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.
K-nearest neighbor (k-NN) classifier can learn non-linear decision surface and requires only one hyperparameter (i.e. value of “k”) for training. The classification accuracy improves as we increase the amount of training data. With an increase in the amount of training data, computational and memory requirements also increases as it has to store and search through the entire training data for classification...
Extreme learning machine (ELM) and support vector machine (SVM) classifiers are developed to detect rales (a gurgling sound that is a symptom of respiratory diseases in poultry). These classifiers operate on Mel-scaled spectral features calculated from recordings of healthy and sick chickens during a vaccine trial. Twenty minutes of labeled data were used to train and test the classifiers, then they...
There is a big challenge in online multi-object tracking-by-detection, which caused by frequent occlusions, false alarms or miss detections and other factors. In this paper, we proposed an improved fast online multi-object tracking method through taking into account the results of multiple single-object trackers and detections synthetically. To solve the fixed scale problem of conventional kernelized...
Real-world data processing problems often involve multiple data modalities, e.g., panchromatic and multispectral images, positron emission tomography (PET) and magnetic resonance imaging (MRI) images. As these modalities capture information associated with the same phenomenon, they must necessarily be correlated, although the precise relation is rarely known. In this paper, we propose a coupled dictionary...
In this paper we address the problem of compressive sensing with multiple measurement vectors. We propose a reconstruction algorithm which learns sparse structure inside each sparse vector and among sparse vectors. The learning is based on a cross entropy cost function. The model is the Bidirectional Long Short-Term Memory that is deep in time. All modifications are done at the decoder so that the...
In this paper, we introduce a novel local feature-based hierarchical framework to produce invariant sparse codes for object recognition. In order to enforce the invariant property for each sample patch (local feature descriptor) in the image, its sparse code is recovered with a dedicated dictionary whose atoms are adaptively chosen from several bags of candidate atoms. The single-layer invariant sparse...
Aesthetic quality estimation of an image is a challenging task. In this paper, we introduce a deep CNN approach to tackle this problem. We adopt the sate-of-the-art object-recognition CNN as our baseline model, and adapt it for handling several high-level attributes. The networks capable of dealing with these high-level concepts are then fused by a learned logical connector for predicting the aesthetic...
Recently deep learning methods have been applied to image super-resolution (SR). Typically, these approaches involve training a single convolutional neural network that is trained to perform resolution enhancement. We propose a new low-complexity but effective algorithm called Superresolution with Coupled Backpropagation (SR-CBP) which builds two Coupled Auto-encoder Networks (CAN), resp. the high-resolution...
Business and government operations generate large volumes of documents to be categorized through machine learning techniques before dissemination and storage. One prerequisite in such classification is to properly choose training documents. Active learning emerges as a technique to achieve better accuracy with fewer training documents by choosing data to learn and querying oracles for unknown labels...
Sound source separation at low-latency requires that each incoming frame of audio data be processed at very low delay, and outputted as soon as possible. For practical purposes involving human listeners, a 20 ms algorithmic delay is the uppermost limit which is comfortable to the listener. In this paper, we propose a low-latency (algorithmic delay < 20 ms) deep neural network (DNN) based source...
We investigate sequence machine learning techniques on raw radio signal time-series data. By applying deep recurrent neural networks we learn to discriminate between several application layer traffic types on top of a constant envelope modulation without using an expert demodulation algorithm. We show that complex protocol sequences can be learned and used for both classification and generation tasks...
This paper addresses the problem of learning a discriminative dictionary from training signals. Given a structured dictionary, each atom of which has its corresponding label, one signal should be mainly constructed by its closely associated atoms. Besides the representations for the same class ought to be very close to form a cluster. Thus we present out-of-label suppression dictionary model with...
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...
The abundant spectrum at millimeter-wave (mmWave) has the potential to greatly increase the capacity of 5G cellular systems. However, to overcome the high pathloss in the mmWave frequencies, beamforming with large antenna arrays is required at both the base station and user equipments for sufficient link budget. This feature is a challenge for beamforming training during initial access due to low...
A low-density spatial downlink reference signal (LDS-RS) design is proposed for frequency-division duplex (FDD) massive full-dimensional multiple-input multiple-output (FD-MIMO) systems. By exploiting the spatial correlation between the channels of different antennas, this scheme can efficiently reduce the downlink RS overhead and therefore enhances the achievable spectral efficiency significantly...
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...
The impact of training on the performance of millimeter wave multi-user multiple-input multiple-output downlink systems based on hybrid analog/digital beamforming is investigated in the regime of a large number of transmit antennas under the uniform random single-path channel model. In particular, the performance loss with respect to the number of training beams is quantified for general training-based...
We propose a decentralized Maximum Likelihood solution for estimating the stochastic renewable power generation and demand in single bus Direct Current (DC) MicroGrids (MGs), with high penetration of droop controlled power electronic converters. The solution relies on the fact that the primary control parameters are set in accordance with the local power generation status of the generators. Therefore,...
Identifying arbitrary power grid topologies in real time based on measurements in the grid is studied. A learning based approach is developed: binary classifiers are trained to approximate the maximum a-posteriori probability (MAP) detectors that each identifies the status of a distinct line. An efficient neural network architecture in which features are shared for inferences of all line statuses...
In this paper we present experimental results for the development of a gesture recognition system using a 77 GHz FMCW radar system. We measure the micro-Doppler signature of a gesturing hand to construct an energy distribution in velocity space over time. A gesturing hand is fundamentally a dynamical system with unobservable “state” (i.e. the name of the gesture) which determines the sequence of associated...
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.