Video Prediction by Learning Hierarchical Representations." Applied Sciences 10, no. 22 (November 23, 2020): 8288. http://dx.doi.org/10.3390/app10228288.
Full textAbstract:
Video prediction which maps a sequence of past video frames into realistic future video frames is a challenging task because it is difficult to generate realistic frames and model the coherent relationship between consecutive video frames. In this paper, we propose a hierarchical sequence-to-sequence prediction approach to address this challenge. We present an end-to-end trainable architecture in which the frame generator automatically encodes input frames into different levels of latent Convolutional Neural Network (CNN) features, and then recursively generates future frames conditioned on the estimated hierarchical CNN features and previous prediction. Our design is intended to automatically learn hierarchical representations of video and their temporal dynamics. Convolutional Long Short-Term Memory (ConvLSTM) is used in combination with skip connections so as to separately capture the sequential structures of multiple levels of hierarchy of features. We adopt Scheduled Sampling for training our recurrent network in order to facilitate convergence and to produce high-quality sequence predictions. We evaluate our method on the Bouncing Balls, Moving MNIST, and KTH human action dataset, and report favorable results as compared to existing methods.
40
Dzwinel, W., D. A. Yuen, K. Boryczko, Y. Ben-Zion, S. Yoshioka, and T. Ito. "Nonlinear multidimensional scaling and visualization of earthquake clusters over space, time and feature space." Nonlinear Processes in Geophysics 12, no. 1 (January 28, 2005): 117–28. http://dx.doi.org/10.5194/npg-12-117-2005.
Full textAbstract:
Abstract. We present a novel technique based on a multi-resolutional clustering and nonlinear multi-dimensional scaling of earthquake patterns to investigate observed and synthetic seismic catalogs. The observed data represent seismic activities around the Japanese islands during 1997-2003. The synthetic data were generated by numerical simulations for various cases of a heterogeneous fault governed by 3-D elastic dislocation and power-law creep. At the highest resolution, we analyze the local cluster structures in the data space of seismic events for the two types of catalogs by using an agglomerative clustering algorithm. We demonstrate that small magnitude events produce local spatio-temporal patches delineating neighboring large events. Seismic events, quantized in space and time, generate the multi-dimensional feature space characterized by the earthquake parameters. Using a non-hierarchical clustering algorithm and nonlinear multi-dimensional scaling, we explore the multitudinous earthquakes by real-time 3-D visualization and inspection of the multivariate clusters. At the spatial resolutions characteristic of the earthquake parameters, all of the ongoing seismicity both before and after the largest events accumulates to a global structure consisting of a few separate clusters in the feature space. We show that by combining the results of clustering in both low and high resolution spaces, we can recognize precursory events more precisely and unravel vital information that cannot be discerned at a single resolution.
41
Vorobeva, Gulnara, and Andrei Vorobev. "MODEL OF INFORMATION INTERACTION BETWEEN ELEMENTS OF MULTILEVEL SYSTEM OF DIGITAL TWINS." Informatics and Automation 20, no. 3 (May 28, 2021): 530–61. http://dx.doi.org/10.15622/ia.2021.3.2.
Full textAbstract:
One of the solutions to the problem of spatio-temporal data anisotropy is the use of a multilevel system of digital twins based on the corresponding industry models and the updated archive data base. The application of this approach has successfully proved itself in information systems for monitoring the parameters of the geomagnetic field and its variations, providing spatio-temporal interpolation of geomagnetic data with an accuracy of 0.81 nT in magnetically quiet periods. At the same time, the problem of information interaction between the levels of the system of digital twins remained unresolved, which is greatly aggravated by the constantly growing volume of data and their heterogeneous nature. The paper proposes a solution to the indicated problem by means of a formalized mechanism for packaging space-time information, in which the identification of data sources is performed on the basis of a hierarchical binary tokenization system. In addition, the proposed software implementation of such an approach is considered, a distinctive feature of which is the combination of traditional clientserver and innovative serverless architectures to implement a highly loaded reactive web application for working with analyzed data. The main stages of the implementation of information interaction are highlighted and programmatically formalized - from obtaining initial information from its sources to verifying data, analyzing them, processing and forming the output information flow of the system. The results of the computational experiments carried out on the example of the problem of monitoring the parameters of the Earth's magnetic field and its variations confirmed the effectiveness of the proposed solutions, expressed both in increasing the reactivity of web-based applications and in increasing the computational speed of formation and filling of information storages that aggregate information from distributed heterogeneous sources.
