Wyniki wyszukiwania - BazTech

1

SARIVA : Smartphone APP for Real-time Intelligent Video Analytics

Clarke C., Angelov P., Yusufu M., Sadeghi-Tehran P.

Journal of Automation Mobile Robotics and Intelligent Systems

|

2014

|

Vol. 8, No. 4

15--19

EN

This paper presents the design, implementation and evaluation of a new smartphone application that is capable of real-time object detection using both stationary and moving cameras for embedded systems, particularly, the Android smartphone platform. A new object detection approach, Optical ORB, is presented which is capable of real-time performance at high definition resolutions on a smartphone. In addition, the developed smartphone application has the ability to connect to a remote server and wirelessly send image frames when moving objects appear in the camera’s field of view; thus, allowing the human operator to only view video frames that are of interest. Evaluation experiments show a capability of achieving real-time performance for high definition (HD) resolution video.

2

Outside the box : an alternative data analytics framework

Angelov P.

Journal of Automation Mobile Robotics and Intelligent Systems

|

2014

|

Vol. 8, No. 2

29--35

EN

In this paper, an alternative framework for data analytics is proposed which is based on the spatially-aware concepts of eccentricity and typicality which represent the density and proximity in the data space. This approach is statistical, but differs from the traditional probability theory which is frequentist in nature. It also differs from the belief and possibility-based approaches as well as from the deterministic first principles approaches, although it can be seen as deterministic in the sense that it provides exactly the same result for the same data. It also differs from the subjective expert-based approaches such as fuzzy sets. It can be used to detect anomalies, faults, form clusters, classes, predictive models, controllers. The main motivation for introducing the new typicality- and eccentricity-based data analytics (TEDA) is the fact that real processes which are of interest for data analytics, such as climate, economic and financial, electro-mechanical, biological, social and psychological etc., are often complex, uncertain and poorly known, but not purely random. Unlike, purely random processes, such as throwing dices, tossing coins, choosing coloured balls from bowls and other games, real life processes of interest do violate the main assumptions which the traditional probability theory requires. At the same time they are seldom deterministic (more precisely, have always uncertainty/noise component which is nondeterministic), creating expert and belief-based possibilistic models is cumbersome and subjective. Despite this, different groups of researchers and practitioners favour and do use one of the above approaches with probability theory being (perhaps) the most widely used one. The proposed new framework TEDA is a systematic methodology which does not require prior assumptions and can be used for development of a range of methods for anomalies and fault detection, image processing, clustering, classification, prediction, control, filtering, regression, etc. In this paper due to the space limitations, only few illustrative examples are provided aiming proof of concept.

3

Intelligent leader-follower behaviour for unmanned ground-based vehicles

Sadeghi-Tehran P., Andreu J., Angelov P., Zhou X.

Journal of Automation Mobile Robotics and Intelligent Systems

|

2011

|

Vol. 5, No. 1

36-46

EN

In this paper an autonomous leader-follower is presented and tested in an unknown and unpredictable environment. Three different types of controller named as First principles-based proportional (P) controller, Fuzzy Logic Controller, and Model-based Predictive Controller are developed and tested in real-time to provide a smooth following behaviour. The follower used the leader's status sent by a smart phone to differentiate between obstacles and the leader and then using two types of sensor, laser and sonar, during the obstacle avoidance procedure. In order to identify the leader again out of many obstacles around, two alternative techniques are proposed using superposition of the scans collected by the laser and predicting the leader's trajectory using evolving Takagi- Sugeno (eTS). At the end, experiments are presented with a real-time mobile robot at Lancaster University.

4

Supplementary crossover operator for genetic algorithms based on the center-of-gravity paradigm

Angelov P.

Control and Cybernetics

|

2001

|

Vol. 30, no 2

159-176

EN

A supplementary crossover operator for genetic algorithms (GA) is proposed in the paper. It performs specific breeding between the two fittest parental chromosomes. The new child chromosome is based on the center of gravity (CoG) paradigm, taking into account both the parental weights (measured by their fitness) and their actual value. It is designed to be used in combination with other crossover and mutation operators (it applies to the best fitted two parental chromosomes only) both in binary and real-valued (evolutionary) GA. Analytical proof of its ability to improve the result is provided for the simplest case of one variable and when the elitist selection strategy is used. The new operator is validated with a number of usually used numerical test functions as well as with a practical example of supply air temperature and flow rate scheduling in a hollow core ventilated slab thermal storage system. The tests indicate that it improves results (the speed of convergence as well as the final result) without a significant increase in computational expenses.