Extreme Learning Machine for Multilayer Perceptron Tang, Jiexiong; Deng, Chenwei; Huang, Guang-Bin
IEEE transaction on neural networks and learning systems,
2016-April, 2016-Apr, 2016-4-00, 20160401, Volume:
27, Issue:
4
Journal Article
Extreme learning machine (ELM) is an emerging learning algorithm for the generalized single hidden layer feedforward neural networks, of which the hidden node parameters are randomly generated and ...the output weights are analytically computed. However, due to its shallow architecture, feature learning using ELM may not be effective for natural signals (e.g., images/videos), even with a large number of hidden nodes. To address this issue, in this paper, a new ELM-based hierarchical learning framework is proposed for multilayer perceptron. The proposed architecture is divided into two main components: 1) self-taught feature extraction followed by supervised feature classification and 2) they are bridged by random initialized hidden weights. The novelties of this paper are as follows: 1) unsupervised multilayer encoding is conducted for feature extraction, and an ELM-based sparse autoencoder is developed via ℓ 1 constraint. By doing so, it achieves more compact and meaningful feature representations than the original ELM; 2) by exploiting the advantages of ELM random feature mapping, the hierarchically encoded outputs are randomly projected before final decision making, which leads to a better generalization with faster learning speed; and 3) unlike the greedy layerwise training of deep learning (DL), the hidden layers of the proposed framework are trained in a forward manner. Once the previous layer is established, the weights of the current layer are fixed without fine-tuning. Therefore, it has much better learning efficiency than the DL. Extensive experiments on various widely used classification data sets show that the proposed algorithm achieves better and faster convergence than the existing state-of-the-art hierarchical learning methods. Furthermore, multiple applications in computer vision further confirm the generality and capability of the proposed learning scheme.
The emergent machine learning technique—extreme learning machines (ELMs)—has become a hot area of research over the past years, which is attributed to the growing research activities and significant ...contributions made by numerous researchers around the world. Recently, it has come to our attention that a number of misplaced notions and misunderstandings are being dissipated on the relationships between ELM and some earlier works. This paper wishes to clarify that (1) ELM theories manage to address the open problem which has puzzled the neural networks, machine learning and neuroscience communities for 60 years: whether hidden nodes/neurons need to be tuned in learning, and proved that in contrast to the common knowledge and conventional neural network learning tenets, hidden nodes/neurons do not need to be iteratively tuned in wide types of neural networks and learning models (Fourier series, biological learning, etc.). Unlike ELM theories, none of those earlier works provides theoretical foundations on feedforward neural networks with random hidden nodes; (2) ELM is proposed for both generalized single-hidden-layer feedforward network and multi-hidden-layer feedforward networks (including biological neural networks); (3) homogeneous architecture-based ELM is proposed for feature learning, clustering, regression and (binary/multi-class) classification. (4) Compared to ELM, SVM and LS-SVM tend to provide suboptimal solutions, and SVM and LS-SVM do not consider feature representations in hidden layers of multi-hidden-layer feedforward networks either.
Full text
Available for:
EMUNI, FIS, FZAB, GEOZS, GIS, IJS, IMTLJ, KILJ, KISLJ, MFDPS, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, SBMB, SBNM, UKNU, UL, UM, UPUK, VKSCE, ZAGLJ
With the ever-growing need for lithium-ion batteries, particularly from the electric transportation industry, a large amount of lithium-ion batteries is bound to retire in the near future, thereby ...leading to serious disposal problems and detrimental impacts on environment and energy conservation. Currently, commercial lithium-ion batteries are composed of transition metal oxides or phosphates, aluminum, copper, graphite, organic electrolytes with harmful lithium salts, polymer separators, and plastic or metallic cases. The lack of proper disposal of spent lithium-ion batteries probably results in grave consequences, such as environmental pollution and waste of resources. Thus, recycling of spent lithium-ion batteries starts to receive attentions in recent years. However, owing to the pursuit of lithium-ion batteries with higher energy density, higher safety and more affordable price, the materials used in lithium-ion batteries are of a wide diversity and ever-evolving, consequently bringing difficulties to the recycling of spent lithium-ion batteries. To address this issue, both technological innovations and the participation of governments are required. This article provides a review of recent advances in recycling technologies of spent lithium-ion batteries, including the development of recycling processes, the products obtained from recycling, and the effects of recycling on environmental burdens. In addition, the remaining challenges and future perspectives are also highlighted.
Display omitted
•Advances in technologies for recycling spent LIBs are reviewed.•Characteristics and development of different recycling processes are discussed.•Products obtained from recycling of spent LIBs are summarized.•Effects of recycling spent LIBs on environmental burdens are presented.•Remaining challenges and future perspectives are highlighted.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK, ZRSKP
4.
Consistent video depth estimation Luo, Xuan; Huang, Jia-Bin; Szeliski, Richard ...
ACM transactions on graphics,
07/2020, Volume:
39, Issue:
4
Journal Article
Peer reviewed
Open access
We present an algorithm for reconstructing dense, geometrically consistent depth for all pixels in a monocular video. We leverage a conventional structure-from-motion reconstruction to establish ...geometric constraints on pixels in the video. Unlike the ad-hoc priors in classical reconstruction, we use a learning-based prior, i.e., a convolutional neural network trained for single-image depth estimation. At test time, we fine-tune this network to satisfy the geometric constraints of a particular input video, while retaining its ability to synthesize plausible depth details in parts of the video that are less constrained. We show through quantitative validation that our method achieves higher accuracy and a higher degree of geometric consistency than previous monocular reconstruction methods. Visually, our results appear more stable. Our algorithm is able to handle challenging hand-held captured input videos with a moderate degree of dynamic motion. The improved quality of the reconstruction enables several applications, such as scene reconstruction and advanced video-based visual effects.
