In the era of big data, analyzing and extracting knowledge from large-scale data sets is a very interesting and challenging task. The application of standard data mining tools in such data sets is ...not straightforward. Hence, a new class of scalable mining method that embraces the huge storage and processing capacity of cloud platforms is required. In this work, we propose a novel distributed partitioning methodology for prototype reduction techniques in nearest neighbor classification. These methods aim at representing original training data sets as a reduced number of instances. Their main purposes are to speed up the classification process and reduce the storage requirements and sensitivity to noise of the nearest neighbor rule. However, the standard prototype reduction methods cannot cope with very large data sets. To overcome this limitation, we develop a MapReduce-based framework to distribute the functioning of these algorithms through a cluster of computing elements, proposing several algorithmic strategies to integrate multiple partial solutions (reduced sets of prototypes) into a single one. The proposed model enables prototype reduction algorithms to be applied over big data classification problems without significant accuracy loss. We test the speeding up capabilities of our model with data sets up to 5.7 millions of instances. The results show that this model is a suitable tool to enhance the performance of the nearest neighbor classifier with big data.
Explainable artificial intelligence: an analytical review Angelov, Plamen P.; Soares, Eduardo A.; Jiang, Richard ...
Wiley interdisciplinary reviews. Data mining and knowledge discovery,
September/October 2021, Letnik:
11, Številka:
5
Journal Article
Recenzirano
Odprti dostop
This paper provides a brief analytical review of the current state‐of‐the‐art in relation to the explainability of artificial intelligence in the context of recent advances in machine learning and ...deep learning. The paper starts with a brief historical introduction and a taxonomy, and formulates the main challenges in terms of explainability building on the recently formulated National Institute of Standards four principles of explainability. Recently published methods related to the topic are then critically reviewed and analyzed. Finally, future directions for research are suggested.
This article is categorized under:
Technologies > Artificial Intelligence
Fundamental Concepts of Data and Knowledge > Explainable AI
Accuracy versus interpretability for different machine learning models.
•A 25kWth prototype for biomass gasification using chemical looping was made.•Natural hematite was used as oxygen carrier in the new prototype configuration.•Gasification temperature, S/B ratio and ...hematite fraction were investigated.•Optimal operation condition for 25kWth prototype was determined.
Biomass gasification using chemical looping (BGCL) presents a promising route to meet syngas production with lattice oxygen instead of molecular oxygen. And natural hematite is an attractive oxygen carrier material catalyzing tar cracking. A 25kWth prototype was made to investigate the performance of BGCL with hematite oxygen carrier in this work. The new prototype configuration is composed of a high velocity fluidized bed as an air reactor, a cyclone, a bubbling fluidized bed as a fuel reactor, and a loop-seal. The effects of gasification temperature, steam-to-biomass (S/B) ratio and hematite mass percentage were investigated. And the optimal operating parameters were determined. Because of the intensive endothermic reactions in the fuel reactor, the gasification temperature decreased sharply for bed materials of 100wt.% silica sand. Only when the hematite mass percentages reached 40wt.%, the gasification temperature was stable. The experimental results also showed that 860°C was the optimal gasification temperature corresponding to higher carbon conversion efficiency and maximal syngas yield. With respect to the effect of S/B ratio, carbon conversion efficiency reached the maximums at the S/B ratio of 1.0, while syngas yield increased firstly and then maintained almost unchanged. The optimal S/B ratio was 1.0 for higher syngas yield without sacrificing the maximal carbon conversion efficiency. When hematite mass percentage was varied in the range of 40–60wt.%, carbon conversion efficiency showed a monotonously increasing trend. However, a contrary trend was observed for gas yields, which reached the maximum when hematite mass percentage was set to 40wt.%. To get a higher syngas yield was the primary goal for BGCL. Therefore, the optimal hematite mass percentage seemed to be 40wt.%.
