A Novel Deep Neural Network that Uses Space-Time Features for Tracking and Recognizing a Moving Object

Abstract

This work proposes a deep neural net (DNN) that accomplishes the reliable visual recognition of a chosen object captured with a webcam and moving in a 3D space. Autoencoding and substitutional reality are used to train a shallow net until it achieves zero tracking error in a discrete ambient. This trained individual is set to work in a real world closed loop system where images coming from a webcam produce displacement information for a moving region of interest (ROI) inside the own image. This loop gives rise to an emergent tracking behavior which creates a self-maintain flow of compressed space-time data. Next, short term memory elements are set to play a key role by creating new representations in terms of a space-time matrix. The obtained representations are delivery as input to a second shallow network which acts as "recognizer". A noise balanced learning method is used to fast train the recognizer with real-world images, giving rise to a simple and yet powerful robotic eye, with a slender neural processor that vigorously tracks and recognizes the chosen object. The system has been tested with real images in real time.

An Early Warning Method for Basic Commodities Price Based on Artificial Neural Networks

“…The early warning model consists of three main components, namely preprocessing, predictive model, and post-processing, as depicted in Figure 1 [24]. Preprocessing: Before all raw data about commodity prices are presented to the predictive model, the preprocessing operations are applied on the data.…”

“…The price surveys were conducted by local government at working days, so the commodity price data represent a daily basis with missing values in weekends and holidays. The data are therefore added to weekly data with the mean function to reduce the volume of the data for computational efficiency [24].…”

“…To select the products on which the forecasts were made, the f1-score criterion is used [24]. The ordering by this factor considered both the quantity and the value of sales for the selection of the most important products.…”

A Novel Fast Feedforward Neural Networks Training Algorithm

“…In recent years neural networks have been the subject of many research projects e.g. [1][2][3][4][5][6][7] and are used in the industry [8][9][10], medicine [11][12][13], finance sector [14][15][16], and many others [17][18][19].…”

Multi-layer neural networks for sales forecasting

“…Moreover, it is used to credit risk management in banks [3], predicting the success of bank's direct marketing [4], analyzing consumer loyalty [5], sport [6], medicine [7] and many other areas. Prediction can be performed by various tools such as learning vector quantization [8], neuro-fuzzy systems [9], data stream classifiers [10], energy-associated tuning [11] or deep neural networks [12]. In the case where part of data is missing we can use rough set-based systems [13].…”