Wyniki wyszukiwania - BazTech

1

Design of fuzzy rule-based classifiers through granulation and consolidation

Riid A., Preden J.-S.

Journal of Artificial Intelligence and Soft Computing Research

|

2017

|

Vol. 7, No. 2

137--147

EN

This paper addresses the issue how to strike a good balance between accuracy and compactness in classification systems - still an important question in machine learning and data mining. The fuzzy rule-based classification approach proposed in current paper exploits the method of rule granulation for error reduction and the method of rule consolidation for complexity reduction. The cooperative nature of those methods - the rules are split in a way that makes efficient rule consolidation feasible and rule consolidation itself is capable of further error reduction - is demonstrated in a number of experiments with nine benchmark classification problems. Further complexity reduction, if necessary, is provided by rule compression.

2

Performing acoustic localization in a network of embedded smart sensors

Astapov S., Ehala J., Preden J.-S.

International Journal of Microelectronics and Computer Science

|

2015

|

Vol. 6, nr 3

86--95

EN

Situation awareness is an important aspect of ubiquitous computer systems, as these systems of systems are highly integrated with the physical world and for successful operation they must maintain high awareness of the environment. Acoustic information is one of the most popular modalities, by which the environment states are estimated. Multi-sensor approaches also provide the possibility for acoustic source localization. This paper considers an acoustic localization system of dual channel smart sensors interconnected through a Wireless Sensor Network (WSN). The low computational power of smart sensor devices requires distribution of localization tasks among WSN nodes. The Initial Search Region Reduction (ISRR) method is used in the WSN to meet this requirement. ISRR, as opposed to conventional localization methods, performs significantly less complex computations and does not require exchange of raw signal between nodes. The system is implemented on smart dust motes utilizing Atmel ATmega128RFA1 processors with integrated 2.4GHz IEEE 802.15.4 compliant radio transceivers. The paper discusses complications introduced by low power hardware and ad-hoc networking, and also reviews conditions of real-time operation.

3

Optimized Acoustic Localization with SRP-PHAT for Monitoring in Distributed Sensor Networks

Astapov S., Berdnikova J., Preden J.-S.

International Journal of Electronics and Telecommunications

|

2013

|

Vol. 59, No. 4

383-390

EN

Acoustic localization by means of sensor arrays has a variety of applications, from conference telephony to environment monitoring. Many of these tasks are appealing for implementation on embedded systems, however large dataflows and computational complexity of multi-channel signal processing impede the development of such systems. This paper proposes a method of acoustic localization targeted for distributed systems, such as Wireless Sensor Networks (WSN). The method builds on an optimized localization algorithm of Steered Response Power with Phase Transform (SRP-PHAT) and simplifies it further by reducing the initial search region, in which the sound source is contained. The sensor array is partitioned into sub-blocks, which may be implemented as independent nodes of WSN. For the region reduction two approaches are handled. One is based on Direction of Arrival estimation and the other – on multilateration. Both approaches are tested on real signals for speaker localization and industrial machinery monitoring applications. Experiment results indicate the method’s potency in both these tasks.