Natural killer/T cell lymphoma (NKTCL) is an aggressive and heterogeneous entity of non-Hodgkin lymphoma, strongly associated with Epstein-Barr virus (EBV) infection. To identify molecular subtypes ...of NKTCL based on genomic structural alterations and EBV sequences, we performed multi-omics study on 128 biopsy samples of newly diagnosed NKTCL and defined three prominent subtypes, which differ significantly in cell of origin, EBV gene expression, transcriptional signatures, and responses to asparaginase-based regimens and targeted therapy. Our findings thus identify molecular networks of EBV-associated pathogenesis and suggest potential clinical strategies on NKTCL.
Display omitted
•Integrated analysis provides insight into the molecular classification in NKTCL•EBV lytic genes play an important role on NKTCL pathogenesis•Genomic alteration-based molecular subtypes associate with clinical outcomes•MYC, histone acetylation, and PD-L1/2 are potential therapeutic targets of NKTCL
Xiong et al. propose an updated molecular subtyping scheme based on integrated analysis of the genomic and transcriptomic features of natural killer/T cell lymphoma from patient biopsies, and provide insights into pathogenesis and therapeutic targeting of the disease.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Nowadays nanomaterials have been widely used to remove heavy metals from water/wastewater due to their large surface area and high reactivity. Humic acid (HA) and fulvic acid (FA) exist ubiquitously ...in aquatic environments and have a variety of functional groups which allow them to complex with metal ions and interact with nanomaterials. These interactions can not only alter the environmental behavior of nanomaterials, but also influence the removal and transportation of heavy metals by nanomaterials. Thus, the interactions and the underlying mechanisms involved warrant specific investigations. This review outlined the effects of HA/FA on the removal of heavy metals from aqueous solutions by various nanomaterials, mainly including carbon-based nanomaterials, iron-based nanomaterials and photocatalytic nanomaterials. Moreover, mechanisms involved in the interactions were discussed and potential environmental implications of HA/FA to nanomaterials and heavy metals were evaluated.
•The review outlined heavy metals' removal from water by nanomaterials affected by HA/FA.•Potential mechanisms involved in the interactions were discussed.•Environmental implications of HA/FA to nanomaterials and heavy metals were evaluated.•Outlook for further challenges and potential development was also offered.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Self-similarity based super-resolution (SR) algorithms are able to produce visually pleasing results without extensive training on external databases. Such algorithms exploit the statistical prior ...that patches in a natural image tend to recur within and across scales of the same image. However, the internal dictionary obtained from the given image may not always be sufficiently expressive to cover the textural appearance variations in the scene. In this paper, we extend self-similarity based SR to overcome this drawback. We expand the internal patch search space by allowing geometric variations. We do so by explicitly localizing planes in the scene and using the detected perspective geometry to guide the patch search process. We also incorporate additional affine transformations to accommodate local shape variations. We propose a compositional model to simultaneously handle both types of transformations. We extensively evaluate the performance in both urban and natural scenes. Even without using any external training databases, we achieve significantly superior results on urban scenes, while maintaining comparable performance on natural scenes as other state-of-the-art SR algorithms.
Extreme learning machine (ELM) is a competitive machine learning technique, which is simple in theory and fast in implementation. The network types are “generalized” single hidden layer feedforward ...networks, which are quite diversified in the form of variety in feature mapping functions or kernels. To deal with data with imbalanced class distribution, a weighted ELM is proposed which is able to generalize to balanced data. The proposed method maintains the advantages from original ELM: (1) it is simple in theory and convenient in implementation; (2) a wide type of feature mapping functions or kernels are available for the proposed framework; (3) the proposed method can be applied directly into multiclass classification tasks. In addition, after integrating with the weighting scheme, (1) the weighted ELM is able to deal with data with imbalanced class distribution while maintain the good performance on well balanced data as unweighted ELM; (2) by assigning different weights for each example according to users' needs, the weighted ELM can be generalized to cost sensitive learning.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK
Ship detection on spaceborne images has attracted great interest in the applications of maritime security and traffic control. Optical images stand out from other remote sensing images in object ...detection due to their higher resolution and more visualized contents. However, most of the popular techniques for ship detection from optical spaceborne images have two shortcomings: 1) Compared with infrared and synthetic aperture radar images, their results are affected by weather conditions, like clouds and ocean waves, and 2) the higher resolution results in larger data volume, which makes processing more difficult. Most of the previous works mainly focus on solving the first problem by improving segmentation or classification with complicated algorithms. These methods face difficulty in efficiently balancing performance and complexity. In this paper, we propose a ship detection approach to solving the aforementioned two issues using wavelet coefficients extracted from JPEG2000 compressed domain combined with deep neural network (DNN) and extreme learning machine (ELM). Compressed domain is adopted for fast ship candidate extraction, DNN is exploited for high-level feature representation and classification, and ELM is used for efficient feature pooling and decision making. Extensive experiments demonstrate that, in comparison with the existing relevant state-of-the-art approaches, the proposed method requires less detection time and achieves higher detection accuracy.
The automatic identification system (AIS) tracks vessel movement by means of electronic exchange of navigation data between vessels, with onboard transceiver, terrestrial, and/or satellite base ...stations. The gathered data contain a wealth of information useful for maritime safety, security, and efficiency. Because of the close relationship between data and methodology in marine data mining and the importance of both of them in marine intelligence research, this paper surveys AIS data sources and relevant aspects of navigation in which such data are or could be exploited for safety of seafaring, namely traffic anomaly detection, route estimation, collision prediction, and path planning.