The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Ultrasonography is a valuable diagnosis method for thyroid nodules. Automatically discriminating benign and malignant nodules in the ultrasound images can provide aided diagnosis suggestions, or increase the diagnosis accuracy when lack of experts. The core problem in this issue is how to capture appropriate features for this specific task. Here, we propose a feature extraction method for ultrasound...
This study explores the application of artificial intelligence on the causal relationship between mining production index and electricity load. The data used is the total mining production index and total electricity consumption in the mining sector sampled on a monthly basis from January 1985 to December 2011 in South Africa. Optimally-pruned and basic extreme learning machines were used to develop...
Tissue segmentation is an important pre-requisite for efficient and accurate diagnostics in digital pathology. However, it is well known that whole-slide scanners can fail in detecting all tissue regions, for example due to the tissue type, or due to weak staining because their tissue detection algorithms are not robust enough. In this paper, we introduce two different convolutional neural network...
Gradient boosting tree (GBT), a widely used machine learning algorithm, achieves state-of-the-art performance in academia, industry, and data analytics competitions. Although existing scalable systems which implement GBT, such as XGBoost and MLlib, perform well for datasets with medium-dimensional features, they can suffer performance degradation for many industrial applications where the trained...
The prediction of stock price movements is considered as a challenging task for financial time series analysis. The difficulty of predicting the trends lies in the dynamic temporality and noise in the stock data. The Echo State Network (ESN) is a popular time series prediction model that considers the temporality of the stock time series, but ESN often falls into the dilemma of over-fitting due to...
In order to explore the inherent laws of ship collision and determine the optimal timing of ship collision avoidance, a Vessel Anti-collision Forewarning method was proposed based on mean impact value (MIV) algorithm and random forest (RF) algorithm. First, the initial index system for vessel anti-collision forewarning was established from vessel static information, vessel dynamic information and...
In this work, we propose a method collaborating the local similarity and local community paradigm with a tunable parameter to balance the contribution of the energy from these two sources. We show that local similarity e.g., common neighbors and local community paradigm e.g., local community links both play significant roles in network evolution; therefore, one cannot ignore or penalize anyone of...
Statistically-optimal Linear Discriminant Analysis (LDA) is formulated as a maximization that involves the nominal statistics of the classes to be discriminated. In practice, however, these nominal statistics are unknown and estimated from a collection of labeled training data. Accordingly, the nominal LDA basis is approximated by the solution of the popular practical LDA problem defined upon these...
Compressed beam-selection (CBS) exploits the limited scattering of the millimeter wave (mmWave) channel using compressed sensing and finds the best beam-pair with limited overhead. The CBS procedure can further benefit from the knowledge of some additional structure in the channel. As mmWave systems are envisioned to be deployed in conjunction with sub-6 GHz systems, we use the spatial information...
We consider stochastic nonparametric regression problems in a reproducing kernel Hilbert space (RKHS), an extension of expected risk minimization to nonlinear function estimation. Popular perception is that kernel methods are inapplicable to online settings, since the generalization of stochastic methods to kernelized function spaces require memory storage that is cubic in the iteration index (“the...
Objective assessment of pathological speech is an important part of existing systems for automatic diagnosis and treatment of various speech disorders. In this paper, we propose a new regression method for this application. Rather than treating speech samples from each speaker as individual data instances, we treat each speaker's data as a probability distribution. We propose a simple non-parametric...
In this paper, we propose a novel method for face hallucination by learning a new distance metric in the low-resolution (LR) patch space (source space). Local patch-based face hallucination methods usually assume that the two manifolds formed by LR and high-resolution (HR) image patches have similar local geometry. However, this assumption does not hold well in practice. Motivated by metric learning...
We explore techniques to significantly improve the compute efficiency and performance of Deep Convolution Networks without impacting their accuracy. To improve the compute efficiency, we focus on achieving high accuracy with extremely low-precision (2-bit) weight networks, and to accelerate the execution time, we aggressively skip operations on zero-values. We achieve the highest reported accuracy...
This paper deals with the separation of music into individual instrument tracks which is known to be a challenging problem. We describe two different deep neural network architectures for this task, a feed-forward and a recurrent one, and show that each of them yields themselves state-of-the art results on the SiSEC DSD100 dataset. For the recurrent network, we use data augmentation during training...
In recent years, so-called, “end-to-end” speech recognition systems have emerged as viable alternatives to traditional ASR frameworks. Keyword search, localizing an orthographic query in a speech corpus, is typically performed by using automatic speech recognition (ASR) to generate an index. Previous work has evaluated the use of end-to-end systems for ASR on well known corpora (WSJ, Switchboard,...
The paper presented a systematic evaluation of the weight sparsity regularization schemes for the deep neural networks applied to the whole brain resting-state functional magnetic resonance imaging data. The weight sparsity regularization was deployed between the visible and hidden layers of the Gaussian-Bernoulli restricted Boltzmann machine (GB-RBM), in which the L0-norm based non-zero value ratio...
A gradient index lens is designed by utilizing quasi-conformal transformation electromagnetics (QCTEM) to define the index distribution in a rotationally symmetric lens. The smooth and continuous nature of QCTEM is investigated and an analytical surrogate model is trained to replace the computationally intensive QCTEM procedure and ray trace simulations. The surrogate model is then incorporated into...
Online social message classification is an important task for E-Commerce companies to mine and classify the customer opinions. In this paper, we have proposed a first of its kind of an efficient message classification algorithm which is independent of tweet content and considers the set of followers who will retweet during the retweet peaks. By including the followers who will retweet during retweet...
Immersive, head-mounted virtual reality (HMD-VR) can be a potentially useful tool for motor rehabilitation. However, it is unclear whether the motor skills learned in HMD-VR transfer to the non-virtual world and vice-versa. Here we used a well-established test of skilled motor learning, the Sequential Visual Isometric Pinch Task (SVIPT), to train individuals in either an HMD-VR or conventional training...
In the information age, blended learning is one of the important ways of teaching reform, it is a kind of new learning mode that blend the learning environment, learning style, learning space and learning process. At the same time, the implementation of "excellent engineer education training program" puts forward new requirements for the cultivation of excellent teachers. Therefore, in this...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.