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.
In order to avoid the problems in traditional forecasting methods which demand too much of various data types and have difficulty in training models, this paper proposes two rapid prediction methods which are called “One by One Comparison” and “Regression as a Whole”. By using the two methods, as long as you get playing index in the first few days of a TV drama, the total playing index accumulation...
Activity recognition plays an important role in human-computer interactions. Recently, Channel State Information (CSI), known as a fine-grained information capturing the properties of WiFi signal propagation, has been widely used for activity recognition in a device-free pattern. Since CSI is much sensitive to ambient changes, CSI can be used as fingerprints as human activities. However, existing...
Machine learning based classifiers used quite often for predicting forest cover types, are the Naïve Bayes classifier, the k-Nearest Neighbors classifier, and the Random forest classifier. This paper is directed towards examining all of these classifiers coupled with feature selection and attribute derivation in order to evaluate which one is best suited for forest cover type classification. Numerous...
In the present article, we consider a problem to evaluate the gain in accuracy of using deep learning network for two language tasks: the automatic text classification according to the authors gender and to identify text sentiment. A preexisting corpus of Russian-language texts RusPersonality labeled with information on their authors (gender, age, psychological testing and so on) has been used for...
Generating robotic grasps for given tasks is a difficult problem. This paper proposes a learning-based approach to generate suitable partial power grasp for a set of tool-using tasks. First a number of valid partial power grasps are sampled in simulation and encoded as a probabilistic model, which encapsulates the relations among the task-specific contact, the graspable object feature and the finger...
This paper presents comparative experiment results of code mixed data with the normal text. We first identify the Languages present in social media text, in the case of code mixed data existing language detector fails to detect language at the word level because of the use of roman script to write their own language. So we bootstrap language identification step and we caluculate the Code Mixe Index...
This paper proposes a new approach to automatically quantify the severity of knee osteoarthritis (OA) from radiographs using deep convolutional neural networks (CNN). Clinically, knee OA severity is assessed using Kellgren & Lawrence (KL) grades, a five point scale. Previous work on automatically predicting KL grades from radiograph images were based on training shallow classifiers using a variety...
Millimeter wave (mmWave) is an attractive option for high data rate applications. Enabling mmWave communications requires appropriate beamforming, which is conventionally realized by a lengthy beam training process. Such beam training will be a challenge for applying mmWave to mobile environments. As a solution, a beam tracking method requiring to train only one beam pair to track a path in the analog...
This paper considers the long-term network resource allocation problem subject to queue stability. The dynamic problem is first reformulated as a static stochastic programming. To tackle the resultant static programming, we study its dual problem which contains finite number of variables in oppose to the primal problem that has infinite dimension. A novel online framework is developed by formulating...
This paper addresses the problem of object counting, which is to estimate the number of objects of interest from an input observation. We formalize the problem as a posterior inference of the count by introducing a particular type of Gaussian mixture for the input observation, whose mixture indexes correspond to the count. Unlike existing approaches in image analysis, which typically perform explicit...
In this paper, we propose an indoor positioning system (IPS) that achieves centimeter accuracy in a complex indoor environment using time-reversal (TR) technique with a single pair of off-the-shelf multi-antenna WiFi devices. The proposed IPS can work under both line-of-sight (LOS) and non-line-of-sight (NLOS) environment. Leveraging the spatial diversity on the multi-antenna WiFi device, the proposed...
In the past years, deep convolutional neural networks (CNNs) have become extremely popular in the computer vision and pattern recognition community. The computational power of modern processors, efficient stochastic optimization algorithms, and large amounts of training data allowed training complex tasks-specific features directly from the data in an end-to-end fashion, as opposed to the traditional...
Automatic image annotation has been an important research topic in facilitating large scale image management and retrieval. Existing methods focus on learning image-tag correlation or correlation between tags to improve annotation accuracy. However, most of these methods evaluate their performance using top-k retrieval performance, where k is fixed. Although such setting gives convenience for comparing...
We propose a max-pooling based loss function for training Long Short-Term Memory (LSTM) networks for small-footprint keyword spotting (KWS), with low CPU, memory, and latency requirements. The max-pooling loss training can be further guided by initializing with a cross-entropy loss trained network. A posterior smoothing based evaluation approach is employed to measure keyword spotting performance...
The traditional approach of mining frequent patterns generates a very large number of patterns of which a substantial fraction are not much interesting for many data analysis tasks. So selecting a small number of patterns from the large output set such that the selected patterns best align with a particular user's interest is an important task. Existing works on pattern summarization do not help,...
We present a density-based Data Pruning method for Deep Reinforcement Learning (DRL) to improve learning stability and long-term memory in rare situations. The method controls density distribution in the experience pool by discarding high correlation data and preserving rare and unique data. We apply our method to Deep Q-networks (DQN) and Deep Deterministic Policy Gradients (DDPG) for testing in...
In this paper we apply particle swarm optimization (PSO) feature selection to enhance Hidden Markov Model (HMM) states and parameters for face recognition systems. Ideal Feature selection for face images based on the idea of collaborative behavior of bird flocking to reduce the feature size and hence recognition time complicity. The framework has been inspected on 400 face pictures of the Olivetti...
This paper proposes a new channel estimation scheme for the multiuser massive multiple-input multiple-output (MIMO) systems in time-varying environment. We introduce a discrete Fourier transform (DFT) aided spatial-temporal basis expansion model (ST-BEM) to reduce the effective dimensions of uplink/downlink channels, such that training overhead and feedback cost could be greatly decreased. The newly...
We propose novel methods for automatically detecting non-stationary segments using non-negative matrix factorization (NMF) with aiming to effective sound annotation. For acoustic event detection or acoustic scene analysis, preparing a sufficient amount of training data is important. However, listening to all recorded signals and annotating them are very time-consuming. Assuming that the observed acoustic...
For the traditional way of Liver disease diagnosis, there exists a certain subjectivity, and easily missed diagnosis and misdiagnosis. The use of a single neural network can not eliminate the redundant information among various indicators, resulting in diagnostic accuracy is not high. In order to improve the correctness of the early diagnosis of liver lesions, This paper proposes a liver disease diagnosis...
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.