Tapio Frantti

Fuzzy logic-based forecasting model

Abstract In this paper a fuzzy logic-based software tool, fuzzy logic advisory tool (FLAT), for demand forecasting of signal transmission products is presented. The FLAT was developed for the prediction of demand of about 1000 different products in order to aid materials purchasing process of about 14,000 different components in the electronics manufacturing processes of Nokia Network Systemss Haukipudas factory. The prediction values of different products are inferred by starting from a set of eight input values. Each input value is fuzzied by the FLAT. Thereafter, fuzzy results are inferred in three sequential phases. In each phase the number of variables is split due to hierarchical structure of the inference module. A data base and a rule base are divided accordingly into three hierarchical levels. Rules are represented by linguistic relations changed into matrix equations form in order to apply linguistic equations framework technique (LE). Fuzzy membership functions for input values are determined on-line from earlier input values of the products. Fuzzy rules were inferred by analyzing behavior of the products together with market experts and product experts of the company. The model is able to produce more accurate decision-making support than more traditional approaches. This is probably due to the model-based approach and systematic data management.

Fuzzy Classifier for Star-Galaxy Separation

The sizes of astronomical surveys are increasing rapidly. Hence, the automatic classification of objects is growing more important. This classification is traditionally based, e.g., on point-spread function fitting. Recently several different neural network approaches have been introduced. In this paper we introduce a simple method that is based on fuzzy set reasoning. The analysis presented here concentrates on separating point sources (stars) from extended ones. The tests show that the neural network approach is superior if compared to direct fuzzy classification. The paper shows that the inherent ability of neural networks to process complex nonlinear data justifies the use of them in astronomical classification. However, a combined fuzzy and neural network approach can be useful at least in special cases.

Automated Star-Galaxy Discrimination for Large Surveys

The size of survey data is increasing rapidly, and the automatic classification of objects is becoming more important. The classification is traditionally based, e.g., on point-spread function (PSF) fitting. Recently, several different neural network approaches have been introduced for classification. In this paper we use both self-organized map and learning vector quantization based neural networks for star-galaxy separation. Finally, we test a hybrid algorithm using fuzzy classifier and back-propagation neural networks. We show that different methods give relatively similar results. The classification accuracy is good enough for real data analysis, and selection between different methods must be done based on algorithmic complexity and availability of preclassified training sets.

Adaptive fuzzy power control for WCDMA mobile radio systems

Abstract In this paper a fuzzy logic based power control for a direct sequence, wideband code-division multiple-access (DS/WCDMA) cellular phone system is introduced. A power control procedure is needed to compensate the fluctuation of the mobiles transmitting power received in a base station and to increase the capacity of mobile communication systems. The input variables of the controller are the power error and the change of the error. The output is the power step size. Simulation results show that the developed fuzzy proportional-integral control stabilizes the power level and decreases the overshoot and rise time.

An expert system for real-time traffic management in wireless local area networks

The paper explores delay-based congestion and flow control and the offloading of real-time traffic from wireless local area networks (WLANs) to mobile cellular networks (MCNs) in multihomed devices. The control system developed is based on an embedded hierarchical expert system. It adjusts transceivers’ traffic flow(s) for prevailing network conditions to achieve application-dependent delay and throughput limits. In wireless networks, delay and throughput depend on the packet size, packet transmission interval, and node connection density. Therefore, the controller on the destination node monitors average one-way delay and the change of one-way delay of the incoming traffic. On this basis, it adjusts the packet size and transmission interval of the source node by transmitting a control command to the source. If the prevailing level of traffic in the network exceeds its capacity despite of the control actions taken, devices prepare for developed asynchronous offloading of traffic to another access network. The control model was validated via simulation of Voice over Internet Protocol (VoIP) traffic in the OMNeT++ network simulator. The results demonstrate that the expert system developed is able to regulate packet sizes to match the prevailing application-dependent optimum and transfer traffic to another network if the network exceed its capacity no matter the control actions taken. Although this work is motivated mainly by issues of congestion and flow control of WLAN systems and the simulations and results were prepared for the IEEE 802.11b system, the approach and techniques are not limited to these systems, but they are applicable for other packet switched access networks (PSANs), too.