42
Giraud, Anne-Lise, Christian Lorenzi, John Ashburner, Jocelyne Wable, Ingrid Johnsrude, Richard Frackowiak, and Andreas Kleinschmidt. "Representation of the Temporal Envelope of Sounds in the Human Brain." Journal of Neurophysiology 84, no. 3 (September 1, 2000): 1588–98. http://dx.doi.org/10.1152/jn.2000.84.3.1588.
Full textAbstract:
The cerebral representation of the temporal envelope of sounds was studied in five normal-hearing subjects using functional magnetic resonance imaging. The stimuli were white noise, sinusoidally amplitude-modulated at frequencies ranging from 4 to 256 Hz. This range includes low AM frequencies (up to 32 Hz) essential for the perception of the manner of articulation and syllabic rate, and high AM frequencies (above 64 Hz) essential for the perception of voicing and prosody. The right lower brainstem (superior olivary complex), the right inferior colliculus, the left medial geniculate body, Heschl's gyrus, the superior temporal gyrus, the superior temporal sulcus, and the inferior parietal lobule were specifically responsive to AM. Global tuning curves in these regions suggest that the human auditory system is organized as a hierarchical filter bank, each processing level responding preferentially to a given AM frequency, 256 Hz for the lower brainstem, 32–256 Hz for the inferior colliculus, 16 Hz for the medial geniculate body, 8 Hz for the primary auditory cortex, and 4–8 Hz for secondary regions. The time course of the hemodynamic responses showed sustained and transient components with reverse frequency dependent patterns: the lower the AM frequency the better the fit with a sustained response model, the higher the AM frequency the better the fit with a transient response model. Using cortical maps of best modulation frequency, we demonstrate that the spatial representation of AM frequencies varies according to the response type. Sustained responses yield maps of low frequencies organized in large clusters. Transient responses yield maps of high frequencies represented by a mosaic of small clusters. Very few voxels were tuned to intermediate frequencies (32–64 Hz). We did not find spatial gradients of AM frequencies associated with any response type. Our results suggest that two frequency ranges (up to 16 and 128 Hz and above) are represented in the cortex by different response types. However, the spatial segregation of these two ranges is not systematic. Most cortical regions were tuned to low frequencies and only a few to high frequencies. Yet, voxels that show a preference for low frequencies were also responsive to high frequencies. Overall, our study shows that the temporal envelope of sounds is processed by both distinct (hierarchically organized series of filters) and shared (high and low AM frequencies eliciting different responses at the same cortical locus) neural substrates. This layout suggests that the human auditory system is organized in a parallel fashion that allows a degree of separate routing for groups of AM frequencies conveying different information and preserves a possibility for integration of complementary features in cortical auditory regions.
43
Hu, Yi, Robert Bergquist, Yue Chen, Yongwen Ke, Jianjun Dai, Zonggui He, and Zhijie Zhang. "Dynamic evolution of schistosomiasis distribution under different control strategies: Results from surveillance covering 1991–2014 in Guichi, China." PLOS Neglected Tropical Diseases 15, no. 1 (January 6, 2021): e0008976. http://dx.doi.org/10.1371/journal.pntd.0008976.
Full textAbstract:
Background Since the founding of the China, the Chinese government, depending on the changing epidemiological situations over time, adopted different strategies to continue the progress towards elimination of schistosomiasis in the country. Although the changing pattern of schistosomiasis distribution in both time and space is well known and has been confirmed by numerous studies, the problem of how these patterns evolve under different control strategies is far from being understood. The purpose of this study is, therefore, to investigate the spatio-temporal change of the distribution of schistosomiasis with special reference to how these patterns evolve under different control strategies. Methodology / Principal findings Parasitological data at the village level were obtained through access to repeated cross-sectional surveys carried out during 1991–2014 in Guichi, a rural district along the Yangtze River in Anhui Province, China. A hierarchical dynamic spatio-temporal model was used to evaluate the evolving pattern of schistosomiasis prevalence, which accounted for mechanism of dynamics of the disease. Descriptive analysis indicates that schistosomiasis prevalence displayed fluctuating high-risk foci during implementation of the chemotherapy-based strategy (1991–2005), while it took on a homogenous pattern of decreasing magnitude in the following period when the integrated strategy was implemented (2006–2014). The dynamic model analysis showed that regularly global propagation of the disease was not present after the effect of proximity to river was taken into account but local pattern transition existed. Maps of predicted prevalence shows that relatively high prevalence (>4%) occasionally occurred before 2006 and prevalence presents a homogenous and decreasing trend over the study area afterwards. Conclusions Proximity to river is still an important determinant for schistosomiasis infection regardless of different types of implemented prevention and control strategies. Between the transition from the chemotherapy-based strategy to the integrated one, we noticed a decreased prevalence. However, schistosomiasis would remain an endemic challenge in these study areas. Further prevention and control countermeasures are warranted.