Federated learning (FL) enables distributed clients to collaboratively learn a global model, suggesting its potential for use in improving data privacy in machine learning. However, although FL has ...made many advances, its performance usually suffers from degradation due to the impact of domain shift when the trained models are applied to unseen domains. To enhance the model's generalization ability, we focus on solving federated domain generalization, which aims to properly generalize a federated model trained based on multiple source domains belonging to different distributions to an unseen target domain. A novel approach, namely Prototype-Decomposed Knowledge Distillation (PDKD), is proposed herein. Concretely, we first aggregate the local class prototypes that are learned from different clients. Subsequently, Singular Value Decomposition (SVD) is employed to decompose the local prototypes to obtain discriminative and generalized global prototypes that contain rich category-related information. Finally, the global prototypes are sent back to all clients. We exploit knowledge distillation to encourage local client models to distill generalized knowledge from the global prototypes, which boosts the generalization ability. Extensive experiments on multiple datasets demonstrate the effectiveness of our method. In particular, when implemented on the Office dataset, our method outperforms FedAvg by around 13.5%, which shows that our method is instrumental in ameliorating the generalization ability of federated models.
Conventional deep CNN-based segmentation approaches have achieved satisfactory performance in recent years, however, they are essentially Big Data-driven technologies and are difficult to generalize ...to unseen categories. Few-shot segmentation is subsequently developed to perform pertinent operations in a low-data regime. Unfortunately, due to the training paradigm and network architecture factors, existing methods are prone to overfit the targets of base categories and yield inaccurate segmentation boundaries, which impedes the research progress to some extent. In this paper, we propose a Holistic Prototype Activation (HPA) network to alleviate these problems. Its novel designs can be summarized in three aspects: 1) A training-free scheme to derive the prior representations of base categories. 2) Prototype Activation Module (PAM) that generates reliable activation maps and well-matched query features by filtering the objects of irrelevant classes with high confidence. 3) Cross-Referenced Decoder (CRD) for interacted feature reweighting and multi-level feature aggregation. Extensive experiments on standard few-shot segmentation benchmarks (PASCAL-5<inline-formula><tex-math notation="LaTeX">^{i}</tex-math> <mml:math><mml:msup><mml:mrow/><mml:mi>i</mml:mi></mml:msup></mml:math><inline-graphic xlink:href="cheng-ieq1-3193587.gif"/> </inline-formula> and COCO-20<inline-formula><tex-math notation="LaTeX">^{i}</tex-math> <mml:math><mml:msup><mml:mrow/><mml:mi>i</mml:mi></mml:msup></mml:math><inline-graphic xlink:href="cheng-ieq2-3193587.gif"/> </inline-formula>) verify the effectiveness of our method. On top of that, the superior performance on multiple extended tasks, such as weak-label segmentation, zero-shot segmentation, and video object segmentation, also illustrates its flexibility and versatility. Our code is publicly available at https://github.com/chunbolang/HPA .
Prototype-based Semantic Segmentation Zhou, Tianfei; Wang, Wenguan
IEEE transactions on pattern analysis and machine intelligence,
2024-Apr-10, Letnik:
PP
Journal Article
Recenzirano
Deep learning based semantic segmentation solutions have yielded compelling results over the preceding decade. They encompass diverse network architectures (FCN based or attention based), along with ...various mask decoding schemes (parametric softmax based or pixel-query based). Despite the divergence, they can be grouped within a unified framework by interpreting the softmax weights or query vectors as learnable class prototypes. In light of this prototype view, we reveal inherent limitations within the parametric segmentation regime, and accordingly develop a nonparametric alternative based on non-learnable prototypes. In contrast to previous approaches that entail the learning of a single weight/query vector per class in a fully parametric manner, our approach represents each class as a set of non-learnable prototypes, relying solely upon the mean features of training pixels within that class. The pixel-wise prediction is thus achieved by nonparametric nearest prototype retrieving. This allows our model to directly shape the pixel embedding space by optimizing the arrangement between embedded pixels and anchored prototypes. It is able to accommodate an arbitrary number of classes with a constant number of learnable parameters. Through empirical evaluation with FCN based and Transformer based segmentation models (i.e., HRNet, Swin, SegFormer, Mask2Former) and backbones (i.e., ResNet, HRNet, Swin, MiT), our nonparametric framework shows superior performance on standard segmentation datasets (i.e., ADE20K, Cityscapes, COCO-Stuff), as well as in large-vocabulary semantic segmentation scenarios. We expect that this study will provoke a rethink of the current de facto semantic segmentation model design.
