Location-Routing Problem of Emergency Facilities under Uncertain Demand by Branch-Price and Cut

This paper studies the location-routing problem of emergency facilities with time window under demand uncertainty. We propose a robust mathematical model in which uncertain requirements are represented by two forms: the support set defined by cardinal constraint set. When the demand value of rescue point changes in a given definition set, the model can ensure the feasibility of each line. We propose a branch and price cutting algorithm, whose pricing problem is a robust resource-constrained shortest path problem. In addition, we take the Wenchuan Earthquake as an example to verify the practicability of the method. The robust model is simulated under different uncertainty levels and distributions and compared with the scheme obtained by the deterministic problem. The results show that the robust model can run successfully and maintain its robustness, and the robust model provides better protection against demand uncertainty. In addition, we find that cost is more sensitive to uncertainty level than protection level, and our proposed model also allows controlling the robustness level of the solution by adjusting the protection level. In all experiments, the cost of robustness is that the routing cost increases by an average of 13.87%.

Forward-Reverse Orthogonal Matching Pursuit-Union-Subspace Pursuit-Based Multiuser Detector for Uplink Grant-Free NOMA Networks

Multiuser Detection (MUD) is quite challenging in uplink grant-free non-orthogonal multiple access wireless communication networks in which users sporadically transmit data. The reason for this is that the base station (BS) must perform detection of both multiuser activity and user signals concurrently, because knowledge of user activity status is not available at the BS. In this paper, a new multiuser detector, named the Forward-Reverse Orthogonal Matching Pursuit–Union–Subspace pursuit (FROMPUS)-based MUD, is proposed. The detector takes advantage of the concept of an initial support set. This serves as initial knowledge that is then employed in the reconstruction of active users’ signals. In addition, the detector uses the “serial-include” technique of incorporating a likely support set element candidates and a reliability testing procedure in which the most prominent elements of the support set are selected. To assess the performance of the proposed detector, computer simulations are performed. The results obtained for various parameter settings show that the FROMPUS performs better than any of the other five detectors considered in this paper. However, this excellent performance comes with a slightly higher computational complexity cost. Nonetheless, the cost is inconsequential, since the detector operates at the BS where complexity is of low priority in comparison to performance.

Using the Homeland Security Exercise and Evaluation Program (HSEEP) Building Block Approach to Implement System Evaluation Theory (SET)

This article shares lessons learned in applying system evaluation theory (SET) to evaluate a Clinical and Translational Research Center (CTR) funded by the National Institutes of Health. After describing how CTR support cores are intended to work interdependently as a system, the case is made for SET as the best fit for evaluating this evaluand. The article then details how the evaluation was also challenged to facilitate a CTR culture shift, helping support cores to move from working autonomously to working together and understanding how the cores’ individual operating processes impact each other. This was achieved by incorporating the Homeland Security Exercise and Evaluation Program (HSEEP) building block approach to implement SET. Each of the seven HSEEP building blocks is examined for alignment with each of SET’s three steps and the ability to systematically support the goal of moving CTR cores toward working interdependently. The implications of using HSEEP to support SET implementation for future evaluations are discussed.

Self-Amplificated Network: Learning fine-grained learner with few samples

Training deep neural networks from only a few examples has been an interesting topic that motivated few shot learning. In this paper, we study the fine-grained image classification problem in a challenging few-shot learning setting, and propose the Self-Amplificated Network (SAN), a method based on meta-learning to tackle this problem. The SAN model consists of three parts, which are the Encoder, Amplification and Similarity Modules. The Encoder Module encodes a fine-grained image input into a feature vector. The Amplification Module is used to amplify subtle differences between fine-grained images based on the self attention mechanism which is composed of multi-head attention. The Similarity Module measures how similar the query image and the support set are in order to determine the classification result. In-depth experiments on three benchmark datasets have showcased that our network achieves superior performance over the competing baselines.

PFMNet: Few-Shot Segmentation with Query Feature Enhancement and Multi-Scale Feature Matching

The datasets in the latest semantic segmentation model often need to be manually labeled for each pixel, which is time-consuming and requires much effort. General models are unable to make better predictions, for new categories of information that have never been seen before, than the few-shot segmentation that has emerged. However, the few-shot segmentation is still faced up with two challenges. One is the inadequate exploration of semantic information conveyed in the high-level features, and the other is the inconsistency of segmenting objects at different scales. To solve these two problems, we have proposed a prior feature matching network (PFMNet). It includes two novel modules: (1) the Query Feature Enhancement Module (QFEM), which makes full use of the high-level semantic information in the support set to enhance the query feature, and (2) the multi-scale feature matching module (MSFMM), which increases the matching probability of multi-scales of objects. Our method achieves an intersection over union average score of 61.3% for one-shot segmentation and 63.4% for five-shot segmentation, which surpasses the state-of-the-art results by 0.5% and 1.5%, respectively.

