Pooling Information Research Articles

CapNet: An Automatic Attention-Based with Mixer Model for Cardiovascular Magnetic Resonance Image Segmentation.

Deep neural networks have shown excellent performance in medical image segmentation, especially for cardiac images. Transformer-based models, though having advantages over convolutional neural networks due to the ability of long-range dependence learning, still have shortcomings such as having a large number of parameters and and high computational cost. Additionally, for better results, they are often pretrained on a larger data, thus requiring large memory size and increasing resource expenses. In this study, we propose a new lightweight but efficient model, namely CapNet, based on convolutions and mixing modules for cardiac segmentation from magnetic resonance images (MRI) that can be trained from scratch with a small amount of parameters. To handle varying sizes and shapes which often occur in cardiac systolic and diastolic phases, we propose attention modules for pooling, spatial, and channel information. We also propose a novel loss called the Tversky Shape Power Distance function based on the shape dissimilarity between labels and predictions that shows promising performances compared to other losses. Experiments on three public datasets including ACDC benchmark, Sunnybrook data, and MS-CMR challenge are conducted and compared with other state of the arts (SOTA). For binary segmentation, the proposed CapNet obtained the Dice similarity coefficient (DSC) of 94% and 95.93% for respectively the Endocardium and Epicardium regions with Sunnybrook dataset, 94.49% for Endocardium, and 96.82% for Epicardium with the ACDC data. Regarding the multiclass case, the average DSC by CapNet is 93.05% for the ACDC data; and the DSC scores for the MS-CMR are 94.59%, 92.22%, and 93.99% for respectively the bSSFP, T2-SPAIR, and LGE sequences of the MS-CMR. Moreover, the statistical significance analysis tests with p-value compared with transformer-based methods and some CNN-based approaches demonstrated that the CapNet, though having fewer training parameters, is statistically significant. The promising evaluation metrics show comparative results in both Dice and IoU indices compared to SOTA CNN-based and Transformer-based architectures.

Multi-party ride-matching problem in the ride-hailing market with bundled option services

As demands for convenient and comfortable mobility grow, transportation network companies (TNCs) begin to diversify the ride-hailing services they offer. Modes that are offered now include ride-pooling (RP), non-ride-pooling (NP), and a third “bundled” option, which combines RP and NP. This emerging bundled option allows riders to be served via either RP or NP mode, whichever becomes available first. This paper examines the added complexity that a ride-hailing service platform faces when it introduces a third bundled option. Incorporating the predicted pooling information in the near future, a ride-matching problem is dedicated to matching vehicles with riders under various scenarios over a number of matching iterations. We formulate the multi-period ride-matching problem using an integer linear programming model with multiple objectives and to make dispatching decisions based on certain matching criteria. The complexity of the problem requires resolution via a two-stage Kuhn-Munkres (2-KM) algorithm, whose robustness is verified by computational tests. Some interesting insights are obtained: (1) how the bundled option impacts system performance metrics depends on whether the supply is sufficient or not; (2) there is an optimal value of the criterion of the maximum pickup time that maximizes the ride-pooling time savings.

CNN with depthwise separable convolutions and combined kernels for rating prediction

Recently, deep learning based techniques exploiting reviews are extensively studied for rating prediction and result in good performance. Some studies consider word level review information along with attention mechanism to capture the most influential content, thus making the methods even complex. Deep neural networks with Depthwise Separable Convolutions have made significant progress in the area of image and video analysis. The success of these techniques encourages adopting them towards improvements in rating prediction using review text. In this paper, we present a novel CNN based architecture with Depthwise Separable Convolutions and Combined Kernels (CNN-DSCK) for rating prediction exploiting product reviews. In the proposed method, we use two parallel CNNs with Depthwise Separable Convolutions to extract semantic features from the text reviews of users and items using different kernels in parallel and then select the important information from these features through pooling. Finally concatenate the pooling information obtained from different kernels in each network. The features obtained through each network are then fused and the most relevant higher-order features are extracted through fully connected dense layer at the top of network. Extensive experiments on real-world datasets demonstrate that CNN-DSCK significantly outperforms state of the art baseline models.

Multi-scale temporal feature-based dense convolutional network for action recognition

We propose a network structure for action recognition that is capable of extracting multi-scale temporal representations of actions. The key of the network is to combine a multi-scale temporal pooling module with a dense connection module, called multi-scale temporal pooling dense convolutional network (MTPDNet). The multi-scale temporal pooling module consists of multiple temporal scale levels. At each scale level, video frames are divided into several segments and a pooling operation is then performed on each segment to get temporal pooling information. The number of segments is set differently at different time scale levels, aiming to obtain multi-scale temporal pooling information. In addition, at each scale level, we adopt a redesigned dense connection module to learn motion representations from temporal pooling information. Finally, predictions are independently made at each scale level and the class scores of each scale level are fused to get the final prediction scores. Experimental results on two standard datasets, UCF101 and HMDB51, demonstrate that MTPDNet gets comparable or even better results among leading methods, which proves the effectiveness of the strategy combining multi-scale temporal pooling and dense connection.