Embedded fuzzy expert system for Adaptive Weighted Fair Queueing

This paper introduces an embedded fuzzy expert system for Adaptive Weighted Fair Queueing (AWFQ) located in the network traffic router to update weights for output queues. WFQ algorithm allows differentiated service for traffic classes according to Quality of Service (QoS) requirements. Link sharing and packet scheduling methods are the most critical factors when guaranteeing QoS. There are many different scheduling mechanisms but adequate and adaptive QoS aware scheduling solutions are still in a phase of development due to the rapid growth of multimedia in the Internet. The proposed AWFQ model in this work simplifies the link sharing to two service classes: one for UDP and another for TCP. The implementation of the model is based on adaptive change of weight coefficients that determine the amount of allowed bandwidth for the service class. New weight coefficients are calculated periodically on routers according to developed embedded fuzzy expert system. It is shown through simulations that the AWFQ model is more stable and reacts faster to different traffic states than the traditional WFQ scheduler. The embedded expert system adjusts the weights of AWFQ with two parameters that are based on the share of the UDP and TCP input traffic data rate and the change of the share of the UDP and TCP input data rate.

Fuzzy packet size control for delay sensitive traffic in ad hoc networks

In this paper is considered optimal packet size definition for delay sensitive traffic in Wireless Local Area Network (WLAN) based ad hoc networks. The aim of the paper is to introduce a fuzzy expert system, which control packet size for prevailing network conditions. The selected input parameters for the expert system are a packet error rate (PER) and a change of PER. The model was valitated by simulating delay sensitive Voice Over Internet Protocol (VoIP traffic). The results demonstrate that the developed fuzzy expert system is able to set packet size values to the prevailing optimum level very fast and to increase number of VoIP connections even 40%.

Fuzzy expert system for load balancing in symmetric multiprocessor systems

The aim of this paper is to describe a fuzzy expert system for load balancing in a symmetric multiprocessor environment. Load balancing algorithms are used to share the load of the system fairly among the processors. The developed load balancing algorithm use on demand based approach instead of the periodic load balancing in order to get fast and fair load balancing with minimal computational overhead. It uses the number of threads per processor and total load of the system as inputs. The method is compared to the periodic and another developed on demand based algorithms. The results show that during the load balancing the periodic algorithm causes temporary idle periods in the processors whereas the developed on demand-based algorithms respond faster to the fluctuating load level, stabilize the load more equally among the processors and increase the performance of the system. The results also proof that the fuzzy load balancer achieves the best load balance among the processors as well as the fastest response time.

Fuzzy packet size optimization for delay sensitive traffic in ad hoc networks

In this paper is considered optimal packet size definition for delay sensitive traffic in WLAN based ad hoc networks. The aim of the paper is to introduce a fuzzy set theory based online sample size definition model, which optimize packet size of delay sensitive traffic for prevailing network conditions. The selected input parameters for the model are a packet error rate (PER) and a change of PER. The model was validated by simulating delay sensitive VoIP traffic. The results prove that the WLAN based ad hoc network with AODV routing and VoIP transactions has an optimal packet size. The results also demonstrate that the developed fuzzy model is able to set sample size values to the prevailing optimum level very fast.

Expert system for gesture recognition in terminal's user interface

Abstract This paper presents and describes a soft computing based expert system for gesture recognition procedure, as a part of intelligent user interface of a mobile terminal. In the presented solution, a terminal includes three acceleration sensors positioned like xyz co-ordinate system in order to get three-dimensional (3D) acceleration vector, xyz . The 3D acceleration vector is, after Doppler spectrum definition, used as an input vector to a fuzzy reasoning unit of embedded expert system, which classifies gestures (time series of acceleration vectors). In the reasoning unit fuzzy rule aided method is used to classification. The method is compared to the fuzzy c-means classification with feature extraction, to the hidden Markov model (HMM) classification and SOM classification. Fuzzy methods classified successfully the test sets. The advantages of the fuzzy methods are computational effectiveness, simple implementation, lower data sample rate requirement and reliability. Moreover, fuzzy methods do not require training like SOM and HMM. Therefore, the methods can be applied to the real time systems where different gestures can be used, for example, instead of the keyboard functions. The computational effectiveness and low sample rate requirement also increases the operational time of device compared to computationally heavy HMM method. Furthermore, the easy implementation and reliability are important factors for the success of the new technologys spreading on the mass market of terminals.