44
Chakhar, Amal, David Hernández-López, Rim Zitouna-Chebbi, Imen Mahjoub, Rocío Ballesteros, and Miguel A. Moreno. "Optimized Software Tools to Generate Large Spatio-Temporal Data Using the Datacubes Concept: Application to Crop Classification in Cap Bon, Tunisia." Remote Sensing 14, no. 19 (October 8, 2022): 5013. http://dx.doi.org/10.3390/rs14195013.
Full textAbstract:
In the context of a changing climate, monitoring agricultural systems is becoming increasingly important. Remote sensing products provide essential information for the crop classification application, which is used to produce thematic maps. High-resolution and regional-scale maps of agricultural land are required to develop better adapted future strategies. Nevertheless, the performance of crop classification using large spatio-temporal data remains challenging due to the difficulties in handling huge amounts of input data (different spatial and temporal resolutions). This paper proposes an innovative approach of remote sensing data management that was used to prepare the input data for the crop classification application. This classification was carried out in the Cap Bon region, Tunisia, to classify citrus groves among two other crop classes (olive groves and open field) using multi-temporal remote sensing data from Sentinel- 1 and Sentinel-2 satellite platforms. Thus, we described the new QGIS plugin “Model Management Tool (MMT)”. This plugin was designed to manage large Earth observation (EO) data. This tool is based on the combination of two concepts: (i) the local nested grid (LNG) called Tuplekeys and (ii) Datacubes. Tuplekeys or special spatial regions were created within a LNG to allow a proper integration between the data of both sensors. The Datacubes concept allows to provide an arranged array of time-series multi-dimensional stacks (space, time and data) of gridded data. Two different classification processes were performed based on the selection of the input feature (the obtained time-series as input data: NDVI and NDVI + VV + VH) and on the most accurate algorithm for each scenario (22 tested classifiers). The obtained results revealed that the best classification performance and highest accuracy were obtained with the scenario using only optical-based information (NDVI), with an overall accuracy OA = 0.76. This result was obtained by support vector machine (SVM). As for the scenario relying on the combination of optical and SAR data (NDVI + VV + VH), it presented an OA = 0.58. Our results demonstrate the usefulness of the new data management tool in organizing the input classification data. Additionally, our results highlight the importance of optical data to provide acceptable classification performance especially for a complex landscape such as that of the Cap Bon. The information obtained from this work will allow the estimation of the water requirements of citrus orchards and the improvement of irrigation scheduling methodologies. Likewise, many future methodologies will certainly rely on the combination of Tuplekeys and Datacubes concepts which have been tested within the MMT tool.
45
Osei, Frank, Alfred Stein, and Anthony Ofosu. "Poisson-Gamma Mixture Spatially Varying Coefficient Modeling of Small-Area Intestinal Parasites Infection." International Journal of Environmental Research and Public Health 16, no. 3 (January 26, 2019): 339. http://dx.doi.org/10.3390/ijerph16030339.