D2N4: A Discriminative Deep Nearest Neighbor Neural Network for Few-Shot Space Target Recognition

With the rapid development of space exploration worldwide, there is a sudden increase in the type and number of spacecraft, thus leading to a more complex space environment. To enhance the ability of space situational awareness, the most important step is to effectively recognize space targets of interests from various spacecraft and debris. Traditional space target recognition approaches adopt manual feature extraction with limited data, resulting in a semantic gap between low-level visual features and high-level semantic representation. Although deep learning models alleviate this problem with a unified framework for combined learning feature extraction and classification simultaneously, it is easy to overfit and leads to poor generalization results when faced with a situation of small examples. To address these issues, we present an end-to-end few-shot deep learning framework for space target recognition, i.e., discriminative deep nearest neighbor neural network (D2N4). Our D2N4 aims to improve the discriminability of the deeply learned features with mainly two strategies. On the one hand, we add an intraclass compactness principle by introducing center loss to efficiently pull deep features of the same classes to their centers and, thus overcoming significant intraclass variation of space target. On the other hand, we introduce the global pooling information for each deep local descriptor to reduce interference from local background noise, thus enhancing the model robustness. In practice, under the joint supervision of soft-max loss and center loss, the deep embedding module and image-to-class metric module are trained in an end-to-end way. Extensive experiments on the space target data set BUAA-SID-share1.0 demonstrate that our simple and effective approach outperforms previous space target recognition methods and is more efficient than recent few-shot approaches. In addition, the proposed framework is equally applicable to natural images and achieves state-of-the-art performance on data sets CUB-200-2010, Stanford Dogs, and Stanford Cars.

A two-stage procedure to pool information across quantile levels in linear quantile regression

ABSTRACTIn linear quantile regression, the regression coefficients for different quantiles are typically estimated separately. Efforts to improve the efficiency of estimators are often based on assumptions of commonality among the slope coefficients. We propose instead a two-stage procedure whereby the regression coefficients are first estimated separately and then smoothed over quantile level. Due to the strong correlation between coefficient estimates at nearby quantile levels, existing bandwidth selectors will pick bandwidths that are too small. To remedy this, we use 10-fold cross-validation to determine a common bandwidth inflation factor for smoothing the intercept as well as slope estimates. Simulation results suggest that the proposed method is effective in pooling information across quantile levels, resulting in estimates that are typically more efficient than the separately obtained estimates and the interquantile shrinkage estimates derived using a fused penalty function. The usefulness of the proposed method is demonstrated in a real data example.

The Study of Pallet Pooling Information Platform Based on Cloud Computing

Effective implementation of pallet pooling system needs a strong information platform to support. Through the analysis of existing pallet pooling information platform (PPIP), the paper pointed out that the existing studies of PPIP are mainly based on traditional IT infrastructures and technologies which have software, hardware, resource utilization, and process restrictions. Because of the advantages of cloud computing technology like strong computing power, high flexibility, and low cost which meet the requirements of the PPIP well, this paper gave a PPIP architecture of two parts based on cloud computing: the users client and the cloud services. The cloud services include three layers, which are IaaS, PaaS, and SaaS. The method of how to deploy PPIP based on cloud computing is proposed finally.

Hype As a Public Good for Innovation

Early stage innovation can benefit from cooperative pooling of distributed information and other innovation resources in order to discover entrepreneurial opportunities (what Allen and Potts (2016) call the ‘innovation commons’). The innovation commons is a private ordering, but social welfare losses arise when innovation commons fail to form, or are small and only weakly cooperative. This results in arrested Schumpeterian development. We suggest a mechanism by which a government can facilitate private cooperation in innovation commons by exploiting the behavioural heuristic of loss aversion through the public provision of targeted technology hype. What we call hypeless technologies can experience innovation failure because of an undersupply of early stage cooperation (i.e. pooling information and resources), retarding entrepreneurial discovery and cruelling the innovation trajectory. Weak cooperation occurs because of missing anticipation of regret (Kahneman and Tversky 1979) about the consequences of not being in the innovation commons. The purpose of hype is not to sell the technology, but to induce awareness that may manifest as loss aversion, which is privately resolved by supplying cooperation.

Bayesian estimation in random effects meta-analysis using a non-informative prior.