Despite the success of convolutional neural network (CNN) in conventional closed-set recognition (CSR), it still lacks robustness for dealing with unknowns (those out of known classes) in open ...environment. To improve the robustness of CNN in open-set recognition (OSR) and meanwhile maintain its high accuracy in CSR, we propose an alternative deep framework called convolutional prototype network (CPN), which keeps CNN for representation learning but replaces the closed-world assumed softmax with an open-world oriented and human-like prototype model. To equip CPN with discriminative ability for classifying known samples, we design several discriminative losses for training. Moreover, to increase the robustness of CPN for unknowns, we interpret CPN from the perspective of generative model and further propose a generative loss, which is essentially maximizing the log-likelihood of known samples and serves as a latent regularization for discriminative learning. The combination of discriminative and generative losses makes CPN a hybrid model with advantages for both CSR and OSR. Under the designed losses, the CPN is trained end-to-end for learning the convolutional network and prototypes jointly. For application of CPN in OSR, we propose two rejection rules for detecting different types of unknowns. Experiments on several datasets demonstrate the efficiency and effectiveness of CPN for both CSR and OSR tasks.
•Several assembly details of a proof-of-concept magnetic refrigeration prototype are presented.•3 versions of magnetic system have been commented.•Magnetic refrigeration experimental results are ...detailed and analyzed.•The prototype has been designed as a 15 kW unit.•The results show a Carnot efficiency of 60% and a temperature span of 21.4 K.
As any innovative development program, magnetic refrigeration still faces many challenges before being widely accepted as an actual replacement technology for cooling. In the last years, more than 50 different types of prototypes of magnetocaloric refrigerators have been presented in literature, with limited cooling power values and/or limited temperature span. This paper presents several assembly details and experimental results of a new proof-of-concept magnetic refrigeration prototype having both a temperature span of more than 20 K and a cooling capacity designed for around 15 kW. It has been made as a part of a pilot project for a large industrial partner to be used for an industrial process. The obtained experimental results have been measured and validated by an exterior independent body. This performance achievement, that we believe to be as the largest rotary magnetic refrigerator ever created, could be a milestone for the future of magnetocaloric chillers.
Metasurfaces have drawn significant attentions due to their superior capability in tailoring electromagnetic waves with a wide frequency range, from microwave to visible light. Recently, programmable ...metasurfaces have demonstrated the ability of manipulating the amplitude or phase of electromagnetic waves in a programmable manner in real time, which renders them especially appealing in the applications of wireless communications. In this paper, we present the fundamental principle of applying programmable metasurface as transmitter for wireless communications. Then, we establish a prototype system of meta-surface-based transmitter to conduct several experiments and measurements over the air, which practically demonstrate the feasibility of using programmable metasurfaces in future communication systems. By exploiting the dynamically controllable property of programmable metasurface, the design, implementation and experimental evaluation of the proposed metasurface-based wireless communication system are presented with the prototype, which realizes single carrier quadrature phase shift keying (QPSK) transmission over the air. In the developed prototype, the phase of the reflected electromagnetic wave of programmable metasurface is directly manipulated in real time according to the baseband control signal, which achieves 2.048 Mbps data transfer rate with video streaming transmission over the air. In addition, experimental result is provided to compare the performance of the proposed metasurface-based architecture against the conventional one. With the slight increase of the transmit power by 5 dB, the same bit error rate (BER) performance can be achieved as the conventional system in the absence of channel coding. Such a result is encouraging considering that the metasurface-based system has the advantages of low hardware cost and simple structure, thus leading to a promising new architecture for wireless communications.
Few-shot image classification has attracted extensive attention, which aims to recognize unseen classes given only a few labeled samples. Due to the large intraclass variances and interclass ...similarity of remote sensing scenes, the task under such circumstance is much more challenging than general few-shot image classification. Most existing prototype-based few-shot algorithms usually calculate prototypes directly from support samples and ignore the validity of prototypes, which results in a decline in the accuracy of subsequent inferences based on prototypes. To tackle this problem, we propose a Siamese-prototype network (SPNet) with prototype self-calibration (SC) and intercalibration (IC). First, to acquire more accurate prototypes, we utilize the supervision information from support labels to calibrate the prototypes generated from support features. This process is called SC. Second, we propose to consider the confidence scores of the query samples as another type of prototypes, which are then used to predict the support samples in the same way. Thus, the information interaction between support and query samples is implicitly a further calibration for prototypes (so-called IC). Our model is optimized with three losses, of which two additional losses help the model to learn more representative prototypes and make more accurate predictions. With no additional parameters to be learned, our model is very lightweight and convenient to employ. The experiments on three public remote sensing image datasets demonstrate competitive performance compared with other advanced few-shot image classification approaches. The source code is available at https://github.com/zoraup/SPNet .