Full textAbstract:
Understanding the spatially varying effects of demographic factors on the spatio-temporal variation of intestinal parasites infections is important for public health intervention and monitoring. This paper presents a hierarchical Bayesian spatially varying coefficient model to evaluate the effects demographic factors on intestinal parasites morbidities in Ghana. The modeling relied on morbidity data collected by the District Health Information Management Systems. We developed Poisson and Poisson-gamma spatially varying coefficient models. We used the demographic factors, unsafe drinking water, unsafe toilet, and unsafe liquid waste disposal as model covariates. The models were fitted using the integrated nested Laplace approximations (INLA). The overall risk of intestinal parasites infection was estimated to be 10.9 per 100 people with a wide spatial variation in the district-specific posterior risk estimates. Substantial spatial variation of increasing multiplicative effects of unsafe drinking water, unsafe toilet, and unsafe liquid waste disposal occurs on the variation of intestinal parasites risk. The structured residual spatial variation widely dominates the unstructured component, suggesting that the unaccounted-for risk factors are spatially continuous in nature. The study concludes that both the spatial distribution of the posterior risk and the associated exceedance probability maps are essential for monitoring and control of intestinal parasites.
46
Alegana, V. A., P. M. Atkinson, C. Pezzulo, A. Sorichetta, D. Weiss, T. Bird, E. Erbach-Schoenberg, and A. J. Tatem. "Fine resolution mapping of population age-structures for health and development applications." Journal of The Royal Society Interface 12, no. 105 (April 2015): 20150073. http://dx.doi.org/10.1098/rsif.2015.0073.
Full textAbstract:
The age-group composition of populations varies considerably across the world, and obtaining accurate, spatially detailed estimates of numbers of children under 5 years is important in designing vaccination strategies, educational planning or maternal healthcare delivery. Traditionally, such estimates are derived from population censuses, but these can often be unreliable, outdated and of coarse resolution for resource-poor settings. Focusing on Nigeria, we use nationally representative household surveys and their cluster locations to predict the proportion of the under-five population in 1 × 1 km using a Bayesian hierarchical spatio-temporal model. Results showed that land cover, travel time to major settlements, night-time lights and vegetation index were good predictors and that accounting for fine-scale variation, rather than assuming a uniform proportion of under 5 year olds can result in significant differences in health metrics. The largest gaps in estimated bednet and vaccination coverage were in Kano, Katsina and Jigawa. Geolocated household surveys are a valuable resource for providing detailed, contemporary and regularly updated population age-structure data in the absence of recent census data. By combining these with covariate layers, age-structure maps of unprecedented detail can be produced to guide the targeting of interventions in resource-poor settings.
47
Turrin, James B., Richard R. Forster, Jeanne M. Sauber, Dorothy K. Hall, and Ronald L. Bruhn. "Effects of bedrock lithology and subglacial till on the motion of Ruth Glacier, Alaska, deduced from five pulses from 1973 to 2012." Journal of Glaciology 60, no. 222 (2014): 771–81. http://dx.doi.org/10.3189/2014jog13j182.
Full textAbstract:
AbstractA pulse is a type of unstable glacier flow intermediate between normal flow and surging. Using Landsat MSS, TM and ETM+ imagery and feature-tracking software, a time series of mostly annual velocity maps from 1973 to 2012 was produced that reveals five pulses of Ruth Glacier, Alaska. Peaks in ice velocity were found in 1981, 1989, 1997, 2003 and 2010, approximately every 7 years. During these peak years the ice velocity increased 300%, from approximately 40 m a–1 to 160 m a–1. Based on the spatio-temporal behavior of Ruth Glacier during the pulse cycles, we suggest the pulses are due to enhanced basal motion via deformation of a subglacial till. The cyclical nature of the pulses is interpreted to be due to a thin till, with low permeability, that causes incomplete drainage of the till between the pulses, followed by eventual recharge and dilation of the till. These findings suggest care is needed when attempting to correlate changes in regional climate with decadal-scale changes in velocity, because in some instances basal conditions may have a greater influence on ice dynamics than climate.
48
Li, Jingting, Ting Wang, and Su-Jing Wang. "Facial Micro-Expression Recognition Based on Deep Local-Holistic Network." Applied Sciences 12, no. 9 (May 5, 2022): 4643. http://dx.doi.org/10.3390/app12094643.