Pooling information from multiple, independent studies (meta-analysis) adds great value to medical research. Random effects models are widely used for this purpose. However, there are many different ways of estimating model parameters, and the choice of estimation procedure may be influential upon the conclusions of the meta-analysis. In this paper, we describe a recently proposed Bayesian estimation procedure and compare it with a profile likelihood method and with the DerSimonian-Laird and Mandel-Paule estimators including the Knapp-Hartung correction. The Bayesian procedure uses a non-informative prior for the overall mean and the between-study standard deviation that is determined by the Berger and Bernardo reference prior principle. The comparison of these procedures focuses on the frequentist properties of interval estimates for the overall mean. The results of our simulation study reveal that the Bayesian approach is a promising alternative producing more accurate interval estimates than those three conventional procedures for meta-analysis. The Bayesian procedure is also illustrated using three examples of meta-analysis involving real data. Copyright © 2016 John Wiley & Sons, Ltd.

Group size advantages to decision making are environmentally contingent in house-hunting Myrmecina ants

Pooling information can allow groups to make better decisions than individuals, an idea that underlies the use of groups to make important decisions in human society. Group size is also thought to influence the accuracy of decision making in nonhuman animals, but despite the enormous variation in the size and composition of animal societies, very few studies have explored this question outside of humans. Furthermore, although both humans and animals need to make decisions in dynamic environments and models suggest that environmental conditions can alter or even invert the advantage of group size, no empirical study has addressed how the advantage of group size may vary with environmental context. In this study I investigated how group size and environmental context influence decision making using an ant model system in which colonies use a quorum-based process to decide collectively among new nesting sites. Decision making unfolded in a similar manner in colonies of different size, as quorum thresholds and task allocation scaled with colony size. Larger colonies, however, made more accurate decisions than small colonies, and in most cases did so more rapidly. There was also an influence of environmental conditions, as whereas the decision accuracy of small groups was comparable to that of large groups in benign conditions, decision making was largely ineffective in small colonies in more challenging conditions. Colonies adapted to different environmental conditions by adjusting quorum thresholds, shifting thresholds down to emphasize speed when under stress and showing a pattern of higher thresholds in complex environments. The advantage to larger colonies probably stems from their greater information collecting and processing ability, which also serves to buffer them from the negative influences of more challenging environments.

A hierarchical model for estimating response time distributions

We present a statistical model for inference with response time (RT) distributions. The model has the following features. First, it provides a means of estimating the shape, scale, and location (shift) of RT distributions. Second, it is hierarchical and models between-subjects and within-subjects variability simultaneously. Third, inference with the model is Bayesian and provides a principled and efficient means of pooling information across disparate data from different individuals. Because the model efficiently pools information across individuals, it is particularly well suited for those common cases in which the researcher collects a limited number of observations from several participants. Monte Carlo simulations reveal that the hierarchical Bayesian model provides more accurate estimates than several popular competitors do. We illustrate the model by providing an analysis of the symbolic distance effect in which participants can more quickly ascertain the relationship between nonadjacent digits than that between adjacent digits.

Necessity of spatial pooling for the perception of heading in nonrigid environments.

This study examined whether the perception of heading is determined by spatially pooling velocity information. Observers were presented displays simulating observer motion through a volume of 3-D objects. To test the importance of spatial pooling, the authors systematically varied the nonrigidity of the flow field using two types of object motion: adding a unique rotation or translation to each object. Calculations of the signal-to-noise (observer velocity-to-object motion) ratio indicated no decrements in performance when the ratio was .39 for object rotation and .45 for object translation. Performance also increased with the number of objects in the scene. These results suggest that heading is determined by mechanisms that use spatial pooling over large regions.

The uses and abuses of meta-analysis.

Meta-analysis is a quantitative process of summary and interpretation which involves pooling information from independent studies concerning a single theme in order to draw conclusions. Greatly increased employment of meta-analysis is currently being advocated for clinical and policy decision making. However, the prestige of meta-analysis is based upon a false model of scientific practice. Interpreting empirical research is an extremely complex activity requiring clinical and scientific knowledge of the field in question; and teams of professional 'meta-analysts' with a primary skill base in information technology and biostatistics cannot take over this role. Meta-analysis is not a hypothesis-testing activity, and cannot legitimately be used to establish the reality of a putative hazard or therapy. The proper use of meta-analysis is to increase the precision of quantitative estimates of health states in populations. If used to estimate an effect, the reality of that effect should have been established by previous scientific studies. But the summary estimate from a meta-analysis can only be directly applied to a target population when the 'meta-protocol' and 'meta-population' match the target situation in all relevant particulars. These constraints can rarely be satisfied in practice, so the results of meta-analysis typically require adjustment--which is a complex, assumption-laden process that negates many of the statistical power advantages of a meta-analysis. Lacking any understanding or acknowledgement of the need for adjustment, most meta-analyses must be regarded as abuses of the technique.