Negative-supervised capsule graph neural network for few-shot text classification

Few-shot text classification aims to learn a classifier from very few labeled text data. Existing studies on this topic mainly adopt prototypical networks and focus on interactive information between support set and query instances to learn generalized class prototypes. However, in the process of encoding, these methods only pay attention to the matching information between support set and query instances, and ignore much useful information about intra-class similarity and inter-class dissimilarity between all support samples. Therefore, in this paper we propose a negative-supervised capsule graph neural network (NSCGNN) which explicitly takes use of the similarity and dissimilarity between samples to make the text representations of the same type closer with each other and the ones of different types farther away, leading to representative and discriminative class prototypes. We firstly construct a graph to obtain text representations in the form of node capsules, where both intra-cluster similarity and inter-cluster dissimilarity between all samples are explored with information aggregation and negative supervision. Then, in order to induce generalized class prototypes based on those node capsules obtained from graph neural network, the dynamic routing algorithm is utilized in our model. Experimental results demonstrate the effectiveness of our proposed NSCGNN model, which outperforms existing few-shot approaches on three benchmark datasets.

Detecting Local Insights from Global Labels: Supervised & Zero-Shot Sequence Labeling via a Convolutional Decomposition

We propose a new, more actionable view of neural network interpretability and data analysis by leveraging the remarkable matching effectiveness of representations derived from deep networks, guided by an approach for class-conditional feature detection. The decomposition of the filterngram interactions of a convolutional neural network and a linear layer over a pre-trained deep network yields a strong binary sequence labeler, with flexibility in producing predictions at— and defining loss functions for—varying label granularities, from the fully-supervised sequence labeling setting to the challenging zero-shot sequence labeling setting, in which we seek tokenlevel predictions but only have document-level labels for training. From this sequence-labeling layer we derive dense representations of the input that can then be matched to instances from training, or a support set with known labels. Such introspection with inference-time decision rules provides a means, in some settings, of making local updates to the model by altering the labels or instances in the support set without re-training the full model. Finally, we construct a particular K-nearest neighbors (K-NN) model from matched exemplar representations that approximates the original model’s predictions and is at least as effective a predictor with respect to the ground-truth labels. This additionally yields interpretable heuristics at the token level for determining when predictions are less likely to be reliable, and for screening input dissimilar to the support set. In effect, we show that we can transform the deep network into a simple weighting over exemplars and associated labels, yielding an introspectable—and modestly updatable— version of the original model.

Uncertainty-Aware Few-Shot Image Classification

Few-shot image classification learns to recognize new categories from limited labelled data. Metric learning based approaches have been widely investigated, where a query sample is classified by finding the nearest prototype from the support set based on their feature similarities. A neural network has different uncertainties on its calculated similarities of different pairs. Understanding and modeling the uncertainty on the similarity could promote the exploitation of limited samples in few-shot optimization. In this work, we propose Uncertainty-Aware Few-Shot framework for image classification by modeling uncertainty of the similarities of query-support pairs and performing uncertainty-aware optimization. Particularly, we exploit such uncertainty by converting observed similarities to probabilistic representations and incorporate them to the loss for more effective optimization. In order to jointly consider the similarities between a query and the prototypes in a support set, a graph-based model is utilized to estimate the uncertainty of the pairs. Extensive experiments show our proposed method brings significant improvements on top of a strong baseline and achieves the state-of-the-art performance.

A Certain Structure of Bipolar Fuzzy Subrings

The role of symmetry in ring theory is universally recognized. The most directly definable universal relation in a symmetric set theory is isomorphism. This article develops a certain structure of bipolar fuzzy subrings, including bipolar fuzzy quotient ring, bipolar fuzzy ring homomorphism, and bipolar fuzzy ring isomorphism. We define (α,β)-cut of bipolar fuzzy set and investigate the algebraic attributions of this phenomenon. We also define the support set of bipolar fuzzy set and prove various important properties relating to this concept. Additionally, we define bipolar fuzzy homomorphism by using the notion of natural ring homomorphism. We also establish a bipolar fuzzy homomorphism between bipolar fuzzy subring of the quotient ring and bipolar fuzzy subring of this ring. We constituted a significant relationship between two bipolar fuzzy subrings of quotient rings under a given bipolar fuzzy surjective homomorphism. We present the construction of an induced bipolar fuzzy isomorphism between two related bipolar fuzzy subrings. Moreover, to discuss the symmetry between two bipolar fuzzy subrings, we present three fundamental theorems of bipolar fuzzy isomorphism.