Full textAbstract:
A micro-expression is a subtle, local and brief facial movement. It can reveal the genuine emotions that a person tries to conceal and is considered an important clue for lie detection. The micro-expression research has attracted much attention due to its promising applications in various fields. However, due to the short duration and low intensity of micro-expression movements, micro-expression recognition faces great challenges, and the accuracy still demands improvement. To improve the efficiency of micro-expression feature extraction, inspired by the psychological study of attentional resource allocation for micro-expression cognition, we propose a deep local-holistic network method for micro-expression recognition. Our proposed algorithm consists of two sub-networks. The first is a Hierarchical Convolutional Recurrent Neural Network (HCRNN), which extracts the local and abundant spatio-temporal micro-expression features. The second is a Robust principal-component-analysis-based recurrent neural network (RPRNN), which extracts global and sparse features with micro-expression-specific representations. The extracted effective features are employed for micro-expression recognition through the fusion of sub-networks. We evaluate the proposed method on combined databases consisting of the four most commonly used databases, i.e., CASME, CASME II, CAS(ME)2, and SAMM. The experimental results show that our method achieves a reasonably good performance.
49
Biondi, F. "Space-time kriging extension of precipitation variability at 12 km spacing from tree-ring chronologies and its implications for drought analysis." Hydrology and Earth System Sciences Discussions 10, no. 4 (April 5, 2013): 4301–35. http://dx.doi.org/10.5194/hessd-10-4301-2013.
Full textAbstract:
Abstract. Understanding and preparing for future hydroclimatic variability greatly benefits from long (i.e., multi-century) records at seasonal to annual time steps that have been gridded at km-scale spatial intervals over a geographic region. Kriging is a geostatistical technique commonly used for optimal interpolation of environmental data, and space-time geostatistical models can improve kriging estimates when long temporal sequences of observations exist at relatively few points on the landscape. Here I present how a network of 22 tree-ring chronologies from single-leaf pinyon (Pinus monophylla) in the central Great Basin of North America was used to extend hydroclimatic records both temporally and spatially. First, the Line of Organic Correlation (LOC) method was used to reconstruct October–May total precipitation anomalies at each tree-ring site, as these ecotonal environments at the lower forest border are typically moisture limited. Individual site reconstructions were then combined using a hierarchical model of spatio-temporal kriging that produced annual anomaly maps on a 12 × 12 km grid during the period in common among all chronologies (1650–1976). Hydro-climatic episodes were numerically identified and modeled using their duration, magnitude, and peak. Spatial patterns were more variable during wet years than during dry years, and the evolution of drought episodes over space and time could be visualized and quantified. The most remarkable episode in the entire reconstruction was the early 1900s pluvial, followed by the late 1800s drought. The 1930s "Dust Bowl" drought was among the top ten hydroclimatic episodes in the past few centuries. These results directly address the needs of water and natural resource managers with respect to planning for "worst case" scenarios of drought duration and magnitude at the watershed level. For instance, it is possible to analyze which geographical areas are more likely to be impacted by severe and sustained droughts at annual or multiannual timescales and at spatial resolutions commonly used by regional climate models.
50
Ioannou, Alexandra E., Enrico F. Creaco, and Chrysi S. Laspidou. "Exploring the Effectiveness of Clustering Algorithms for Capturing Water Consumption Behavior at Household Level." Sustainability 13, no. 5 (March 1, 2021): 2603. http://dx.doi.org/10.3390/su13052603.
Full textAbstract:
As water scarcity becomes more prevalent, the analysis of urban water consumption patterns at the consumer level and the estimation of the corresponding water demand for water utility are expected to be among the top priorities of water companies in the near future. This study proposes a comprehensive methodology for water managers to achieve an efficient operation of urban water networks, by successfully detecting residential water consumption patterns corresponding to different household needs and behaviors. The methodology uses Self Organizing Maps as the main clustering algorithm in combination with K-means and Hierarchical Agglomerative Clustering. The objective is to create clusters in a literature dataset that includes water consumption from 21 customers located in Milford, Ohio, USA, for a 7-month period. Originally, water consumption data was recorded for every water use incident in the household, while for this analysis, the information is converted to half-hourly water consumption. Individual customers with similar consumption behavior are clustered and water-consumption curves are calculated for each cluster; these curves can be used by the water utility to obtain estimates of the spatio-temporal distribution of demand, thus giving insight into peak demands at different locations. Statistical indices of agreement are used to confirm a good agreement between the estimated and observed water use, when clustering is employed. The resulting curves show a clear improvement in capturing water consumption behavior at household level, when compared to corresponding curves obtained without clustering. This analysis offers water utilities an innovative solution that relies on real time data and uses data science principles for optimizing water supply and network operation and provides tools for the efficient use of water resources.